subject:(Depth estimation)

University of Texas – Austin

1. -1801-9896. Perceptual monocular depth estimation.

Degree: PhD, Electrical and Computer Engineering, 2020, University of Texas – Austin

URL: http://dx.doi.org/10.26153/tsw/8461

► Monocular depth estimation (MDE), which is the task of using a single image to predict scene depths, has gained considerable interest, in large part owing… (more)

▼ Monocular depth estimation (MDE), which is the task of using a single image to predict scene depths, has gained considerable interest, in large part owing to the popularity of applying deep learning methods to solve “computer vision problems”. Monocular cues provide sufficient data for humans to instantaneously extract an understanding of scene geometries and relative depths, which is evidence of both the processing power of the human visual system and the predictive power of the monocular data. However, developing computational models to predict depth from monocular images remains challenging. Hand-designed MDE features do not perform particularly well, and even current “deep” models are still evolving. Here we propose a novel approach that uses perceptually-relevant natural scene statistics (NSS) features to predict depths from monocular images in a simple, scale-agnostic way that is competitive with state-of-the-art systems. While the statistics of natural photographic images have been successfully used in a variety of image and video processing, analysis, and quality assessment tasks, they have never been applied in a predictive end-to-end deep-learning model for monocular depth. Here we accomplish this by developing a new closed-form bivariate model of image luminances and use features extracted from this model and from other NSS models to drive a novel deep learning framework for predicting depth given a single image. We then extend our perceptually-based MDE model to fisheye images, which suffer from severe spatial distortions, and we show that our method that uses monocular cues performs comparably to our best fisheye stereo matching approach. Fisheye cameras have become increasingly popular in automotive applications, because they provide a wider (approximately 180 degrees) field-of-view (FoV), thereby giving drivers and driver assistance systems more visibility with minimal hardware. We explore fisheye stereo as it pertains to the problem of automotive surround-view (SV), specifically, which is a system comprising four fisheye cameras positioned on the front, right, rear, and left sides of a vehicle. The SV system perspectively transforms the images captured by these four cameras and stitches them together in a birdseye-view representation of the scene centered around the ego vehicle to display to the driver. With the camera axes oriented orthogonally away from each other and with each camera capturing approximately 180 degrees laterally, there exists an overlap in FoVs between adjacent cameras. It is within these regions where we have stereo vision, and can thus triangulate depths with an appropriate correspondence matching method. Each stereo system within the SV configuration has a wide baseline and two orthogonally-divergent camera axes, both of which make traditional methods for estimating stereo correspondences perform poorly. Our stereo pipeline, which relies on a neural network trained for predicting stereo correspondences, performs well even when the stereo system has limited overlap in FoVs and… Advisors/Committee Members: Bovik, Alan C. (Alan Conrad), 1958- (advisor), Ghosh, Joydeep (committee member), Vikalo, Haris (committee member), Huang, Qixing (committee member), Mueller, Martin (committee member).

Subjects/Keywords: Monocular depth estimation; Natural scene statistics; Depth estimation; Perceptual depth estimation; Bivariate natural scene statistics; Bivariate correlation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

-1801-9896. (2020). Perceptual monocular depth estimation. (Doctoral Dissertation). University of Texas – Austin. Retrieved from http://dx.doi.org/10.26153/tsw/8461

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Chicago Manual of Style (16^th Edition):

-1801-9896. “Perceptual monocular depth estimation.” 2020. Doctoral Dissertation, University of Texas – Austin. Accessed April 22, 2021. http://dx.doi.org/10.26153/tsw/8461.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

MLA Handbook (7^th Edition):

-1801-9896. “Perceptual monocular depth estimation.” 2020. Web. 22 Apr 2021.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Vancouver:

-1801-9896. Perceptual monocular depth estimation. [Internet] [Doctoral dissertation]. University of Texas – Austin; 2020. [cited 2021 Apr 22]. Available from: http://dx.doi.org/10.26153/tsw/8461.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Council of Science Editors:

-1801-9896. Perceptual monocular depth estimation. [Doctoral Dissertation]. University of Texas – Austin; 2020. Available from: http://dx.doi.org/10.26153/tsw/8461

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Universitat Autònoma de Barcelona

2. Cheda, Diego. Monocular Depth Cues in Computer Vision Applications.

Degree: Departament de Ciències de la Computació, 2012, Universitat Autònoma de Barcelona

URL: http://hdl.handle.net/10803/121644

► Depth perception is a key aspect of human vision. It is a routine and essential visual task that the human do effortlessly in many daily… (more)

▼ Depth perception is a key aspect of human vision. It is a routine and essential visual task that the human do effortlessly in many daily activities. This has often been associated with stereo vision, but humans have an amazing ability to perceive depth relations even from a single image by using several monocular cues. In the computer vision field, if image depth information were available, many tasks could be posed from a different perspective for the sake of higher performance and robustness. Nevertheless, given a single image, this possibility is usually discarded, since obtaining depth information has frequently been performed by three-dimensional reconstruction techniques, requiring two or more images of the same scene taken from different viewpoints. Recently, some proposals have shown the feasibility of computing depth information from single images. In essence, the idea is to take advantage of a priori knowledge of the acquisition conditions and the observed scene to estimate depth from monocular pictorial cues. These approaches try to precisely estimate the scene depth maps by employing computationally demanding techniques. However, to assist many computer vision algorithms, it is not really necessary computing a costly and detailed depth map of the image. Indeed, just a rough depth description can be very valuable in many problems. In this thesis, we have demonstrated how coarse depth information can be integrated in different tasks following holistic and alternative strategies to obtain more precise and robustness results. In that sense, we have proposed a simple, but reliable enough technique, whereby image scene regions are categorized into discrete depth ranges to build a coarse depth map. Based on this representation, we have explored the potential usefulness of our method in three application domains from novel viewpoints: camera rotation parameters estimation, background estimation and pedestrian candidate generation. In the first case, we have computed camera rotation mounted in a moving vehicle from two novels methods that identify distant elements in the image, where the translation component of the image flow field is negligible. In background estimation, we have proposed a novel method to reconstruct the background by penalizing close regions in a cost function, which integrates color, motion, and depth terms. Finally, we have benefited of geometric and depth information available on single images for pedestrian candidate generation to significantly reduce the number of generated windows to be further processed by a pedestrian classifier. In all cases, results have shown that our depth-based approaches contribute to better performances. Advisors/Committee Members: [email protected] (authoremail), true (authoremailshow), Ponsa Mussarra, Daniel (director), López Peña, Antonio M. (Antonio Manuel) (codirector), true (authorsendemail).

Subjects/Keywords: Monocular depth cues; Computer vision; Depth estimation; Tecnologies; 62

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Cheda, D. (2012). Monocular Depth Cues in Computer Vision Applications. (Thesis). Universitat Autònoma de Barcelona. Retrieved from http://hdl.handle.net/10803/121644

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Cheda, Diego. “Monocular Depth Cues in Computer Vision Applications.” 2012. Thesis, Universitat Autònoma de Barcelona. Accessed April 22, 2021. http://hdl.handle.net/10803/121644.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Cheda, Diego. “Monocular Depth Cues in Computer Vision Applications.” 2012. Web. 22 Apr 2021.

Vancouver:

Cheda D. Monocular Depth Cues in Computer Vision Applications. [Internet] [Thesis]. Universitat Autònoma de Barcelona; 2012. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/10803/121644.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Cheda D. Monocular Depth Cues in Computer Vision Applications. [Thesis]. Universitat Autònoma de Barcelona; 2012. Available from: http://hdl.handle.net/10803/121644

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Australian National University

3. Qiu, Jiayan. Convolutional Neural Network based Age Estimation from Facial Image and Depth Prediction from Single Image .

Degree: 2016, Australian National University

URL: http://hdl.handle.net/1885/102510

► Convolutional neural network (CNN), one of the most commonly used deep learning methods, has been applied to various computer vision and pattern recognition tasks, and… (more)

▼ Convolutional neural network (CNN), one of the most commonly used deep learning methods, has been applied to various computer vision and pattern recognition tasks, and has achieved state-of-the-art performance. Most recent research work on CNN focuses on the innovations of the structure. This thesis explores both the innovation of structure and final label encoding of CNN. To evaluate the performance of our proposed network structure and label encoding method, two computer vision tasks are conducted, namely age estimation from facial image and depth estimation from a single image. For age estimation from facial image, we propose a novel hierarchical aggregation based deep network to learn aging features from facial images and apply our encoding method to transfer the discrete aging labels into a possibility label, which enables the CNN to conduct a classification task rather than regression task. In contrast to traditional aging features, where identical filter is applied to the en- tire facial image, our deep aging feature can capture both local and global cues in aging. Under our formulation, convolutional neural network (CNN) is employed to extract region specific features at lower layers. Then, low layer features are hierarchically aggregated by using fully connected way to consecutive higher layers. The resultant aging feature is of dimensionality 110, which achieves both good discriminative ability and efficiency. Experimental results of age prediction on the MORPH-II and the FG-NET databases show that the proposed deep aging feature outperforms state-of-the-art aging features by a margin. Depth estimation from a single image is an essential component toward understanding the 3D geometry of a scene. Compared with depth estimation from stereo images, depth map estimation from a single image is an extremely challenging task. This thesis addresses this task by regression with deep features, combined with surface normal constrained depth refinement. The proposed framework consists of two steps. First, we implement a convolutional neural network (CNN) to learn the mapping from multi-scale image patches to depth on the super-pixel level. In this step, we apply the proposed label encoding method to transfer the continuous depth labels to be possibility vectors, which reformulates the regression task to a classification task. Second, we refine predicted depth at the super-pixel level to the pixel level by exploiting surface normal constraints on depth map. Experimental results of depth estimation on the NYU2 dataset show that the proposed method achieves a promising performance and has a better performance compared with methods without the proposed label encoding. The above tasks show the proposed label encoding method has promising performance, which is another direction of CNN …

Subjects/Keywords: Convolutional Neural Network; Deep Learning; Computer Vision; Age Estimation; Depth Estimation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Qiu, J. (2016). Convolutional Neural Network based Age Estimation from Facial Image and Depth Prediction from Single Image . (Thesis). Australian National University. Retrieved from http://hdl.handle.net/1885/102510

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Qiu, Jiayan. “Convolutional Neural Network based Age Estimation from Facial Image and Depth Prediction from Single Image .” 2016. Thesis, Australian National University. Accessed April 22, 2021. http://hdl.handle.net/1885/102510.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Qiu, Jiayan. “Convolutional Neural Network based Age Estimation from Facial Image and Depth Prediction from Single Image .” 2016. Web. 22 Apr 2021.

Vancouver:

Qiu J. Convolutional Neural Network based Age Estimation from Facial Image and Depth Prediction from Single Image . [Internet] [Thesis]. Australian National University; 2016. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/1885/102510.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Qiu J. Convolutional Neural Network based Age Estimation from Facial Image and Depth Prediction from Single Image . [Thesis]. Australian National University; 2016. Available from: http://hdl.handle.net/1885/102510

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

IUPUI

4. Emerson, David R. 3-D Scene Reconstruction for Passive Ranging Using Depth from Defocus and Deep Learning.

Degree: 2019, IUPUI

URL: http://hdl.handle.net/1805/19900

►

Indiana University-Purdue University Indianapolis (IUPUI)

Depth estimation is increasingly becoming more important in computer vision. The requirement for autonomous systems to gauge their surroundings is… (more)

▼

Indiana University-Purdue University Indianapolis (IUPUI)

Depth estimation is increasingly becoming more important in computer vision. The requirement for autonomous systems to gauge their surroundings is of the utmost importance in order to avoid obstacles, preventing damage to itself and/or other systems or people. Depth measuring/estimation systems that use multiple cameras from multiple views can be expensive and extremely complex. And as these autonomous systems decrease in size and available power, the supporting sensors required to estimate depth must also shrink in size and power consumption. This research will concentrate on a single passive method known as Depth from Defocus (DfD), which uses an in-focus and out-of-focus image to infer the depth of objects in a scene. The major contribution of this research is the introduction of a new Deep Learning (DL) architecture to process the the in-focus and out-of-focus images to produce a depth map for the scene improving both speed and performance over a range of lighting conditions. Compared to the previous state-of-the-art multi-label graph cuts algorithms applied to the synthetically blurred dataset the DfD-Net produced a 34.30% improvement in the average Normalized Root Mean Square Error (NRMSE). Similarly the DfD-Net architecture produced a 76.69% improvement in the average Normalized Mean Absolute Error (NMAE). Only the Structural Similarity Index (SSIM) had a small average decrease of 2.68% when compared to the graph cuts algorithm. This slight reduction in the SSIM value is a result of the SSIM metric penalizing images that appear to be noisy. In some instances the DfD-Net output is mottled, which is interpreted as noise by the SSIM metric. This research introduces two methods of deep learning architecture optimization. The first method employs the use of a variant of the Particle Swarm Optimization (PSO) algorithm to improve the performance of the DfD-Net architecture. The PSO algorithm was able to find a combination of the number of convolutional filters, the size of the filters, the activation layers used, the use of a batch normalization layer between filters and the size of the input image used during training to produce a network architecture that resulted in an average NRMSE that was approximately 6.25% better than the baseline DfD-Net average NRMSE. This optimized architecture also resulted in an average NMAE that was 5.25% better than the baseline DfD-Net average NMAE. Only the SSIM metric did not see a gain in performance, dropping by 0.26% when compared to the baseline DfD-Net average SSIM value. The second method illustrates the use of a Self Organizing Map clustering method to reduce the number convolutional filters in the DfD-Net to reduce the overall run time of the architecture while still retaining the network performance exhibited prior to the reduction. This method produces a reduced DfD-Net architecture that has a run time decrease of between 14.91% and 44.85% depending on the hardware architecture that…

Advisors/Committee Members: Christopher, Lauren A., Ben Miled, Zina, King, Brian, Salama, Paul.

Subjects/Keywords: Depth estimation; Deep Learning; Depth from Focus; Microfluidic Lens; LIDAR; Particle Swarm Optimization (PSO)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Emerson, D. R. (2019). 3-D Scene Reconstruction for Passive Ranging Using Depth from Defocus and Deep Learning. (Thesis). IUPUI. Retrieved from http://hdl.handle.net/1805/19900

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Emerson, David R. “3-D Scene Reconstruction for Passive Ranging Using Depth from Defocus and Deep Learning.” 2019. Thesis, IUPUI. Accessed April 22, 2021. http://hdl.handle.net/1805/19900.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Emerson, David R. “3-D Scene Reconstruction for Passive Ranging Using Depth from Defocus and Deep Learning.” 2019. Web. 22 Apr 2021.

Vancouver:

Emerson DR. 3-D Scene Reconstruction for Passive Ranging Using Depth from Defocus and Deep Learning. [Internet] [Thesis]. IUPUI; 2019. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/1805/19900.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Emerson DR. 3-D Scene Reconstruction for Passive Ranging Using Depth from Defocus and Deep Learning. [Thesis]. IUPUI; 2019. Available from: http://hdl.handle.net/1805/19900

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Brunel University

5. Akuha Solomon Aondoakaa, Akuha Solomon Aondoakaa. Depth estimation from a single holoscopic 3D image and image up-sampling with deep-learning.

Degree: PhD, 2020, Brunel University

URL: http://bura.brunel.ac.uk/handle/2438/20610 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814416

► 3D depth information is widely utilized in industries such as security, autonomous vehicles, robotics, 3D printing, AR/VR entertainment, cinematography and medical science. However, state-of-the-art imaging… (more)

▼ 3D depth information is widely utilized in industries such as security, autonomous vehicles, robotics, 3D printing, AR/VR entertainment, cinematography and medical science. However, state-of-the-art imaging and 3D depth-sensing technologies are rather complicated or expensive and still lack scalability and interoperability. The research identified, entails the development of an innovative technique for reliable and efficient 3D depth estimation that deliver better accuracy. The proposed (1) multilayer Holoscopic 3D encoding technique reduces the computational cost of extracting viewpoint images from complex structured Holoscopic 3D data by 95%, by using labelled multilayer elemental images. It also addresses misplacement of elemental image pixels due to lens distortion error. The multilayer Holoscopic 3D encoding computing efficiency leads to the implementation of real-time 3D depth-dependent applications. Also, (2) an innovative approach of a deep learning-based single image super-resolution framework is developed and evaluated. It identified that learning-based image up-sampling techniques could be used regardless of inadequate 3D training data, as 2D training data can yield the same results. (3) The research is extended further by implementation of an H3D depth disparity -based framework, where a Holoscopic content adaptation technique for extracting semi-segmented stereo viewpoint image is introduced, and the design of a smart 3D depth mapping technique is proposed. Particularly, it provides a somewhat accurate 3D depth estimation from H3D images in near real-time. Holoscopic 3D image has thousands of perspective elemental images from omnidirectional viewpoint images and (4) a novel 3D depth estimation technique is developed to estimates 3D depth information directly from a single Holoscopic 3D image without the loss of any angular information and the introduction of unwanted artefacts. The proposed 3D depth measurement techniques are computationally efficient and robust with high accuracy; these can be incorporated in real-time applications of autonomous vehicles, security and AR/VR for real-time interaction.

Subjects/Keywords: Computer vision; Structure from motion; 3D depth estimation; Stereoscopic 3D depth; Holoscopic 3D feature extraction

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Akuha Solomon Aondoakaa, A. S. A. (2020). Depth estimation from a single holoscopic 3D image and image up-sampling with deep-learning. (Doctoral Dissertation). Brunel University. Retrieved from http://bura.brunel.ac.uk/handle/2438/20610 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814416

Chicago Manual of Style (16^th Edition):

Akuha Solomon Aondoakaa, Akuha Solomon Aondoakaa. “Depth estimation from a single holoscopic 3D image and image up-sampling with deep-learning.” 2020. Doctoral Dissertation, Brunel University. Accessed April 22, 2021. http://bura.brunel.ac.uk/handle/2438/20610 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814416.

MLA Handbook (7^th Edition):

Akuha Solomon Aondoakaa, Akuha Solomon Aondoakaa. “Depth estimation from a single holoscopic 3D image and image up-sampling with deep-learning.” 2020. Web. 22 Apr 2021.

Vancouver:

Akuha Solomon Aondoakaa ASA. Depth estimation from a single holoscopic 3D image and image up-sampling with deep-learning. [Internet] [Doctoral dissertation]. Brunel University; 2020. [cited 2021 Apr 22]. Available from: http://bura.brunel.ac.uk/handle/2438/20610 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814416.

Council of Science Editors:

Akuha Solomon Aondoakaa ASA. Depth estimation from a single holoscopic 3D image and image up-sampling with deep-learning. [Doctoral Dissertation]. Brunel University; 2020. Available from: http://bura.brunel.ac.uk/handle/2438/20610 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814416

University of Cincinnati

6. Sun, Yi. Depth Estimation Methodology for Modern Digital Photography.

Degree: PhD, Engineering and Applied Science: Electrical Engineering, 2019, University of Cincinnati

URL: http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563527854489549

► In the modern world, electronic devices with graphical imaging capability, such as digital cameras, projectors, mobile phones, and et cetera, are taking important roles to… (more)

▼ In the modern world, electronic devices with graphical imaging capability, such as digital cameras, projectors, mobile phones, and et cetera, are taking important roles to support modern life. In order for these devices to work properly and take the pictures people want, focusing mechanism, especially autofocus mechanism, is of pivotal importance. This involves obtaining three-dimension information from the scene being captured.To acquire three-dimensional information, the most apparent way is by capturing stereoscopic images with multiple lenses. However, the requirement of multiple lenses can sometimes become an obstacle for implementation, especially for modern digital photographic devices, for instance, digital cameras and camcorders. Most of them are designed to work with a single optical lens. This situation became the motivation for creating algorithms to cooperate with one lens only, and depth-from-defocus (DFD) is one of them.Depth-from-defocus (DFD) is a widely used three-dimensional reconstruction technique. It has certain practical advantages over other three-dimensional image processing techniques. It works perfectly fine with only one lens, and it does not require direct interaction with the scene. With the increasing appearance of high resolution, large aperture lens and high spec camera in modern digital photography, the occurrence of DFD is increasing rapidly as well. In this dissertation research, three approaches for estimating depth information using DFD are designed and presented. They used multiple images as the input to provide sufficient information for depth estimation, and focused on different aspects of the problem, such as depth accuracy, spatial resolution, and applicability of the algorithm. The first approach aimed at creating a depth map which can accurately register the depth of objects. In order to achieve this, multiple images of the same scene will be used to provide sufficient information to the algorithm. The depth map from the first approach can be used as the gold standard for other depth estimation methods, but it will suffer from its low spatial resolution. This will cause problems when estimating the depth at object boundary locations. Therefore the second approach provided a method to create depth maps which have the same resolution as the input images. Both first and second approaches utilized classical image processing process. Meanwhile, the third approach integrated the idea of neural network and deep learning into DFD algorithm. We created a new database containing about 20,000 images of seven patterns at different depth, and used them to estimate target depth. A modified VGGNet has been used as the structure of our convolutional neural network (CNN). Our experiment showed promising results comparing to other CNN applications. Advisors/Committee Members: Wee, William (Committee Chair).

Subjects/Keywords: Electrical Engineering; Depth Estimation; Digital Photography; Digital Camera; Depth-from-defocus; Multiple Images

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Sun, Y. (2019). Depth Estimation Methodology for Modern Digital Photography. (Doctoral Dissertation). University of Cincinnati. Retrieved from http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563527854489549

Chicago Manual of Style (16^th Edition):

Sun, Yi. “Depth Estimation Methodology for Modern Digital Photography.” 2019. Doctoral Dissertation, University of Cincinnati. Accessed April 22, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563527854489549.

MLA Handbook (7^th Edition):

Sun, Yi. “Depth Estimation Methodology for Modern Digital Photography.” 2019. Web. 22 Apr 2021.

Vancouver:

Sun Y. Depth Estimation Methodology for Modern Digital Photography. [Internet] [Doctoral dissertation]. University of Cincinnati; 2019. [cited 2021 Apr 22]. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563527854489549.

Council of Science Editors:

Sun Y. Depth Estimation Methodology for Modern Digital Photography. [Doctoral Dissertation]. University of Cincinnati; 2019. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563527854489549

KTH

7. Möckelind, Christoffer. Improving deep monocular depth predictions using dense narrow field of view depth images.

Degree: RPL, 2018, KTH

URL: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235660

►

In this work we study a depth prediction problem where we provide a narrow field of view depth image and a wide field of… (more)

Subjects/Keywords: Deep learning; Monocular; Depth estimation; Narrow field of view; RGB; RGBD; Noicy depth; Dense depth; Narrow depth; Sparse depth; Computer Sciences; Datavetenskap (datalogi)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Möckelind, C. (2018). Improving deep monocular depth predictions using dense narrow field of view depth images. (Thesis). KTH. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235660

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Möckelind, Christoffer. “Improving deep monocular depth predictions using dense narrow field of view depth images.” 2018. Thesis, KTH. Accessed April 22, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235660.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Möckelind, Christoffer. “Improving deep monocular depth predictions using dense narrow field of view depth images.” 2018. Web. 22 Apr 2021.

Vancouver:

Möckelind C. Improving deep monocular depth predictions using dense narrow field of view depth images. [Internet] [Thesis]. KTH; 2018. [cited 2021 Apr 22]. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235660.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Möckelind C. Improving deep monocular depth predictions using dense narrow field of view depth images. [Thesis]. KTH; 2018. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235660

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Johannes Gutenberg Universität Mainz

8. Gamer, Matthias. Reliability and consistency affect the integration of visual depth cues.

Degree: 2008, Johannes Gutenberg Universität Mainz

URL: http://ubm.opus.hbz-nrw.de/volltexte/2008/1742/

►

Abstract Originalsprache (englisch) Visual perception relies on a two-dimensional projection of the viewed scene on the retinas of both eyes. Thus, visual depth has to… (more)

▼

Abstract Originalsprache (englisch) Visual perception relies on a two-dimensional projection of the viewed scene on the retinas of both eyes. Thus, visual depth has to be reconstructed from a number of different cues that are subsequently integrated to obtain robust depth percepts. Existing models of sensory integration are mainly based on the reliabilities of individual cues and disregard potential cue interactions. In the current study, an extended Bayesian model is proposed that takes into account both cue reliability and consistency. Four experiments were carried out to test this model's predictions. Observers had to judge visual displays of hemi-cylinders with an elliptical cross section, which were constructed to allow for an orthogonal variation of several competing depth cues. In Experiment 1 and 2, observers estimated the cylinder's depth as defined by shading, texture, and motion gradients. The degree of consistency among these cues was systematically varied. It turned out that the extended Bayesian model provided a better fit to the empirical data compared to the traditional model which disregards covariations among cues. To circumvent the potentially problematic assessment of single-cue reliabilities, Experiment 3 used a multiple-observation task, which allowed for estimating perceptual weights from multiple-cue stimuli. Using the same multiple-observation task, the integration of stereoscopic disparity, shading, and texture gradients was examined in Experiment 4. It turned out that less reliable cues were downweighted in the combined percept. Moreover, a specific influence of cue consistency was revealed. Shading and disparity seemed to be processed interactively while other cue combinations could be well described by additive integration rules. These results suggest that cue combination in visual depth perception is highly flexible and depends on single-cue properties as well as on interrelations among cues. The extension of the traditional cue combination model is defended in terms of the necessity for robust perception in ecologically valid environments and the current findings are discussed in the light of emerging computational theories and neuroscientific approaches.

Abstract deutsch Da die visuelle Wahrnehmung auf einer zweidimensionalen, retinalen Projektion der betrachteten Szenerie beruht, muss räumliche Tiefe aus verschiedenen Tiefenhinweisen erschlossen werden. Die Kombination dieser Merkmale führt nachfolgend zu einem stabilen Perzept. Aktuelle Modelle sensorischer Integration schreiben den Reliabilitäten einzelner Tiefenmerkmale eine prominente Rolle zu, vernachlässigen dabei jedoch deren Interaktionen untereinander. In der vorliegenden Studie wurde ein erweitertes Bayesianisches Modell erarbeitet und in vier Experimenten überprüft, das sowohl Reliabilität als auch Konsistenz verschiedener Wahrnehmungskanäle berücksichtigt. Probanden schätzten die räumliche Tiefe visuell präsentierter Halbzylinder mit elliptischer Grundfläche ein. In den Experimenten 1 und 2 wurden partiell konsistente…

Subjects/Keywords: Sensorische Integration, Tiefenkriterien; Sensory Integration, Cue Fusion, Depth Estimation; Psychology

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Gamer, M. (2008). Reliability and consistency affect the integration of visual depth cues. (Doctoral Dissertation). Johannes Gutenberg Universität Mainz. Retrieved from http://ubm.opus.hbz-nrw.de/volltexte/2008/1742/

Chicago Manual of Style (16^th Edition):

Gamer, Matthias. “Reliability and consistency affect the integration of visual depth cues.” 2008. Doctoral Dissertation, Johannes Gutenberg Universität Mainz. Accessed April 22, 2021. http://ubm.opus.hbz-nrw.de/volltexte/2008/1742/.

MLA Handbook (7^th Edition):

Gamer, Matthias. “Reliability and consistency affect the integration of visual depth cues.” 2008. Web. 22 Apr 2021.

Vancouver:

Gamer M. Reliability and consistency affect the integration of visual depth cues. [Internet] [Doctoral dissertation]. Johannes Gutenberg Universität Mainz; 2008. [cited 2021 Apr 22]. Available from: http://ubm.opus.hbz-nrw.de/volltexte/2008/1742/.

Council of Science Editors:

Gamer M. Reliability and consistency affect the integration of visual depth cues. [Doctoral Dissertation]. Johannes Gutenberg Universität Mainz; 2008. Available from: http://ubm.opus.hbz-nrw.de/volltexte/2008/1742/

NSYSU

9. Cheng, Yuan-Chen. Efficient 3D Reconstruction System for Large-scale Scene.

Degree: Master, Electrical Engineering, 2017, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0319117-181337

► In this thesis, an efficient 3D reconstruction system is proposed to solve the problem of the huge computation of 3D reconstruction for large-scale scene. The… (more)

Subjects/Keywords: color mapping; keyframe selection; camera pose estimation; 3D reconstruction; depth cameras

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Cheng, Y. (2017). Efficient 3D Reconstruction System for Large-scale Scene. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0319117-181337

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Cheng, Yuan-Chen. “Efficient 3D Reconstruction System for Large-scale Scene.” 2017. Thesis, NSYSU. Accessed April 22, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0319117-181337.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Cheng, Yuan-Chen. “Efficient 3D Reconstruction System for Large-scale Scene.” 2017. Web. 22 Apr 2021.

Vancouver:

Cheng Y. Efficient 3D Reconstruction System for Large-scale Scene. [Internet] [Thesis]. NSYSU; 2017. [cited 2021 Apr 22]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0319117-181337.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Cheng Y. Efficient 3D Reconstruction System for Large-scale Scene. [Thesis]. NSYSU; 2017. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0319117-181337

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

10. Καπρινιώτης, Αχιλλέας. Εκτίμηση βάθους σκηνής από κάμερα τοποθετημένη σε αυτοκίνητο που κινείται.

Degree: 2014, University of Patras

URL: http://hdl.handle.net/10889/7779

►

Στη διπλωματική αυτή εργασία αναλύεται η εκτίμηση του βάθους μίας άκαμπτης σκηνής από κάμερα τοποθετημένη σε αυτοκίνητο που κινείται. Στο κεφάλαιο 1 γίνεται μία εισαγωγή… (more)

▼

Στη διπλωματική αυτή εργασία αναλύεται η εκτίμηση του βάθους μίας άκαμπτης σκηνής από κάμερα τοποθετημένη σε αυτοκίνητο που κινείται. Στο κεφάλαιο 1 γίνεται μία εισαγωγή στον τομέα της Υπολογιστικής Όρασης και δίνονται μερικά παραδείγματα εφαρμογών της. Στο κεφάλαιο 2 περιγράφονται βασικές αρχές της προβολικής γεωμετρίας που χρησιμοποιείται ως μαθηματικό υπόβαθρο για τα επόμενα κεφάλαια. Στο κεφάλαιο 3 γίνεται λόγος για το θεωρητικό μοντέλο της κάμερας, των παραμέτρων της και των παραμορφώσεων που υπεισέρχονται στο μοντέλο αυτό. Στο κεφάλαιο 4 αναφέρεται η διαδικασία βαθμονόμησης της κάμερας, μαζί με την υλοποίησή της. Στο κεφάλαιο 5 παρουσιάζονται γενικές κατηγορίες των στερεοσκοπικών αλγορίθμων που χρησιμοποιούνται, καθώς και τα κατάλληλα μέτρα ομοιότητάς τους. Στο κεφάλαιο 6 γίνεται αναφορά στον ανιχνευτή γωνιών Harris και γίνεται η εφαρμογή του τόσο ως προς την ανίχνευση των γωνιών, όσο και ως προς την αντιστοίχιση των 2 εικόνων. Στο κεφάλαιο 7 αναλύεται η θεωρία του αλγόριθμου SIFT και δίνεται ένα παράδειγμα ανίχνευσης και αντιστοίχισης χαρακτηριστικών. Στο κεφάλαιο 8 επισημαίνονται οι βασικές αρχές της επιπολικής γεωμετρίας, καθώς η σημασία της διόρθωσης των εικόνων. Στο κεφάλαιο 9 αναφέρεται η συνολική διαδικασία που ακολουθήθηκε, μαζί με την περιγραφή και την υλοποίηση των μεθόδων εκτίμησης βάθους που χρησιμοποιήθηκαν.

The current master’s thesis analyzes the depth estimation of a rigid scene from a camera attached to a moving vehicle. The first chapter gives an introduction to the field of Computer Vision and provides some examples of its applications. The second chapter describes basic principles of projective geometry that are being used as mathematical background for the next chapters. The third chapter refers to the theoretical modeling of a camera, along with its parameters and the distortions that appear in this model. The forth chapter deals with the camera calibration procedure, along with its implementation. Chapter five presents general categories of stereoscopic algorithms, along with their similarity measures. Chapter six talks about Harris corner detector and its implementation in detecting corners and in the matching process as well. Chapter 7 analyzes the SIFT algorithm theory and gives an example of detecting and matching features. Chapter 8 highlights basic principles of epipolar geometry and stresses out the importance of image rectification. Chapter nine presents the procedure that has been followed, along with the description and implementation of the depth estimation methods that have been used.

Advisors/Committee Members: Δερματάς, Ευάγγελος, Kapriniotis, Achilleas, Μπερμπερίδης, Κωνσταντίνος, Ψαράκης, Εμμανουήλ.

Subjects/Keywords: Εκτίμηση βάθους; Στερεοσκοπική αντιστοίχιση; 006.37; Depth estimation; Stereo correspondence

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Καπρινιώτης, �. (2014). Εκτίμηση βάθους σκηνής από κάμερα τοποθετημένη σε αυτοκίνητο που κινείται. (Masters Thesis). University of Patras. Retrieved from http://hdl.handle.net/10889/7779

Chicago Manual of Style (16^th Edition):

Καπρινιώτης, Αχιλλέας. “Εκτίμηση βάθους σκηνής από κάμερα τοποθετημένη σε αυτοκίνητο που κινείται.” 2014. Masters Thesis, University of Patras. Accessed April 22, 2021. http://hdl.handle.net/10889/7779.

MLA Handbook (7^th Edition):

Καπρινιώτης, Αχιλλέας. “Εκτίμηση βάθους σκηνής από κάμερα τοποθετημένη σε αυτοκίνητο που κινείται.” 2014. Web. 22 Apr 2021.

Vancouver:

Καπρινιώτης �. Εκτίμηση βάθους σκηνής από κάμερα τοποθετημένη σε αυτοκίνητο που κινείται. [Internet] [Masters thesis]. University of Patras; 2014. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/10889/7779.

Council of Science Editors:

Καπρινιώτης �. Εκτίμηση βάθους σκηνής από κάμερα τοποθετημένη σε αυτοκίνητο που κινείται. [Masters Thesis]. University of Patras; 2014. Available from: http://hdl.handle.net/10889/7779

University of Delaware

11. Guo, Xinqing. Combining learning and computational imaging for 3D inference.

Degree: PhD, University of Delaware, Department of Computer and Information Sciences, 2017, University of Delaware

URL: http://udspace.udel.edu/handle/19716/23209

► Acquiring 3D geometry of the scene is a key task in computer vision. Applications are numerous, from classical object reconstruction and scene understanding to the… (more)

▼ Acquiring 3D geometry of the scene is a key task in computer vision. Applications are numerous, from classical object reconstruction and scene understanding to the more recent visual SLAM and autonomous driving. Recent advances in computational imaging have enabled many new solutions to tackle the problem of 3D reconstruction. By modifying the camera's components, computational imaging optically encodes the scene, then decodes it with tailored algorithms. ☐ This dissertation focuses on exploring new computational imaging techniques, combined with recent advances in deep learning, to infer 3D geometry of the scene. In general, our approaches can be categorized into active and passive 3D sensing. ☐ For active illumination methods, we propose two solutions: first, we present a multi-flash (MF) system implemented on the mobile platform. Using the sequence of images captured by the MF system, we can extract the depth edges of the scene, and further estimate a depth map on a mobile device. Next, we show a portable immersive system that is capable of acquiring and displaying high fidelity 3D reconstructions using a set of RGB-D sensors. The system is based on structured light technique and is able to recover 3D geometry of the scene in real time. We have also developed a visualization system that allows users to dynamically visualize the event from new perspectives at arbitrary time instances in real time. ☐ For passive sensing methods, we focus on light field based depth estimation. For depth inference from a single light field, we present an algorithm that is tailored for barcode images. Our algorithm analyzes the statistics of raw light field images and conducts depth estimation with real time speed for fast refocusing and decoding. To mimic the human vision system, we investigate the dual light field input and propose a unified deep learning based framework to extract depth from both disparity cue and focus cue. To facilitate training, we have created a large dual focal stack database with ground truth disparity. While above solution focuses on fusing depth from focus and stereo, we also exploit combing depth from defocus and stereo, with an all-focus stereo pair and a defocused image of one of the stereo views as input. We have adopted the hourglass network architecture to extract depth from the image triplets. We have then studied and explored multiple neural network architectures to improve depth inference. We demonstrate that our deep learning based approaches preserve the strength of focus/defocus cue and disparity cue while effectively suppressing their weaknesses. Advisors/Committee Members: Yu, Jingyi.

Subjects/Keywords: Applied sciences; Computational imaging; Deep learning; Depth estimation; Light field

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Guo, X. (2017). Combining learning and computational imaging for 3D inference. (Doctoral Dissertation). University of Delaware. Retrieved from http://udspace.udel.edu/handle/19716/23209

Chicago Manual of Style (16^th Edition):

Guo, Xinqing. “Combining learning and computational imaging for 3D inference.” 2017. Doctoral Dissertation, University of Delaware. Accessed April 22, 2021. http://udspace.udel.edu/handle/19716/23209.

MLA Handbook (7^th Edition):

Guo, Xinqing. “Combining learning and computational imaging for 3D inference.” 2017. Web. 22 Apr 2021.

Vancouver:

Guo X. Combining learning and computational imaging for 3D inference. [Internet] [Doctoral dissertation]. University of Delaware; 2017. [cited 2021 Apr 22]. Available from: http://udspace.udel.edu/handle/19716/23209.

Council of Science Editors:

Guo X. Combining learning and computational imaging for 3D inference. [Doctoral Dissertation]. University of Delaware; 2017. Available from: http://udspace.udel.edu/handle/19716/23209

University of Houston

12. Liang, Hong 1984-. Addressing several key outstanding issues and extending the capability of the inverse scattering subseries for internal multiple attenuation, depth imaging, and parameter estimation.

Degree: PhD, Physics, 2013, University of Houston

URL: http://hdl.handle.net/10657/522

► The objective of seismic exploration is to determine the physical properties of the Earth's subsurface in order to detect potential hydrocarbon accumulations. The inverse scattering… (more)

▼ The objective of seismic exploration is to determine the physical properties of the Earth's subsurface in order to detect potential hydrocarbon accumulations. The inverse scattering series (ISS) is a multi-dimensional direct method that can perform all of the tasks associated with inversion only using the measured data and a chosen reference medium. This is achieved in stages using task-specific subseries that accomplish: (1) free-surface multiple removal; (2) internal multiple removal; (3) depth imaging; and (4) parameter estimation. This dissertation provides deeper comprehension of current ISS strengths and shortcomings for internal multiple removal, and caveats and understanding of ISS depth imaging and parameter estimation, which can be used to progress and develop further capability as part of a strategy to address the current outstanding challenges in exploration seismology. This dissertation is composed of three topics. The first topic extends the capability of the current ISS internal multiple attenuation algorithm by addressing one of its shortcomings. The current ISS internal multiple attenuator has provided added-value compared to other demultiple methods for complex media where multiple generators are not easy or able to be identified. However, this single term has its own strengths and limitations. Under certain circumstances, spurious events can be produced by the ISS leading-order attenuator. In this dissertation, higher-order terms in the ISS that address the spurious events generation from the leading-order attenuator are identified. Adding the higher-order terms to the current algorithm provides a more capable ISS internal multiple attenuation algorithm, which retains the benefit of the original algorithm and addresses the shortcoming due to spurious events. This work is part of the strategy to provide further capability for internal multiple attenuation in onshore or complex offshore exploration areas. The second project focuses on the generation and prediction of internal multiples in thin-layer models. A new method (named the reflector spectrum) based on the reflectivity forward modeling is presented to illustrate where internal multiples are generated in thin layers. The modeling of sub-resolution internal multiples leads to the concept of effective primaries. By comparing the modeling and prediction of internal multiples, it is shown that sub-resolution internal multiples cannot be predicted by the ISS internal multiple attenuator and internal multiples generated by resolvable reflectors can be accommodated by the ISS method. The third topic in the dissertation studies and evaluates the impact of matching or mismatching between the earth model type (e.g., acoustic, elastic, isotropic, anisotropic earth) that generates the data and the assumed model type behind the processing methods for ISS depth imaging and parameter estimation. Numerical results show that for ISS depth imaging and inversion applications, when the model type assumed in the processing algorithm is less complicated… Advisors/Committee Members: Weglein, Arthur B. (advisor), Francis, David J. (committee member), Hungerford, Ed V. (committee member), Su, Wu-Pei (committee member), Reiter, George F. (committee member).

Subjects/Keywords: Inverse scattering series; Multiple attenuation; Depth imaging; Parameter estimation; Physics

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Liang, H. 1. (2013). Addressing several key outstanding issues and extending the capability of the inverse scattering subseries for internal multiple attenuation, depth imaging, and parameter estimation. (Doctoral Dissertation). University of Houston. Retrieved from http://hdl.handle.net/10657/522

Chicago Manual of Style (16^th Edition):

Liang, Hong 1984-. “Addressing several key outstanding issues and extending the capability of the inverse scattering subseries for internal multiple attenuation, depth imaging, and parameter estimation.” 2013. Doctoral Dissertation, University of Houston. Accessed April 22, 2021. http://hdl.handle.net/10657/522.

MLA Handbook (7^th Edition):

Liang, Hong 1984-. “Addressing several key outstanding issues and extending the capability of the inverse scattering subseries for internal multiple attenuation, depth imaging, and parameter estimation.” 2013. Web. 22 Apr 2021.

Vancouver:

Liang H1. Addressing several key outstanding issues and extending the capability of the inverse scattering subseries for internal multiple attenuation, depth imaging, and parameter estimation. [Internet] [Doctoral dissertation]. University of Houston; 2013. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/10657/522.

Council of Science Editors:

Liang H1. Addressing several key outstanding issues and extending the capability of the inverse scattering subseries for internal multiple attenuation, depth imaging, and parameter estimation. [Doctoral Dissertation]. University of Houston; 2013. Available from: http://hdl.handle.net/10657/522

KTH

13. Nassir, Cesar. Domain-Independent Moving Object Depth Estimation using Monocular Camera.

Degree: RPL, 2018, KTH

URL: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233519

►

Today automotive companies across the world strive to create vehicles with fully autonomous capabilities. There are many benefits of developing autonomous vehicles, such as… (more)

▼

Today automotive companies across the world strive to create vehicles with fully autonomous capabilities. There are many benefits of developing autonomous vehicles, such as reduced traffic congestion, increased safety and reduced pollution, etc. To be able to achieve that goal there are many challenges ahead, one of them is visual perception. Being able to estimate depth from a 2D image has been shown to be a key component for 3D recognition, reconstruction and segmentation. Being able to estimate depth in an image from a monocular camera is an ill-posed problem since there is ambiguity between the mapping from colour intensity and depth value. Depth estimation from stereo images has come far compared to monocular depth estimation and was initially what depth estimation relied on. However, being able to exploit monocular cues is necessary for scenarios when stereo depth estimation is not possible. We have presented a novel CNN network, BiNet which is inspired by ENet, to tackle depth estimation of moving objects using only a monocular camera in real-time. It performs better than ENet in the Cityscapes dataset while adding only a small overhead to the complexity.

I dag strävar bilföretag över hela världen för att skapa fordon med helt autonoma möjligheter. Det finns många fördelar med att utveckla autonoma fordon, såsom minskad trafikstockning, ökad säkerhet och minskad förorening, etc. För att kunna uppnå det målet finns det många utmaningar framåt, en av dem är visuell uppfattning. Att kunna uppskatta djupet från en 2D-bild har visat sig vara en nyckelkomponent för 3D-igenkännande, rekonstruktion och segmentering. Att kunna uppskatta djupet i en bild från en monokulär kamera är ett svårt problem eftersom det finns tvetydighet mellan kartläggningen från färgintensitet och djupvärde. Djupestimering från stereobilder har kommit långt jämfört med monokulär djupestimering och var ursprungligen den metod som man har förlitat sig på. Att kunna utnyttja monokulära bilder är dock nödvändig för scenarier när stereodjupuppskattning inte är möjligt. Vi har presenterat ett nytt nätverk, BiNet som är inspirerat av ENet, för att ta itu med djupestimering av rörliga objekt med endast en monokulär kamera i realtid. Det fungerar bättre än ENet med datasetet Cityscapes och lägger bara till en liten kostnad på komplexiteten.

Subjects/Keywords: Robotics; Deep Learning; Computer Vision; Depth Estimation; Robotics; Robotteknik och automation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Nassir, C. (2018). Domain-Independent Moving Object Depth Estimation using Monocular Camera. (Thesis). KTH. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233519

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Nassir, Cesar. “Domain-Independent Moving Object Depth Estimation using Monocular Camera.” 2018. Thesis, KTH. Accessed April 22, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233519.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Nassir, Cesar. “Domain-Independent Moving Object Depth Estimation using Monocular Camera.” 2018. Web. 22 Apr 2021.

Vancouver:

Nassir C. Domain-Independent Moving Object Depth Estimation using Monocular Camera. [Internet] [Thesis]. KTH; 2018. [cited 2021 Apr 22]. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233519.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Nassir C. Domain-Independent Moving Object Depth Estimation using Monocular Camera. [Thesis]. KTH; 2018. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233519

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Arizona

14. Peng, Kuo-Shiuan. Toward Joint Scene Understanding Using Deep Convolutional Neural Network: Object State, Depth, and Segmentation .

Degree: 2019, University of Arizona

URL: http://hdl.handle.net/10150/636671

► Semantic understanding is the foundation of an intelligent system in the field of computer vision. Particularly, the real-time usage of the automation systems, such as… (more)

Subjects/Keywords: depth estimation; semantic object; semantic segmentation; semantic understanding

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Peng, K. (2019). Toward Joint Scene Understanding Using Deep Convolutional Neural Network: Object State, Depth, and Segmentation . (Doctoral Dissertation). University of Arizona. Retrieved from http://hdl.handle.net/10150/636671

Chicago Manual of Style (16^th Edition):

Peng, Kuo-Shiuan. “Toward Joint Scene Understanding Using Deep Convolutional Neural Network: Object State, Depth, and Segmentation .” 2019. Doctoral Dissertation, University of Arizona. Accessed April 22, 2021. http://hdl.handle.net/10150/636671.

MLA Handbook (7^th Edition):

Peng, Kuo-Shiuan. “Toward Joint Scene Understanding Using Deep Convolutional Neural Network: Object State, Depth, and Segmentation .” 2019. Web. 22 Apr 2021.

Vancouver:

Peng K. Toward Joint Scene Understanding Using Deep Convolutional Neural Network: Object State, Depth, and Segmentation . [Internet] [Doctoral dissertation]. University of Arizona; 2019. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/10150/636671.

Council of Science Editors:

Peng K. Toward Joint Scene Understanding Using Deep Convolutional Neural Network: Object State, Depth, and Segmentation . [Doctoral Dissertation]. University of Arizona; 2019. Available from: http://hdl.handle.net/10150/636671

Georgia Tech

15. Raza, Syed H. Temporally consistent semantic segmentation in videos.

Degree: PhD, Electrical and Computer Engineering, 2014, Georgia Tech

URL: http://hdl.handle.net/1853/53455

► The objective of this Thesis research is to develop algorithms for temporally consistent semantic segmentation in videos. Though many different forms of semantic segmentations exist,… (more)

▼ The objective of this Thesis research is to develop algorithms for temporally consistent semantic segmentation in videos. Though many different forms of semantic segmentations exist, this research is focused on the problem of temporally-consistent holistic scene understanding in outdoor videos. Holistic scene understanding requires an understanding of many individual aspects of the scene including 3D layout, objects present, occlusion boundaries, and depth. Such a description of a dynamic scene would be useful for many robotic applications including object reasoning, 3D perception, video analysis, video coding, segmentation, navigation and activity recognition. Scene understanding has been studied with great success for still images. However, scene understanding in videos requires additional approaches to account for the temporal variation, dynamic information, and exploiting causality. As a first step, image-based scene understanding methods can be directly applied to individual video frames to generate a description of the scene. However, these methods do not exploit temporal information across neighboring frames. Further, lacking temporal consistency, image-based methods can result in temporally-inconsistent labels across frames. This inconsistency can impact performance, as scene labels suddenly change between frames. The objective of our this study is to develop temporally consistent scene descriptive algorithms by processing videos efficiently, exploiting causality and data-redundancy, and cater for scene dynamics. Specifically, we achieve our research objectives by (1) extracting geometric context from videos to give broad 3D structure of the scene with all objects present, (2) Detecting occlusion boundaries in videos due to depth discontinuity, (3) Estimating depth in videos by combining monocular and motion features with semantic features and occlusion boundaries. Advisors/Committee Members: Essa, Irfan (advisor), Anderson, David (advisor), Yezzi, Anthony (committee member), Barnes, Christopher (committee member), Dellaert, Frank (committee member), Sukthankar, Rahul (committee member).

Subjects/Keywords: Semantic segmentation; Temporal consistency; Causality; Videos; Occlusion boundaries; Depth estimation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Raza, S. H. (2014). Temporally consistent semantic segmentation in videos. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/53455

Chicago Manual of Style (16^th Edition):

Raza, Syed H. “Temporally consistent semantic segmentation in videos.” 2014. Doctoral Dissertation, Georgia Tech. Accessed April 22, 2021. http://hdl.handle.net/1853/53455.

MLA Handbook (7^th Edition):

Raza, Syed H. “Temporally consistent semantic segmentation in videos.” 2014. Web. 22 Apr 2021.

Vancouver:

Raza SH. Temporally consistent semantic segmentation in videos. [Internet] [Doctoral dissertation]. Georgia Tech; 2014. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/1853/53455.

Council of Science Editors:

Raza SH. Temporally consistent semantic segmentation in videos. [Doctoral Dissertation]. Georgia Tech; 2014. Available from: http://hdl.handle.net/1853/53455

University of Minnesota

16. Mitra, Pallavi. Monocular Depth Estimation using Adversarial Training.

Degree: MS, Computer Science, 2020, University of Minnesota

URL: http://hdl.handle.net/11299/216319

► Monocular depth estimation is a fundamentally challenging problem in Computer Vision. It is useful for Robotics applications where design constraints prohibit the use of multiple… (more)

Subjects/Keywords: autonomous driving; Generative adversarial networks; global; Monocular depth estimation; supervised

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Mitra, P. (2020). Monocular Depth Estimation using Adversarial Training. (Masters Thesis). University of Minnesota. Retrieved from http://hdl.handle.net/11299/216319

Chicago Manual of Style (16^th Edition):

Mitra, Pallavi. “Monocular Depth Estimation using Adversarial Training.” 2020. Masters Thesis, University of Minnesota. Accessed April 22, 2021. http://hdl.handle.net/11299/216319.

MLA Handbook (7^th Edition):

Mitra, Pallavi. “Monocular Depth Estimation using Adversarial Training.” 2020. Web. 22 Apr 2021.

Vancouver:

Mitra P. Monocular Depth Estimation using Adversarial Training. [Internet] [Masters thesis]. University of Minnesota; 2020. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/11299/216319.

Council of Science Editors:

Mitra P. Monocular Depth Estimation using Adversarial Training. [Masters Thesis]. University of Minnesota; 2020. Available from: http://hdl.handle.net/11299/216319

University of Sydney

17. Fu, Huan. Robust Dense Prediction for Visual Perception .

Degree: 2019, University of Sydney

URL: http://hdl.handle.net/2123/20123

► Dense prediction or pixel-level labeling targets at predicting labels of interest (e.g., categories, depth values, flow vectors, and edge probabilities) for each pixel of an… (more)

▼ Dense prediction or pixel-level labeling targets at predicting labels of interest (e.g., categories, depth values, flow vectors, and edge probabilities) for each pixel of an input image. This middle-level computer vision problem plays a crucial role in establishing visual perception systems for the future intelligent world. Therefore, tremendous efforts have been made in the past decades to explore the solution for robust dense prediction, and recent studies have continuously obtained significant progress relying on deep Fully Convolutional Networks (FCNs). According to the expected label, dense prediction contains a set of subtasks. Building robust models for each task must examine the particular property, but the main intuition and motivation for the network architecture development are shared across different tasks. In the thesis, we take the well-known problems of scene parsing, monocular depth estimation, and edge detection as examples, and devise some advanced and highly extensible techniques by addressing both the individual and collective issues for robust dense prediction. Specific to scene parsing, employing hierarchical convolutional features is essential to obtain high-resolution and fine-grained predictions. Previous algorithms regularly aggregate them via concatenation or linear combination, which cannot sufficiently exploit the diversities of the contextual information and the spatial inhomogeneity of a scene. We propose some novel attention mechanisms, i.e., adaptive hierarchical feature aggregation (AHFA) and mixture-of-experts (MoE), to re-weight different levels of features at each spatial location according to the local structure and surrounding contextual information before aggregation. Existing works on depth estimation often overlook the strong inherent ordinal correlation of depth values resulting in inferior performance. Motivated by the observation, we introduce the ranking mechanism for depth estimation by proposing an effective ordinal regression constraint. For edge detection, common approaches simply predict the boundary probability for each pixel individually from the receptive fields where the pixel is centered at. Differently, we propose that modeling the boundary structures or position sensitive scores are more flexible because of the implied feature competition for the prediction of each spatial position. We also study unsupervised domain mapping which is of general applicability, enabling a consolidated solution for dense prediction. Advanced unsupervised domain mapping approaches mainly rely on Generative Adversarial Networks (GANs) to make the prediction indistinguishable from reality (e.g., generated pseudo parsing vs. truth parsing), and reduce the solution space with high-level constraints and assumptions to guarantee that an input and the corresponding output are paired up in a meaningful way in the absence of unmatched training samples. However, they overlook the special property of images that simple geometric transformations do not change the semantics of an image. With…

Subjects/Keywords: dense prediction; domain mapping; scene parsing; GANs; depth estimation; boundary detection

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Fu, H. (2019). Robust Dense Prediction for Visual Perception . (Thesis). University of Sydney. Retrieved from http://hdl.handle.net/2123/20123

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Fu, Huan. “Robust Dense Prediction for Visual Perception .” 2019. Thesis, University of Sydney. Accessed April 22, 2021. http://hdl.handle.net/2123/20123.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Fu, Huan. “Robust Dense Prediction for Visual Perception .” 2019. Web. 22 Apr 2021.

Vancouver:

Fu H. Robust Dense Prediction for Visual Perception . [Internet] [Thesis]. University of Sydney; 2019. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/2123/20123.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Fu H. Robust Dense Prediction for Visual Perception . [Thesis]. University of Sydney; 2019. Available from: http://hdl.handle.net/2123/20123

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of New South Wales

18. Li, Qiang. High quality depth estimation for multi-view video.

Degree: Engineering & Information Technology Canberra, 2012, University of New South Wales

URL: http://handle.unsw.edu.au/1959.4/52142 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:10812/SOURCE01?view=true

► This thesis presents new techniques to improve the quality of adaptive structured light based depth estimation for multi-view video. By interleaving structured light with ambient… (more)

▼ This thesis presents new techniques to improve the quality of adaptive structured light based depth estimation for multi-view video. By interleaving structured light with ambient light on a frame-by-frame basis, the proposed methods can potentially capture both texture video under only ambient light for image rendering and video under both ambient light and structured light for depth estimation at video rates. By using structured light with adaptive colours which account for ambient light conditions and the colours of objects, the proposed methods not only avoid matching ambiguities in textureless areas and areas with repetitive textures but also perform robustly in areas with rich colours and textures under ambient light conditions.Firstly, a new structured light approach using adaptive colours is proposed. The adaptive colours are acquired using principal component analysis in the RGB colour space of the image of the scene under ambient light conditions. Based on a projected grid pattern of adaptive colours, a new depth estimation technique combining active and passive approaches is proposed. This technique shows the advantage of adaptive structured light over constant colours and the advantage of combining both active and passive approaches over active-only or passive-only techniques.A second new depth estimation technique using adaptive structured light and a shiftable window-based global optimization algorithm is proposed. This technique shows the advantage of adaptive structured light over random colors and generates a depth map with sharp depth discontinuities and half-pixel accuracy using the global optimization in an iterative way. A random noise pattern instead of a grid pattern is employed to improve the performance of depth estimation around object boundaries.A third new depth estimation technique using the dual-tree complex wavelet transform (DTCWT), graph cut and adaptive structured light is proposed. This technique employs the phase difference between coefficients from the DTCWT as a robust similarity measure and has the ability to keep clear depth discontinuities and detect clean and continuous occlusion areas.Finally, using the depth maps generated by the proposed techniques, image rendering is implemented through 3D warping to verify the feasibility of the proposed depth estimation techniques for multi-view video. Advisors/Committee Members: Pickering, Mark, Engineering & Information Technology, UNSW Canberra, UNSW, Frater, Michael, Engineering & Information Technology, UNSW Canberra, UNSW.

Subjects/Keywords: adaptive structured light; depth estimation; multi-view video

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Li, Q. (2012). High quality depth estimation for multi-view video. (Doctoral Dissertation). University of New South Wales. Retrieved from http://handle.unsw.edu.au/1959.4/52142 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:10812/SOURCE01?view=true

Chicago Manual of Style (16^th Edition):

Li, Qiang. “High quality depth estimation for multi-view video.” 2012. Doctoral Dissertation, University of New South Wales. Accessed April 22, 2021. http://handle.unsw.edu.au/1959.4/52142 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:10812/SOURCE01?view=true.

MLA Handbook (7^th Edition):

Li, Qiang. “High quality depth estimation for multi-view video.” 2012. Web. 22 Apr 2021.

Vancouver:

Li Q. High quality depth estimation for multi-view video. [Internet] [Doctoral dissertation]. University of New South Wales; 2012. [cited 2021 Apr 22]. Available from: http://handle.unsw.edu.au/1959.4/52142 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:10812/SOURCE01?view=true.

Council of Science Editors:

Li Q. High quality depth estimation for multi-view video. [Doctoral Dissertation]. University of New South Wales; 2012. Available from: http://handle.unsw.edu.au/1959.4/52142 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:10812/SOURCE01?view=true

University of Adelaide

19. Zhan, Huangying. Self-Supervised Learning for Geometry.

Degree: 2020, University of Adelaide

URL: http://hdl.handle.net/2440/129566

► This thesis focuses on two fundamental problems in robotic vision, scene geometry understanding and camera tracking. While both tasks have been the subject of research… (more)

▼ This thesis focuses on two fundamental problems in robotic vision, scene geometry understanding and camera tracking. While both tasks have been the subject of research in robotic vision, numerous geometric solutions have been proposed in the past decades. In this thesis, we cast the geometric problems as machine learning problems, specifically, deep learning problems. Differ from conventional supervised learning methods that using expensive annotations as the supervisory signal, we advocate for the use of geometry as a supervisory signal to improve the perceptual capabilities in robots, namely Geometry Self-supervision. With the geometry self-supervision, we allow robots to learn and infer the 3D structure of the scene and ego-motion by watching videos, instead of expensive ground-truth annotation in traditional supervised learning problems. Followed by showing the use of geometry for deep learning, we show the possibilities of integrating self-supervised models with traditional geometry-based methods as a hybrid solution for solving the mapping and tracking problem. We focus on an end-to-end mapping problem from stereo data in the first part of this thesis, namely Deep Stereo Matching. Stereo matching is one of the oldest problems in computer vision. Classical approaches to stereo matching typically rely on handcrafted features and a multiple-step solution. Recent deep learning methods utilize deep neural networks to achieve end-to-end trained approaches while significantly outperforming classic methods. We propose a novel data acquisition pipeline using an untethered device (Microsoft HoloLens) with a Time-of-Flight (ToF) depth camera and stereo cameras to collect real-world data. A novel semi-supervised method is proposed to train networks with ground-truth supervision and self-supervision. The large scale real-world stereo dataset with semi-dense annotation and dense self-supervision allow our deep stereo matching network to generalize better when compared to prior arts. Mapping and tracking using a single camera (Monocular) is a harder problem when compared to that using a stereo camera due to varies well-known challenges. In the second part of this thesis, We decouple the problem into single view depth estimation (mapping) and two view visual odometry (tracking) and propose a self-supervised framework, namely SelfTAM, which jointly learns the depth estimator and the odometry estimator. The self-supervised problem is usually formulated as an energy minimization problem consist of an energy of data consistency in multi-view (e.g. photometric) and an energy of prior regularization (e.g. depth smoothness prior). We strengthen the supervision signal with a deep feature consistency energy term and a surface normal regularization term. Though our method trains models with stereo sequence such that a real-world scaling factor is naturally incorporated, only monocular data is required in the inference stage. In the last part of this thesis, we revisit the basics of visual odometry and explore the best practice to… Advisors/Committee Members: Reid, Ian (advisor), Carneiro, Gustavo (advisor), School of Computer Science (school).

Subjects/Keywords: Deep learning; un/self-supervised learning; visual odometry; depth estimation; SLAM

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Zhan, H. (2020). Self-Supervised Learning for Geometry. (Thesis). University of Adelaide. Retrieved from http://hdl.handle.net/2440/129566

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Zhan, Huangying. “Self-Supervised Learning for Geometry.” 2020. Thesis, University of Adelaide. Accessed April 22, 2021. http://hdl.handle.net/2440/129566.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Zhan, Huangying. “Self-Supervised Learning for Geometry.” 2020. Web. 22 Apr 2021.

Vancouver:

Zhan H. Self-Supervised Learning for Geometry. [Internet] [Thesis]. University of Adelaide; 2020. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/2440/129566.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Zhan H. Self-Supervised Learning for Geometry. [Thesis]. University of Adelaide; 2020. Available from: http://hdl.handle.net/2440/129566

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

York University

20. Stransky, Debi. First and Second Order Stereoscopic Processing of Fused and Diplopic Targets.

Degree: PhD, Psychology (Functional Area: Brain, Behaviour & Cognitive Science, 2015, York University

URL: http://hdl.handle.net/10315/29941

► Depth from stereopsis is due to the positional difference between the two eyes, which results in each eye receiving a different view of the world.… (more)

▼ Depth from stereopsis is due to the positional difference between the two eyes, which results in each eye receiving a different view of the world. Although progress has been made in understanding how the visual system processes stereoscopic stimuli, a number of questions remain. The goal of this work was to assess the relationship between the perceptual, the temporal and the 1st- /2nd- order dichotomies of stereopsis and in doing so, determine an appropriate method for measuring depth from large disparities. To this end, stereosensitivity and perceived depth were assessed using 1st- and 2nd- order stimuli over a range of test disparities and conditions. The main contributions of this research are as follows: 1) The sustained/transient dichotomy proposed by Edwards, Pope and Schor (2000) is best considered in terms of the spatial dichotomy proposed by Hess and Wilcox (1994). At large disparities it is not possible to categorize performance based on exposure duration alone; 2) There is not a simple correspondence between Ogle's (1952) patent / qualitative perceptual categories and the 1st- /2nd- order dichotomy proposed by Hess and Wilcox (1994); 3) Quantitative depth is provided by both 1st- and 2nd- order mechanisms in the fused range, but only the 2nd- order signal is used when stimuli are diplopic; 3) The quantitative depth provided by a 2nd- order stimulus scales with envelope size; and 4) The monoptic depth phenomenon may be related to depth from diplopic stimuli, but for conditions tested here when both monoptic depth and 2nd- order stereopsis are available, the latter is used to encode depth percepts. The results reported here expand on earlier work on 1st- and 2nd- order stereopsis and address the issues in the methodologies used to study depth from large disparities. These results are consistent with the widely accepted filter-rectify-filter model of 2nd- order processing, and 1st- and 2nd- order stimuli are likely encoded by disparity-sensitive neurons via a two-stream model (see Wilson, Ferrera, and Yo (1992); Zhou and Baker (1993)). Advisors/Committee Members: Wilcox, Laurie M. (advisor).

Subjects/Keywords: Experimental psychology; Psychology; Neurosciences; Stereopsis; Stereoscopic 3D; 1st- order; 2nd- order; Non-linear mechanism; Fused; Fusion; Diplopic; Diplopia; Depth; Disparity; Metric depth; Depth estimation; Stereoacuity; Stereosensitivity; Spatial dichotomy; Monoptic depth

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Stransky, D. (2015). First and Second Order Stereoscopic Processing of Fused and Diplopic Targets. (Doctoral Dissertation). York University. Retrieved from http://hdl.handle.net/10315/29941

Chicago Manual of Style (16^th Edition):

Stransky, Debi. “First and Second Order Stereoscopic Processing of Fused and Diplopic Targets.” 2015. Doctoral Dissertation, York University. Accessed April 22, 2021. http://hdl.handle.net/10315/29941.

MLA Handbook (7^th Edition):

Stransky, Debi. “First and Second Order Stereoscopic Processing of Fused and Diplopic Targets.” 2015. Web. 22 Apr 2021.

Vancouver:

Stransky D. First and Second Order Stereoscopic Processing of Fused and Diplopic Targets. [Internet] [Doctoral dissertation]. York University; 2015. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/10315/29941.

Council of Science Editors:

Stransky D. First and Second Order Stereoscopic Processing of Fused and Diplopic Targets. [Doctoral Dissertation]. York University; 2015. Available from: http://hdl.handle.net/10315/29941

University of California – San Diego

21. Liu, Lee-Kang. From Image to Video, Depth Data Reconstruction from a Subset of Samples: Representations, Algorithms, and Sampling Strategies.

Degree: Electrical Engineering (Signal and Image Proc), 2015, University of California – San Diego

URL: http://www.escholarship.org/uc/item/98f001p4

► Depth data acquisition has drawn considerable interest in recent years as a result of the rapid development of 3D technology. A large number of acquisition… (more)

▼ Depth data acquisition has drawn considerable interest in recent years as a result of the rapid development of 3D technology. A large number of acquisition techniques are based on hardware devices, e.g., infra-red sensors, time-of-flight camera, and LiDAR, etc, whereas they have limited performance due to poor depth precision and low resolution. In some situations computational methods are preferred due to its flexibility and low cost. These computational techniques, typically known as depth estimation algorithms, estimate depth maps (in terms of disparities) from a pair of stereo images. However, existing computational techniques are sensitive to various factors such as noise, camera alignment, and illumination, resulting that a few samples are reliable. Therefore, dense depth data reconstruction from sparse samples is a significant technological challenge.In this thesis, we mainly consider the problem of dense depth data reconstruction from a subset of samples. We present computationally efficient methods to estimate dense depth maps from sparse measurements, and we further extend the work to dense depth video estimation. Working on single depth image, we have three main contributions: First, we provide empirical evidence that depth maps can be encoded much more sparsely than natural images by using common dictionaries such as wavelets and contourlets, and show that disparity maps can be sparsely represented by a combined wavelet and contourlet dictionary. Second, we propose a subgradient algorithm for dense depth image reconstruction, and propose an alternating direction methods of multipliers (ADMM) algorithm with a multi-scale warm start procedure to further speed up the convergence. Third, we propose a two-stage randomized sampling scheme to optimally choose the sampling locations, thus maximizing the reconstruction performance for a given sampling budget. Experimental results show that the proposed methods produce high quality dense depth estimates, and are robust to noisy measurements.For dealing with depth video sequences, a framework for depth video reconstruction from a subset of samples is proposed. By redefining classical dense depth estimation into two individual problems, sensing and synthesis, we propose a motion compensation assisted sampling (MCAS) scheme and a spatio-temporal depth reconstruction (STDR) algorithm for reconstructing depth video sequences from a subset of samples. Using the 3-dimensional extensible dictionary, 3D-DWT, and applying alternating direction method of multiplier technique, the proposed STDR algorithm possesses scability for temporal volume and efficiency for processing large scale depth data. Exploiting the temporal information and corresponding RGB images, the proposed MCAS scheme achieves an efficient 1-Stage sampling. Experimental results show that the proposed depth reconstruction framework outperforms the existing methods and is competitive comparing to our previous work on sampling single depth image, which requires a pilot signal in the 2-Stage sampling scheme.…

Subjects/Keywords: Engineering; Alternating Direction Method of Multipliers; Dense Depth Estimation; Depth Enhancement; Image and Video Processing; Sparse Reconstruction

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Liu, L. (2015). From Image to Video, Depth Data Reconstruction from a Subset of Samples: Representations, Algorithms, and Sampling Strategies. (Thesis). University of California – San Diego. Retrieved from http://www.escholarship.org/uc/item/98f001p4

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Liu, Lee-Kang. “From Image to Video, Depth Data Reconstruction from a Subset of Samples: Representations, Algorithms, and Sampling Strategies.” 2015. Thesis, University of California – San Diego. Accessed April 22, 2021. http://www.escholarship.org/uc/item/98f001p4.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Liu, Lee-Kang. “From Image to Video, Depth Data Reconstruction from a Subset of Samples: Representations, Algorithms, and Sampling Strategies.” 2015. Web. 22 Apr 2021.

Vancouver:

Liu L. From Image to Video, Depth Data Reconstruction from a Subset of Samples: Representations, Algorithms, and Sampling Strategies. [Internet] [Thesis]. University of California – San Diego; 2015. [cited 2021 Apr 22]. Available from: http://www.escholarship.org/uc/item/98f001p4.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Liu L. From Image to Video, Depth Data Reconstruction from a Subset of Samples: Representations, Algorithms, and Sampling Strategies. [Thesis]. University of California – San Diego; 2015. Available from: http://www.escholarship.org/uc/item/98f001p4

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

22. Moukari, Michel. Estimation de profondeur à partir d'images monoculaires par apprentissage profond : Depth estimation from monocular images by deep learning.

Degree: Docteur es, Informatique, 2019, Normandie

URL: http://www.theses.fr/2019NORMC211

►

La vision par ordinateur est une branche de l'intelligence artificielle dont le but est de permettre à une machine d'analyser, de traiter et de comprendre… (more)

▼

La vision par ordinateur est une branche de l'intelligence artificielle dont le but est de permettre à une machine d'analyser, de traiter et de comprendre le contenu d'images numériques. La compréhension de scène en particulier est un enjeu majeur en vision par ordinateur. Elle passe par une caractérisation à la fois sémantique et structurelle de l'image, permettant d'une part d'en décrire le contenu et, d'autre part, d'en comprendre la géométrie. Cependant tandis que l'espace réel est de nature tridimensionnelle, l'image qui le représente, elle, est bidimensionnelle. Une partie de l'information 3D est donc perdue lors du processus de formation de l'image et il est d'autant plus complexe de décrire la géométrie d'une scène à partir d'images 2D de celle-ci.Il existe plusieurs manières de retrouver l'information de profondeur perdue lors de la formation de l'image. Dans cette thèse nous nous intéressons à l’estimation d'une carte de profondeur étant donné une seule image de la scène. Dans ce cas, l'information de profondeur correspond, pour chaque pixel, à la distance entre la caméra et l'objet représenté en ce pixel. L'estimation automatique d'une carte de distances de la scène à partir d'une image est en effet une brique algorithmique critique dans de très nombreux domaines, en particulier celui des véhicules autonomes (détection d’obstacles, aide à la navigation).Bien que le problème de l'estimation de profondeur à partir d'une seule image soit un problème difficile et intrinsèquement mal posé, nous savons que l'Homme peut apprécier les distances avec un seul œil. Cette capacité n'est pas innée mais acquise et elle est possible en grande partie grâce à l'identification d'indices reflétant la connaissance a priori des objets qui nous entourent. Par ailleurs, nous savons que des algorithmes d'apprentissage peuvent extraire ces indices directement depuis des images. Nous nous intéressons en particulier aux méthodes d’apprentissage statistique basées sur des réseaux de neurones profond qui ont récemment permis des percées majeures dans de nombreux domaines et nous étudions le cas de l'estimation de profondeur monoculaire.

Computer vision is a branch of artificial intelligence whose purpose is to enable a machine to analyze, process and understand the content of digital images. Scene understanding in particular is a major issue in computer vision. It goes through a semantic and structural characterization of the image, on one hand to describe its content and, on the other hand, to understand its geometry. However, while the real space is three-dimensional, the image representing it is two-dimensional. Part of the 3D information is thus lost during the process of image formation and it is therefore non trivial to describe the geometry of a scene from 2D images of it.There are several ways to retrieve the depth information lost in the image. In this thesis we are interested in estimating a depth map given a single image of the scene. In this case, the depth information corresponds, for each pixel, to the distance…

Advisors/Committee Members: Jurie, Frédéric (thesis director).

Subjects/Keywords: Apprentissage Statistique; Réseau de Neurones Convolutionnel; Estimation de Profondeur; Complétion de Profondeur; Evaluation d'Incertitude; Deep Learning; Convolutional Neural Network; Computer Vision; Depth Estimation; Monocular; 3D; Uncertainty Assessment; Depth Completion

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Moukari, M. (2019). Estimation de profondeur à partir d'images monoculaires par apprentissage profond : Depth estimation from monocular images by deep learning. (Doctoral Dissertation). Normandie. Retrieved from http://www.theses.fr/2019NORMC211

Chicago Manual of Style (16^th Edition):

Moukari, Michel. “Estimation de profondeur à partir d'images monoculaires par apprentissage profond : Depth estimation from monocular images by deep learning.” 2019. Doctoral Dissertation, Normandie. Accessed April 22, 2021. http://www.theses.fr/2019NORMC211.

MLA Handbook (7^th Edition):

Moukari, Michel. “Estimation de profondeur à partir d'images monoculaires par apprentissage profond : Depth estimation from monocular images by deep learning.” 2019. Web. 22 Apr 2021.

Vancouver:

Moukari M. Estimation de profondeur à partir d'images monoculaires par apprentissage profond : Depth estimation from monocular images by deep learning. [Internet] [Doctoral dissertation]. Normandie; 2019. [cited 2021 Apr 22]. Available from: http://www.theses.fr/2019NORMC211.

Council of Science Editors:

Moukari M. Estimation de profondeur à partir d'images monoculaires par apprentissage profond : Depth estimation from monocular images by deep learning. [Doctoral Dissertation]. Normandie; 2019. Available from: http://www.theses.fr/2019NORMC211

23. Mollén, Katarina. Water Depth Estimation Using Ultrasound Pulses for Handheld Diving Equipment.

Degree: The Institute of Technology, 2015, Linköping UniversityLinköping University

URL: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-117061

►

This thesis studies the design and implementation of an ultra-sonic water depth sounder. The depth sounder is implemented in a hand-held smart console used… (more)

▼

This thesis studies the design and implementation of an ultra-sonic water depth sounder. The depth sounder is implemented in a hand-held smart console used by divers. Since the idea of echo sounding is to measure the flight time between transmitting the signal and receiving the echo, the main challenge of this task is to find a time-of-flight (ToF) estimation for a signal in noise. It should be suitable for this specific application and robust when implemented in the device. The thesis contains an investigation of suitable ToF methods. More detailed evaluations of the matched filter, also known as the correlation method, and the linear phase approach are done. Aspects like pulse frequency and duration, speed of sound in water and underwater noise are taken into account. The ToF-methods are evaluated through simulation and experiments. The matched filter approach is found suitable based on these simulations and tests with signals recorded by the console. This verification leads to the implementation of the algorithm on the device. The algorithm is tested in real time, the results are evaluated and improvements suggested.

Denna rapport behandlar skattning av vattendjup med hjälp av ultraljudspulser och implementation av detta. Djupmätaren implementeras i en handhållen dykarkonsoll. Eftersom grundidén i ekolodning är att mäta tiden mellan att pulsen skickas iväg och att ekot tas emot är en stor del av utmaningen att hitta en lämplig metod för att skatta flykttiden för en signal i brus. Metoden ska passa för detta användingsområde och vara robust. Rapporten tar upp tidigare forskning gjord inom flykttidsestimering. De metoder som utvärderas för implementation är det matchade filtret, också kallad korrelationsmetoden, och linjär fas-metoden. Andra aspekter som avvägs och utreds är pulsfrekvens och pulsvaraktighet, ljudets hastighet och brus under vattnet. Metoderna för att skatta flykttid utvärderas genom simuleringar. Det matchade filtret bedöms vara lämpligt baserat på dessa simuleringar och experiment med data inspelad med konsollen. Denna verifikation leder till att algoritmen implementeras på konsollen. Den implementerade algoritmen testas i realtid, resultaten utvärderas och förbättringar föreslås.

Subjects/Keywords: Depth sounding; Echo sounding; Underwater ultrasounding; Time of flight estimation; Time delay estimation; Matched filter; Cross correlation; GCC; PHAT; ML

4 more images…

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Mollén, K. (2015). Water Depth Estimation Using Ultrasound Pulses for Handheld Diving Equipment. (Thesis). Linköping UniversityLinköping University. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-117061

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Mollén, Katarina. “Water Depth Estimation Using Ultrasound Pulses for Handheld Diving Equipment.” 2015. Thesis, Linköping UniversityLinköping University. Accessed April 22, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-117061.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Mollén, Katarina. “Water Depth Estimation Using Ultrasound Pulses for Handheld Diving Equipment.” 2015. Web. 22 Apr 2021.

Vancouver:

Mollén K. Water Depth Estimation Using Ultrasound Pulses for Handheld Diving Equipment. [Internet] [Thesis]. Linköping UniversityLinköping University; 2015. [cited 2021 Apr 22]. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-117061.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Mollén K. Water Depth Estimation Using Ultrasound Pulses for Handheld Diving Equipment. [Thesis]. Linköping UniversityLinköping University; 2015. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-117061

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Johannes Gutenberg Universität Mainz

24. Frech, Birte. Verhaltensphysiologische Analyse der visuellen Wahrnehmung räumlicher Tiefe beim Goldfisch.

Degree: 2009, Johannes Gutenberg Universität Mainz

URL: http://ubm.opus.hbz-nrw.de/volltexte/2009/2116/

►

Die Frage, wie es zur visuellen Wahrnehmung räumlicher Tiefe kommt, wenn das Retinabild nur zweidimensional ist, gehört zu den grundlegenden Proble-men der Hirnforschung. Für Tiere,… (more)

▼

Die Frage, wie es zur visuellen Wahrnehmung räumlicher Tiefe kommt, wenn das Retinabild nur zweidimensional ist, gehört zu den grundlegenden Proble-men der Hirnforschung. Für Tiere, die sich aktiv in ihrer Umgebung bewegen, herrscht ein großer Selektionsdruck Entfernungen und Größen richtig einzu-schätzen. Ziel der vorliegenden Arbeit war es, herauszufinden, ob und wie gut Goldfische Objekte allein aufgrund des Abstandes unterscheiden können und woraus sie Information über den Abstand gewinnen. Hierzu wurde ein Ver-suchsaufbau mit homogen weißem Hintergrund entworfen, in dem die Akkom-modation als Entfernungsinformationen verwendet werden kann, weniger je-doch die Bewegungsparallaxe. Die Goldfische lernten durch operante Konditio-nierung einen Stimulus (schwarze Kreisscheibe) in einem bestimmten Abstand zu wählen, während ein anderer, gleichgroßer Stimulus so entfernt wie möglich präsentiert wurde. Der Abstand zwischen den Stimuli wurde dann verringert, bis die Goldfische keine sichere Wahl für den Dressurstimulus mehr treffen konnten. Die Unterscheidungsleistung der Goldfische wurde mit zunehmendem Abstand des Dressurstimulus immer geringer. Eine Wiederholung der Versuche mit unscharfen Stimu¬lus¬kon¬turen brachte keine Verschlechterung in der Unter-scheidung, was Akkommodation wenig wahrscheinlich macht. Um die Größen-konstanz beim Goldfisch zu testen, wurden die Durchmesser der unterschiedlich entfernten Stimuli so angepasst, dass sie für den Goldfisch die gleiche Retina-bildgröße hatten. Unter diesen Bedingungen waren die Goldfische nicht in der Lage verschieden entfernte Stimuli zu unterscheiden und somit Größenkonstanz zu leisten. Es fand demnach keine echte Entfernungsbestimmung oder Tiefen-wahrneh¬mung statt. Die Unterscheidung der verschieden entfernten Stimuli erfolgte allein durch deren Abbildungsgröße auf der Retina. Dass die Goldfische bei diesem Experiment nicht akkommodieren, wurde durch Infrarot-Photoretinoskopie gezeigt. Somit lässt sich Akkommodation für die Entfer-nungsbestimmung in diesen Versuchen ausschließen. Für diese Leistung und die Größenkonstanz ist vermutlich die Bewegungsparallaxe entscheidend.

The question, how the visual perception of spatial depth is possible with a two dimensional retinal image, is one of the fundamental problems in brain research. There is a high selection pressure for active moving animals to judge distances and sizes correctly. The purpose of this thesis was to find out how good goldfish are in discriminating objects only by distance and which information they may use. A setup with a homogenous white sur-rounding was designed to limit visual depth cues mainly to accommodation and less to motion parallax. Goldfish were trained by operant conditioning to choose one stimulus in a defined distance, while another equally sized stimulus was presented a far as possible from the first one. The distance between the stimuli was decreased until the goldfish could no longer tell them apart. The discrimination ability of the goldfish of two similar sized stimuli in…

Subjects/Keywords: Sehen, Entfernungswahrnehmung, Goldfisch, operante Kondtionierung; depth perception, distance estimation, vision, goldfish, operant conditioning; Life sciences

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Frech, B. (2009). Verhaltensphysiologische Analyse der visuellen Wahrnehmung räumlicher Tiefe beim Goldfisch. (Doctoral Dissertation). Johannes Gutenberg Universität Mainz. Retrieved from http://ubm.opus.hbz-nrw.de/volltexte/2009/2116/

Chicago Manual of Style (16^th Edition):

Frech, Birte. “Verhaltensphysiologische Analyse der visuellen Wahrnehmung räumlicher Tiefe beim Goldfisch.” 2009. Doctoral Dissertation, Johannes Gutenberg Universität Mainz. Accessed April 22, 2021. http://ubm.opus.hbz-nrw.de/volltexte/2009/2116/.

MLA Handbook (7^th Edition):

Frech, Birte. “Verhaltensphysiologische Analyse der visuellen Wahrnehmung räumlicher Tiefe beim Goldfisch.” 2009. Web. 22 Apr 2021.

Vancouver:

Frech B. Verhaltensphysiologische Analyse der visuellen Wahrnehmung räumlicher Tiefe beim Goldfisch. [Internet] [Doctoral dissertation]. Johannes Gutenberg Universität Mainz; 2009. [cited 2021 Apr 22]. Available from: http://ubm.opus.hbz-nrw.de/volltexte/2009/2116/.

Council of Science Editors:

Frech B. Verhaltensphysiologische Analyse der visuellen Wahrnehmung räumlicher Tiefe beim Goldfisch. [Doctoral Dissertation]. Johannes Gutenberg Universität Mainz; 2009. Available from: http://ubm.opus.hbz-nrw.de/volltexte/2009/2116/

University of California – Merced

25. Hu, Zhe. Camera Shake Removal From One Single Image.

Degree: Electrical Engineering and Computer Science, 2015, University of California – Merced

URL: http://www.escholarship.org/uc/item/9p46c1k2

► Image blur is one of the most fundamental and challenging problems in photography. It causes significant image degradation, especially in the low light conditions where… (more)

Subjects/Keywords: Computer science; Camera shake removal; depth estimation; good region; Light streaks; Non-uniform model; Prior

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Hu, Z. (2015). Camera Shake Removal From One Single Image. (Thesis). University of California – Merced. Retrieved from http://www.escholarship.org/uc/item/9p46c1k2

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Hu, Zhe. “Camera Shake Removal From One Single Image.” 2015. Thesis, University of California – Merced. Accessed April 22, 2021. http://www.escholarship.org/uc/item/9p46c1k2.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Hu, Zhe. “Camera Shake Removal From One Single Image.” 2015. Web. 22 Apr 2021.

Vancouver:

Hu Z. Camera Shake Removal From One Single Image. [Internet] [Thesis]. University of California – Merced; 2015. [cited 2021 Apr 22]. Available from: http://www.escholarship.org/uc/item/9p46c1k2.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Hu Z. Camera Shake Removal From One Single Image. [Thesis]. University of California – Merced; 2015. Available from: http://www.escholarship.org/uc/item/9p46c1k2

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

26. Nguyen, Hieu. 3D Shape, Deformation, Motion and Vibration Measurements using the Stereo-vision-based Techniques.

Degree: 2019, The Catholic University of America

URL: http://hdl.handle.net/1961/cuislandora:213668

►

Full-field 3D sensing techniques for shape, deformation, motion, and vibration measurements have emerged as an important tool for numerous applications in various fields. As technologies… (more)

▼

Full-field 3D sensing techniques for shape, deformation, motion, and vibration measurements have emerged as an important tool for numerous applications in various fields. As technologies evolve, there is a high demand to extend the capabilities of the 3D sensing to achieve fast-speed, high-accuracy, and broad-range performance. This dissertation aims to conduct imaging-based research on exploring algorithms and techniques to carry out the 3D shape, deformation, motion and vibration measurements with high accuracy and fast speed. Two stereo-vision-based 3D imaging techniques are investigated: fringe projection profilometry (FPP) and digital image correlation (DIC) techniques. They normally include three key steps: (1) camera calibration, (2) image matching and (3) coordinate determination. Previously, a high-accuracy camera calibration technique based on hyper-precise control-point detection has been developed. Therefore, this dissertation puts emphasis on exploring algorithms related to image matching and 3D coordinate determination as well as the design of the hardware setup. The research work comprises three main components: -Exploration of real-time, high-accuracy 3D imaging and shape measurement techniques using the FPP approach. By encoding three phase-shifted patterns into the red, green, and blue (RGB) channels of a color image and controlling a projector to project the RGB channels individually, the technique can conduct the 3D measurements in real time by synchronizing the projector and the camera. Meanwhile, the measurement accuracy is dramatically improved by introducing novel phase determination schemes.-Exploration of high-accuracy 3D shape, deformation, motion and vibration measurement techniques using the DIC approach. In this work, infrared patterns projected from the Kinect sensor are adopted to considerably facilitate the correlation analysis with enhanced accuracy. Moreover, a technique to acquire 3D digital images of human face without the use of active lighting and artificial patterns is proposed. A few advanced schemes, such as feature-matching-based initial guess, multiple subsets, iterative optimization algorithm, and reliability-guided computation path, are employed.-Incorporation of the deep convolution neural networks (CNNs) concepts into the 3D sensing technique. A single-shot 3D shape reconstruction technique integrating the FPP with the CNNs is proposed. Unlike other complex methods, the novel technique uses an end-to-end network to directly reconstruct a 3D image from its 2D counterpart.

Optics

Artificial intelligence

Mechanical engineering

3D Imaging, Convolutional Neural Networks, Deep learning, Depth estimation, Stereo Vision, Structured light illumination

Mechanical Engineering

Degree Awarded: Ph.D. Mechanical Engineering. The Catholic University of America

Advisors/Committee Members: The Catholic University of America (Degree granting institution), Wang, Zhaoyang (Thesis advisor), Abot, Jandro (Committee member), Nehmetallah, Georges (Committee member), Liu, Hang (Committee member), Nguyen, Charles (Committee member).

Subjects/Keywords: 3D Imaging; Convolutional Neural Networks; Deep learning; Depth estimation; Stereo Vision; Structured light illumination

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Nguyen, H. (2019). 3D Shape, Deformation, Motion and Vibration Measurements using the Stereo-vision-based Techniques. (Thesis). The Catholic University of America. Retrieved from http://hdl.handle.net/1961/cuislandora:213668

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Nguyen, Hieu. “3D Shape, Deformation, Motion and Vibration Measurements using the Stereo-vision-based Techniques.” 2019. Thesis, The Catholic University of America. Accessed April 22, 2021. http://hdl.handle.net/1961/cuislandora:213668.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Nguyen, Hieu. “3D Shape, Deformation, Motion and Vibration Measurements using the Stereo-vision-based Techniques.” 2019. Web. 22 Apr 2021.

Vancouver:

Nguyen H. 3D Shape, Deformation, Motion and Vibration Measurements using the Stereo-vision-based Techniques. [Internet] [Thesis]. The Catholic University of America; 2019. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/1961/cuislandora:213668.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Nguyen H. 3D Shape, Deformation, Motion and Vibration Measurements using the Stereo-vision-based Techniques. [Thesis]. The Catholic University of America; 2019. Available from: http://hdl.handle.net/1961/cuislandora:213668

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Brunel University

27. Alazawi, Eman. Holoscopic 3D image depth estimation and segmentation techniques.

Degree: PhD, 2015, Brunel University

URL: http://bura.brunel.ac.uk/handle/2438/10517 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.642452

► Today’s 3D imaging techniques offer significant benefits over conventional 2D imaging techniques. The presence of natural depth information in the scene affords the observer an… (more)

▼ Today’s 3D imaging techniques offer significant benefits over conventional 2D imaging techniques. The presence of natural depth information in the scene affords the observer an overall improved sense of reality and naturalness. A variety of systems attempting to reach this goal have been designed by many independent research groups, such as stereoscopic and auto-stereoscopic systems. Though the images displayed by such systems tend to cause eye strain, fatigue and headaches after prolonged viewing as users are required to focus on the screen plane/accommodation to converge their eyes to a point in space in a different plane/convergence. Holoscopy is a 3D technology that targets overcoming the above limitations of current 3D technology and was recently developed at Brunel University. This work is part W4.1 of the 3D VIVANT project that is funded by the EU under the ICT program and coordinated by Dr. Aman Aggoun at Brunel University, West London, UK. The objective of the work described in this thesis is to develop estimation and segmentation techniques that are capable of estimating precise 3D depth, and are applicable for holoscopic 3D imaging system. Particular emphasis is given to the task of automatic techniques i.e. favours algorithms with broad generalisation abilities, as no constraints are placed on the setting. Algorithms that provide invariance to most appearance based variation of objects in the scene (e.g. viewpoint changes, deformable objects, presence of noise and changes in lighting). Moreover, have the ability to estimate depth information from both types of holoscopic 3D images i.e. Unidirectional and Omni-directional which gives horizontal parallax and full parallax (vertical and horizontal), respectively. The main aim of this research is to develop 3D depth estimation and 3D image segmentation techniques with great precision. In particular, emphasis on automation of thresholding techniques and cues identifications for development of robust algorithms. A method for depth-through-disparity feature analysis has been built based on the existing correlation between the pixels at a one micro-lens pitch which has been exploited to extract the viewpoint images (VPIs). The corresponding displacement among the VPIs has been exploited to estimate the depth information map via setting and extracting reliable sets of local features. ii Feature-based-point and feature-based-edge are two novel automatic thresholding techniques for detecting and extracting features that have been used in this approach. These techniques offer a solution to the problem of setting and extracting reliable features automatically to improve the performance of the depth estimation related to the generalizations, speed and quality. Due to the resolution limitation of the extracted VPIs, obtaining an accurate 3D depth map is challenging. Therefore, sub-pixel shift and integration is a novel interpolation technique that has been used in this approach to generate super-resolution VPIs. By shift and integration of a set of up-sampled low…

Subjects/Keywords: 621.36; Holoscopic 3D image; Depth map estimation; Segmentation; Super resolution image; Subjective evaluation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Alazawi, E. (2015). Holoscopic 3D image depth estimation and segmentation techniques. (Doctoral Dissertation). Brunel University. Retrieved from http://bura.brunel.ac.uk/handle/2438/10517 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.642452

Chicago Manual of Style (16^th Edition):

Alazawi, Eman. “Holoscopic 3D image depth estimation and segmentation techniques.” 2015. Doctoral Dissertation, Brunel University. Accessed April 22, 2021. http://bura.brunel.ac.uk/handle/2438/10517 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.642452.

MLA Handbook (7^th Edition):

Alazawi, Eman. “Holoscopic 3D image depth estimation and segmentation techniques.” 2015. Web. 22 Apr 2021.

Vancouver:

Alazawi E. Holoscopic 3D image depth estimation and segmentation techniques. [Internet] [Doctoral dissertation]. Brunel University; 2015. [cited 2021 Apr 22]. Available from: http://bura.brunel.ac.uk/handle/2438/10517 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.642452.

Council of Science Editors:

Alazawi E. Holoscopic 3D image depth estimation and segmentation techniques. [Doctoral Dissertation]. Brunel University; 2015. Available from: http://bura.brunel.ac.uk/handle/2438/10517 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.642452

National University of Ireland – Galway

28. Javidnia, Hossein. Contributions to the measurement of depth in consumer imaging .

Degree: 2018, National University of Ireland – Galway

URL: http://hdl.handle.net/10379/7398

► This thesis aims to examine and investigate methods that could potentially utilize images captured by consumer cameras such as smartphones to estimate depth and generate… (more)

Subjects/Keywords: Depth estimation; Consumer imaging; 3D reconstruction; Electrical and Electronic Engineering; Engineering and Informatics

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Javidnia, H. (2018). Contributions to the measurement of depth in consumer imaging . (Thesis). National University of Ireland – Galway. Retrieved from http://hdl.handle.net/10379/7398

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Javidnia, Hossein. “Contributions to the measurement of depth in consumer imaging .” 2018. Thesis, National University of Ireland – Galway. Accessed April 22, 2021. http://hdl.handle.net/10379/7398.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Javidnia, Hossein. “Contributions to the measurement of depth in consumer imaging .” 2018. Web. 22 Apr 2021.

Vancouver:

Javidnia H. Contributions to the measurement of depth in consumer imaging . [Internet] [Thesis]. National University of Ireland – Galway; 2018. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/10379/7398.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Javidnia H. Contributions to the measurement of depth in consumer imaging . [Thesis]. National University of Ireland – Galway; 2018. Available from: http://hdl.handle.net/10379/7398

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Arizona

29. Salahieh, Basel. Computational Imaging For Miniature Cameras .

Degree: 2015, University of Arizona

URL: http://hdl.handle.net/10150/581305

► Miniature cameras play a key role in numerous imaging applications ranging from endoscopy and metrology inspection devices to smartphones and head-mount acquisition systems. However, due… (more)

▼ Miniature cameras play a key role in numerous imaging applications ranging from endoscopy and metrology inspection devices to smartphones and head-mount acquisition systems. However, due to the physical constraints, the imaging conditions, and the low quality of small optics, their imaging capabilities are limited in terms of the delivered resolution, the acquired depth of field, and the captured dynamic range. Computational imaging jointly addresses the imaging system and the reconstructing algorithms to bypass the traditional limits of optical systems and deliver better restorations for various applications. The scene is encoded into a set of efficient measurements which could then be computationally decoded to output a richer estimate of the scene as compared with the raw images captured by conventional imagers. In this dissertation, three task-based computational imaging techniques are developed to make low-quality miniature cameras capable of delivering realistic high-resolution reconstructions, providing full-focus imaging, and acquiring depth information for high dynamic range objects. For the superresolution task, a non-regularized direct superresolution algorithm is developed to achieve realistic restorations without being penalized by improper assumptions (e.g., optimizers, priors, and regularizers) made in the inverse problem. An adaptive frequency-based filtering scheme is introduced to upper bound the reconstruction errors while still producing more fine details as compared with previous methods under realistic imaging conditions. For the full-focus imaging task, a computational depth-based deconvolution technique is proposed to bring a scene captured by an ordinary fixed-focus camera to a full-focus based on a depth-variant point spread function prior. The ringing artifacts are suppressed on three levels: block tiling to eliminate boundary artifacts, adaptive reference maps to reduce ringing initiated by sharp edges, and block-wise deconvolution or depth-based masking to suppress artifacts initiated by neighboring depth-transition surfaces. Finally for the depth acquisition task, a multi-polarization fringe projection imaging technique is introduced to eliminate saturated points and enhance the fringe contrast by selecting the proper polarized channel measurements. The developed technique can be easily extended to include measurements captured under different exposure times to obtain more accurate shape rendering for very high dynamic range objects. Advisors/Committee Members: Liang, Rongguang (advisor), Rodriguez, Jeffrey J (advisor), Liang, Rongguang (committeemember), Rodriguez, Jeffrey J. (committeemember), Bilgin, Ali (committeemember), Milster, Thomas D. (committeemember).

Subjects/Keywords: Computational Imaging; Deconvolution; Depth Estimation; Image Reconstruction; Superresolution; Electrical & Computer Engineering; Cameras

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Salahieh, B. (2015). Computational Imaging For Miniature Cameras . (Doctoral Dissertation). University of Arizona. Retrieved from http://hdl.handle.net/10150/581305

Chicago Manual of Style (16^th Edition):

Salahieh, Basel. “Computational Imaging For Miniature Cameras .” 2015. Doctoral Dissertation, University of Arizona. Accessed April 22, 2021. http://hdl.handle.net/10150/581305.

MLA Handbook (7^th Edition):

Salahieh, Basel. “Computational Imaging For Miniature Cameras .” 2015. Web. 22 Apr 2021.

Vancouver:

Salahieh B. Computational Imaging For Miniature Cameras . [Internet] [Doctoral dissertation]. University of Arizona; 2015. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/10150/581305.

Council of Science Editors:

Salahieh B. Computational Imaging For Miniature Cameras . [Doctoral Dissertation]. University of Arizona; 2015. Available from: http://hdl.handle.net/10150/581305

University of Edinburgh

30. Horna Carranza, Luis Alberto. Specialised global methods for binocular and trinocular stereo matching.

Degree: PhD, 2017, University of Edinburgh

URL: http://hdl.handle.net/1842/29017

► The problem of estimating depth from two or more images is a fundamental problem in computer vision, which is commonly referred as to stereo matching.… (more)

Subjects/Keywords: depth estimation; stereo matching; binocular stereo matching algorithm; 3D; trinocular; trinocular algorithms; binocular algorithms

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Horna Carranza, L. A. (2017). Specialised global methods for binocular and trinocular stereo matching. (Doctoral Dissertation). University of Edinburgh. Retrieved from http://hdl.handle.net/1842/29017

Chicago Manual of Style (16^th Edition):

Horna Carranza, Luis Alberto. “Specialised global methods for binocular and trinocular stereo matching.” 2017. Doctoral Dissertation, University of Edinburgh. Accessed April 22, 2021. http://hdl.handle.net/1842/29017.

MLA Handbook (7^th Edition):

Horna Carranza, Luis Alberto. “Specialised global methods for binocular and trinocular stereo matching.” 2017. Web. 22 Apr 2021.

Vancouver:

Horna Carranza LA. Specialised global methods for binocular and trinocular stereo matching. [Internet] [Doctoral dissertation]. University of Edinburgh; 2017. [cited 2021 Apr 22]. Available from: http://hdl.handle.net/1842/29017.

Council of Science Editors:

Horna Carranza LA. Specialised global methods for binocular and trinocular stereo matching. [Doctoral Dissertation]. University of Edinburgh; 2017. Available from: http://hdl.handle.net/1842/29017

Open Access Theses and Dissertations