You searched for subject:(3D Reconstruction).
Showing records 1 – 30 of
629 total matches.
◁ [1] [2] [3] [4] [5] … [21] ▶
Rochester Institute of Technology
1.
Pieszala, James.
3D Gaze Point Localization and Visualization Using LiDAR-based 3D Reconstructions.
Degree: MS, Computer Science (GCCIS), 2015, Rochester Institute of Technology
URL: https://scholarworks.rit.edu/theses/8936 
► We present a novel pipeline for localizing a free roaming eye tracker within a LiDAR-based 3D reconstructed scene with high levels of accuracy. By…
(more)
▼ We present a novel pipeline for localizing a free roaming eye tracker within a LiDAR-based
3D reconstructed scene with high levels of accuracy. By utilizing a combination of
reconstruction algorithms that leverage the strengths of global versus local capture methods and user-assisted refinement, we reduce drift errors associated with Dense Simultaneous Localization and Mapping (D-SLAM) techniques. Our framework supports region-of-interest (ROI) annotation and gaze statistics generation and the ability to visualize gaze in
3D from an immersive first person or third person perspective. This approach gives unique insights into viewers' problem solving and search task strategies and has high applicability in indoor static environments such as crime scenes.
Advisors/Committee Members: Reynold Bailey.
Subjects/Keywords: 3D computer vision; 3D gaze; 3D reconstruction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Pieszala, J. (2015). 3D Gaze Point Localization and Visualization Using LiDAR-based 3D Reconstructions. (Masters Thesis). Rochester Institute of Technology. Retrieved from https://scholarworks.rit.edu/theses/8936
Chicago Manual of Style (16th Edition):
Pieszala, James. “3D Gaze Point Localization and Visualization Using LiDAR-based 3D Reconstructions.” 2015. Masters Thesis, Rochester Institute of Technology. Accessed January 23, 2021.
https://scholarworks.rit.edu/theses/8936.
MLA Handbook (7th Edition):
Pieszala, James. “3D Gaze Point Localization and Visualization Using LiDAR-based 3D Reconstructions.” 2015. Web. 23 Jan 2021.
Vancouver:
Pieszala J. 3D Gaze Point Localization and Visualization Using LiDAR-based 3D Reconstructions. [Internet] [Masters thesis]. Rochester Institute of Technology; 2015. [cited 2021 Jan 23].
Available from: https://scholarworks.rit.edu/theses/8936.
Council of Science Editors:
Pieszala J. 3D Gaze Point Localization and Visualization Using LiDAR-based 3D Reconstructions. [Masters Thesis]. Rochester Institute of Technology; 2015. Available from: https://scholarworks.rit.edu/theses/8936
University of Southern California
2.
Kang, Zhuoliang.
Accurate 3D model acquisition from imagery data.
Degree: PhD, Computer Science, 2015, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/572252/rec/481
► Acquisition of geometric 3D models from 2D imagery has been essential for various applications. In particular, this dissertation investigates two important application scenarios: city‐scale 3D…
(more)
▼ Acquisition of geometric
3D models from 2D imagery has
been essential for various applications. In particular, this
dissertation investigates two important application scenarios:
city‐scale
3D reconstruction from aerial imagery and general
3D
model acquisition with a commodity camera. ❧ The first part of this
dissertation explores an online solution to the problem. We propose
an approach to solve camera pose estimation and dense
reconstruction from Wide Area Aerial Surveillance (WAAS) videos
captured by an airborne platform. Our approach solves them in an
online fashion: it incrementally updates a sparse
3D map and
estimates the camera pose as each new frame arrives; depth maps of
selected key frames are computed using a variational method and
integrated to produce a full
3D model via volumetric
reconstruction. In practice, aerial imagery is usually captured
using a multi‐camera system. We propose an approach for camera pose
estimation of multi‐camera aerial imagery which is parallelized on
multiple GPUs for efficiency. The approach is also extended for
progressive
3D model acquisition with a hand‐held camera. ❧ In many
scenarios, online approach is not a necessity and accuracy has
higher priority over efficiency. In the second part, we present
MeshRecon, a mesh‐based offline system composed of three modules: a
dense point cloud is generated using multi‐resolution plane sweep
method; an initial mesh model is extracted from the point cloud via
global optimization considering visibility information of all
images; the mesh model is then iteratively refined to capture
structural details by optimizing the photometric consistency and
spatial regularization. The major processes are parallelized on GPU
for efficiency. For the aerial imagery case, we evaluate our system
on several real-world multi‐camera aerial imagery datasets, each
covering an urban scenario of several square kilometers.
Quantitative result shows that the reconstructed geometric
3D model
is highly accurate with error smaller than 1 meter over the entire
city. Besides aerial imagery, we also evaluate its performance on
general geometric
3D model acquisition of real‐world objects.
Result shows that the system is robust and flexible for various
types of objects at different scales in both indoor and outdoor
environments. Based on city
3D models reconstructed at different
times, we present a system for city‐scale geometry change detection
by performing comparisons at the
3D geometry level. Our system is
able to detect geometry changes at different scales, ranging from a
building cluster to small‐scale vegetation changes, with high
accuracy. In the end, we conclude the dissertation with
contributions and future work.
Advisors/Committee Members: Medioni, Gerard G.Medioni, Gérard G. (Committee Chair), Li, Hao (Committee Member), Sawchuk, Alexander A. (Sandy) (Committee Member).
Subjects/Keywords: computer vision; 3D reconstruction; urban reconstruction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Kang, Z. (2015). Accurate 3D model acquisition from imagery data. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/572252/rec/481
Chicago Manual of Style (16th Edition):
Kang, Zhuoliang. “Accurate 3D model acquisition from imagery data.” 2015. Doctoral Dissertation, University of Southern California. Accessed January 23, 2021.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/572252/rec/481.
MLA Handbook (7th Edition):
Kang, Zhuoliang. “Accurate 3D model acquisition from imagery data.” 2015. Web. 23 Jan 2021.
Vancouver:
Kang Z. Accurate 3D model acquisition from imagery data. [Internet] [Doctoral dissertation]. University of Southern California; 2015. [cited 2021 Jan 23].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/572252/rec/481.
Council of Science Editors:
Kang Z. Accurate 3D model acquisition from imagery data. [Doctoral Dissertation]. University of Southern California; 2015. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/572252/rec/481
3.
Chhatkuli, Ajad.
Local analytic and global convex methods for the 3D reconstruction of isometric deformable surfaces. : Méthodes Analytiques Locales et Méthodes Globales Convexes pour la Reconstruction 3D de Surfaces Isométriquement Déformables.
Degree: Docteur es, Sciences pour l'ingenieur, 2016, Clermont-Ferrand 1
URL: http://www.theses.fr/2016CLF1MM27
► Cette thèse contribue au problème de la reconstruction 3D pour les surfaces déformables avec une seule caméra. Afin de modéliser la déformation de la surface,…
(more)
▼ Cette thèse contribue au problème de la reconstruction 3D pour les surfaces déformables avec une seule caméra. Afin de modéliser la déformation de la surface, nous considérons l’isométrie puisque de nombreuses déformations d’objets réels sont quasi-isométriques. L’isométrie implique que, lors de sa déformation, la surface ne peut pas être étirée ou compressée. Nous étudions deux problèmes. Le premier est le problème basé sur une modèle 3D de référence et une seule image. L’état de l’art propose une méthode locale et analytique de calcul direct de profondeur sous l’hypothèse d’isométrie. Dans cette méthode, la solution pour le gradient de la profondeur n’est pas utilisée. Nous prouvons que cette méthode s’avère instable lorsque la géométrie de la caméra tend à être affine. Nous fournissons des méthodes alternatives basées sur les solutions analytiques locales des quantités de premier ordre, telles que les gradients de profondeur ou les normales de la surface. Nos méthodes sont stables dans toutes les géométries de projection. Dans le deuxième type de problème de reconstruction sans modèle 3D de référence, on obtient les formes de l’objet à partir d’un ensemble d’images où il apparaît déformé. Nous fournissons des solutions locales et globales basées sur le modéle de la caméra perspective. Dans la méthode locale ou par point, nous résolvons pour la normale de la surface en chaque point en supposant que la surface est infinitésimalement plane. Nous calculons ensuite la surface par intégration. Dans la méthode globale, nous trouvons une relaxation convexe du problème. Celle-ci est basée sur la relaxation de l’isométrie en contrainte d’inextensibilité et sur la maximisation de la profondeur en chaque point de la surface. Cette solution combine toutes les contraintes en un seul programme d’optimisation convexe qui calcule la profondeur et utilise une représentation éparse de la surface. Nous détaillons les expériences approfondies qui ont été réalisées pour démontrer l’efficacité de chacune des méthodes. Les expériences montrent que notre solution libre de modèle de référence local fonctionne mieux que la plupart des méthodes précédentes. Notre méthode local avec un modèle 3D de référence et notre méthode globale sans modèle 3D apportent de meilleurs résultats que les méthodes de l’état de l’art en étant robuste au bruit de la correspondance. En particulier, nous sommes en mesure de reconstruire des déformations complexes, non-lisses et d’articulations avec la seconde méthode; alors qu’avec la première, nous pouvons reconstruire avec précision de déformations larges à partir d’images prises avec des très longues focales.
This thesis contributes to the problem of 3D reconstruction for deformable surfaces using a single camera. In order to model surface deformation, we use the isometric prior because many real object deformations are near-isometric. Isometry implies that the surface cannot stretch or compress. We tackle two different problems. The first is called Shape-from-Template where the object’s deformed shape is…
Advisors/Committee Members: Bartoli, Adrien (thesis director), Pizarro, Daniel (thesis director).
Subjects/Keywords: Reconstruction non-rigide.; Reconstruction 3D; Surface isométric; Non-rigid Reconstruction.; Isométric surfaces,; 3D Reconstruction,; 616
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Chhatkuli, A. (2016). Local analytic and global convex methods for the 3D reconstruction of isometric deformable surfaces. : Méthodes Analytiques Locales et Méthodes Globales Convexes pour la Reconstruction 3D de Surfaces Isométriquement Déformables. (Doctoral Dissertation). Clermont-Ferrand 1. Retrieved from http://www.theses.fr/2016CLF1MM27
Chicago Manual of Style (16th Edition):
Chhatkuli, Ajad. “Local analytic and global convex methods for the 3D reconstruction of isometric deformable surfaces. : Méthodes Analytiques Locales et Méthodes Globales Convexes pour la Reconstruction 3D de Surfaces Isométriquement Déformables.” 2016. Doctoral Dissertation, Clermont-Ferrand 1. Accessed January 23, 2021.
http://www.theses.fr/2016CLF1MM27.
MLA Handbook (7th Edition):
Chhatkuli, Ajad. “Local analytic and global convex methods for the 3D reconstruction of isometric deformable surfaces. : Méthodes Analytiques Locales et Méthodes Globales Convexes pour la Reconstruction 3D de Surfaces Isométriquement Déformables.” 2016. Web. 23 Jan 2021.
Vancouver:
Chhatkuli A. Local analytic and global convex methods for the 3D reconstruction of isometric deformable surfaces. : Méthodes Analytiques Locales et Méthodes Globales Convexes pour la Reconstruction 3D de Surfaces Isométriquement Déformables. [Internet] [Doctoral dissertation]. Clermont-Ferrand 1; 2016. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2016CLF1MM27.
Council of Science Editors:
Chhatkuli A. Local analytic and global convex methods for the 3D reconstruction of isometric deformable surfaces. : Méthodes Analytiques Locales et Méthodes Globales Convexes pour la Reconstruction 3D de Surfaces Isométriquement Déformables. [Doctoral Dissertation]. Clermont-Ferrand 1; 2016. Available from: http://www.theses.fr/2016CLF1MM27
4.
Haouchine, Nazim.
Image-guided simulation for augmented reality during hepatic surgery : Simulation guidée par l’image pour la réalité augmentée durant la chirurgie hépatique.
Degree: Docteur es, Informatique, 2015, Université Lille I – Sciences et Technologies
URL: http://www.theses.fr/2015LIL10009
► L’objectif principal de cette thèse est de fournir aux chirurgiens des outils d’aide à la décision pré et per-opératoire lors d’interventions minimalement invasives en chirurgie…
(more)
▼ L’objectif principal de cette thèse est de fournir aux chirurgiens des outils d’aide à la décision pré et per-opératoire lors d’interventions minimalement invasives en chirurgie hépatique. Ces interventions reposent en général sur des techniques de laparoscopie ou plus récemment d’endoscopie flexible. Lors de telles interventions, le chirurgien cherche à retirer un nombre souvent important de tumeurs hépatiques, tout en préservant le rôle fonctionnel du foie. Cela implique de définir une hépatectomie optimale, c’est à dire garantissant un volume du foie post-opératoire d’au moins 55% du foie initial et préservant au mieux la vascularisation hépatique. Bien qu’une planification de l’intervention puisse actuellement s’envisager sur la base de données pré-opératoire spécifiques au patient, les mouvements importants du foie et ses déformations lors de l’intervention rendent cette planification très difficile à exploiter en pratique. Les travaux proposés dans cette thèse visent à fournir des outils de réalité augmentée utilisables en conditions per-opératoires et permettant de visualiser à chaque instant la position des tumeurs et réseaux vasculaires hépatiques.
The main objective of this thesis is to provide surgeons with tools for pre and intra-operative decision support during minimally invasive hepatic surgery. These interventions are usually based on laparoscopic techniques or, more recently, flexible endoscopy. During such operations, the surgeon tries to remove a significant number of liver tumors while preserving the functional role of the liver. This involves defining an optimal hepatectomy, i.e. ensuring that the volume of post-operative liver is at least at 55% of the original liver and the preserving at hepatic vasculature. Although intervention planning can now be considered on the basis of preoperative patient-specific, significant movements of the liver and its deformations during surgery data make this very difficult to use planning in practice. The work proposed in this thesis aims to provide augmented reality tools to be used in intra-operative conditions in order to visualize the position of tumors and hepatic vascular networks at any time.
Advisors/Committee Members: Cotin, Stéphane (thesis director), Berger, Marie-Odile (thesis director), Dequidt, Jérémie (thesis director).
Subjects/Keywords: Reconstruction 3D; Suivi visuel; 003.3
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Haouchine, N. (2015). Image-guided simulation for augmented reality during hepatic surgery : Simulation guidée par l’image pour la réalité augmentée durant la chirurgie hépatique. (Doctoral Dissertation). Université Lille I – Sciences et Technologies. Retrieved from http://www.theses.fr/2015LIL10009
Chicago Manual of Style (16th Edition):
Haouchine, Nazim. “Image-guided simulation for augmented reality during hepatic surgery : Simulation guidée par l’image pour la réalité augmentée durant la chirurgie hépatique.” 2015. Doctoral Dissertation, Université Lille I – Sciences et Technologies. Accessed January 23, 2021.
http://www.theses.fr/2015LIL10009.
MLA Handbook (7th Edition):
Haouchine, Nazim. “Image-guided simulation for augmented reality during hepatic surgery : Simulation guidée par l’image pour la réalité augmentée durant la chirurgie hépatique.” 2015. Web. 23 Jan 2021.
Vancouver:
Haouchine N. Image-guided simulation for augmented reality during hepatic surgery : Simulation guidée par l’image pour la réalité augmentée durant la chirurgie hépatique. [Internet] [Doctoral dissertation]. Université Lille I – Sciences et Technologies; 2015. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2015LIL10009.
Council of Science Editors:
Haouchine N. Image-guided simulation for augmented reality during hepatic surgery : Simulation guidée par l’image pour la réalité augmentée durant la chirurgie hépatique. [Doctoral Dissertation]. Université Lille I – Sciences et Technologies; 2015. Available from: http://www.theses.fr/2015LIL10009
Delft University of Technology
5.
Zhang, Yu (author).
High Accuracy Eye-Tracker For Proton Clinic Environment.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e
► This project aims to improve the accuracy of the eye tracking system, which consists of two cameras and two infrared LED light sources. This highly…
(more)
▼ This project aims to improve the accuracy of the eye tracking system, which consists of two cameras and two infrared LED light sources. This highly non-invasive technology, which is the feature-based video-oculographic eye tracking system, determines the position of the eye by monitoring the eye features such as the pupil center and glints. The accuracy of estimating the eye position and orientation is critical in the proton clinic environment, and is to be required higher than those in commercially available eye-tracking system.
Electrical Engineer | Embedded Systems
Advisors/Committee Members: Verhaegen, Michel (mentor), Soloviev, Oleg (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: stereo camera; 3d reconstruction; calibration
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Zhang, Y. (. (2019). High Accuracy Eye-Tracker For Proton Clinic Environment. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e
Chicago Manual of Style (16th Edition):
Zhang, Yu (author). “High Accuracy Eye-Tracker For Proton Clinic Environment.” 2019. Masters Thesis, Delft University of Technology. Accessed January 23, 2021.
http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e.
MLA Handbook (7th Edition):
Zhang, Yu (author). “High Accuracy Eye-Tracker For Proton Clinic Environment.” 2019. Web. 23 Jan 2021.
Vancouver:
Zhang Y(. High Accuracy Eye-Tracker For Proton Clinic Environment. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Jan 23].
Available from: http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e.
Council of Science Editors:
Zhang Y(. High Accuracy Eye-Tracker For Proton Clinic Environment. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e
Delft University of Technology
6.
Wu, H. (author).
Integration of 2D architectural floor plans into Indoor OpenStreetMap for reconstructing 3D building models.
Degree: 2015, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:26a4c6b8-8ea0-4246-b30e-5c83a28cccb4
► All existing data sources used to reconstruct 3D building models have certain restrictions. An eye-catching alternative is IndoorOSM, one of the most popular examples of…
(more)
▼ All existing data sources used to reconstruct 3D building models have certain restrictions. An eye-catching alternative is IndoorOSM, one of the most popular examples of the newly evolved crowdsourced geodata. The potential power of this rich and simple-formatted data source has been proven by many researches. However, a fatal flaw of IndoorOSM is also pointed out, which is its accuracy. Another promising data source that has been looked into is 2D architectural floor plans. They are also commonly available and full of detailed indoor information. Due to the inconsistencies and ambiguities existing among real-life floor plans, previous researches all are established on different user cases. Althogh sharing a common pipeline, they differ from each other in every step, from the data structure, processing procedure to the 3D reconstruction method. The combination of these two data sources can be beneficial, because architectural floor plans can offer IndoorOSM better accuracy and extensive indoor information while IndoorOSM can provide a unified data structure and 3D reconstruction workflow for information extracted from floor plans. Based on a throughout review of the characters of real-life floor plans, a set of rules are proposed to redraw architectural floor plans from real life. These rules mainly focus on reorganizing information contained in floor plans, taking advantages of the layering and blocking functions supported by CAD application. The original geometry and graphical representation in the raw floor plans is reserved as much as possible. Redrawing is only required when unstandardized representation is encountered. Then, an automatic process is accordingly presented to extract desired information from the redrawn floor plans into an IndoorOSM database. Finally, highly detailed CityGML LoD4 models with interior structures can be generated using a method proposed by Dr. Marcus Goetz. The pipeline is tested with several floor plans from real life for 3D reconstruction. User feedback validated the feasibility and efficiency of the redrawing rules.
Geomatics
Geomatics
Architecture and The Built Environment
Advisors/Committee Members: Zlatanova, S. (mentor), Liu, L. (mentor).
Subjects/Keywords: 3D reconstruction; IndoorOSM; floor plans
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wu, H. (. (2015). Integration of 2D architectural floor plans into Indoor OpenStreetMap for reconstructing 3D building models. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:26a4c6b8-8ea0-4246-b30e-5c83a28cccb4
Chicago Manual of Style (16th Edition):
Wu, H (author). “Integration of 2D architectural floor plans into Indoor OpenStreetMap for reconstructing 3D building models.” 2015. Masters Thesis, Delft University of Technology. Accessed January 23, 2021.
http://resolver.tudelft.nl/uuid:26a4c6b8-8ea0-4246-b30e-5c83a28cccb4.
MLA Handbook (7th Edition):
Wu, H (author). “Integration of 2D architectural floor plans into Indoor OpenStreetMap for reconstructing 3D building models.” 2015. Web. 23 Jan 2021.
Vancouver:
Wu H(. Integration of 2D architectural floor plans into Indoor OpenStreetMap for reconstructing 3D building models. [Internet] [Masters thesis]. Delft University of Technology; 2015. [cited 2021 Jan 23].
Available from: http://resolver.tudelft.nl/uuid:26a4c6b8-8ea0-4246-b30e-5c83a28cccb4.
Council of Science Editors:
Wu H(. Integration of 2D architectural floor plans into Indoor OpenStreetMap for reconstructing 3D building models. [Masters Thesis]. Delft University of Technology; 2015. Available from: http://resolver.tudelft.nl/uuid:26a4c6b8-8ea0-4246-b30e-5c83a28cccb4
7.
KOZLOV, IGOR V.
ANALYSIS OF UNCERTAINTY IN UNDERWATER MULTIVIEW RECONSTRUCTION.
Degree: MS, 2018, University of New Hampshire
URL: https://scholars.unh.edu/thesis/1246
► Multiview reconstruction, a method for creating 3D models from multiple images from different views, has been a popular topic of research in the eld of…
(more)
▼ Multiview
reconstruction, a method for creating
3D models from multiple images from different views, has been a popular topic of research in the eld of computer vision in the last two decades. Increased availability of high-quality cameras led to the development of advanced techniques and algorithms. However, little attention has been paid to multiview
reconstruction in underwater conditions. Researchers in a wide variety of elds (e.g. marine biology, archaeology, and geology) could benefit from having
3D models of seafloor and underwater objects. Cameras, designed to operate in air, must be put in protective housings to work underwater. This affects the image formation process. The largest source of underwater image distortion results from refraction of light, which occurs when light rays travel through boundaries between media with different refractive indices. This study addresses methods for accounting for light refraction when using a static rig with multiple cameras. We define a set of procedures to achieve optimal underwater
reconstruction results, and we analyze the expected quality of the
3D models' measurements.
Advisors/Committee Members: Philip J Hatcher, R D Bergeron, Yuri Rzhanov.
Subjects/Keywords: 3D reconstruction; Image Processing
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
KOZLOV, I. V. (2018). ANALYSIS OF UNCERTAINTY IN UNDERWATER MULTIVIEW RECONSTRUCTION. (Thesis). University of New Hampshire. Retrieved from https://scholars.unh.edu/thesis/1246
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
KOZLOV, IGOR V. “ANALYSIS OF UNCERTAINTY IN UNDERWATER MULTIVIEW RECONSTRUCTION.” 2018. Thesis, University of New Hampshire. Accessed January 23, 2021.
https://scholars.unh.edu/thesis/1246.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
KOZLOV, IGOR V. “ANALYSIS OF UNCERTAINTY IN UNDERWATER MULTIVIEW RECONSTRUCTION.” 2018. Web. 23 Jan 2021.
Vancouver:
KOZLOV IV. ANALYSIS OF UNCERTAINTY IN UNDERWATER MULTIVIEW RECONSTRUCTION. [Internet] [Thesis]. University of New Hampshire; 2018. [cited 2021 Jan 23].
Available from: https://scholars.unh.edu/thesis/1246.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
KOZLOV IV. ANALYSIS OF UNCERTAINTY IN UNDERWATER MULTIVIEW RECONSTRUCTION. [Thesis]. University of New Hampshire; 2018. Available from: https://scholars.unh.edu/thesis/1246
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Waterloo
8.
Cavan, Neil.
Reconstruction of 3D Points From Uncalibrated Underwater Video.
Degree: 2011, University of Waterloo
URL: http://hdl.handle.net/10012/6242
► This thesis presents a 3D reconstruction software pipeline that is capable of generating point cloud data from uncalibrated underwater video. This research project was undertaken…
(more)
▼ This thesis presents a 3D reconstruction software pipeline that is capable of generating
point cloud data from uncalibrated underwater video. This research project was undertaken
as a partnership with 2G Robotics, and the pipeline described in this thesis will become
the 3D reconstruction engine for a software product that can generate photo-realistic 3D
models from underwater video. The pipeline proceeds in three stages: video tracking,
projective reconstruction, and autocalibration.
Video tracking serves two functions: tracking recognizable feature points, as well as selecting well-spaced
keyframes with a wide enough baseline to be used in the reconstruction. Video tracking is accomplished
using Lucas-Kanade optical flow as implemented in the OpenCV toolkit. This simple and
widely used method is well-suited to underwater video, which is taken by carefully piloted
and slow-moving underwater vehicles.
Projective reconstruction is the process of simultaneously calculating the motion of the
cameras and the 3D location of observed points in the scene. This is accomplished using
a geometric three-view technique. Results are presented
showing that the projective reconstruction algorithm detailed here compares favourably to
state-of-the-art methods.
Autocalibration is the process of transforming a projective reconstruction, which is not
suitable for visualization or measurement, into a metric space where it can be used. This
is the most challenging part of the 3D reconstruction pipeline, and this thesis presents a
novel autocalibration algorithm. Results are shown for two existing cost function-based
methods in the literature which failed when applied to underwater video, as well as the
proposed hybrid method. The hybrid method combines the best parts of its two parent
methods, and produces good results on underwater video.
Final results are shown for the 3D reconstruction pipeline operating on short under-
water video sequences to produce visually accurate 3D point clouds of the scene, suitable
for photorealistic rendering. Although further work remains to extend and improve the
pipeline for operation on longer sequences, this thesis presents a proof-of-concept method
for 3D reconstruction from uncalibrated underwater video.
Subjects/Keywords: 3D Reconstruction; Computer Vision; Autocalibration
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Cavan, N. (2011). Reconstruction of 3D Points From Uncalibrated Underwater Video. (Thesis). University of Waterloo. Retrieved from http://hdl.handle.net/10012/6242
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Cavan, Neil. “Reconstruction of 3D Points From Uncalibrated Underwater Video.” 2011. Thesis, University of Waterloo. Accessed January 23, 2021.
http://hdl.handle.net/10012/6242.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Cavan, Neil. “Reconstruction of 3D Points From Uncalibrated Underwater Video.” 2011. Web. 23 Jan 2021.
Vancouver:
Cavan N. Reconstruction of 3D Points From Uncalibrated Underwater Video. [Internet] [Thesis]. University of Waterloo; 2011. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/10012/6242.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Cavan N. Reconstruction of 3D Points From Uncalibrated Underwater Video. [Thesis]. University of Waterloo; 2011. Available from: http://hdl.handle.net/10012/6242
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Louisiana State University
9.
Ravi, Padmapriya.
Efficient Dense 3D Reconstruction Using Image Pairs.
Degree: MSEE, Electrical and Computer Engineering, 2014, Louisiana State University
URL: etd-01122015-013948
;
https://digitalcommons.lsu.edu/gradschool_theses/3277
► The 3D reconstruction of a scene from 2D images is an important topic in the _x000C_eld of Computer Vision due to the high demand…
(more)
▼ The 3D reconstruction of a scene from 2D images is an important topic in the _x000C_eld of Computer Vision due to the high demand in various applications such as gaming, animations, face recognition, parts inspections, etc. The accuracy of a 3D reconstruction is highly dependent on the accuracy of the correspondence matching between the images. For the purpose of high accuracy of 3D reconstruction system using just two images of the scene, it is important to _x000C_nd accurate correspondence between the image pairs. In this thesis, we implement an accurate 3D reconstruction system from two images of the scene at di_x000B_erent orientation using a normal digital camera. We use epipolar geometry to improvise the performance of the initial coarse correspondence matches between the images. Finally we calculate the reprojection error of the 3D reconstruction system before and after re_x000C_ning the correspondence matches using the epipolar geometry and compare the performance between them. Even though many feature-based correspondence matching techniques provide robust matching required for 3D reconstruction, it gives only coarse correspondence matching between the images. This is not su_x000E_cient to reconstruct the detailed 3D structure of the objects. Therefore we use our improvised image matching to calculate the camera parameters and implement dense image matching using thin-plate spline interpolation, which interpolates the surface based on the initial control points obtained from coarse correspondence matches. Since the thin-plate spline interpolates highly dense points from a very few control points, the correspondence mapping between the images are not accurate. We propose a new method to improve the performance of the dense image matching using epipolar geometry and intensity based thin-plate spline interpolation. We apply the proposed method for 3D reconstruction using two images. Finally, we develop systematic evaluation for our dense 3D reconstruction system and discuss the results.
Subjects/Keywords: 3D reconstruction; multiple view geometry
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ravi, P. (2014). Efficient Dense 3D Reconstruction Using Image Pairs. (Masters Thesis). Louisiana State University. Retrieved from etd-01122015-013948 ; https://digitalcommons.lsu.edu/gradschool_theses/3277
Chicago Manual of Style (16th Edition):
Ravi, Padmapriya. “Efficient Dense 3D Reconstruction Using Image Pairs.” 2014. Masters Thesis, Louisiana State University. Accessed January 23, 2021.
etd-01122015-013948 ; https://digitalcommons.lsu.edu/gradschool_theses/3277.
MLA Handbook (7th Edition):
Ravi, Padmapriya. “Efficient Dense 3D Reconstruction Using Image Pairs.” 2014. Web. 23 Jan 2021.
Vancouver:
Ravi P. Efficient Dense 3D Reconstruction Using Image Pairs. [Internet] [Masters thesis]. Louisiana State University; 2014. [cited 2021 Jan 23].
Available from: etd-01122015-013948 ; https://digitalcommons.lsu.edu/gradschool_theses/3277.
Council of Science Editors:
Ravi P. Efficient Dense 3D Reconstruction Using Image Pairs. [Masters Thesis]. Louisiana State University; 2014. Available from: etd-01122015-013948 ; https://digitalcommons.lsu.edu/gradschool_theses/3277
University of Sydney
10.
Zhang, Donghao.
Automatic Neuron Reconstruction Based on 3D Microscopic Images
.
Degree: 2016, University of Sydney
URL: http://hdl.handle.net/2123/15390
► The digital reconstruction of single neurons from 3D microscopic images plays an important role for understanding the neuron morphology and function. However the accurate automatic…
(more)
▼ The digital reconstruction of single neurons from 3D microscopic images plays an important role for understanding the neuron morphology and function. However the accurate automatic neuron reconstruction remains a challenging task due to the varying image quality and the complexity in the arborisation of neurons. In this thesis, a novel automatic neuron reconstruction framework is proposed with image enhancement pipelines, soma volume reconstruction and neuron tree tracing. A Neuron Stalker algorithm is first designed to trace the neuronal tree structure based on local gradient vector flows. A more advanced neuron tracing algorithm, so called Rivulet, is further proposed by performing iterative back-tracking on the results of fast-marching with long branches are iteratively extracted. The proposed automatic neuron reconstruction framework was evaluated with various datasets provided by Diadem challenge and the recent BigNeuron project, and demonstrated great robustness to discontinuous and noisy neuronal structures in 3D microscopic images. It also outperformed the other state-of-the–art methods in terms of accuracy of neuronal morphological reconstruction.
Subjects/Keywords: 3D Neuron Reconstruction;
Neuron Morphology
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Zhang, D. (2016). Automatic Neuron Reconstruction Based on 3D Microscopic Images
. (Thesis). University of Sydney. Retrieved from http://hdl.handle.net/2123/15390
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Zhang, Donghao. “Automatic Neuron Reconstruction Based on 3D Microscopic Images
.” 2016. Thesis, University of Sydney. Accessed January 23, 2021.
http://hdl.handle.net/2123/15390.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Zhang, Donghao. “Automatic Neuron Reconstruction Based on 3D Microscopic Images
.” 2016. Web. 23 Jan 2021.
Vancouver:
Zhang D. Automatic Neuron Reconstruction Based on 3D Microscopic Images
. [Internet] [Thesis]. University of Sydney; 2016. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/2123/15390.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Zhang D. Automatic Neuron Reconstruction Based on 3D Microscopic Images
. [Thesis]. University of Sydney; 2016. Available from: http://hdl.handle.net/2123/15390
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Michigan
11.
Chen, Weifeng.
Learning Single-Image 3D from the Internet.
Degree: PhD, Computer Science & Engineering, 2020, University of Michigan
URL: http://hdl.handle.net/2027.42/163248
► Single-image 3D refers to the task of recovering 3D properties such as depth and surface normals from an RGB image. It is one of the…
(more)
▼ Single-image
3D refers to the task of recovering
3D properties such as depth and surface normals from an RGB image. It is one of the fundamental problems in Computer Vision, and its progress has the potential to bring major advancement to various other fields in vision. Although significant progress has been made in this field, the current best systems still struggle to perform well on arbitrary images "in the wild", i.e. images that depict all kinds of contents and scenes. One major obstacle is the lack of diverse training data. This dissertation makes contributions towards solving the data issue by extracting
3D supervision from the Internet, and proposing novel algorithms to learn from Internet
3D to significantly advance single-view
3D perception.
First, we have constructed "Depth in the Wild" (DIW), a depth dataset consisting of 0.5 million diverse images. Each image is manually annotated with randomly sampled points and their relative depth. After benchmarking state-of-the-art single-view
3D systems on DIW, we found that even though current arts perform well on existing datasets, they perform poorly on images in the wild. We then propose a novel algorithm that learns to estimate depth using annotations of relative depth. Compared to the state of the art, our algorithm is simpler and performs better. Experiments show that our algorithm, combined with existing RGB-D data and our new relative depth annotations, significantly improves single-image depth perception in the wild.
Second, we have constructed "Surface Normals in the Wild" (SNOW), a dataset with 60K Internet images, each manually annotated with the surface normal for one randomly sampled point. We explore advancing depth perception in the wild using surface normal as supervision. To train networks with surface normal annotations, we propose two novel losses, one that emphasizes depth accuracy, and another one that emphasizes surface normal accuracy. Experiments show that our approach significantly improves the quality of depth estimation in the wild.
Third, we have constructed "Open Annotations of Single-Image Surfaces" (OASIS), a large-scale dataset for single-image
3D in the wild. It consists of pixel-wise reconstructions of
3D surfaces for 140K randomly sampled Internet images. Six types of
3D properties are manually annotated for each image: occlusion boundary (depth discontinuity), fold boundary (normal discontinuity), surface normal, relative depth, relative normal (orthogonal, parallel, or neither), and planarity (planar or not). The rich annotations of human
3D perception in OASIS open up new research opportunities on a spectrum of single-image
3D tasks – they provide in-the-wild ground truths either for the first time, or at a much larger scale than prior work. By benchmarking leading deep learning models on a variety of
3D tasks, we observe a large room for performance improvement, pointing to ample research opportunities for designing new learning algorithms for single-image
3D.
Finally, we have constructed "YouTube3D", a large-scale…
Advisors/Committee Members: Deng, Jia (committee member), Fouhey, David Ford (committee member), Mei, Qiaozhu (committee member), Johnson, Justin Christopher (committee member).
Subjects/Keywords: 3D Reconstruction; Computer Science; Engineering
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Chen, W. (2020). Learning Single-Image 3D from the Internet. (Doctoral Dissertation). University of Michigan. Retrieved from http://hdl.handle.net/2027.42/163248
Chicago Manual of Style (16th Edition):
Chen, Weifeng. “Learning Single-Image 3D from the Internet.” 2020. Doctoral Dissertation, University of Michigan. Accessed January 23, 2021.
http://hdl.handle.net/2027.42/163248.
MLA Handbook (7th Edition):
Chen, Weifeng. “Learning Single-Image 3D from the Internet.” 2020. Web. 23 Jan 2021.
Vancouver:
Chen W. Learning Single-Image 3D from the Internet. [Internet] [Doctoral dissertation]. University of Michigan; 2020. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/2027.42/163248.
Council of Science Editors:
Chen W. Learning Single-Image 3D from the Internet. [Doctoral Dissertation]. University of Michigan; 2020. Available from: http://hdl.handle.net/2027.42/163248
12.
Arnaud, Adrien.
Études et conception d'algorithmes de reconstruction 3D sur tablettes : génération automatique de modèles 3D éditables de bâtiments existants : Study and Conception of 3D Reconstruction Algorithms on Tablets : Automatic Generation of 3D Editable Models of Existing Buildings.
Degree: Docteur es, Informatique, 2018, Paris Saclay
URL: http://www.theses.fr/2018SACLS512
► L'objectif de ces travaux de thèse consiste à mettre en place des solutions algorithmiques permettant de reconstruire un modèle 3D éditable d'un environnement intérieur à…
(more)
▼ L'objectif de ces travaux de thèse consiste à mettre en place des solutions algorithmiques permettant de reconstruire un modèle 3D éditable d'un environnement intérieur à l'aide d'une tablette équipée d'un capteur de profondeur.Ces travaux s'inscrivent dans le contexte de la rénovation d'intérieur. Les normes Européennes poussent à la rénovation énergétique et à la modélisation 3D des bâtiments existants. Des outils professionnels utilisant des capteurs de type LIDAR permettent de reconstruire des nuages de points de très grande qualité, mais sont coûteux et longs à mettre en œuvre. De plus, il est très difficile d'identifier automatiquement les constituants d'un bâtiment pour en exporter un modèle 3D éditable complet.Dans le cadre de la rénovation d’intérieur, il n'est pas nécessaire de disposer des informations sur l'ensemble du bâtiment, seules les principales dimensions et surfaces sont nécessaires. Nous pouvons alors envisager d'automatiser complètement le processus de modélisation 3D.La mise sur le marché de capteurs de profondeur intégrables sur tablettes, et l'augmentation des capacités de calcul de ces dernières nous permet d'envisager l'adaptation d'algorithmes de reconstruction 3D classiques à ces supports.Au cours de ces travaux, nous avons envisagé deux approches de reconstruction 3D différentes. La première approche s'appuie sur des méthodes de l'état de l'art. Elle consiste à générer un maillage 3D d'un environnement intérieur en temps réel sur tablette, puis d'utiliser ce maillage 3D pour identifier la structure globale du bâtiment (murs, portes et fenêtres). La deuxième approche envisagée consiste à générer un modèle 3D éditable en temps réel, sans passer par un maillage intermédiaire. De cette manière beaucoup plus d'informations sont disponibles pour pouvoir détecter les éléments structuraux. Nous avons en effet à chaque instant donné un nuage de points complet ainsi que l'image couleur correspondante. Nous avons dans un premier temps mis en place deux algorithmes de segmentation planaire en temps réel. Puis, nous avons mis en place un algorithme d'analyse de ces plans permettant d'identifier deux plans identiques sur plusieurs prises de vue différentes. Nous sommes alors capables d'identifier les différents murs contenus dans l'environnement capturé, et nous pouvons mettre à jour leurs informations géométriques en temps réel.
This thesis works consisted to implement algorithmic solutions to reconstruct an editable 3D model of an indoor environment using a tablet equipped with a depth sensor.These works are part of the context of interior renovation. European standards push for energy renovation and 3D modeling of existing buildings. Professional tools using LIDAR-type sensors make it possible to reconstruct high-quality point clouds, but are costly and time-consuming to implement. In addition, it is very difficult to automatically identify the constituents of a building to export a complete editable 3D model.As part of the interior renovation, it is not necessary to have information on the…
Advisors/Committee Members: Ammi, Mehdi (thesis director).
Subjects/Keywords: Reconstruction 3D; Systèmes mobiles; Segmentation 3D; 3D reconstruction; Mobile devices; 3D segmentation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Arnaud, A. (2018). Études et conception d'algorithmes de reconstruction 3D sur tablettes : génération automatique de modèles 3D éditables de bâtiments existants : Study and Conception of 3D Reconstruction Algorithms on Tablets : Automatic Generation of 3D Editable Models of Existing Buildings. (Doctoral Dissertation). Paris Saclay. Retrieved from http://www.theses.fr/2018SACLS512
Chicago Manual of Style (16th Edition):
Arnaud, Adrien. “Études et conception d'algorithmes de reconstruction 3D sur tablettes : génération automatique de modèles 3D éditables de bâtiments existants : Study and Conception of 3D Reconstruction Algorithms on Tablets : Automatic Generation of 3D Editable Models of Existing Buildings.” 2018. Doctoral Dissertation, Paris Saclay. Accessed January 23, 2021.
http://www.theses.fr/2018SACLS512.
MLA Handbook (7th Edition):
Arnaud, Adrien. “Études et conception d'algorithmes de reconstruction 3D sur tablettes : génération automatique de modèles 3D éditables de bâtiments existants : Study and Conception of 3D Reconstruction Algorithms on Tablets : Automatic Generation of 3D Editable Models of Existing Buildings.” 2018. Web. 23 Jan 2021.
Vancouver:
Arnaud A. Études et conception d'algorithmes de reconstruction 3D sur tablettes : génération automatique de modèles 3D éditables de bâtiments existants : Study and Conception of 3D Reconstruction Algorithms on Tablets : Automatic Generation of 3D Editable Models of Existing Buildings. [Internet] [Doctoral dissertation]. Paris Saclay; 2018. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2018SACLS512.
Council of Science Editors:
Arnaud A. Études et conception d'algorithmes de reconstruction 3D sur tablettes : génération automatique de modèles 3D éditables de bâtiments existants : Study and Conception of 3D Reconstruction Algorithms on Tablets : Automatic Generation of 3D Editable Models of Existing Buildings. [Doctoral Dissertation]. Paris Saclay; 2018. Available from: http://www.theses.fr/2018SACLS512
13.
Burns, Calum.
Super résolution de texture pour la reconstruction 3D fine : Texture Super Resolution for 3D Reconstruction.
Degree: Docteur es, Traitement du signal et des images, 2018, Université Paris-Saclay (ComUE)
URL: http://www.theses.fr/2018SACLS026
► La reconstruction 3D multi-vue atteint désormais un niveau de maturité industrielle : des utilisateurs non-experts peuvent produire des modèles 3D large-échelle de qualité à l'aide…
(more)
▼ La
reconstruction 3D multi-vue atteint désormais un niveau de maturité industrielle : des utilisateurs non-experts peuvent produire des modèles
3D large-échelle de qualité à l'aide de logiciels commerciaux. Ces reconstructions utilisent des capteurs haut de gamme comme des LIDAR ou des appareils photos de type DSLR, montés sur un trépied et déplacés autour de la scène. Ces protocoles d'acquisition sont mal adaptés à l’inspection d’infrastructures de grande taille, à géométrie complexe. Avec l'évolution rapide des capacités des micro-drones, il devient envisageable de leur confier ce type de tâche. Un tel choix modifie les données d’acquisition : on passe d’un ensemble restreint de photos de qualité, soigneusement acquises par l’opérateur, à une séquence d'images à cadence vidéo, sujette à des variations de qualité image dues, par exemple, au bougé et au défocus.Les données vidéo posent problème aux logiciels de photogrammétrie du fait de la combinatoire élevée engendrée par le grand nombre d’images. Nous proposons d’exploiter l’intégralité des images en deux étapes. Au cours de la première, la
reconstruction 3D est obtenue en sous-échantillonnant temporellement la séquence, lors de la seconde, la restitution haute résolution de texture est obtenue en exploitant l'ensemble des images. L'intérêt de la texture est de permettre de visualiser des détails fins du modèle numérisé qui ont été perdus dans le bruit géométrique de la
reconstruction. Cette augmentation de qualité se fait via des techniques de Super Résolution (SR).Pour atteindre cet objectif nous avons conçu et réalisé une chaîne algorithmique prenant, en entrée, la séquence vidéo acquise et fournissant, en sortie, un modèle
3D de la scène avec une texture sur-résolue. Cette chaîne est construite autour d’un algorithme de
reconstruction 3D multi-vues de l’état de l’art pour la partie géométrique.Une contribution centrale de notre chaîne est la méthode de recalage employée afin d’atteindre la précision sub-pixellique requise pour la SR. Contrairement aux données classiquement utilisées en SR, nos prises de vues sont affectées par un mouvement
3D, face à une scène à géométrie
3D, ce qui entraîne des mouvements image complexes. La précision intrinsèque des méthodes de
reconstruction 3D est insuffisante pour effectuer un recalage purement géométrique, ainsi nous appliquons un raffinement supplémentaire par flot optique. Le résultat de cette méthode de restitution de texture SR est d'abord comparée qualitativement à une approche concurrente de l’état de l’art.Ces appréciations qualitatives sont renforcées par une évaluation quantitative de qualité image. Nous avons à cet effet élaboré un protocole d’évaluation quantitatif de techniques de SR appliquées sur des surfaces
3D. Il est fondé sur l'utilisation de mires fractales binaires, initialement proposées par S. Landeau. Nous avons étendu ces idées au contexte de SR sur des surfaces courbes. Cette méthode est employée ici pour valider les choix de notre méthode de SR, mais elle s'applique à l'évaluation de toute…
Advisors/Committee Members: Champagnat, Frédéric (thesis director).
Subjects/Keywords: Reconstruction 3D; Super résolution; Texture; 3D Reconstruction; Super resolution; Texture mapping
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Burns, C. (2018). Super résolution de texture pour la reconstruction 3D fine : Texture Super Resolution for 3D Reconstruction. (Doctoral Dissertation). Université Paris-Saclay (ComUE). Retrieved from http://www.theses.fr/2018SACLS026
Chicago Manual of Style (16th Edition):
Burns, Calum. “Super résolution de texture pour la reconstruction 3D fine : Texture Super Resolution for 3D Reconstruction.” 2018. Doctoral Dissertation, Université Paris-Saclay (ComUE). Accessed January 23, 2021.
http://www.theses.fr/2018SACLS026.
MLA Handbook (7th Edition):
Burns, Calum. “Super résolution de texture pour la reconstruction 3D fine : Texture Super Resolution for 3D Reconstruction.” 2018. Web. 23 Jan 2021.
Vancouver:
Burns C. Super résolution de texture pour la reconstruction 3D fine : Texture Super Resolution for 3D Reconstruction. [Internet] [Doctoral dissertation]. Université Paris-Saclay (ComUE); 2018. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2018SACLS026.
Council of Science Editors:
Burns C. Super résolution de texture pour la reconstruction 3D fine : Texture Super Resolution for 3D Reconstruction. [Doctoral Dissertation]. Université Paris-Saclay (ComUE); 2018. Available from: http://www.theses.fr/2018SACLS026
Delft University of Technology
14.
van Apeldoorn, Naphur (author).
3D Reconstruction of Niniveh: A casestudy on the Bas-reliefs of the Southwest Palace of Sennacherib with monocular images.
Degree: 2017, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:54b5c5c4-1a36-4571-b0d4-4ef0450c311e
► Parts of the Southwest Palace of Sennacherib (700 BC), which were located in Nineveh (Iraq), are now destroyed by the ongoing conflict in Iraq and…
(more)
▼ Parts of the Southwest Palace of Sennacherib (700 BC), which were located in Nineveh (Iraq), are now destroyed by the ongoing conflict in Iraq and Syria. The palace rooms used to be decorated with numerous Assyrian reliefs. Luckily, digital pictures of the site are available thanks to an Italian expedition in 2002. The goal of this research is to physically reproduce the destroyed reliefs using this photo database. First photogrammetry was used to rebuild the global dimensions of the reliefs. The details are reconstructed by fusing a highly detailed depth map retrieved with Shape from Luminance (SFL), together with a coarser Artificial Reconstruction. The fused reconstruction was evaluated with the eigenvalues of the Hessian. The eigenvalues give an intuitive measure about the shapes of the reliefs. The RMSE of the results improve up to 44.4% compared to the usage of an intensity (grey) image. The final 3D models are used to produce full size reproductions with 3D printing and CNC milling.
Biorobotics
Advisors/Committee Members: Lenseigne, Boris (mentor), Jonker, Pieter (mentor), Dik, Joris (graduation committee), Geraedts, Jo (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: 3D Reconstruction; Niniveh; image reconstruction; Monocular; 3D printing; Cultural Heritage
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
van Apeldoorn, N. (. (2017). 3D Reconstruction of Niniveh: A casestudy on the Bas-reliefs of the Southwest Palace of Sennacherib with monocular images. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:54b5c5c4-1a36-4571-b0d4-4ef0450c311e
Chicago Manual of Style (16th Edition):
van Apeldoorn, Naphur (author). “3D Reconstruction of Niniveh: A casestudy on the Bas-reliefs of the Southwest Palace of Sennacherib with monocular images.” 2017. Masters Thesis, Delft University of Technology. Accessed January 23, 2021.
http://resolver.tudelft.nl/uuid:54b5c5c4-1a36-4571-b0d4-4ef0450c311e.
MLA Handbook (7th Edition):
van Apeldoorn, Naphur (author). “3D Reconstruction of Niniveh: A casestudy on the Bas-reliefs of the Southwest Palace of Sennacherib with monocular images.” 2017. Web. 23 Jan 2021.
Vancouver:
van Apeldoorn N(. 3D Reconstruction of Niniveh: A casestudy on the Bas-reliefs of the Southwest Palace of Sennacherib with monocular images. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Jan 23].
Available from: http://resolver.tudelft.nl/uuid:54b5c5c4-1a36-4571-b0d4-4ef0450c311e.
Council of Science Editors:
van Apeldoorn N(. 3D Reconstruction of Niniveh: A casestudy on the Bas-reliefs of the Southwest Palace of Sennacherib with monocular images. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:54b5c5c4-1a36-4571-b0d4-4ef0450c311e
15.
Hmida, Rihab.
Vision et reconstruction 3D : application à la robotique mobile : Vision and 3D reconstruction : application to Mobile Robotics.
Degree: Docteur es, Systèmes automatiques et micro-électroniques, 2016, Montpellier; Laboratoire d'électronique et de micro-électronique (Monastir, Tunisie)
URL: http://www.theses.fr/2016MONTT335
► Avec l’évolution des processus technologiques, l’intérêt pour la robotique mobile n’a de cesse d’augmenter depuis quelques années, notamment pour remplacer l’homme dans des environnements à…
(more)
▼ Avec l’évolution des processus technologiques, l’intérêt pour la robotique mobile n’a de cesse d’augmenter depuis quelques années, notamment pour remplacer l’homme dans des environnements à risque (zones radioactives, robots militaires) ou des zones qui lui sont inaccessibles (exploration planétaire ou sous-marine), ou à des échelles différentes (robot à l’intérieur d’une canalisation, voire robot chirurgical à l’intérieur du corps humain). Dans ce même contexte, les systèmes de navigation destinés plus particulièrement à l’exploration sous-marine suscitent de plus en plus l’intérêt de plusieurs géologues, roboticiens et scientifiques en vue de mieux connaître et caractériser les réseaux sous-marins. Pour des raisons de sécurité optimale, de nouvelles technologies (Radar, Sonar, système de caméras,..) ont été développées pour remplacer les plongeurs humains.C’est dans ce cadre que s’intègre les travaux de cette thèse ayant comme objectif la mise en œuvre d’un système de vision stéréoscopique permettant l’acquisition d’informations utiles et le développement d’un algorithme pour la restitution de la structure 3D d’un environnement confiné aquatique. Notre système est composé d’une paire de capteurs catadioptriques et d’une ceinture de pointeurs lasers permettant d’identifier des amers visuels de la scène et d’une plateforme pour l’exécution du processus de traitement des images acquises. La chaîne de traitement est précédée par une phase d’étalonnage effectuée hors-ligne pour la modélisation géométrique du système complet. L’algorithme de traitement consiste à une analyse pixellique des images stéréoscopiques pour l’extraction des projections lasers 2D et reconstruire leurs correspondants 3D en se basant sur les paramètres d’étalonnage.La mise en œuvre du système complet sur une plateforme logicielle demande un temps d’exécution supérieur à celui exigé par l’application. Les travaux clôturant ce mémoire s’adressent à cette problématique, et proposent une solution permettant de simplifier le développement et l’implémentation d’applications temps-réel sur des plateformes basées sur un dispositif FPGA. La mise en œuvre de notre application a été effectuée et une étude des performances est présentée tout en considérant les besoins de l’application et ses exigences de point de vue précision, rapidité et taux d’efficacité.
With the development of technological processes, interest in mobile robotics is constantly increasing in recent years, particularly to replace human in environments of risk (radioactive areas, military robots) or areas that are inaccessible (planetary or underwater exploration), or at different scales (robot within a pipeline or surgical robot inside the human body). In the same context, navigation systems are designed specifically for underwater exploration which is attracting more and more interest of several geologists, robotics and scientists in order to better understand and characterize submarine environment. For optimal security, new technologies (radar, sonar, camera system, ..) have been…
Advisors/Committee Members: Zapata, René (thesis director), Mtibaa, Abdellatif (thesis director).
Subjects/Keywords: Vision; Reconstruction 3D; Robotique; Vision; 3D reconstruction; Robotics
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Hmida, R. (2016). Vision et reconstruction 3D : application à la robotique mobile : Vision and 3D reconstruction : application to Mobile Robotics. (Doctoral Dissertation). Montpellier; Laboratoire d'électronique et de micro-électronique (Monastir, Tunisie). Retrieved from http://www.theses.fr/2016MONTT335
Chicago Manual of Style (16th Edition):
Hmida, Rihab. “Vision et reconstruction 3D : application à la robotique mobile : Vision and 3D reconstruction : application to Mobile Robotics.” 2016. Doctoral Dissertation, Montpellier; Laboratoire d'électronique et de micro-électronique (Monastir, Tunisie). Accessed January 23, 2021.
http://www.theses.fr/2016MONTT335.
MLA Handbook (7th Edition):
Hmida, Rihab. “Vision et reconstruction 3D : application à la robotique mobile : Vision and 3D reconstruction : application to Mobile Robotics.” 2016. Web. 23 Jan 2021.
Vancouver:
Hmida R. Vision et reconstruction 3D : application à la robotique mobile : Vision and 3D reconstruction : application to Mobile Robotics. [Internet] [Doctoral dissertation]. Montpellier; Laboratoire d'électronique et de micro-électronique (Monastir, Tunisie); 2016. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2016MONTT335.
Council of Science Editors:
Hmida R. Vision et reconstruction 3D : application à la robotique mobile : Vision and 3D reconstruction : application to Mobile Robotics. [Doctoral Dissertation]. Montpellier; Laboratoire d'électronique et de micro-électronique (Monastir, Tunisie); 2016. Available from: http://www.theses.fr/2016MONTT335
Brno University of Technology
16.
Karásek, Miroslav.
Zpracování a vizualizace stereo snímků: Stereo image processing and visualisation.
Degree: 2019, Brno University of Technology
URL: http://hdl.handle.net/11012/17300
► This thesis deals with the processing of stereo images. It described the principles of calibration and rectification of stereo images. The thesis described several methods…
(more)
▼ This thesis deals with the processing of stereo images. It described the principles of calibration and rectification of stereo images. The thesis described several methods for finding important points. SURF method is then implemented for practical solution. Finding correspondences is realized using the methods of image processing library OpenCV. Reconstructed spatial coordinates of points and write by the format specified VRML97. Finally, there is introduced evaluated accuracy of spatial data acquisition and comparison of computational cost generated programs.
Advisors/Committee Members: Petyovský, Petr (advisor), Richter, Miloslav (referee).
Subjects/Keywords: 3D zobrazování; 3d rekonstrukce; 3d rektifikace; prezentace 3D obrazu; OpenCV; 3D imaging; 3d reconstruction; 3d rectification; 3D image presentation; OpenCV
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Karásek, M. (2019). Zpracování a vizualizace stereo snímků: Stereo image processing and visualisation. (Thesis). Brno University of Technology. Retrieved from http://hdl.handle.net/11012/17300
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Karásek, Miroslav. “Zpracování a vizualizace stereo snímků: Stereo image processing and visualisation.” 2019. Thesis, Brno University of Technology. Accessed January 23, 2021.
http://hdl.handle.net/11012/17300.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Karásek, Miroslav. “Zpracování a vizualizace stereo snímků: Stereo image processing and visualisation.” 2019. Web. 23 Jan 2021.
Vancouver:
Karásek M. Zpracování a vizualizace stereo snímků: Stereo image processing and visualisation. [Internet] [Thesis]. Brno University of Technology; 2019. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/11012/17300.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Karásek M. Zpracování a vizualizace stereo snímků: Stereo image processing and visualisation. [Thesis]. Brno University of Technology; 2019. Available from: http://hdl.handle.net/11012/17300
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
17.
Li, Si.
Data acquisition modeling and hybrid coronary tree 3D reconstruction in C-arm CBCT imaging : Modélisation du processus d'acquisition et reconstruction 3D hybride d'arbres coronaires en angiographie RX rotationelle.
Degree: Docteur es, Traitement du signal et télécommunications, 2017, Rennes 1; Southeast university (Nanjing, China)
URL: http://www.theses.fr/2017REN1S133
► L'angiographie coronarienne RX (ou coronarographie) reste la modalité de référence permettant de déterminer avec précision le degré et le nombre de sténoses coronariennes ainsi que…
(more)
▼ L'angiographie coronarienne RX (ou coronarographie) reste la modalité de référence permettant de déterminer avec précision le degré et le nombre de sténoses coronariennes ainsi que le nombre de vaisseaux atteints. L'objectif de ce travail de thèse de doctorat concerne l'amélioration de la reconstruction 3D des coronaires afin d'améliorer le diagnostic, ainsi que la sécurité et la précision des interventions minimalement invasives. Dans un premier temps, une contribution majeure vise à améliorer l'étape de calibration du système d'imagerie rotationnelle R-X. Premièrement, nous avons donc proposé un nouvel algorithme de calibrage basé objet inspiré de la méthode de Xu et al, dédié au système robotisé Artis Zeego. Deuxièmement, nous transposons les géométries de projection dans le système de coordonnées du C-arm. Nous avons proposé des modèles de mouvement des géométries de projection en considérant objectivement et systématiquement tous les facteurs possibles. Ces modèles de mouvement permettent de simplifier la procédure de calibration en routine clinique. The résultats expérimentaux indiquent que les modèles de mouvement proposés ont une précision acceptable afin estimer les paramètres d'acquisition. Dans un second temps, une contribution majeure vise à proposer une nouvelle méthode de reconstruction des coronaires par compensation de mouvement. Les étapes de reconstruction sont: l'opérateur de projection, la segmentation des projections acquises, le recalage iconique, la reconstruction initiale et la reconstruction avec compensation de mouvement. Nous avons opté pour l'opérateur de projection Distance Driven simplifié proposé par Oukili. Nous avons adopté comme mesure de similarité l'information Mutuelle (MI) avec un terme de rigidité. Pour optimiser cette fonction de coût, nous avons utilisé la méthode Advanced Adaptive Stochastic Gradient Descent (ASGD). Nous avons adopté une reconstruction statistique itérative basée on MAP et l'a priori L0. Les résultats expérimentaux indiquent que la méthode proposée améliore visuellement la qualité de la reconstruction. Le contraste et les détails des reconstructions sont améliorés par compensation de mouvement.
The rotational angiography RX of the coronaries is a standard modality to determine the degree and the number of the coronaries stenosis. The objective of this dissertation aims at improving the 3D reconstruction of the coronary arteries, which can improve the diagnosis, the security and the precision of the minimal invasive interventions.For the first part, the major contribution is improving the calibration procedure of the rotational R-X imaging system. First, we propose a new calibration algorithm based on the classical helical phantom on the Artis-Zeego system. Second, we transfer the geometries to the C-arm coordinate system. Last, we propose the movement models of the projection geometries objectively and systematically at 3 representative work positions. The movement models simplify the clinical procedures. The experiment results indicate that the proposed…
Advisors/Committee Members: Toumoulin, Christine (thesis director), Luo, Limin (thesis director).
Subjects/Keywords: Artis-Zeego; Calibration; 3d reconstruction 3d; Modèles de mouvement; 3D reconstruction; Artis-Zeego
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Li, S. (2017). Data acquisition modeling and hybrid coronary tree 3D reconstruction in C-arm CBCT imaging : Modélisation du processus d'acquisition et reconstruction 3D hybride d'arbres coronaires en angiographie RX rotationelle. (Doctoral Dissertation). Rennes 1; Southeast university (Nanjing, China). Retrieved from http://www.theses.fr/2017REN1S133
Chicago Manual of Style (16th Edition):
Li, Si. “Data acquisition modeling and hybrid coronary tree 3D reconstruction in C-arm CBCT imaging : Modélisation du processus d'acquisition et reconstruction 3D hybride d'arbres coronaires en angiographie RX rotationelle.” 2017. Doctoral Dissertation, Rennes 1; Southeast university (Nanjing, China). Accessed January 23, 2021.
http://www.theses.fr/2017REN1S133.
MLA Handbook (7th Edition):
Li, Si. “Data acquisition modeling and hybrid coronary tree 3D reconstruction in C-arm CBCT imaging : Modélisation du processus d'acquisition et reconstruction 3D hybride d'arbres coronaires en angiographie RX rotationelle.” 2017. Web. 23 Jan 2021.
Vancouver:
Li S. Data acquisition modeling and hybrid coronary tree 3D reconstruction in C-arm CBCT imaging : Modélisation du processus d'acquisition et reconstruction 3D hybride d'arbres coronaires en angiographie RX rotationelle. [Internet] [Doctoral dissertation]. Rennes 1; Southeast university (Nanjing, China); 2017. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2017REN1S133.
Council of Science Editors:
Li S. Data acquisition modeling and hybrid coronary tree 3D reconstruction in C-arm CBCT imaging : Modélisation du processus d'acquisition et reconstruction 3D hybride d'arbres coronaires en angiographie RX rotationelle. [Doctoral Dissertation]. Rennes 1; Southeast university (Nanjing, China); 2017. Available from: http://www.theses.fr/2017REN1S133
18.
Gélard, William.
Modélisation 3D et suivi visuel pour caractériser le phénotype de variétés de tournesol : 3D modeling and tracking to characterize the phenotype of sunflower varieties.
Degree: Docteur es, Informatique et robotique, 2018, Université Toulouse III – Paul Sabatier
URL: http://www.theses.fr/2018TOU30207
► L'augmentation constante de la demande alimentaire et énergétique dans le monde associée au réchauffement et changements climatiques ont poussé les recherches en agronomie vers le…
(more)
▼ L'augmentation constante de la demande alimentaire et énergétique dans le monde associée au réchauffement et changements climatiques ont poussé les recherches en agronomie vers le développement d'une agriculture plus durable et l'amélioration de la performance des cultures. Pour répondre à ces demandes, les chercheurs ont concentré leurs efforts sur le développement de méthodes de génotypage à haut débit (l'étude de la séquence génomique des plantes) et ont permis aux biologistes d'identifier les génotypes d'une grande quantité de plantes. De plus, comprendre les relations qui lient les génotypes (ADN) aux phénotypes (caractéristiques visuelles) qui évoluent en fonction des conditions d'irrigation, d'illumination ou de température est devenu un enjeu majeur dans la recherche agricole. Alors que les méthodes de génotypage ont été rapidement améliorées et automatisées au cours de la dernière décennie, les méthodes de phénotypage restent manuelles et parfois destructrices. Ces méthodes consistent à mesurer certains paramètres visuels d'une plante telle que : la hauteur de la tige principale, le nombre de feuilles, les angles d'initiation des feuilles ou la surface foliaire et plus important encore, à suivre ces paramètres tout au long de la croissance des plantes. Par conséquent, le nombre de plantes à cultiver est très important et les mesures prennent beaucoup de temps. Avec l'émergence des nouvelles technologies en vision par ordinateur et en robotique, les chercheurs en agronomie y ont vu un intérêt certain en vue d'automatiser la collecte et les mesures des données visuelles sur les plantes. La thèse porte sur la conception, le développement et la validation de traitements haut débit à exécuter automatiquement sur des images acquises sur des plantes de tournesol, en vue d'amplifier les capacités de phénotypage par les chercheurs en agronomie (et ultérieurement les évaluateurs de variétés et les semenciers). L'objectif est la mise au point d'un protocole d'acquisition d'images (en plante isolée) depuis un robot mobile (ou un système d'acquisition autonome) permettant d'améliorer, de moderniser et d'automatiser les méthodes de phénotypage actuelles afin d'aider les chercheurs en agronomie à collecter une grande quantité de données. Motivés par le souhait d'effectuer un phénotypage à haut débit, nous proposons une approche
3D pour extraire automatiquement les caractéristiques visuelles des plantes de tournesol cultivées en pot. Tout d'abord, un nuage de points
3D d'une plante est acquis avec des techniques classiques de Structure-from-Motion. Une étape de segmentation est ensuite effectuée pour extraire la tige principale et les feuilles. Dans le but de suivre les caractéristiques visuelles pendant la croissance des plantes, en particulier, suivre l'expansion foliaire de chaque feuille, une étape de labellisation basée sur le modèle botanique d'une plante est appliquée pour leur affecter une étiquette unique qui ne changera pas avec le temps. Enfin, les caractéristiques visuelles sont extraites et les résultats…
Advisors/Committee Members: Herbulot, Ariane (thesis director), Debaeke, Philippe (thesis director).
Subjects/Keywords: Phénotypage 3D; Tournesols; Reconstruction et segmentation 3D; Nuages de points 3D
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Gélard, W. (2018). Modélisation 3D et suivi visuel pour caractériser le phénotype de variétés de tournesol : 3D modeling and tracking to characterize the phenotype of sunflower varieties. (Doctoral Dissertation). Université Toulouse III – Paul Sabatier. Retrieved from http://www.theses.fr/2018TOU30207
Chicago Manual of Style (16th Edition):
Gélard, William. “Modélisation 3D et suivi visuel pour caractériser le phénotype de variétés de tournesol : 3D modeling and tracking to characterize the phenotype of sunflower varieties.” 2018. Doctoral Dissertation, Université Toulouse III – Paul Sabatier. Accessed January 23, 2021.
http://www.theses.fr/2018TOU30207.
MLA Handbook (7th Edition):
Gélard, William. “Modélisation 3D et suivi visuel pour caractériser le phénotype de variétés de tournesol : 3D modeling and tracking to characterize the phenotype of sunflower varieties.” 2018. Web. 23 Jan 2021.
Vancouver:
Gélard W. Modélisation 3D et suivi visuel pour caractériser le phénotype de variétés de tournesol : 3D modeling and tracking to characterize the phenotype of sunflower varieties. [Internet] [Doctoral dissertation]. Université Toulouse III – Paul Sabatier; 2018. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2018TOU30207.
Council of Science Editors:
Gélard W. Modélisation 3D et suivi visuel pour caractériser le phénotype de variétés de tournesol : 3D modeling and tracking to characterize the phenotype of sunflower varieties. [Doctoral Dissertation]. Université Toulouse III – Paul Sabatier; 2018. Available from: http://www.theses.fr/2018TOU30207
Université Montpellier II
19.
Méline, Arnaud.
Fusion multimodale pour la cartographie sous-marine : Multimodal fusion for underwater mapping.
Degree: Docteur es, Systèmes Automatiques et Microélectroniques, 2013, Université Montpellier II
URL: http://www.theses.fr/2013MON20005
► Le but de ce travail est d'analyser des scènes sous-marines naturelles et en particulier cartographier des environnements sous-marins en 3D. Il existe aujourd'hui de nombreuses…
(more)
▼ Le but de ce travail est d'analyser des scènes sous-marines naturelles et en particulier cartographier des environnements sous-marins en 3D. Il existe aujourd'hui de nombreuses techniques pour résoudre ce problème. L'originalité de ce travail se trouve dans la fusion de deux cartes obtenues avec des capteurs de différentes résolutions. Dans un premier temps, un engin autonome (ou un bateau) analyse les fonds marins avec un sonar multifaisceaux et crée une première carte globale de la zone. Cette carte est ensuite décomposée en petites cellules représentant une mosaïque du fond marin. Une deuxième analyse est ensuite réalisée sur certaines cellules particulières à l'aide d'un second capteur avec une résolution plus élevée. Cela permettra d'obtenir une carte détaillée 3D de la cellule. Un véhicule autonome sous-marin ou un plongeur muni d'un système de vision stéréoscopique effectuera cette acquisition.Ce projet se décompose en deux parties, la première s'intéressera à la reconstruction 3D de scènes sous-marines en milieu contraint à l'aide d'une paire stéréoscopique. La deuxième partie de l'étude portera sur l'aspect multimodal. Dans notre cas, nous utilisons cette méthode pour obtenir des reconstructions précises d'objets d'intérêts archéologiques (statues, amphores, etc.) détectés sur la carte globale.La première partie du travail concerne la reconstruction 3D de la scène sous-marine. Même si aujourd'hui le monde de la vision a permis de mieux appréhender ce type d'image, l'étude de scène sous-marine naturelle pose encore de nombreux problèmes. Nous avons pris en compte les bruits sous-marins lors de la création du modèle 3D vidéo ainsi que lors de la calibration des appareils photos. Une étude de robustesse à ces bruits a été réalisée sur deux méthodes de détections et d'appariements de points d'intérêt. Cela a permis d'obtenir des points caractéristiques précis et robustes pour le modèle 3D. La géométrie épipolaire nous a permis de projeter ces points en 3D. La texture a été ajoutée sur les surfaces obtenues par triangulation de Delaunay.La deuxième partie consiste à fusionner le modèle 3D obtenu précédemment et la carte acoustique. Dans un premier temps, afin d'aligner les deux modèles 3D (le modèle vidéo et le modèle acoustique), nous appliquons un recalage approximatif en sélectionnant manuellement quelques paires de points équivalents sur les deux nuages de points. Pour augmenter la précision de ce dernier, nous utilisons un algorithme ICP (Iterative Closest Points).Dans ce travail nous avons créé une carte 3D sous-marine multimodale réalisée à l'aide de modèles 3D « vidéo » et d'une carte acoustique globale.
This work aims to analyze natural underwater scenes and it focuses on mapping underwater environment in 3D. Today, many methods exist to solve this problem. The originality of this work lies in the fusion of two maps obtained from sensors of different resolutions. Initially, an autonomous vehicle (or boat) analyzes the seabed with multibeam sonar and creates a first global map of the area. This map is…
Advisors/Committee Members: Jouvencel, Bruno (thesis director), Triboulet, Jean (thesis director).
Subjects/Keywords: Vision sous-marine; Reconstruction 3D; Fusion / Recalage 3D; Cartographie; Underwater vision; 3D reconstruction; Fusion / 3D registration; Mapping
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Méline, A. (2013). Fusion multimodale pour la cartographie sous-marine : Multimodal fusion for underwater mapping. (Doctoral Dissertation). Université Montpellier II. Retrieved from http://www.theses.fr/2013MON20005
Chicago Manual of Style (16th Edition):
Méline, Arnaud. “Fusion multimodale pour la cartographie sous-marine : Multimodal fusion for underwater mapping.” 2013. Doctoral Dissertation, Université Montpellier II. Accessed January 23, 2021.
http://www.theses.fr/2013MON20005.
MLA Handbook (7th Edition):
Méline, Arnaud. “Fusion multimodale pour la cartographie sous-marine : Multimodal fusion for underwater mapping.” 2013. Web. 23 Jan 2021.
Vancouver:
Méline A. Fusion multimodale pour la cartographie sous-marine : Multimodal fusion for underwater mapping. [Internet] [Doctoral dissertation]. Université Montpellier II; 2013. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2013MON20005.
Council of Science Editors:
Méline A. Fusion multimodale pour la cartographie sous-marine : Multimodal fusion for underwater mapping. [Doctoral Dissertation]. Université Montpellier II; 2013. Available from: http://www.theses.fr/2013MON20005
20.
Valade, Charles.
Développement d'une méthodologie adaptée à l'industrie microélectronique pour la reconstruction topographique par imagerie SEM à faisceau inclinable : Development of a methodology adapted to the microelectronics industry for topographic reconstruction by tilt beam SEM imaging.
Degree: Docteur es, Nanoélectronique et nanotechnologie, 2020, Université Grenoble Alpes
URL: http://www.theses.fr/2020GRALT015
► Avec l’avancée des technologies de la microélectronique, l’architecture des composants électroniques devient de plus en plus compliquée. Or, la connaissance des caractéristiques dimensionnelles des structures…
(more)
▼ Avec l’avancée des technologies de la microélectronique, l’architecture des composants électroniques devient de plus en plus compliquée. Or, la connaissance des caractéristiques dimensionnelles des structures réalisées est importante pour pouvoir comprendre et optimiser le comportement de ces composants. C’est pourquoi il existe un besoin de développer des méthodes de mesure tridimensionnelles rapides et non destructives.Le microscope électronique à balayage (SEM) est largement utilisé pour réaliser des mesures dimensionnelles car il répond aux problématiques de rapidité et de non-destructivité. Cependant l’obtention d’informations tridimensionnelles quantitatives et précises est un challenge.Grâce à un microscope électronique dont le faisceau électronique peut être incliné, il est possible d’obtenir des images à différents angles de vue. A partir de l’analyse de ces images, la hauteur et l’angle des flancs du motif observé peuvent être déterminés géométriquement.Cependant, l’imagerie électronique étant le résultat des interactions électrons-matière, il est important de comprendre l’origine de la formation des images SEM, pour pouvoir les analyser correctement. C’est pourquoi une étude a été menée grâce à un logiciel de simulation physique pour observer et comprendre l’impact de la topographie d’un motif sur l’image SEM résultante.A partir de ces observations, des métriques ont été créées sur les images SEM pour les analyser quantitativement. Un modèle linéaire a ensuite été créé grâce aux simulations physiques pour estimer les grandeurs topographiques à partir de ces métriques. Il a ensuite été calibré sur des mesures SEM réelles, en les comparant à des mesures tridimensionnelles de référence par microscopie à force atomique (AFM). Ce modèle a été créé pour la reconstruction de motifs de type "ligne" en silicium gravé. Grâce à ce modèle, des reconstructions de motifs réelles ont été réalisées. Enfin un travail sur la création d’un modèle pour les motifs de type "tranchée" et "dense" en silicium gravé a été initié.
With the advancement of microelectronics technologies, the architecture of electronic components is becoming increasingly complicated. However, knowledge of the dimensional characteristics of the structures is important in order to be able to understand and optimize the behavior of these components. This is why there is a need to develop rapid, non-destructive three-dimensional measurement methods.The scanning electron microscope (SEM) is widely used to carry out dimensional measurements because it responds to the problems of speed and non-destructivity. However, obtaining quantitative and precise three-dimensional information is a challenge.Thanks to an electron microscope whose electron beam can be tilted, it is possible to obtain images at different viewing angles. From the analysis of these images, the height and the sidewall angles of the observed pattern can be determined geometrically.However, since electronic imaging is the result of electron-matter interactions, it is important to understand…
Advisors/Committee Members: Gourgon, Cécile (thesis director), Besacier, Maxime (thesis director), Sungauer, Elodie (thesis director), Hazart, Jérôme (thesis director).
Subjects/Keywords: Métrologie; Cd-Sem 3d; Reconstruction 3D; Modèle linéaire; Simulation; Metrology; Cd-Sem 3d; 3D reconstruction; Linear model; Simulation; 620
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Valade, C. (2020). Développement d'une méthodologie adaptée à l'industrie microélectronique pour la reconstruction topographique par imagerie SEM à faisceau inclinable : Development of a methodology adapted to the microelectronics industry for topographic reconstruction by tilt beam SEM imaging. (Doctoral Dissertation). Université Grenoble Alpes. Retrieved from http://www.theses.fr/2020GRALT015
Chicago Manual of Style (16th Edition):
Valade, Charles. “Développement d'une méthodologie adaptée à l'industrie microélectronique pour la reconstruction topographique par imagerie SEM à faisceau inclinable : Development of a methodology adapted to the microelectronics industry for topographic reconstruction by tilt beam SEM imaging.” 2020. Doctoral Dissertation, Université Grenoble Alpes. Accessed January 23, 2021.
http://www.theses.fr/2020GRALT015.
MLA Handbook (7th Edition):
Valade, Charles. “Développement d'une méthodologie adaptée à l'industrie microélectronique pour la reconstruction topographique par imagerie SEM à faisceau inclinable : Development of a methodology adapted to the microelectronics industry for topographic reconstruction by tilt beam SEM imaging.” 2020. Web. 23 Jan 2021.
Vancouver:
Valade C. Développement d'une méthodologie adaptée à l'industrie microélectronique pour la reconstruction topographique par imagerie SEM à faisceau inclinable : Development of a methodology adapted to the microelectronics industry for topographic reconstruction by tilt beam SEM imaging. [Internet] [Doctoral dissertation]. Université Grenoble Alpes; 2020. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2020GRALT015.
Council of Science Editors:
Valade C. Développement d'une méthodologie adaptée à l'industrie microélectronique pour la reconstruction topographique par imagerie SEM à faisceau inclinable : Development of a methodology adapted to the microelectronics industry for topographic reconstruction by tilt beam SEM imaging. [Doctoral Dissertation]. Université Grenoble Alpes; 2020. Available from: http://www.theses.fr/2020GRALT015
NSYSU
21.
Liu, Qiao-Yuan.
3D SHAPE RECONSTRUCTION USING PROJECTED FRINGE PROFILOMETRY FOR AN IMAGE BLURRED BY LINEAR MOTION.
Degree: Master, Electro-Optical Engineering, 2008, NSYSU
URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0811108-153522
► A projected fringe profilometry (PFP) is an optical measurements technology which is widely used at present in gauging the object's three dimensional appearance. PFP is…
(more)
▼ A projected fringe profilometry (PFP) is an optical measurements technology which is widely used at present in gauging the object's three dimensional appearance. PFP is frequently used in detecting the quality of products in the industry due to the specialty of non-contact type, the short retrieve time and low environmental effect. As a result of the development for many years, PFP treats in the gauging static state of the object's three dimensional appearance has had the extremely fine gauging efficiency and the precision in , however in the dynamic inspected object in the gauging , not yet was still mature. If could to develop a set of gauging way in the dynamic inspected object , the application would be more widespread.
Taking PFP as the gauging principle, analyzing the changes between the dynamic treat measured object and the fringe. Using the simple mathematics to describe the interaction relations between the fringe and the inspected the object. Finally, reconstructed the inspected object' three dimensional appearance. May know biggest superiority by the experimental process, in the situation of without losing the information of fringe, PFP can reconstruct the inspected object' three dimensional appearance and do not need the motion condition information.
Advisors/Committee Members: Ann-Kuo Chu (chair), Chao-Kuei Lee (committee member), Yi-Jen Chiu (chair), Wei-Hung Su (committee member).
Subjects/Keywords: 3D shape reconstruction; projected fringe profilometry
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Liu, Q. (2008). 3D SHAPE RECONSTRUCTION USING PROJECTED FRINGE PROFILOMETRY FOR AN IMAGE BLURRED BY LINEAR MOTION. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0811108-153522
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Liu, Qiao-Yuan. “3D SHAPE RECONSTRUCTION USING PROJECTED FRINGE PROFILOMETRY FOR AN IMAGE BLURRED BY LINEAR MOTION.” 2008. Thesis, NSYSU. Accessed January 23, 2021.
http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0811108-153522.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Liu, Qiao-Yuan. “3D SHAPE RECONSTRUCTION USING PROJECTED FRINGE PROFILOMETRY FOR AN IMAGE BLURRED BY LINEAR MOTION.” 2008. Web. 23 Jan 2021.
Vancouver:
Liu Q. 3D SHAPE RECONSTRUCTION USING PROJECTED FRINGE PROFILOMETRY FOR AN IMAGE BLURRED BY LINEAR MOTION. [Internet] [Thesis]. NSYSU; 2008. [cited 2021 Jan 23].
Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0811108-153522.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Liu Q. 3D SHAPE RECONSTRUCTION USING PROJECTED FRINGE PROFILOMETRY FOR AN IMAGE BLURRED BY LINEAR MOTION. [Thesis]. NSYSU; 2008. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0811108-153522
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Universiteit Utrecht
22.
Winden, K. van.
Automatically Constructing the Third Dimension of IMGeo.
Degree: 2012, Universiteit Utrecht
URL: http://dspace.library.uu.nl:8080/handle/1874/259136
► The past year a new Dutch standard for the registration of large scale topography was released, called IMGeo 2.0. This standard includes descriptions and attributes…
(more)
▼ The past year a new Dutch standard for the registration of large scale topography was released, called IMGeo 2.0. This standard includes descriptions and attributes for the majority of objects seen in public spaces. A possible extension to IMGeo 2.0 allows all objects to be modelled in
3D, based on object descriptions and techniques from the CityGML standard. This thesis explores the feasibility of automatically constructing such
3D models by combining 2D geometries and
3D height information. Numerous methods for this type of construction already exist, differing in objects reconstructed, amount of detail, restrictions on construction approach, assumptions on input data and requirements on output data. The approaches created in this thesis aim to construct
3D models in a robust way, accepting sub-optimal results as long as they are a decent and valid representation of reality. Four different construction methods were designed. The first builds large 2.5D terrain models based on point triangulation. These 2.5D surface models form the basis of the actual
3D models. The second and third method construct horizontal roof
3D block models of buildings, with one approach dividing the roof based on point clusters and the other using repeated square subdivisions. The last and most complex method tries to construct
3D building models with full roof shapes using plane and line detection techniques. Degrees of success vary across these methods, with lower success rates the more complex the models become. The constructed terrain model has a number of improvements over a standard triangulation, but terrain generalization is really a field of its own and a lot more improvement can be accomplished. The methods for block models proved to be robust and performed quite well, but can be improved with respect to roof border accuracy. The method that constructs full roof shapes is not robust enough yet, but shows promising possibilities. Overall some creative ways to automatically construct
3D models have been designed, either entirely from scratch or as a modification of existing work, combining techniques from amongst others the fields of geometric algorithms and image processing.
Advisors/Committee Members: Kreveld, M.J. van.
Subjects/Keywords: IMGeo; 3D; terrain model; building reconstruction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Winden, K. v. (2012). Automatically Constructing the Third Dimension of IMGeo. (Masters Thesis). Universiteit Utrecht. Retrieved from http://dspace.library.uu.nl:8080/handle/1874/259136
Chicago Manual of Style (16th Edition):
Winden, K van. “Automatically Constructing the Third Dimension of IMGeo.” 2012. Masters Thesis, Universiteit Utrecht. Accessed January 23, 2021.
http://dspace.library.uu.nl:8080/handle/1874/259136.
MLA Handbook (7th Edition):
Winden, K van. “Automatically Constructing the Third Dimension of IMGeo.” 2012. Web. 23 Jan 2021.
Vancouver:
Winden Kv. Automatically Constructing the Third Dimension of IMGeo. [Internet] [Masters thesis]. Universiteit Utrecht; 2012. [cited 2021 Jan 23].
Available from: http://dspace.library.uu.nl:8080/handle/1874/259136.
Council of Science Editors:
Winden Kv. Automatically Constructing the Third Dimension of IMGeo. [Masters Thesis]. Universiteit Utrecht; 2012. Available from: http://dspace.library.uu.nl:8080/handle/1874/259136
University of California – Irvine
23.
Rodriguez Alegre, Irene.
Breast MRI Segmentation and Density Analysis, 3D Model Reconstruction and Quadrant Regional Segmentation.
Degree: Electrical and Computer Engineering, 2015, University of California – Irvine
URL: http://www.escholarship.org/uc/item/5p38c1hj
► One of the most helpful factors to consider when evaluating the development of breast cancer is the independent risk factor known as breast density. The…
(more)
▼ One of the most helpful factors to consider when evaluating the development of breast cancer is the independent risk factor known as breast density. The breast density factor is the ratio between the volume of fibroglandular tissue to the total volume of the breasts. It is a measurement that always has to be considered by the radiologists for detection and diagnosis of breast cancer.In this thesis we present an analysis method to calculate this breast density factor, the analysis is based on image segmentation algorithms. The images being segmented come from breast magnetic resonance imaging, breast MRI, which provides better results than conventional x-ray mammograms. The first part of this thesis focuses on the breast MRI template-based segmentation method. The implemented method was first proposed by Muqing Lin et al. in our center back in 2010. The developed method is applied to segment the different slices with 1-3 mm thickness obtained for every breast. As also demonstrated in this first part of the thesis, the method provides successful results for segmentation and calculation of the percentage of breast density. The second part of this thesis is dedicated to describe a method used to reconstruct a 3D model of the breasts from the MRI slices obtained for each patient. The tool performs a breast alignment correction, followed by the 3D reconstruction and a video generation where we can observe the 3D model from different angles and with different rotation and speed.Finally, the third part of this thesis involves the study of the breasts by the regional segmentation of the quadrants. Several studies have demonstrated that the probability of breast cancer is not the same at every quadrant. Therefore it is an interesting option for the radiologists to be able to observe a 3D representation of the breast divided in quadrants.
Subjects/Keywords: Engineering; 3D reconstruction; Breast MRI; MRI; Segmentation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Rodriguez Alegre, I. (2015). Breast MRI Segmentation and Density Analysis, 3D Model Reconstruction and Quadrant Regional Segmentation. (Thesis). University of California – Irvine. Retrieved from http://www.escholarship.org/uc/item/5p38c1hj
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Rodriguez Alegre, Irene. “Breast MRI Segmentation and Density Analysis, 3D Model Reconstruction and Quadrant Regional Segmentation.” 2015. Thesis, University of California – Irvine. Accessed January 23, 2021.
http://www.escholarship.org/uc/item/5p38c1hj.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Rodriguez Alegre, Irene. “Breast MRI Segmentation and Density Analysis, 3D Model Reconstruction and Quadrant Regional Segmentation.” 2015. Web. 23 Jan 2021.
Vancouver:
Rodriguez Alegre I. Breast MRI Segmentation and Density Analysis, 3D Model Reconstruction and Quadrant Regional Segmentation. [Internet] [Thesis]. University of California – Irvine; 2015. [cited 2021 Jan 23].
Available from: http://www.escholarship.org/uc/item/5p38c1hj.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Rodriguez Alegre I. Breast MRI Segmentation and Density Analysis, 3D Model Reconstruction and Quadrant Regional Segmentation. [Thesis]. University of California – Irvine; 2015. Available from: http://www.escholarship.org/uc/item/5p38c1hj
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Alberta
24.
Guo,Xingzhou.
Vision-based Tracking of Worker Trajectories in Built
Workplaces for Safety and Health Study.
Degree: MS, Department of Civil and Environmental
Engineering, 2016, University of Alberta
URL: https://era.library.ualberta.ca/files/cb5644r761
► Construction sites are the place where personnel and equipment work closely. In such workplaces, human movement dynamically adapts to the surrounding circumstances which are congested…
(more)
▼ Construction sites are the place where personnel and
equipment work closely. In such workplaces, human movement
dynamically adapts to the surrounding circumstances which are
congested and continually changing. Acquisition of worker
trajectories and measurement of physical value of workplaces,
however, typically requires on-site investigation, and thus is a
time-consuming and error-prone process. Insufficient understanding
of manual tasks and working environments in terms of operational
planning and analysis can lead to unreasonable work plans,
irrational layout design of the workplace, and unsafe equipment
operation. As a result, workers are facing risks caused by adverse
jobsite conditions. Accordingly, the purpose of this research is to
improve worker health and safety on construction sites through
designing a safer workplace, eliminating potential injuries caused
by unhealthy motion, and reducing risks of equipment operation.
Specifically, stereo videos are collected by a stereo vision camera
to record the dimension of construction workplaces and also to
record worker movements. Then the depth information contained in
the stereo videos are analyzed and processed (e.g., computing
disparity from stereo videos and reconstructing 3D scenes from a
disparity map) to quickly extract worker trajectories and to
accurately rebuild 3D models of workplaces. The acquired geometry
information of worker movements and workplace models can assist
personnel in designing better project plans to facilitate the
following three aspects: (1) providing necessary inputs for motion
study to design a healthier motion plan; (2) providing a visible 3D
model of workplaces to recognize unsafe workplace layouts; and (3)
enabling operators to identify potential risks and hazards during
equipment operation and then achieve safer equipment
operations.
Subjects/Keywords: Trajectories; Built workplaces; 3D reconstruction; Safety; Health
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Guo,Xingzhou. (2016). Vision-based Tracking of Worker Trajectories in Built
Workplaces for Safety and Health Study. (Masters Thesis). University of Alberta. Retrieved from https://era.library.ualberta.ca/files/cb5644r761
Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete
Chicago Manual of Style (16th Edition):
Guo,Xingzhou. “Vision-based Tracking of Worker Trajectories in Built
Workplaces for Safety and Health Study.” 2016. Masters Thesis, University of Alberta. Accessed January 23, 2021.
https://era.library.ualberta.ca/files/cb5644r761.
Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete
MLA Handbook (7th Edition):
Guo,Xingzhou. “Vision-based Tracking of Worker Trajectories in Built
Workplaces for Safety and Health Study.” 2016. Web. 23 Jan 2021.
Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete
Vancouver:
Guo,Xingzhou. Vision-based Tracking of Worker Trajectories in Built
Workplaces for Safety and Health Study. [Internet] [Masters thesis]. University of Alberta; 2016. [cited 2021 Jan 23].
Available from: https://era.library.ualberta.ca/files/cb5644r761.
Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete
Council of Science Editors:
Guo,Xingzhou. Vision-based Tracking of Worker Trajectories in Built
Workplaces for Safety and Health Study. [Masters Thesis]. University of Alberta; 2016. Available from: https://era.library.ualberta.ca/files/cb5644r761
Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete
Cornell University
25.
Wilson, Kyle.
Robustly Modeling The World From Photos.
Degree: PhD, Applied Mathematics, 2016, Cornell University
URL: http://hdl.handle.net/1813/44330
► A camera is a device for compressing rich information about the visual appearance of the three-dimensional world into a two-dimensional image. This process is inherently…
(more)
▼ A camera is a device for compressing rich information about the visual appearance of the three-dimensional world into a two-dimensional image. This process is inherently lossy: given an image, we can make educated guesses about the world's shape and appearance, but there is not enough information for our guesses to be certain. However, if we take several pictures from different viewpoints we can reason more confidently. This thesis focuses on shape: How can we determine the geometry of the world from a collection of photos? This problem is classically called Structure from Motion. We find the structure (shape of the world) from camera motion (different viewpoints). Internet photo collections are an especially interesting source of data. With simple searches we can collect the raw information to reconstruct
3D models of famous world landmarks or entire cities. However, the photos we download are disorganized and noisy, and will not have been collected with
3D reconstruction in mind. While some impressive demonstrations of Structure from Motion systems exist, the next generation of solvers will need to be far more robust to the many types of difficulties encountered in the wild. To this end, many recent solvers pose the problem in a new way, using relative relationships between images to infer first the orientations, and then the positions of every camera in a scene. This framework promises faster runtime and greater robustness. I contribute a theoretical analysis of the difficulty of finding camera orientations, giving a way to decide which problems are tractable and which ones might be too hard and should be reformulated. I also propose a new solver with an accompanying outlier filter for finding camera positions. However, some of the hardest scenes are those which contain ambiguous structures: objects that look the same but are not. These induce self-consistent errors which are often too confusing for solvers to resolve correctly. I describe a scalable system which uses a graph-topological cue from a visibility graph to detect and remove these sources of error. Together these improvements work towards a robust solution to the Structure from Motion problem, so that we can reliably build
3D models of the world, even from noisy and confusing internet photo collections.
Advisors/Committee Members: Snavely,Keith Noah (chair), Connelly,Robert (committee member), Bindel,David S. (committee member), Bala,Kavita (committee member).
Subjects/Keywords: Computer Vision; Structure from Motion; 3D Reconstruction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wilson, K. (2016). Robustly Modeling The World From Photos. (Doctoral Dissertation). Cornell University. Retrieved from http://hdl.handle.net/1813/44330
Chicago Manual of Style (16th Edition):
Wilson, Kyle. “Robustly Modeling The World From Photos.” 2016. Doctoral Dissertation, Cornell University. Accessed January 23, 2021.
http://hdl.handle.net/1813/44330.
MLA Handbook (7th Edition):
Wilson, Kyle. “Robustly Modeling The World From Photos.” 2016. Web. 23 Jan 2021.
Vancouver:
Wilson K. Robustly Modeling The World From Photos. [Internet] [Doctoral dissertation]. Cornell University; 2016. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/1813/44330.
Council of Science Editors:
Wilson K. Robustly Modeling The World From Photos. [Doctoral Dissertation]. Cornell University; 2016. Available from: http://hdl.handle.net/1813/44330
26.
Nawaf, Mohamad Motasem.
3D structure estimation from image stream in urban environment : Estimation de la structure 3D d'un environnement urbain à partir d'un flux vidéo.
Degree: Docteur es, Image, vision, signal, 2014, Saint-Etienne
URL: http://www.theses.fr/2014STET4024
► Dans le domaine de la vision par ordinateur, l’estimation de la structure d’une scène 3D à partir d’images 2D constitue un problème fondamental. Parmi les…
(more)
▼ Dans le domaine de la vision par ordinateur, l’estimation de la structure d’une scène
3D à partir d’images 2D constitue un problème fondamental. Parmi les applications concernées par cette problématique, nous nous sommes intéressés dans le cadre de cette thèse à la modélisation d’un environnement urbain. Nous nous sommes intéressés à la
reconstruction de scènes
3D à partir d’images monoculaires générées par un véhicule en mouvement. Ici, plusieurs défis se posent à travers les différentes étapes de la chaine de traitement inhérente à la
reconstruction 3D. L’un de ces défis vient du fait de l’absence de zones suffisamment texturées dans certaines scènes urbaines, d’où une
reconstruction 3D (un nuage de points
3D) trop éparse. De plus, du fait du mouvement du véhicule, d’une image à l’autre il n’y a pas toujours un recouvrement suffisant entre différentes vues consécutives d’une même scène. Dans ce contexte, et ce afin de lever les verrous ci-dessus mentionnés, nous proposons d’estimer, de reconstruire, la structure d’une scène
3D par morceaux en se basant sur une hypothèse de planéité. Nous proposons plusieurs améliorations à la chaine de traitement associée à la
reconstruction 3D. D’abord, afin de structurer, de représenter, la scène sous la forme d’entités planes nous proposons une nouvelle méthode de
reconstruction 3D, basée sur le regroupement de pixels similaires (superpixel segmentation), qui à travers une représentation multi-échelle pondérée fusionne les informations de couleur et de mouvement. Cette méthode est basée sur l’estimation de la probabilité de discontinuités locales aux frontières des régions calculées à partir du gradient (gradientbased boundary probability estimation). Afin de prendre en compte l’incertitude liée à l’estimation du mouvement, une pondération par morceaux est appliquée à chaque pixel en fonction de cette incertitude. Cette méthode génère des regroupements de pixels (superpixels) non contraints en termes de taille et de forme. Pour certaines applications, telle que la
reconstruction 3D à partir d’une séquence d’images, des contraintes de taille sont nécessaires. Nous avons donc proposé une méthode qui intègre à l’algorithme SLIC (Simple Linear Iterative Clustering) l’information de mouvement. L’objectif étant d’obtenir une
reconstruction 3D plus dense qui estime mieux la structure de la scène. Pour atteindre cet objectif, nous avons aussi introduit une nouvelle distance qui, en complément de l’information de mouvement et de données images, prend en compte la densité du nuage de points. Afin d’augmenter la densité du nuage de points utilisé pour reconstruire la structure de la scène sous la forme de surfaces planes, nous proposons une nouvelle approche qui mixte plusieurs méthodes d’appariement et une méthode de flot optique dense. Cette méthode est basée sur un système de pondération qui attribue un poids pré-calculé par apprentissage à chaque point reconstruit. L’objectif est de contrôler l’impact de ce système de pondération, autrement dit la qualité de la
reconstruction, en…
Advisors/Committee Members: Trémeau, Alain (thesis director).
Subjects/Keywords: Reconstruction 3D; Regroupement de pixels; Structure du mouvement; Regroupement; Modélisation 3D; Reconstruction urbaine; Apprentissage automatique; 3D reconstruction; Superpixel segmentation; Structure from motion; Clustering; 3D modeling; Urban reconstruction; Machine learning
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Nawaf, M. M. (2014). 3D structure estimation from image stream in urban environment : Estimation de la structure 3D d'un environnement urbain à partir d'un flux vidéo. (Doctoral Dissertation). Saint-Etienne. Retrieved from http://www.theses.fr/2014STET4024
Chicago Manual of Style (16th Edition):
Nawaf, Mohamad Motasem. “3D structure estimation from image stream in urban environment : Estimation de la structure 3D d'un environnement urbain à partir d'un flux vidéo.” 2014. Doctoral Dissertation, Saint-Etienne. Accessed January 23, 2021.
http://www.theses.fr/2014STET4024.
MLA Handbook (7th Edition):
Nawaf, Mohamad Motasem. “3D structure estimation from image stream in urban environment : Estimation de la structure 3D d'un environnement urbain à partir d'un flux vidéo.” 2014. Web. 23 Jan 2021.
Vancouver:
Nawaf MM. 3D structure estimation from image stream in urban environment : Estimation de la structure 3D d'un environnement urbain à partir d'un flux vidéo. [Internet] [Doctoral dissertation]. Saint-Etienne; 2014. [cited 2021 Jan 23].
Available from: http://www.theses.fr/2014STET4024.
Council of Science Editors:
Nawaf MM. 3D structure estimation from image stream in urban environment : Estimation de la structure 3D d'un environnement urbain à partir d'un flux vidéo. [Doctoral Dissertation]. Saint-Etienne; 2014. Available from: http://www.theses.fr/2014STET4024
University of Cambridge
27.
Logothetis, Fotios.
Detailed and Practical 3D Reconstruction with Advanced Photometric Stereo Modelling.
Degree: PhD, 2019, University of Cambridge
URL: https://www.repository.cam.ac.uk/handle/1810/292450
► Object 3D reconstruction has always been one of the main objectives of computer vision. After many decades of research, most techniques are still unsuccessful at…
(more)
▼ Object 3D reconstruction has always been one of the main objectives of computer vision. After many decades of research, most techniques are still unsuccessful at recovering high resolution surfaces, especially for objects with limited surface texture. Moreover, most shiny materials are particularly hard to reconstruct.
Photometric Stereo (PS), which operates by capturing multiple images under changing illumination has traditionally been one of the most successful techniques at recovering a large amount of surface details, by exploiting the relationship between shading and local shape. However, using PS has been highly impractical because most approaches are only applicable in a very controlled lab setting and limited to objects experiencing diffuse reflection.
Nevertheless, recent advances in differential modelling have made complicated Photometric Stereo models possible and variational optimisations for these kinds of models show remarkable resilience to real world imperfections such as non-Gaussian noise and other outliers. Thus, a highly accurate, photometric-based reconstruction system is now possible.
The contribution of this thesis is threefold. First of all, the Photometric Stereo model is extended in order to be able to deal with arbitrary ambient lighting. This is a step towards acquisition in a non-fully controlled lab setting. Secondly, the need for a priori knowledge of the light source brightness and attenuation characteristics is relaxed as an alternating optimisation procedure is proposed which is able to estimate these parameters. This extension allows for quick acquisition with inexpensive LEDs that exhibit unpredictable illumination characteristics (flickering etc). Finally, a volumetric parameterisation is proposed which allows one to tackle the multi-view Photometric Stereo problem in a similar manner, in a simple unified differential model. This final extension allows for complete object reconstruction merging information from multiple images taken from multiple viewpoints and variable illumination.
The theoretical work in this thesis is experimentally evaluated in a number of challenging real world experiments, with data captured by custom-made hardware. In addition, the applicability of the generality of the proposed models is demonstrated by presenting a differential model for the shape of polarisation problem, which leads to a unified optimisation problem, fusing information from both methods. This allows for the acquisition of geometrical information about objects such as semi-transparent glass, hitherto hard to deal with.
Subjects/Keywords: Computer Vision; Photometric Stereo; 3D reconstruction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Logothetis, F. (2019). Detailed and Practical 3D Reconstruction with Advanced Photometric Stereo Modelling. (Doctoral Dissertation). University of Cambridge. Retrieved from https://www.repository.cam.ac.uk/handle/1810/292450
Chicago Manual of Style (16th Edition):
Logothetis, Fotios. “Detailed and Practical 3D Reconstruction with Advanced Photometric Stereo Modelling.” 2019. Doctoral Dissertation, University of Cambridge. Accessed January 23, 2021.
https://www.repository.cam.ac.uk/handle/1810/292450.
MLA Handbook (7th Edition):
Logothetis, Fotios. “Detailed and Practical 3D Reconstruction with Advanced Photometric Stereo Modelling.” 2019. Web. 23 Jan 2021.
Vancouver:
Logothetis F. Detailed and Practical 3D Reconstruction with Advanced Photometric Stereo Modelling. [Internet] [Doctoral dissertation]. University of Cambridge; 2019. [cited 2021 Jan 23].
Available from: https://www.repository.cam.ac.uk/handle/1810/292450.
Council of Science Editors:
Logothetis F. Detailed and Practical 3D Reconstruction with Advanced Photometric Stereo Modelling. [Doctoral Dissertation]. University of Cambridge; 2019. Available from: https://www.repository.cam.ac.uk/handle/1810/292450
KTH
28.
Ivarsson, Caroline.
Combining Street View and Aerial Images to Create Photo-Realistic 3D City Models.
Degree: Geodesy and Geoinformatics, 2014, KTH
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-164258
► This thesis evaluates two different approaches of using panoramic street view images for creating more photo-realistic 3D city models comparing to 3D city models…
(more)
▼ This thesis evaluates two different approaches of using panoramic street view images for creating more photo-realistic 3D city models comparing to 3D city models based on only aerial images. The thesis work has been carried out at Blom Sweden AB with the use of their software and data. The main purpose of this thesis work has been to investigate if street view images can aid in creating more photo-realistic 3D city models on street level through an automatic or semi-automatic approach. Two different approaches have been investigated in this thesis work: using the street view images for texturing already generated 3D building models and using the street view images directly for reconstructing 3D city models. Data was collected over the study area of KTH, Stockholm, Sweden and the models were created with the two software TerraPhoto, used for texturing, and Smart3DCapture, used for reconstruction. The created models were analyzed and compared with the models based on only aerial images and the two approaches were compared to each other. Through using also street view images when creating city models the models are shown to become more photo-realistic representations on street level compared to the models based on only aerial images. The two tested approaches create very different 3D city models in terms of what is visible in the final model, a textured buildings model or a fully reconstructed environment, and also contains different amount of involved manual work. The textured models contain only the buildings and tend to look very flat because the street images are being projected onto flat building walls whereas the reconstructed models reconstructs everything being visible in the images, trees, cars etc., and create a full scale 3D city model. There are however limitations associated with using street view images when modeling cities since they only contain information on the ground level and no information about roofs or higher parts of the city environment and the street view images therefore need to be used in combination with aerial images. Using the street view images for reconstructing city models showed some complications in terms of wavy facades, bumpy roads and objects such as trees being inaccurately modeled. The texturing approach creates less visually pleasing models since objects such as trees and lighting poles are being projected onto the facades. The models based on aerial images look more visually appealing compared to when also using the street view images but lack the resolution be considered as photo-realistic on street level. This thesis work has shown that there is potential in using street view images when creating photo-realistic 3D city models on street level even though it is not yet a semi-automatic or automatic approach.
Denna rapport beskriver två olika tillvägagångssätt för att använda panorama gatubilder för att skapa mer fotorealistiska 3D stadsmodeller jämfört med att enbart använda sig av flygbilder. Arbetet har genomförts i samarbete med Blom Sweden…
Subjects/Keywords: 3D city model; photo-realistic; texture; reconstruction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ivarsson, C. (2014). Combining Street View and Aerial Images to Create Photo-Realistic 3D City Models. (Thesis). KTH. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-164258
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Ivarsson, Caroline. “Combining Street View and Aerial Images to Create Photo-Realistic 3D City Models.” 2014. Thesis, KTH. Accessed January 23, 2021.
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-164258.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Ivarsson, Caroline. “Combining Street View and Aerial Images to Create Photo-Realistic 3D City Models.” 2014. Web. 23 Jan 2021.
Vancouver:
Ivarsson C. Combining Street View and Aerial Images to Create Photo-Realistic 3D City Models. [Internet] [Thesis]. KTH; 2014. [cited 2021 Jan 23].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-164258.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Ivarsson C. Combining Street View and Aerial Images to Create Photo-Realistic 3D City Models. [Thesis]. KTH; 2014. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-164258
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Linköping University
29.
Jonsson, Mikael.
Make it Flat : Detection and Correction of Planar Regions in Triangle Meshes.
Degree: Computer Vision, 2016, Linköping University
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-126589
► The art of reconstructing a real-world scene digitally has been on the mind of researchers for decades. Recently, it has attracted more and more…
(more)
▼ The art of reconstructing a real-world scene digitally has been on the mind of researchers for decades. Recently, it has attracted more and more attention from companies seeing a chance to bring this kind of technology to the market. Digital reconstruction of buildings in particular is a niche that has both potential and room for improvement. With this background, this thesis will present the design and evaluation of a pipeline made to find and correct approximately flat surfaces in architectural scenes. The scenes are 3D-reconstructed triangle meshes based on RGB images. The thesis will also comprise an evaluation of a few different components available for doing this, leading to a choice of best components. The goal is to improve the visual quality of the reconstruction. The final pipeline is designed with two blocks - one to detect initial plane seeds and one to refine the detected planes. The first block makes use of a multi-label energy formulation on the graph that describes the reconstructed surface. Penalties are assigned to each vertex and each edge of the graph based on the vertex labels, effectively describing a Markov Random Field. The energy is minimized with the help of the alpha-expansion algorithm. The second block uses heuristics for growing the detected plane seeds, merging similar planes together and extracting deviating details. Results on several scenes are presented, showing that the visual quality has been improved while maintaining accuracy compared with ground truth data.
Konsten att digitalt rekonstruera en verklig miljö har länge varit intressant för forskare. Nyligen har området även tilldragit sig mer och mer uppmärksamhet från företag som ser en möjlighet att föra den här typen av teknik till produkter på marknaden. I synnerhet är digital rekonstruktion av byggnader en nisch som har både stor potential och möjlighet till förbättring. Med denna bakgrund så presenterar detta examensarbete designen för och utvärderingen av en pipeline som skapats för att detektera och rätta till approximativt platta regioner i arkitektoniska miljöer. Miljöerna är 3D-rekonstruerade triangelmeshar skapade från RGB-bilder. Examensarbetet omfattar även utvärdering av olika komponenter för att uppnå detta, som avslutas med att de mest lämpliga komponenterna presenteras. Målet i korthet är att förbättra den visuella kvaliteten av en rekonstruerad modell. Den slutgiltiga pipelinen består av två övergripande block - ett för att detektera initiala plan och ett för att förbättra de funna planen. Det första blocket använder en multi-label energiformulering på grafen som beskriver den rekonstruerade ytan. Straffvärden tilldelas varje vertex och varje båge i grafen baserade på varje vertex label. På så sätt beskriver grafen ett Markov Random Field. Energin är sedan minimerad med alpha-expansion-algoritmen. Det andra blocket använder heuristiker för att låta planen växa, slå ihop närliggande plan och för att extrahera avvikande detaljer. Resultat på flera miljöer presenteras också för…
Subjects/Keywords: 3D reconstruction; Markov Random Field; plane detection
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Jonsson, M. (2016). Make it Flat : Detection and Correction of Planar Regions in Triangle Meshes. (Thesis). Linköping University. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-126589
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Jonsson, Mikael. “Make it Flat : Detection and Correction of Planar Regions in Triangle Meshes.” 2016. Thesis, Linköping University. Accessed January 23, 2021.
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-126589.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Jonsson, Mikael. “Make it Flat : Detection and Correction of Planar Regions in Triangle Meshes.” 2016. Web. 23 Jan 2021.
Vancouver:
Jonsson M. Make it Flat : Detection and Correction of Planar Regions in Triangle Meshes. [Internet] [Thesis]. Linköping University; 2016. [cited 2021 Jan 23].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-126589.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Jonsson M. Make it Flat : Detection and Correction of Planar Regions in Triangle Meshes. [Thesis]. Linköping University; 2016. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-126589
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Georgia Tech
30.
Srinivasan, Natesh.
An image-based approach for 3D reconstruction of urban scenes using architectural symmetries.
Degree: PhD, Computer Science, 2018, Georgia Tech
URL: http://hdl.handle.net/1853/60276
► In this dissertation, I focus on an important, generalizable and freely available sub-category of semantic information in addressing modern reconstruction challenges: the notion of symmetry.…
(more)
▼ In this dissertation, I focus on an important, generalizable and freely available sub-category of semantic information in addressing modern
reconstruction challenges: the notion of symmetry. The emphasis in the
3D modeling of urban scenes has shifted in the past decade. The current goal of the
reconstruction community is to provide dense, CAD-like representations of the
3D built environment. In my thesis I focus on five main contributions exploiting symmetry in
3D scenes that advance this agenda: I provide a framework for modeling complex symmetries in 1D, 2D and
3D built upon the mathematical theory of symmetry and lattices, with an emphasis on how this applies to urban scenes. Drawing largely on crystallographic theory, but also considering lattice-free symmetries, my intent was to create a firm basis for computer vision applications in my thesis and beyond. I develop a probabilistic modeling framework based on Bayes' networks that provides a set of generative models for symmetric scenes. Doing so allows us to exploit the physical meaning of the variables that are generating the symmetries to form probabilistic priors. In addition, it serves as the foundational basis of a factor graph framework for optimizing the parameters of symmetry and its subsequent use in
3D reconstruction methods. I provide a novel voting scheme in a polar transformation space to determine the lattice parameters of a symmetric scene that have a lattice-like structure. I demonstrate that my algorithm is more robust to the variations in the quality of the point clouds generated from Structure from Motion (SfM) algorithms, as compared to state of the art techniques that vote in a Cartesian coordinate space. By exploiting the full generative modeling introduced earlier, I show that one can obtain a detailed
3D reconstruction from a single image of a building or structure, while simultaneously determining the camera parameters. I discuss the interaction of the generative model of symmetry in an image projection space and show how one can infer the complex
3D symmetry of the scene using 2D measurements in only a single image, extending previous work in this area to more general symmetries. Finally, I address the topic of joint SfM and symmetry detection. SfM is currently an indispensable tool in computer vision, but it is still not sufficiently agnostic to the type of environment that we are trying to reconstruct. Highly symmetric scenes present one such problem to model SfM methods. I show that instead of being a hindrance, symmetry can be a powerful constraint in providing dense and photo-realistic
3D models of the scene. In particular, I discuss three cases in which I use all the other contributions in this thesis to advancing the state of the art in
3D reconstruction to much more general symmetries than those that are hitherto considered.
Advisors/Committee Members: Liu, Yanxi (committee member), Hays, James (committee member), Rehg, James (committee member).
Subjects/Keywords: Computer vision; 3D reconstruction; Scene understanding; Symmetry
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Srinivasan, N. (2018). An image-based approach for 3D reconstruction of urban scenes using architectural symmetries. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/60276
Chicago Manual of Style (16th Edition):
Srinivasan, Natesh. “An image-based approach for 3D reconstruction of urban scenes using architectural symmetries.” 2018. Doctoral Dissertation, Georgia Tech. Accessed January 23, 2021.
http://hdl.handle.net/1853/60276.
MLA Handbook (7th Edition):
Srinivasan, Natesh. “An image-based approach for 3D reconstruction of urban scenes using architectural symmetries.” 2018. Web. 23 Jan 2021.
Vancouver:
Srinivasan N. An image-based approach for 3D reconstruction of urban scenes using architectural symmetries. [Internet] [Doctoral dissertation]. Georgia Tech; 2018. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/1853/60276.
Council of Science Editors:
Srinivasan N. An image-based approach for 3D reconstruction of urban scenes using architectural symmetries. [Doctoral Dissertation]. Georgia Tech; 2018. Available from: http://hdl.handle.net/1853/60276
◁ [1] [2] [3] [4] [5] … [21] ▶
. 
Open Access Theses and Dissertations