subject:(Image processing Digital techniques )

Oregon State University

1. Chuang, Chih-Lan Jasmine. Application of digital image correlation in material parameter estimation and vibration analysis of carbon fiber composite and aluminum plates.

Degree: MS, Mechanical Engineering, 2012, Oregon State University

URL: http://hdl.handle.net/1957/30170

► Identifying material parameters in composite plates is a necessary first step in a variety of structural applications. For example, understanding the material parameters of carbon… (more)

▼ Identifying material parameters in composite plates is a necessary first step in a variety of structural applications. For example, understanding the material parameters of carbon fiber composite is important in investigating sensor and actuator placement on micro-air-vehicle wings for control and wing morphing purposes. Knowing the material parameters can also help examine the health of composite structures and detect wear or defects. Traditional testing methods for finding material parameters such as stiffness and damping require multiple types of experiments such as tensile tests and shaker tests. These tests are not without complications. Methods such as tensile testing can be destructive to the test specimens while use of strain gages and accelerometers can be inappropriate due to the lightweight nature of the structures. The proposed inverse problem testing methods using digital image correlation via high speed cameras can potentially eliminate the disadvantages of traditional methods as well as determine the required material parameters including stiffness and damping by conducting only one type of experiment. These material parameters include stiffness and damping for both isotropic and orthotropic materials, and ply angle layup specifically for carbon fiber materials. A finite element model based on the Kirchoff-Love thin plate theory is used to produce theoretical data for comparison with experimental data collected using digital image correlation. Shaker experiments are also carried out using digital image correlation to investigate the modal frequencies as validation of the results of the inverse problem. We apply these techniques first to an aluminum plate for which material parameters are known to test the performance and efficiency of the method. We then apply the method to a composite plates to determine not only these parameters, but also the layup angle. The inverse problem successfully estimates the Young's modulus and damping for the aluminum material. In addition, the vibration analysis produces consistent resonance frequencies for the first two modes for both theoretical and experimental data. However, carbon fiber plates present challenges due to limitations of the Kirchoff-Love plate theory used as the underlining theoretical model for the finite element approximation used in the inverse problem, resulting in a persistent mismatch of resonance frequencies in experimental data. Advisors/Committee Members: Batten, Belinda (advisor), Bay, Brian (committee member).

Subjects/Keywords: Image processing – Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Chuang, C. J. (2012). Application of digital image correlation in material parameter estimation and vibration analysis of carbon fiber composite and aluminum plates. (Masters Thesis). Oregon State University. Retrieved from http://hdl.handle.net/1957/30170

Chicago Manual of Style (16^th Edition):

Chuang, Chih-Lan Jasmine. “Application of digital image correlation in material parameter estimation and vibration analysis of carbon fiber composite and aluminum plates.” 2012. Masters Thesis, Oregon State University. Accessed March 07, 2021. http://hdl.handle.net/1957/30170.

MLA Handbook (7^th Edition):

Chuang, Chih-Lan Jasmine. “Application of digital image correlation in material parameter estimation and vibration analysis of carbon fiber composite and aluminum plates.” 2012. Web. 07 Mar 2021.

Vancouver:

Chuang CJ. Application of digital image correlation in material parameter estimation and vibration analysis of carbon fiber composite and aluminum plates. [Internet] [Masters thesis]. Oregon State University; 2012. [cited 2021 Mar 07]. Available from: http://hdl.handle.net/1957/30170.

Council of Science Editors:

Chuang CJ. Application of digital image correlation in material parameter estimation and vibration analysis of carbon fiber composite and aluminum plates. [Masters Thesis]. Oregon State University; 2012. Available from: http://hdl.handle.net/1957/30170

University of Johannesburg

2. Coetzee, Willie. Removal of rain from images by means of digital filters and camera obscuration techniques.

Degree: 2014, University of Johannesburg

URL: http://hdl.handle.net/10210/11524

►

M. Ing. (Mechanical Engineering)

This research aims at identifying techniques which can be used to remove rain from a digitized rain distorted image. The research… (more)

Subjects/Keywords: Image processing - Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Coetzee, W. (2014). Removal of rain from images by means of digital filters and camera obscuration techniques. (Thesis). University of Johannesburg. Retrieved from http://hdl.handle.net/10210/11524

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):

Coetzee, Willie. “Removal of rain from images by means of digital filters and camera obscuration techniques.” 2014. Thesis, University of Johannesburg. Accessed March 07, 2021. http://hdl.handle.net/10210/11524.

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

MLA Handbook (7^th Edition):

Coetzee, Willie. “Removal of rain from images by means of digital filters and camera obscuration techniques.” 2014. Web. 07 Mar 2021.

Vancouver:

Coetzee W. Removal of rain from images by means of digital filters and camera obscuration techniques. [Internet] [Thesis]. University of Johannesburg; 2014. [cited 2021 Mar 07]. Available from: http://hdl.handle.net/10210/11524.

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

Council of Science Editors:

Coetzee W. Removal of rain from images by means of digital filters and camera obscuration techniques. [Thesis]. University of Johannesburg; 2014. Available from: http://hdl.handle.net/10210/11524

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

University of Johannesburg

3. Visser, Willem. HandsFree: a marker-free visual based input prototype for menu driven systems.

Degree: 2010, University of Johannesburg

URL: http://hdl.handle.net/10210/3056

►

M.Ing.

This dissertation proposes a marker-free visual based interface device to be used with menu driven systems. This system, called HandsFree, uses the Graphics Processing… (more)

Subjects/Keywords: Image processing digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Visser, W. (2010). HandsFree: a marker-free visual based input prototype for menu driven systems. (Thesis). University of Johannesburg. Retrieved from http://hdl.handle.net/10210/3056

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):

Visser, Willem. “HandsFree: a marker-free visual based input prototype for menu driven systems.” 2010. Thesis, University of Johannesburg. Accessed March 07, 2021. http://hdl.handle.net/10210/3056.

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

MLA Handbook (7^th Edition):

Visser, Willem. “HandsFree: a marker-free visual based input prototype for menu driven systems.” 2010. Web. 07 Mar 2021.

Vancouver:

Visser W. HandsFree: a marker-free visual based input prototype for menu driven systems. [Internet] [Thesis]. University of Johannesburg; 2010. [cited 2021 Mar 07]. Available from: http://hdl.handle.net/10210/3056.

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

Council of Science Editors:

Visser W. HandsFree: a marker-free visual based input prototype for menu driven systems. [Thesis]. University of Johannesburg; 2010. Available from: http://hdl.handle.net/10210/3056

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

4. Yeo, Si Yong. Implicit deformable models for biomedical image segmentation.

Degree: PhD, 2011, Swansea University

URL: https://cronfa.swan.ac.uk/Record/cronfa42416 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.678505

► In this thesis, new methods for the efficient segmentation of images are presented. The proposed methods are based on the deformable model approach, and can… (more)

▼ In this thesis, new methods for the efficient segmentation of images are presented. The proposed methods are based on the deformable model approach, and can be used efficiently in the segmentation of complex geometries from various imaging modalities. A novel deformable model that is based on a geometrically induced external force field which can be conveniently generalized to arbitrary dimensions is presented. This external force field is based on hypothesized interactions between the relative geometries of the deformable model and the object boundary characterized by image gradient. The evolution of the deformable model is solved using the level set method so that topological changes are handled automatically. The relative geometrical configurations between the deformable model and the object boundaries contributes to a dynamic vector force field that changes accordingly as the deformable model evolves. The geometrically induced dynamic interaction force has been shown to greatly improve the deformable model performance in acquiring complex geometries and highly concave boundaries, and give the deformable model a high invariance in initialization configurations. The voxel interactions across the whole image domain provides a global view of the object boundary representation, giving the external force a long attraction range. The bidirectionality of the external force held allows the new deformable model to deal with arbitrary cross-boundary initializations, and facilitates the handling of weak edges and broken boundaries. In addition, it is shown that by enhancing the geometrical interaction field with a nonlocal edge-preserving algorithm, the new deformable model can effectively overcome image noise. A comparative study on the segmentation of various geometries with different topologies from both synthetic and real images is provided, and the proposed method is shown to achieve significant improvements against several existing techniques. A robust framework for the segmentation of vascular geometries is described. In particular, the framework consists of image denoising, optimal object edge representation, and segmentation using implicit deformable model. The image denoising is based on vessel enhancing diffusion which can be used to smooth out image noise and enhance the vessel structures. The image object boundaries are derived using an edge detection technique which can produce object edges of single pixel width. The image edge information is then used to derive the geometric interaction field for optimal object edge representation. The vascular geometries are segmented using an implict deformable model. A region constraint is added to the deformable model which allows it to easily get around calcified regions and propagate across the vessels to segment the structures efficiently. The presented framework is ai)plied in the accurate segmentation of carotid geometries from medical images. A new segmentation model with statistical shape prior using a variational approach is also presented in this thesis. The…

Subjects/Keywords: 621.36; Image processing – Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Yeo, S. Y. (2011). Implicit deformable models for biomedical image segmentation. (Doctoral Dissertation). Swansea University. Retrieved from https://cronfa.swan.ac.uk/Record/cronfa42416 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.678505

Chicago Manual of Style (16^th Edition):

Yeo, Si Yong. “Implicit deformable models for biomedical image segmentation.” 2011. Doctoral Dissertation, Swansea University. Accessed March 07, 2021. https://cronfa.swan.ac.uk/Record/cronfa42416 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.678505.

MLA Handbook (7^th Edition):

Yeo, Si Yong. “Implicit deformable models for biomedical image segmentation.” 2011. Web. 07 Mar 2021.

Vancouver:

Yeo SY. Implicit deformable models for biomedical image segmentation. [Internet] [Doctoral dissertation]. Swansea University; 2011. [cited 2021 Mar 07]. Available from: https://cronfa.swan.ac.uk/Record/cronfa42416 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.678505.

Council of Science Editors:

Yeo SY. Implicit deformable models for biomedical image segmentation. [Doctoral Dissertation]. Swansea University; 2011. Available from: https://cronfa.swan.ac.uk/Record/cronfa42416 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.678505

Rutgers University

5. Ren, Baozhang. Development of an efficient RGB-D annotation tool for video sequence.

Degree: MS, Computer Science, 2020, Rutgers University

URL: https://rucore.libraries.rutgers.edu/rutgers-lib/62750/

► With the prevalence of neural networks and deep learning models, more data is required to expand the domain as well as to improve the accuracy… (more)

Subjects/Keywords: RGBD; Image processing – Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Ren, B. (2020). Development of an efficient RGB-D annotation tool for video sequence. (Masters Thesis). Rutgers University. Retrieved from https://rucore.libraries.rutgers.edu/rutgers-lib/62750/

Chicago Manual of Style (16^th Edition):

Ren, Baozhang. “Development of an efficient RGB-D annotation tool for video sequence.” 2020. Masters Thesis, Rutgers University. Accessed March 07, 2021. https://rucore.libraries.rutgers.edu/rutgers-lib/62750/.

MLA Handbook (7^th Edition):

Ren, Baozhang. “Development of an efficient RGB-D annotation tool for video sequence.” 2020. Web. 07 Mar 2021.

Vancouver:

Ren B. Development of an efficient RGB-D annotation tool for video sequence. [Internet] [Masters thesis]. Rutgers University; 2020. [cited 2021 Mar 07]. Available from: https://rucore.libraries.rutgers.edu/rutgers-lib/62750/.

Council of Science Editors:

Ren B. Development of an efficient RGB-D annotation tool for video sequence. [Masters Thesis]. Rutgers University; 2020. Available from: https://rucore.libraries.rutgers.edu/rutgers-lib/62750/

Hong Kong University of Science and Technology

6. Li, Sijin. Compression of similar images.

Degree: 2012, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-7776 ; https://doi.org/10.14711/thesis-b1197973 ; http://repository.ust.hk/ir/bitstream/1783.1-7776/1/th_redirect.html

► With wide spread availability of digital cameras, smart phones and other imaging devices, large amount of similar images are routinely created. Such images need to… (more)

▼ With wide spread availability of digital cameras, smart phones and other imaging devices, large amount of similar images are routinely created. Such images need to be compressed for storage and communication purposes. Instead of compressing each image individually, it is possible to achieve higher compression efficiency by compressing the whole set of similar images together. Any such similar image compression scheme needs to support random access as users may want to access the images in any random order. To reduce the inter-image redundancy, one key problem is the construction of predictors to minimize the inter-image redundancy. The existing methods are not effective in their predictors and intra prediction design. In this thesis, we propose a compression method for medical images based on low frequency features of the images. We observe that the pairwise similarities among the similar images are not uniform among the images. Some pairs have similarity for a relatively small frequency band only. Some have similarity for wider frequency bands. Motivated by this, we propose a set of multi-level low frequency templates as predictors for each image. The resulting difference images tend to have lower entropy and require fewer bits to encode than the single-level low frequency template method. Results suggest that up to 30% of gain is possible. The performance gain is more obvious in larger sets of similar images with higher dissimilarity. We also propose an effective compression scheme for photo albums based on global/local motion estimation and compensation, and intra prediction. We observe that many photos in photo albums are very similar in the sense that basically they capture the same scene with different camera zoom factors, different rotational positions and different translational positions. The global motion estimation and compensation can account for such camera motion among similar photos. On the other hand, the local motion estimation and compensation can account for object motions. Experiments suggest that this algorithm can achieve considerable performance gain. Index Terms— Image compression, set redundancy compression, photo album compression

Subjects/Keywords: Image compression ; Image processing – Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Li, S. (2012). Compression of similar images. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-7776 ; https://doi.org/10.14711/thesis-b1197973 ; http://repository.ust.hk/ir/bitstream/1783.1-7776/1/th_redirect.html

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):

Li, Sijin. “Compression of similar images.” 2012. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-7776 ; https://doi.org/10.14711/thesis-b1197973 ; http://repository.ust.hk/ir/bitstream/1783.1-7776/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Li, Sijin. “Compression of similar images.” 2012. Web. 07 Mar 2021.

Vancouver:

Li S. Compression of similar images. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2012. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-7776 ; https://doi.org/10.14711/thesis-b1197973 ; http://repository.ust.hk/ir/bitstream/1783.1-7776/1/th_redirect.html.

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

Council of Science Editors:

Li S. Compression of similar images. [Thesis]. Hong Kong University of Science and Technology; 2012. Available from: http://repository.ust.hk/ir/Record/1783.1-7776 ; https://doi.org/10.14711/thesis-b1197973 ; http://repository.ust.hk/ir/bitstream/1783.1-7776/1/th_redirect.html

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

Hong Kong University of Science and Technology

7. Zou, Ruobing. Digital photo album compression and HEVC related issues.

Degree: 2013, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-7872 ; https://doi.org/10.14711/thesis-b1214734 ; http://repository.ust.hk/ir/bitstream/1783.1-7872/1/th_redirect.html

► In recent years, the advance in computer, IC, internet, cloud, and multimedia technologies have led to widespread usage of digital photos and videos in our… (more)

▼ In recent years, the advance in computer, IC, internet, cloud, and multimedia technologies have led to widespread usage of digital photos and videos in our everyday multimedia-enabled lives. A consumer can easily have many photo albums each of which contain many JPEG images taken in the same occasion. Typically many photos taken in the same occasion are similar, with similar people and background. With explosive growth of photo albums in the consumers personal computer and in the cloud (such as facebook, twitter, Google, Renren, etc), the cost to store and transmit such digital images can be very significant. Thus it is important to compress these images efficiently. In this thesis, we propose some novel effective photo album compression algorithms to achieve higher compression efficiency than existing methods. Observing that many images in albums are similar, we assume that similar images can be clustered and identified and we develop efficient ways to compress each set of similar JPEG images using video coding techniques. Our approach is to arrange all the similar images into some kind tree structure with many roots and branches and then apply video coding technique along each branch. To maximize the inter-frame correlation between adjacent photos along the branches in a tree, we consider both the minimum spanning tree (MST) and the spanning forest to achieve minimum inter-frame prediction cost. As an unconstrained tree can be very deep which can result in very long delay during random access, we consider trees with limited depth to achieve good random access performance. Taking advantage of the latest High Efficiency Video Coding (HEVC) standard, we consider several possible HEVC frame configuration in search of the best. Our methods can support common photo albums operations such as addition of new images, deletion of useless images and modification of existing images. Experiments suggest that the proposed methods can achieve signficant gain in coding efficiency compared with the common JPEG format. Apart from the above research, this thesis also contains an improvement to HEVC. In the state-of-art video coding standard HEVC, temporal motion vector (MV) predictor is adopted in order to improve coding efficiency. However, motion vector information in reference frames, which is used by temporal MV predictor, takes large amount of bits in memory storage. Therefore motion data needs to be compressed before storing into buffer. Accordingly we propose an adaptive motion data storage reduction method. First, it divides the current 16x16 block in the reference frame into four partitions. One MV is sampled from each partition and all sampled MVs form a MV candidate set. Then it will check if one or two MVs should be stored into the MV buffer by checking the maximum distance between any two of the MVs in the candidate set. If the maximum distance is greater than a certain threshold, the motion data of the two MVs that have maximum distance are put into memory; otherwise the motion data of the upper left block is stored.…

Subjects/Keywords: Image compression ; Image processing ; Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Zou, R. (2013). Digital photo album compression and HEVC related issues. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-7872 ; https://doi.org/10.14711/thesis-b1214734 ; http://repository.ust.hk/ir/bitstream/1783.1-7872/1/th_redirect.html

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):

Zou, Ruobing. “Digital photo album compression and HEVC related issues.” 2013. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-7872 ; https://doi.org/10.14711/thesis-b1214734 ; http://repository.ust.hk/ir/bitstream/1783.1-7872/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Zou, Ruobing. “Digital photo album compression and HEVC related issues.” 2013. Web. 07 Mar 2021.

Vancouver:

Zou R. Digital photo album compression and HEVC related issues. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2013. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-7872 ; https://doi.org/10.14711/thesis-b1214734 ; http://repository.ust.hk/ir/bitstream/1783.1-7872/1/th_redirect.html.

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

Council of Science Editors:

Zou R. Digital photo album compression and HEVC related issues. [Thesis]. Hong Kong University of Science and Technology; 2013. Available from: http://repository.ust.hk/ir/Record/1783.1-7872 ; https://doi.org/10.14711/thesis-b1214734 ; http://repository.ust.hk/ir/bitstream/1783.1-7872/1/th_redirect.html

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

Hong Kong University of Science and Technology

8. Pang, Jiahao. Graph-based image restoration and subpixel-based image scaling : analysis in the continuous domain.

Degree: 2016, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-87531 ; https://doi.org/10.14711/thesis-b1731778 ; http://repository.ust.hk/ir/bitstream/1783.1-87531/1/th_redirect.html

► To process discrete digital images, a straightforward approach is to view them as arrays of numbers and then directly operate on the arrays. An alternative… (more)

▼ To process discrete digital images, a straightforward approach is to view them as arrays of numbers and then directly operate on the arrays. An alternative paradigm, however, is to regard them as samples from continuous signals. Hence, we can apply a continuous model to analyze and resolve discrete image processing problems. By virtue of this continuous-domain paradigm, more mathematical tools become available and formal continuous analysis can be performed, providing profound insights into the problem being considered. Moreover, for problems involving entities that are inherently continuous, it is more accurate to do analysis in the continuous domain. In this thesis, we focus on two image processing problems: graph-based image restoration and subpixel-based image scaling. Unlike existing works applying the continuous-domain paradigm, it is non-trivial to analyze these two problems in the continuous domain. However, we manage to do so and answer/resolve several fundamental aspects of the two problems. We first consider the problem of image restoration with graph Laplacian regularization. A graph Laplacian regularizer is a recent, popular prior assuming the target pixel patch to be smooth with respect to an appropriately chosen graph. However, the mechanisms and implications of imposing the graph Laplacian regularizer on the original inverse problem are not well understood. In this work, we interpret neighborhood graphs of pixel patches as discrete counterparts of Riemannian manifolds and perform analysis in the continuous domain, bringing novel understandings to several key problems of graph Laplacian regularization. Specifically, we show the convergence of the graph Laplacian regularizer to a continuous-domain functional and derive the optimal graph Laplacian regularizer for the problem of image denoising. Then with the notion of anisotropic diffusion, we explain the behavior of graph Laplacian regularization during iterations, e.g., its tendency to promote piecewise smooth signals under certain settings. To verify the analysis, an iterative image denoising algorithm is developed. Experimental results show that our algorithm performs competitively with state-of-the-art denoising methods for natural images, and outperforms them significantly for piecewise smooth images. In the second problem, we aim at re-scaling a given image for a color display panel by controlling its subpixels individually, so as to improve the luminance resolution of the displayed image. However, improved luminance resolution brings chrominance distortion, making it crucial to suppress color error while maintaining sharpness. Moreover, it is difficult to develop a scheme that is applicable for various subpixel arrangements and for arbitrary scaling factors. By taking into account the low-pass nature of the human visual system (HVS), we address the aforementioned issues with a generalized continuous-domain analysis model. Our developed continuous-domain algorithm is accurate. The error of the resulting images is only introduced by the discrete…

Subjects/Keywords: Image processing ; Digital techniques ; Image reconstruction

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Pang, J. (2016). Graph-based image restoration and subpixel-based image scaling : analysis in the continuous domain. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-87531 ; https://doi.org/10.14711/thesis-b1731778 ; http://repository.ust.hk/ir/bitstream/1783.1-87531/1/th_redirect.html

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):

Pang, Jiahao. “Graph-based image restoration and subpixel-based image scaling : analysis in the continuous domain.” 2016. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-87531 ; https://doi.org/10.14711/thesis-b1731778 ; http://repository.ust.hk/ir/bitstream/1783.1-87531/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Pang, Jiahao. “Graph-based image restoration and subpixel-based image scaling : analysis in the continuous domain.” 2016. Web. 07 Mar 2021.

Vancouver:

Pang J. Graph-based image restoration and subpixel-based image scaling : analysis in the continuous domain. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2016. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-87531 ; https://doi.org/10.14711/thesis-b1731778 ; http://repository.ust.hk/ir/bitstream/1783.1-87531/1/th_redirect.html.

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

Council of Science Editors:

Pang J. Graph-based image restoration and subpixel-based image scaling : analysis in the continuous domain. [Thesis]. Hong Kong University of Science and Technology; 2016. Available from: http://repository.ust.hk/ir/Record/1783.1-87531 ; https://doi.org/10.14711/thesis-b1731778 ; http://repository.ust.hk/ir/bitstream/1783.1-87531/1/th_redirect.html

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

Ryerson University

9. Farzam, Masoud. Hyperspectral image analysis using a simultaneous denoising and intrinsic order selection (DIOS) approach.

Degree: 2011, Ryerson University

URL: https://digital.library.ryerson.ca/islandora/object/RULA%3A1212

► Recent hyperspectral applications demand for higher accuracy and speed. This thesis develops a hyperspectral application analysis solution to address challenges in the different steps of… (more)

▼ Recent hyperspectral applications demand for higher accuracy and speed. This thesis develops a hyperspectral application analysis solution to address challenges in the different steps of denoising, order selection and unmixing of hyperspectral application data. Currently, all these steps process the data in cascade to achieve the optimum results. While in existing approaches the desired criterion is different in these steps, the proposed simultaneous Denoising and Intrinsic Order Selection (DIOS) method unifies these criteria. This property not only makes more sense for the desired optimization problem, but also leads to a faster processing algorithm. Consequently, DIOS avoids possible error propagation from the denoising stage to the dimension estimation stage, leading to more accurate results. The proposed method is based on minimizing the estimated Mean Square Error (MSE). The success rate of existing dimension estimation methods declines with the increase of image dimension and the decrease of Signal-to-Noise Ratio (SNR).The most competitive method fails to detect the correct dimension in 30% of cases around 2dB. However, in simulation results DIOS is shown to be successful with a failure rate of about 5%. The proposed unmixing method, based on a simple least square estimation, improves the speed performance least 10 times for an average-sized data cube of 2MB. Compared to some well known existing approaches, the unmixing method improves the estimated MSE up to 60% for SNR<10dB. A new whitening process for hyperspectral applications with coloured noise is also proposed. Since the proposed method avoids the inversion of large matrices, computational complexity is substantially decreased. In the presence of coloured noise, simulation results show that the proposed whitening method lowers the MSE of unmixing and outperforms the existing whitening methods particularly when the noise correction factors increase. Advisors/Committee Members: Beheshti, Soosan (Thesis advisor), Ryerson University (Degree grantor).

Subjects/Keywords: Electronic noise – Prevention.; Signal processing – Digital techniques; Image processing – Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Farzam, M. (2011). Hyperspectral image analysis using a simultaneous denoising and intrinsic order selection (DIOS) approach. (Thesis). Ryerson University. Retrieved from https://digital.library.ryerson.ca/islandora/object/RULA%3A1212

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):

Farzam, Masoud. “Hyperspectral image analysis using a simultaneous denoising and intrinsic order selection (DIOS) approach.” 2011. Thesis, Ryerson University. Accessed March 07, 2021. https://digital.library.ryerson.ca/islandora/object/RULA%3A1212.

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

MLA Handbook (7^th Edition):

Farzam, Masoud. “Hyperspectral image analysis using a simultaneous denoising and intrinsic order selection (DIOS) approach.” 2011. Web. 07 Mar 2021.

Vancouver:

Farzam M. Hyperspectral image analysis using a simultaneous denoising and intrinsic order selection (DIOS) approach. [Internet] [Thesis]. Ryerson University; 2011. [cited 2021 Mar 07]. Available from: https://digital.library.ryerson.ca/islandora/object/RULA%3A1212.

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

Council of Science Editors:

Farzam M. Hyperspectral image analysis using a simultaneous denoising and intrinsic order selection (DIOS) approach. [Thesis]. Ryerson University; 2011. Available from: https://digital.library.ryerson.ca/islandora/object/RULA%3A1212

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

Ryerson University

10. Ahmad, Zeeshan. Comparative analysis of different image denoising methods in spatial and transform domain.

Degree: 2017, Ryerson University

URL: https://digital.library.ryerson.ca/islandora/object/RULA%3A6540

► Digital Images are the best source for humans to see, visualize, think, extract information and make conclusions. However during the acquisition of images, noise superimposes… (more)

Subjects/Keywords: Electronic noise – Prevention; Signal processing – Digital techniques; Image processing – Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Ahmad, Z. (2017). Comparative analysis of different image denoising methods in spatial and transform domain. (Thesis). Ryerson University. Retrieved from https://digital.library.ryerson.ca/islandora/object/RULA%3A6540

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):

Ahmad, Zeeshan. “Comparative analysis of different image denoising methods in spatial and transform domain.” 2017. Thesis, Ryerson University. Accessed March 07, 2021. https://digital.library.ryerson.ca/islandora/object/RULA%3A6540.

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

MLA Handbook (7^th Edition):

Ahmad, Zeeshan. “Comparative analysis of different image denoising methods in spatial and transform domain.” 2017. Web. 07 Mar 2021.

Vancouver:

Ahmad Z. Comparative analysis of different image denoising methods in spatial and transform domain. [Internet] [Thesis]. Ryerson University; 2017. [cited 2021 Mar 07]. Available from: https://digital.library.ryerson.ca/islandora/object/RULA%3A6540.

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

Council of Science Editors:

Ahmad Z. Comparative analysis of different image denoising methods in spatial and transform domain. [Thesis]. Ryerson University; 2017. Available from: https://digital.library.ryerson.ca/islandora/object/RULA%3A6540

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

Ryerson University

11. Vo, Luan. Multifactor Systematic Risk Analysis Based on Time-varying Signal Processing Models.

Degree: 2012, Ryerson University

URL: https://digital.library.ryerson.ca/islandora/object/RULA%3A2178

► This thesis applies the time-varying signal processing models to track the multifactor systematic risk in the Fama-French model. The mean reverting, random walk and random… (more)

Subjects/Keywords: Image processing – Digital techniques; Optical pattern recognition

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Vo, L. (2012). Multifactor Systematic Risk Analysis Based on Time-varying Signal Processing Models. (Thesis). Ryerson University. Retrieved from https://digital.library.ryerson.ca/islandora/object/RULA%3A2178

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):

Vo, Luan. “Multifactor Systematic Risk Analysis Based on Time-varying Signal Processing Models.” 2012. Thesis, Ryerson University. Accessed March 07, 2021. https://digital.library.ryerson.ca/islandora/object/RULA%3A2178.

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

MLA Handbook (7^th Edition):

Vo, Luan. “Multifactor Systematic Risk Analysis Based on Time-varying Signal Processing Models.” 2012. Web. 07 Mar 2021.

Vancouver:

Vo L. Multifactor Systematic Risk Analysis Based on Time-varying Signal Processing Models. [Internet] [Thesis]. Ryerson University; 2012. [cited 2021 Mar 07]. Available from: https://digital.library.ryerson.ca/islandora/object/RULA%3A2178.

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

Council of Science Editors:

Vo L. Multifactor Systematic Risk Analysis Based on Time-varying Signal Processing Models. [Thesis]. Ryerson University; 2012. Available from: https://digital.library.ryerson.ca/islandora/object/RULA%3A2178

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

University of California – Merced

12. Swenson, Daniel. Intensity-constrained total variation regularization for image denoising and deblurring.

Degree: Applied Mathematics, 2011, University of California – Merced

URL: http://www.escholarship.org/uc/item/9zd4p95b

► Many problems in digital image processing are problems in digital image restoration. Our goal in this technical report is to examine what benefits are incurred… (more)

Subjects/Keywords: Computer Engineering. Digital techniques.; Image processing

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Swenson, D. (2011). Intensity-constrained total variation regularization for image denoising and deblurring. (Thesis). University of California – Merced. Retrieved from http://www.escholarship.org/uc/item/9zd4p95b

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):

Swenson, Daniel. “Intensity-constrained total variation regularization for image denoising and deblurring.” 2011. Thesis, University of California – Merced. Accessed March 07, 2021. http://www.escholarship.org/uc/item/9zd4p95b.

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

MLA Handbook (7^th Edition):

Swenson, Daniel. “Intensity-constrained total variation regularization for image denoising and deblurring.” 2011. Web. 07 Mar 2021.

Vancouver:

Swenson D. Intensity-constrained total variation regularization for image denoising and deblurring. [Internet] [Thesis]. University of California – Merced; 2011. [cited 2021 Mar 07]. Available from: http://www.escholarship.org/uc/item/9zd4p95b.

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

Council of Science Editors:

Swenson D. Intensity-constrained total variation regularization for image denoising and deblurring. [Thesis]. University of California – Merced; 2011. Available from: http://www.escholarship.org/uc/item/9zd4p95b

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

University of Delaware

13. Kocamaz, Mehmet Kemal. Low dimensional vs point-wise complex object detection, refinement and tracking.

Degree: PhD, University of Delaware, Department of Computer and Information Sciences, 2014, University of Delaware

URL: http://udspace.udel.edu/handle/19716/13392

► In this dissertation, I focus on algorithms to detect, refine, and track complex visual objects, as determined by their shape, appearance, or range of motion.… (more)

▼ In this dissertation, I focus on algorithms to detect, refine, and track complex visual objects, as determined by their shape, appearance, or range of motion. Two different classes of representations, namely low-dimensional and point-wise (non-parametric), are explored, compared, and analyzed by combining multiple features from both imaging and depth sensors. Such perception modules may provide crucial decision-making and planning information for intelligent systems, and we show links to several robotic application areas. On one side, a multimodal human detection algorithm which utilizes multiple sensor data sources is detailed. The human is represented in a low-dimensional space, and a ladar-camera architecture is constructed which with visual and geometric cues improves on the detection rate and speed of conventional human classifiers. Unlike existing approaches, the proposed human classifier does not make any restrictive assumptions on the range scan positions, and thus is applicable to a wide range of real-life detection tasks. On another side, a modified graph cut-based method is proposed to refine complex objects – e.g. human hands, hiking trails for navigation, and household objects – from a rough estimate of the object pose given by a low-dimensional shape detector or tracker. The standard graph cut method is modified to incorporate color and shape distance terms, adaptively weighting them at run time to favor the most informative cue in different visual conditions. Also, this method is extended for point-wise tracking of the objects through iterative refinement without estimation of the object displacement over time. Moreover, a novel algorithm which combines low- and high-level observations in a graph cut framework is developed for the purpose of refining low-dimensional representations of the human shape provided by some human detection or tracking methods. A multi-layer graph cut framework is introduced to combine low-level observations such as color and depth with high-level cues including the estimated ground plane and point-wise shape confidence scores given by a classifier. Lastly, a point-wise tracking algorithm which fuses multiple cues obtained from depth and color cameras is developed. It employs a motion estimation technique in which displacements are calculated from the 3-D locations of image keypoints matched between frames. Color and point-wise shape cues are combined in the same feature vector to allow adaptive weighting in different parts of the scene. This tracker is generic in that it does not make any assumptions or restrictions about the shape of the object, and experiments demonstrate better dense point-wise tracking performance than comparable algorithms over large viewpoint changes and object deformations. Advisors/Committee Members: Rasmussen, Christopher.

Subjects/Keywords: Imaging systems.; Image processing – Digital techniques.; Algorithms.

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Kocamaz, M. K. (2014). Low dimensional vs point-wise complex object detection, refinement and tracking. (Doctoral Dissertation). University of Delaware. Retrieved from http://udspace.udel.edu/handle/19716/13392

Chicago Manual of Style (16^th Edition):

Kocamaz, Mehmet Kemal. “Low dimensional vs point-wise complex object detection, refinement and tracking.” 2014. Doctoral Dissertation, University of Delaware. Accessed March 07, 2021. http://udspace.udel.edu/handle/19716/13392.

MLA Handbook (7^th Edition):

Kocamaz, Mehmet Kemal. “Low dimensional vs point-wise complex object detection, refinement and tracking.” 2014. Web. 07 Mar 2021.

Vancouver:

Kocamaz MK. Low dimensional vs point-wise complex object detection, refinement and tracking. [Internet] [Doctoral dissertation]. University of Delaware; 2014. [cited 2021 Mar 07]. Available from: http://udspace.udel.edu/handle/19716/13392.

Council of Science Editors:

Kocamaz MK. Low dimensional vs point-wise complex object detection, refinement and tracking. [Doctoral Dissertation]. University of Delaware; 2014. Available from: http://udspace.udel.edu/handle/19716/13392

Hong Kong University of Science and Technology

14. Yu, Zhiding. Graph embedding and arbitrarily shaped clustering for unsupervised image segmentation.

Degree: 2012, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-7770 ; https://doi.org/10.14711/thesis-b1197947 ; http://repository.ust.hk/ir/bitstream/1783.1-7770/1/th_redirect.html

► Image segmentation refers to the process of grouping pixels into spatially continuous regions based on certain similarity measure. One could ﬁnd its considerable applications in… (more)

▼ Image segmentation refers to the process of grouping pixels into spatially continuous regions based on certain similarity measure. One could ﬁnd its considerable applications in computer vision since it plays a key role in bridging low level information to high level semantic information. Segmentation remains one of the fundamental computer vision problems. Depending on whether there is human interaction, image segmentation can be divided into interactive and non-interactive ones. Based on the learning mode, image segmentation can be classiﬁed into supervised and unsupervised ones. In this thesis, we address the problem of non-interactive, unsupervised image segmentation, aiming at grouping perceptually similar pixels or superpixels into regions. It is expected that segmentations can serve as intermediate input for many high level scene understanding tasks, and that better segmentation results potentially lead to more accurate interpretation of objects and scenes. However, the problem remains challenging in the sense that it is very difﬁcult to model and design methods with segmentation performance that matches human level accuracy without any human interaction or strong prior - constraints that are often rare or even unavailable under real circumstances. In addition, ﬁnding a good image partitioning often results in the searching in a very complex or high dimensional solution space. So computational complexity becomes another key issue considering the real implementation of image segmentation algorithms. Regarding these challenges, this research proposes novel models that improve the state of the art unsupervised segmentation performance within the scope of acceptable computational cost, where segmentation performance is subjectively evaluated. The purpose is to generate image partitioning results that subjectively suffer less from both oversegmentation and overmerging, both of which can seriously degrade the performance of subsequent applications. Our research effort mainly focuses on graph theory and mode seeking, on top of which better boundary estimation and clustering models are proposed for image segmentation. We believe graphs often carry important structural information. And we want to utilize this information to guide data clustering and image segmentation. The segmentation accuracy depends largely on both the clustering performance and the designed feature. For clustering, we propose a graph-based contour ﬁnding method and minimum spanning tree (MST) embedded mode seeking. An MST is a connected graph that preserves intrinsic compact structures of a data set. It is able to ﬁnd manifold-like structures or elongated clusters since it shares common features with k-nearest neighbor (k-NN) graph - a graph that has been widely used in ﬁnding manifold structures. Thus the MST embedded mode seeking shows larger ﬂexibility and tolerance on cluster shapes. On the image domain, MST serves as a good spatial smoothness constraint in image domain. The introduction of MST signiﬁcantly helps to boost the performance of…

Subjects/Keywords: Image processing – Digital techniques ; Computer graphics

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Yu, Z. (2012). Graph embedding and arbitrarily shaped clustering for unsupervised image segmentation. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-7770 ; https://doi.org/10.14711/thesis-b1197947 ; http://repository.ust.hk/ir/bitstream/1783.1-7770/1/th_redirect.html

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):

Yu, Zhiding. “Graph embedding and arbitrarily shaped clustering for unsupervised image segmentation.” 2012. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-7770 ; https://doi.org/10.14711/thesis-b1197947 ; http://repository.ust.hk/ir/bitstream/1783.1-7770/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Yu, Zhiding. “Graph embedding and arbitrarily shaped clustering for unsupervised image segmentation.” 2012. Web. 07 Mar 2021.

Vancouver:

Yu Z. Graph embedding and arbitrarily shaped clustering for unsupervised image segmentation. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2012. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-7770 ; https://doi.org/10.14711/thesis-b1197947 ; http://repository.ust.hk/ir/bitstream/1783.1-7770/1/th_redirect.html.

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

Council of Science Editors:

Yu Z. Graph embedding and arbitrarily shaped clustering for unsupervised image segmentation. [Thesis]. Hong Kong University of Science and Technology; 2012. Available from: http://repository.ust.hk/ir/Record/1783.1-7770 ; https://doi.org/10.14711/thesis-b1197947 ; http://repository.ust.hk/ir/bitstream/1783.1-7770/1/th_redirect.html

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

Hong Kong University of Science and Technology

15. Zhu, Siyu CSE. Accurate, scalable and parallel structure from motion.

Degree: 2017, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-88943 ; https://doi.org/10.14711/thesis-991012532269103412 ; http://repository.ust.hk/ir/bitstream/1783.1-88943/1/th_redirect.html

► Structure from motion is a photogrammetric technique for estimating 3D structures from 2D images and large-scale Structure from Motion is still challenging in three aspects,… (more)

▼ Structure from motion is a photogrammetric technique for estimating 3D structures from 2D images and large-scale Structure from Motion is still challenging in three aspects, namely accuracy, scalability and efficiency. The target of this work is to handle highly accurate and consistent large-scale Structure from Motion problems in a parallel and scalable manner. First, we propose a scalable distributed formulation to handle Structure from Motion problems far exceeding the memory of a single computer in parallel. Different from the previous methods which drastically simplify the parameters of Structure from Motion, we propose a camera clustering algorithm to divide a large Structure from Motion problem into smaller sub-problems in terms of camera clusters with overlapping while preserving as many connectivity among cameras and tracks as possible. We next exploit a hybrid formulation using the relative motions from local incremental Structure from Motion into a global motion averaging framework to produce superior accurate and consistent initial camera poses. Our scalable formulation in terms of camera clusters is highly applicable to the whole Structure from Motion pipeline including track generation, local Structure from Motion, 3D point triangulation and bundle adjustment. To achieve scalable distributed motion averaging, we base on the scalable formulation in terms of camera clusters to decouple the full motion averaging problem into several sub-problems with respect to their local coordinate frames encoded by similarity transformations for independent optimization in parallel. Then, we can merge sub-problems globally without caching the whole reconstruction in memory at once. The proposed distributed and robust framework supplements the majority of the state-of-the-art motion averaging approaches with superior improvement in efficiency and robustness. As for large-scale bundle adjustment, eliminating statistical redundancy in multi-view geometry is of great importance to efficient 3D reconstruction. Our approach takes the full set of images with initial calibration and recovered sparse 3D points as inputs, and obtains a subset of views that preserve the final reconstruction accuracy and completeness well. Moreover, global bundle adjustment usually converges to a non-zero residual and produces sub-optimal camera poses for local areas, which leads to loss of details for high-resolution reconstruction. Instead of trying harder to optimize everything globally, we argue that we should live with the non-zero residual and adapt the camera poses to local areas. To this end, we propose a segment-based approach to readjust the camera poses locally and improve the reconstruction for fine geometry details. This significantly reduces severe propagated errors and estimation biases caused by the initial global adjustment. Together these techniques enable the first pipeline able to reconstruct highly accurate and consistent camera poses from more than one million high-resolution images in parallel with the state-of-the-art…

Subjects/Keywords: Image processing ; Digital techniques ; Photogrammetry ; Computer vision

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Zhu, S. C. (2017). Accurate, scalable and parallel structure from motion. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-88943 ; https://doi.org/10.14711/thesis-991012532269103412 ; http://repository.ust.hk/ir/bitstream/1783.1-88943/1/th_redirect.html

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):

Zhu, Siyu CSE. “Accurate, scalable and parallel structure from motion.” 2017. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-88943 ; https://doi.org/10.14711/thesis-991012532269103412 ; http://repository.ust.hk/ir/bitstream/1783.1-88943/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Zhu, Siyu CSE. “Accurate, scalable and parallel structure from motion.” 2017. Web. 07 Mar 2021.

Vancouver:

Zhu SC. Accurate, scalable and parallel structure from motion. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2017. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-88943 ; https://doi.org/10.14711/thesis-991012532269103412 ; http://repository.ust.hk/ir/bitstream/1783.1-88943/1/th_redirect.html.

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

Council of Science Editors:

Zhu SC. Accurate, scalable and parallel structure from motion. [Thesis]. Hong Kong University of Science and Technology; 2017. Available from: http://repository.ust.hk/ir/Record/1783.1-88943 ; https://doi.org/10.14711/thesis-991012532269103412 ; http://repository.ust.hk/ir/bitstream/1783.1-88943/1/th_redirect.html

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

Hong Kong University of Science and Technology

16. Hu, Zhaoxu ECE. A new perspective correction method for display-camera visible light communications using screen door patterns.

Degree: 2017, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-91071 ; https://doi.org/10.14711/thesis-991012554966603412 ; http://repository.ust.hk/ir/bitstream/1783.1-91071/1/th_redirect.html

► The ubiquity of camera and display devices provides a unique opportunity for low-cost realizations of widespread device-to-device communications in the specific form of display-camera visible… (more)

▼ The ubiquity of camera and display devices provides a unique opportunity for low-cost realizations of widespread device-to-device communications in the specific form of display-camera visible light communications. A major impairment of the display-camera communication channel is the perspective distortion, which is a non-linear transform acting on the pixel locations of a displayed image/video. Conventionally, dedicated training patterns are required for estimating the perspective distortion parameters, which determine how the locations of the image/video captured by a camera are distorted. In this thesis, a novel algorithm of perspective distortion estimation for images captured from a display device without requiring training patterns is presented. It takes advantage of the pixel grid structure of common display devices, which can be observed as the screen door patterns of the captured images, as an implicit training pattern. A geometric model of the screen door pattern under perspective distortion is proposed and its validity has been verified using captured images from common display devices. Based on the proposed geometric model, the problem of perspective distortion estimation is formulated as an optimization problem. The display pixel grid lines associated with a captured image are detected using the modified Hough transform and are used to obtain coarse estimates of the three angle parameters of the perspective distortion. Together with some known physical parameters of camera devices, these three angles are used to construct an initial guess solution. An iterative algorithm is derived to produce a much improved solution to the formulated optimization problem in estimating the modified perspective distortion parameters. Using the estimated perspective distortion parameters, perspective correction is applied to the captured image to reconstruct the original image. Since both of the displayed and captured images are digital with signal samples in discrete pixel locations only, natural interpolation is used in the perspective correction process. Experimental results show that satisfactory estimation accuracy for perspective correction can be achieved by the proposed algorithm for images with various types of content.

Subjects/Keywords: Optical communications ; Image processing ; Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Hu, Z. E. (2017). A new perspective correction method for display-camera visible light communications using screen door patterns. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-91071 ; https://doi.org/10.14711/thesis-991012554966603412 ; http://repository.ust.hk/ir/bitstream/1783.1-91071/1/th_redirect.html

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, Zhaoxu ECE. “A new perspective correction method for display-camera visible light communications using screen door patterns.” 2017. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-91071 ; https://doi.org/10.14711/thesis-991012554966603412 ; http://repository.ust.hk/ir/bitstream/1783.1-91071/1/th_redirect.html.

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, Zhaoxu ECE. “A new perspective correction method for display-camera visible light communications using screen door patterns.” 2017. Web. 07 Mar 2021.

Vancouver:

Hu ZE. A new perspective correction method for display-camera visible light communications using screen door patterns. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2017. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-91071 ; https://doi.org/10.14711/thesis-991012554966603412 ; http://repository.ust.hk/ir/bitstream/1783.1-91071/1/th_redirect.html.

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

Council of Science Editors:

Hu ZE. A new perspective correction method for display-camera visible light communications using screen door patterns. [Thesis]. Hong Kong University of Science and Technology; 2017. Available from: http://repository.ust.hk/ir/Record/1783.1-91071 ; https://doi.org/10.14711/thesis-991012554966603412 ; http://repository.ust.hk/ir/bitstream/1783.1-91071/1/th_redirect.html

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

Hong Kong University of Science and Technology

17. Xiao, Yao CSE. Shadow removal and object proposal generation for RGB-D images.

Degree: 2017, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-91072 ; https://doi.org/10.14711/thesis-991012554867203412 ; http://repository.ust.hk/ir/bitstream/1783.1-91072/1/th_redirect.html

► In recent years, the emergence of reliable and low-cost RGB-D sensors (e.g., Microsoft Kinect) has expended the dimension of a single image from 2D to… (more)

▼ In recent years, the emergence of reliable and low-cost RGB-D sensors (e.g., Microsoft Kinect) has expended the dimension of a single image from 2D to 3D. With the aiding of additional depth channel the 3D spatial information is discovered to compensate 2D image plane, in which way many computer vision tasks are boosted. In this thesis, we present the research of extending two vision tasks, shadow removal and object proposal generation, from RGB to a single RGB-D image. Shadow removal is a classical and challenging computer vision problem. First we propose an automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove both hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar normals, spatial locations and chromaticity should have similar colors. A modified nonlocal matching is used to compute a shadow confidence map that localizes well hard shadow boundary, thus handling hard and soft shadows within the same framework. Then the detected shadows will be removed by a constrained linear optimization to reconstruct a shadow-less image. We compare our results produced using state-of-the-art shadow removal on single RGB images, and intrinsic image decomposition on standard RGB-D datasets. Our second task is to generate object proposals from RGB-D images. But before that we present a novel method to produce proposals for 2D images. Object proposals are the potential object candidates in the detection pipeline. Besides, distance metric plays a key role in grouping superpixels to produce the proposals for object detection. We observe that existing distance metrics work primarily for low complexity cases. In this thesis, we develop a novel distance metric for grouping two superpixels in high-complexity scenarios. Combining them, a complexity-adaptive distance measure is produced that achieves improved grouping in different levels of complexity. Our extensive experimentation shows that our method can achieve good results in the PASCAL VOC 2012 dataset surpassing the latest state-of-the-art methods. Next we focus on the task of extracting 3D region proposals from indoor RGB-D images, which aims to produce bounding boxes of candidate objects. 3D voxel grid contains large amount of redundant space. To rule out less-informative voxels and to simplify the problem we introduce a space compression procedure to squash 3D space to 2D ”tile” grid. After each tile is layered in vertical direction individually, we propose Structural Constrained Parametric Min-Cuts (S-CPMC) to group the tilted space. The extracted tiles are further processed to reconstruct 3D bounding boxes through geodesic distance transformation (GDT) from the generated tile hypotheses. Finally the object hypotheses are ranked by a trained ranker. Experiments show that our algorithm achieves comparing result to stat-of-the-art on SUN-RGBD dataset.

Subjects/Keywords: Image processing ; Digital techniques ; Computer graphics

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Xiao, Y. C. (2017). Shadow removal and object proposal generation for RGB-D images. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-91072 ; https://doi.org/10.14711/thesis-991012554867203412 ; http://repository.ust.hk/ir/bitstream/1783.1-91072/1/th_redirect.html

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):

Xiao, Yao CSE. “Shadow removal and object proposal generation for RGB-D images.” 2017. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-91072 ; https://doi.org/10.14711/thesis-991012554867203412 ; http://repository.ust.hk/ir/bitstream/1783.1-91072/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Xiao, Yao CSE. “Shadow removal and object proposal generation for RGB-D images.” 2017. Web. 07 Mar 2021.

Vancouver:

Xiao YC. Shadow removal and object proposal generation for RGB-D images. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2017. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-91072 ; https://doi.org/10.14711/thesis-991012554867203412 ; http://repository.ust.hk/ir/bitstream/1783.1-91072/1/th_redirect.html.

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

Council of Science Editors:

Xiao YC. Shadow removal and object proposal generation for RGB-D images. [Thesis]. Hong Kong University of Science and Technology; 2017. Available from: http://repository.ust.hk/ir/Record/1783.1-91072 ; https://doi.org/10.14711/thesis-991012554867203412 ; http://repository.ust.hk/ir/bitstream/1783.1-91072/1/th_redirect.html

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

Hong Kong University of Science and Technology

18. Lin, Xuxiang. Automated colorization of video subtitles.

Degree: 2011, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-7146 ; https://doi.org/10.14711/thesis-b1136742 ; http://repository.ust.hk/ir/bitstream/1783.1-7146/1/th_redirect.html

► Subtitling, or captioning, refers to the process of presenting textual information about a video scene usually at the bottom of the display. This process is… (more)

Subjects/Keywords: Image processing – Digital techniques ; Closed captioning

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Lin, X. (2011). Automated colorization of video subtitles. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-7146 ; https://doi.org/10.14711/thesis-b1136742 ; http://repository.ust.hk/ir/bitstream/1783.1-7146/1/th_redirect.html

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):

Lin, Xuxiang. “Automated colorization of video subtitles.” 2011. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-7146 ; https://doi.org/10.14711/thesis-b1136742 ; http://repository.ust.hk/ir/bitstream/1783.1-7146/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Lin, Xuxiang. “Automated colorization of video subtitles.” 2011. Web. 07 Mar 2021.

Vancouver:

Lin X. Automated colorization of video subtitles. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2011. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-7146 ; https://doi.org/10.14711/thesis-b1136742 ; http://repository.ust.hk/ir/bitstream/1783.1-7146/1/th_redirect.html.

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

Council of Science Editors:

Lin X. Automated colorization of video subtitles. [Thesis]. Hong Kong University of Science and Technology; 2011. Available from: http://repository.ust.hk/ir/Record/1783.1-7146 ; https://doi.org/10.14711/thesis-b1136742 ; http://repository.ust.hk/ir/bitstream/1783.1-7146/1/th_redirect.html

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

Hong Kong University of Science and Technology

19. Xu, Pengfei. Pattern-aware selection and arrangement of graphic elements.

Degree: 2015, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-76054 ; https://doi.org/10.14711/thesis-b1450576 ; http://repository.ust.hk/ir/bitstream/1783.1-76054/1/th_redirect.html

► Selection and arrangement of graphic elements are two fundamental tasks in many text and graphic editing scenarios. Traditional interactive techniques such as lasso selection, snapping… (more)

▼ Selection and arrangement of graphic elements are two fundamental tasks in many text and graphic editing scenarios. Traditional interactive techniques such as lasso selection, snapping and arrangement commands are provided by most graphic editors to aid the users in accomplishing these tasks. However, these techniques often ignore the underlying patterns of the elements, requiring the users to perform explicit and tedious operations to achieve the goal of the manipulation. It is expected that the amount of user interaction can be reduced by exploiting the patterns of the elements. Nevertheless, designing effective pattern-aware interaction tools is challenging due to the ambiguities in the patterns presented by the elements and the operations issued by the user. This thesis focuses on developing effective pattern-aware interactive techniques to aid the users in the selection and arrangement of elements. In particular, we propose three interactive techniques which adopt different strategies to resolve the ambiguities that may arise during manipulation. First, we introduce a selection tool called Lazy Selection. It is a scribble-based tool for quick selection of one or more desired shape elements by roughly stroking through the elements. Our algorithm automatically refines the selection and reveals the user’s intention. It first extracts selection candidates from the scribble-covered elements by examining the underlying patterns and then ranks them based on their location and shape with respect to the user-sketched scribble. Such a design makes this tool tolerant to imprecise input systems and applicable to touch systems without suffering from the fat finger problem. Second, we present GACA, a group-aware command-based arrangement tool. Compared with the traditional command-based arrangement tools, it reduces the number of selection operations and command invocations. The key idea is that an issued arrangement command is in fact very informative, instructing the tool how to automatically decompose a 2D layout into multiple 1D groups, each one being compatible with the command. The tool uses a parameter-free, command-driven grouping approach so that users can easily predict our grouping results. We also designed a simple user interface to enable explicit control of grouping and arrangement. Third, we present a framework for automatic global beautification of layouts. To facilitate ambiguity resolution in layout beautification, we include a novel user interface for visualizing and editing inferred relationships. Our interface provides a preview of the beautified layout with inferred constraints, without directly modifying the input layout. In this way, the user can easily keep refining beautification results by interactively repositioning and/or resizing elements in the input layout. In addition, we present a gestural interface for editing automatically inferred constraints by directly interacting with the visualized constraints via simple gestures.

Subjects/Keywords: Image processing ; Digital techniques ; Pattern recognition systems

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Xu, P. (2015). Pattern-aware selection and arrangement of graphic elements. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-76054 ; https://doi.org/10.14711/thesis-b1450576 ; http://repository.ust.hk/ir/bitstream/1783.1-76054/1/th_redirect.html

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):

Xu, Pengfei. “Pattern-aware selection and arrangement of graphic elements.” 2015. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-76054 ; https://doi.org/10.14711/thesis-b1450576 ; http://repository.ust.hk/ir/bitstream/1783.1-76054/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Xu, Pengfei. “Pattern-aware selection and arrangement of graphic elements.” 2015. Web. 07 Mar 2021.

Vancouver:

Xu P. Pattern-aware selection and arrangement of graphic elements. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2015. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-76054 ; https://doi.org/10.14711/thesis-b1450576 ; http://repository.ust.hk/ir/bitstream/1783.1-76054/1/th_redirect.html.

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

Council of Science Editors:

Xu P. Pattern-aware selection and arrangement of graphic elements. [Thesis]. Hong Kong University of Science and Technology; 2015. Available from: http://repository.ust.hk/ir/Record/1783.1-76054 ; https://doi.org/10.14711/thesis-b1450576 ; http://repository.ust.hk/ir/bitstream/1783.1-76054/1/th_redirect.html

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

Hong Kong University of Science and Technology

20. Ahmed, Ashfaq CBME. Interpolation techniques for division of focal plane polarization image sensors.

Degree: 2018, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-104948 ; https://doi.org/10.14711/thesis-991012634968003412 ; http://repository.ust.hk/ir/bitstream/1783.1-104948/1/th_redirect.html

► The aim of this research is to introduce novel and efficient interpolation algorithms to interpret polarization information for division of focal plane polarization image sensors.… (more)

Subjects/Keywords: Biosensors ; Polariscope ; Image processing ; Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Ahmed, A. C. (2018). Interpolation techniques for division of focal plane polarization image sensors. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-104948 ; https://doi.org/10.14711/thesis-991012634968003412 ; http://repository.ust.hk/ir/bitstream/1783.1-104948/1/th_redirect.html

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):

Ahmed, Ashfaq CBME. “Interpolation techniques for division of focal plane polarization image sensors.” 2018. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-104948 ; https://doi.org/10.14711/thesis-991012634968003412 ; http://repository.ust.hk/ir/bitstream/1783.1-104948/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Ahmed, Ashfaq CBME. “Interpolation techniques for division of focal plane polarization image sensors.” 2018. Web. 07 Mar 2021.

Vancouver:

Ahmed AC. Interpolation techniques for division of focal plane polarization image sensors. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2018. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-104948 ; https://doi.org/10.14711/thesis-991012634968003412 ; http://repository.ust.hk/ir/bitstream/1783.1-104948/1/th_redirect.html.

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

Council of Science Editors:

Ahmed AC. Interpolation techniques for division of focal plane polarization image sensors. [Thesis]. Hong Kong University of Science and Technology; 2018. Available from: http://repository.ust.hk/ir/Record/1783.1-104948 ; https://doi.org/10.14711/thesis-991012634968003412 ; http://repository.ust.hk/ir/bitstream/1783.1-104948/1/th_redirect.html

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

Nelson Mandela Metropolitan University

21. Campbell, Sydney. Experiences of analogue-trained radiographers utilising digital imaging in projection radiography.

Degree: Faculty of Health Sciences, 2017, Nelson Mandela Metropolitan University

URL: http://hdl.handle.net/10948/14796

► The professional work of a radiographer encompasses both patient care and the use of technology. The technology employed could either be analogue or digital technology.… (more)

▼ The professional work of a radiographer encompasses both patient care and the use of technology. The technology employed could either be analogue or digital technology. Since 1973, the analogue imaging system has slowly been replaced by digital radiography imaging systems. Despite the many advantages of digital imaging it does present the radiographer with added responsibilities. Furthermore, analogue-trained radiographers have found adjusting to digital imaging especially challenging. The aim of the study was to explore and describe the experiences of analogue-trained radiographers utilising digital imaging in projection radiography with the intention of developing guidelines to equip radiography managers to assist analogue-trained radiographers to better utilise digital imaging. The researcher used Schlossberg’s Transition Theory as a lens to look at the experiences of analogue-trained radiographers using digital imaging to produce radiographs. The research study used a qualitative design which was explorative, descriptive and contextual in nature. The target population included all diagnostic radiographers (public and private) in the local municipality who were registered with the Health Professions Council of South Africa. Purposive sampling was employed to select the radiographers that represented all radiographers in the Nelson Mandela Bay Health District. The sample included all radiographers who fulfilled the identified selection criteria. The selected participants were recruited to take part in in-depth, semi-structured individual interviews. The data was analysed using a computer-aided qualitative data analysis software package, ATLAS.ti. The trustworthiness of this study was ensured by applying Guba’s model of trustworthiness that includes credibility, transferability, dependability and confirmability. The ethical principles of respect for persons, beneficence and justice, as espoused by the Belmont Report, were adhered to in order to ensure that the study was conducted in an ethical manner. Two themes emanated from the data, namely the evolution of the radiographer when faced with the advances in technology as well the role that the work environment played in the manner that the participants experienced the change. The experiences of the participants were described using direct quotations from the interviews and a literature control was used to verify the participants’ experiences. Evidence was found of radiographer indifference towards exposure selection, dose optimisation and placement of anatomical side markers when utilising digital imaging. Finally, guidelines were developed to equip radiography managers to assist analogue-trained radiographers to better utilise digital imaging. In addition, the guidelines will assist all other radiographers to better utilise digital imaging.

Subjects/Keywords: Radiography, Medical – Digital techniques; Angiography; Image processing – Digital techniques; Radiography

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Campbell, S. (2017). Experiences of analogue-trained radiographers utilising digital imaging in projection radiography. (Thesis). Nelson Mandela Metropolitan University. Retrieved from http://hdl.handle.net/10948/14796

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):

Campbell, Sydney. “Experiences of analogue-trained radiographers utilising digital imaging in projection radiography.” 2017. Thesis, Nelson Mandela Metropolitan University. Accessed March 07, 2021. http://hdl.handle.net/10948/14796.

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

MLA Handbook (7^th Edition):

Campbell, Sydney. “Experiences of analogue-trained radiographers utilising digital imaging in projection radiography.” 2017. Web. 07 Mar 2021.

Vancouver:

Campbell S. Experiences of analogue-trained radiographers utilising digital imaging in projection radiography. [Internet] [Thesis]. Nelson Mandela Metropolitan University; 2017. [cited 2021 Mar 07]. Available from: http://hdl.handle.net/10948/14796.

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

Council of Science Editors:

Campbell S. Experiences of analogue-trained radiographers utilising digital imaging in projection radiography. [Thesis]. Nelson Mandela Metropolitan University; 2017. Available from: http://hdl.handle.net/10948/14796

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

Michigan State University

22. Mahfoodh, Abo Talib. Visual data representation and coding based on tensor decomposition and super-resolution.

Degree: 2016, Michigan State University

URL: http://etd.lib.msu.edu/islandora/object/etd:4275

►

Thesis Ph. D. Michigan State University. Electrical Engineering 2016

Tensor based methods have been used in a wide range of signal processing applications. A particular… (more)

▼

Thesis Ph. D. Michigan State University. Electrical Engineering 2016

Tensor based methods have been used in a wide range of signal processing applications. A particular area of interest is tensor decomposition, which can be used to reduce the dimensionality of the massive multidimensional data. Hence, tensor decomposition can be considered as a high dimension extension of popular Singular Value Decomposition (SVD) methods used for matrix analysis. The lower dimension representation of tensors resulting from tensor decomposition can be used for classification, pattern recognition, and reconstruction. Our objective in the first part of this thesis, is to develop a tensor coding framework based on a tensor decomposition method for visual data efficient representation and compression. As part of the proposed tensor coding framework, we developed a tensor decomposition algorithm that decomposed the input tensor into a set of rank-one tensors. The proposed decomposition is designed to be efficient specifically for visual data. The proposed tensor decomposition algorithm is applied in a block-wise approach. Two partitioning methods are proposed for tensor coding framework which are uniform and adaptive tree partitioning. The former subdivide a region into a set of equal size blocks while the later subdivide a region into a set of variable size blocks. The decision whether to subdivide the region or not is made based on the existing amount of the information and the overall available bitrate. A tree data structure stores the partitioning structure information which is required for the tensor reconstruction process.Furthermore, an encoder/decoder framework is proposed for compressing and storing the decomposed data. The proposed framework provides a number of desirable properties especially at the decoder side which can be critical for some applications. Low complexity reconstruction, random access, and scalability are the main properties that we have targeted. We demonstrate the viability of the proposed tensor coding framework by employing it for the representation and coding of three types of data sets: hyperspectral/multispectral images, bio-metric face image ensembles, and low motion videos. These data sets can be arranged as either three or four dimensional tensors. For each application, we show that the compression efficiency along with the inherited properties of the proposed tensor coding framework, provide a competitive approach to the current standard methods. In the second part of the thesis, we propose an example-based super-resolution algorithm for a new framework of scalable video streaming. The proposed method is applicable to scalable videos where the enhancement layer of some frames might be dropped due to changing network conditions. This leads to a streaming scenario that we call Inconsistent Scalable Video (ISV) streaming. At the decoder, the frames with the enhancement layer are used as a dictionary for super-resolving other video frames whose enhancement layers were dropped. The proposed…

Advisors/Committee Members: Radha, Hayder, Tong, Yiying, Aviyente, Selin, Udpa, Lalita.

Subjects/Keywords: Signal processing – Digital techniques – Data processing; Signal processing – Digital techniques; Image compression; Electrical engineering

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Mahfoodh, A. T. (2016). Visual data representation and coding based on tensor decomposition and super-resolution. (Thesis). Michigan State University. Retrieved from http://etd.lib.msu.edu/islandora/object/etd:4275

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):

Mahfoodh, Abo Talib. “Visual data representation and coding based on tensor decomposition and super-resolution.” 2016. Thesis, Michigan State University. Accessed March 07, 2021. http://etd.lib.msu.edu/islandora/object/etd:4275.

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

MLA Handbook (7^th Edition):

Mahfoodh, Abo Talib. “Visual data representation and coding based on tensor decomposition and super-resolution.” 2016. Web. 07 Mar 2021.

Vancouver:

Mahfoodh AT. Visual data representation and coding based on tensor decomposition and super-resolution. [Internet] [Thesis]. Michigan State University; 2016. [cited 2021 Mar 07]. Available from: http://etd.lib.msu.edu/islandora/object/etd:4275.

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

Council of Science Editors:

Mahfoodh AT. Visual data representation and coding based on tensor decomposition and super-resolution. [Thesis]. Michigan State University; 2016. Available from: http://etd.lib.msu.edu/islandora/object/etd:4275

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

Hong Kong University of Science and Technology

23. Huang, Wenjian. Communications over display-camera channels under a visual constrain.

Degree: 2014, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-87446 ; https://doi.org/10.14711/thesis-b1333742 ; http://repository.ust.hk/ir/bitstream/1783.1-87446/1/th_redirect.html

► Due to the ubiquity of smartphones, research on data communications over display-camera channels has received increasing attention in recent years. Such communication systems are characterized… (more)

▼ Due to the ubiquity of smartphones, research on data communications over display-camera channels has received increasing attention in recent years. Such communication systems are characterized by the use of cameras as receivers and electronic displays as transmitters. Common 2D barcodes can be viewed as examples of such communication systems which involve channel coding, modulation, channel estimation, demodulation and channel decoding. Recently introduced systems, such as VCode, PixNet, LightSync, etc., exploit a series of time-varying 2D patterns to transmit a larger amount of data. However, most of these communication systems have not been designed to provide meaningful visual information to human eyes and they typically sacriﬁce visual appearance in order to guarantee machine-readability. Though electronic displays were originally designed for showing visual information such as images and videos, few prior works have considered simultaneous image (or video) displaying and data transmission. Motivated by mobile advertising and related applications, in this thesis, we propose novel designs of display-camera communication systems, which can effectively combine high quality image (or video) displaying and data transmission. Our novel image based communication system over display-camera channels, called MarkCode, can display images with such an impressive visual quality that human eyes cannot easily differentiate the encoded images from the original ones. This is accomplished by formulating the waveform modulation design as a quadratic programming convex optimization problem. MarkCode is inspired by image watermarking, which is a mature technology that enables users to hide secret data in image ﬁles for later retrieval. However, the latter cannot recover the hidden data from a camera captured image which is typically corrupted by complicated distortions, such as geometric distortion, inter-symbol interference, motion blurs, etc. We address these challenges by introducing our imperceptible waveform modulation scheme and online supervised pattern recognition based demodulation scheme. In other words, MarkCode can be viewed as an advanced communication system designed for transmission of imperceptible image watermarks over display-camera channels. We also extend MarkCode to the so-called VMarkCode, which is a novel display-camera communication system designed for transmitting imperceptible video water-marks. By viewing VMarkCode as a random network coding system, we developed subspace coding based inter-frame encoding and decoding methods to allow complete data reconstruction based on randomly retrieved video frames. Finally, experimental results are presented to demonstrate that our MarkCode and VMarkCode systems can display high visual quality images and videos, respectively, without sacriﬁcing decodability in some practical situations.

Subjects/Keywords: Digital images ; Data processing ; Mathematical models ; Digital video ; Image processing ; Digital techniques ; Image compression

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Huang, W. (2014). Communications over display-camera channels under a visual constrain. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-87446 ; https://doi.org/10.14711/thesis-b1333742 ; http://repository.ust.hk/ir/bitstream/1783.1-87446/1/th_redirect.html

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):

Huang, Wenjian. “Communications over display-camera channels under a visual constrain.” 2014. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-87446 ; https://doi.org/10.14711/thesis-b1333742 ; http://repository.ust.hk/ir/bitstream/1783.1-87446/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Huang, Wenjian. “Communications over display-camera channels under a visual constrain.” 2014. Web. 07 Mar 2021.

Vancouver:

Huang W. Communications over display-camera channels under a visual constrain. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2014. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-87446 ; https://doi.org/10.14711/thesis-b1333742 ; http://repository.ust.hk/ir/bitstream/1783.1-87446/1/th_redirect.html.

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

Council of Science Editors:

Huang W. Communications over display-camera channels under a visual constrain. [Thesis]. Hong Kong University of Science and Technology; 2014. Available from: http://repository.ust.hk/ir/Record/1783.1-87446 ; https://doi.org/10.14711/thesis-b1333742 ; http://repository.ust.hk/ir/bitstream/1783.1-87446/1/th_redirect.html

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

Nelson Mandela Metropolitan University

24. Gifford, Dean. A deep learning approach to classifying tyres using sidewall images.

Degree: 2019, Nelson Mandela Metropolitan University

URL: http://hdl.handle.net/10948/39720

► End of Life Tyres (ELT's) pose a potential health and environmental risk when dumped in illegal stockpiles. For recycling to be considered feasible, a profitable… (more)

▼ End of Life Tyres (ELT's) pose a potential health and environmental risk when dumped in illegal stockpiles. For recycling to be considered feasible, a profitable business opportunity needs to be created. One method of making the recycling process of tyres more profitable is by understanding the compounds found within each tyre. This study aims at classifying these tyres in order to achieve this knowledge. A literature review was done to investigate neural networks, convolutional neural networks as well as existing deep learning architectures for image classification. A deep learning approach was applied in order to classify the logos of tyres as these approaches have proved their success in both image classification and more specifically logo classification. Although tyre classification has been implemented in the past, a deep learning approach has not been applied and the logo has not been the classifying element in any other studies. The main difference of this study compared to previous research surrounding deep learning and logo classification is the properties of the tyre logo. Logos on tyres are very similar in colour as they are purely formed in rubber and very seldom have any colour to them. Additionally, the embossed logos can contain variation among same branded tyres due to small inconsistencies in the moulds. The implementation of this deep learning solution saw multiple convolutional neural networks implemented. Some of these architectures were also implemented using transferred learning. The metrics obtained as outputs from training and testing the architectures were the accuracy, precision, recall, and F1-score. These metrics were compared in conjunction with the confusion matrix produced from testing. To ensure that variance was accounted for in the experiments, the k-fold cross-validation technique was adopted. The results of this study identified that one convolutional neural network model, MobileNet, was particularly well suited for the context of classifying logos on tyre sidewalls. The MobileNet architecture had the highest performance metrics for both training from scratch (96.7% accuracy) and transferred learning (98.8% accuracy). Three other models performed particularly well when trained from scratch, these were a modification of the LeNet architecture, ResNet50 and InceptionV3. The transferred learning results were also impressive with four out of the 5 models achieving an accuracy above 94%. Interestingly, the ResNet50 architecture failed to train when transferred learning was applied. Contrasting to this, the two models VGG16 and VGG19 failed to train when trained from scratch but performed equally as well as the other models when transferred learning was implemented. This indicates that although transferred learning can improve the performance of models, it is highly dependent on the task as well as the model. Overall the results obtained proved that a deep learning approach could be applied in order to classify tyres accurately.

Subjects/Keywords: Image processing – Digital techniques; Image processing; Computer science

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Gifford, D. (2019). A deep learning approach to classifying tyres using sidewall images. (Thesis). Nelson Mandela Metropolitan University. Retrieved from http://hdl.handle.net/10948/39720

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):

Gifford, Dean. “A deep learning approach to classifying tyres using sidewall images.” 2019. Thesis, Nelson Mandela Metropolitan University. Accessed March 07, 2021. http://hdl.handle.net/10948/39720.

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

MLA Handbook (7^th Edition):

Gifford, Dean. “A deep learning approach to classifying tyres using sidewall images.” 2019. Web. 07 Mar 2021.

Vancouver:

Gifford D. A deep learning approach to classifying tyres using sidewall images. [Internet] [Thesis]. Nelson Mandela Metropolitan University; 2019. [cited 2021 Mar 07]. Available from: http://hdl.handle.net/10948/39720.

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

Council of Science Editors:

Gifford D. A deep learning approach to classifying tyres using sidewall images. [Thesis]. Nelson Mandela Metropolitan University; 2019. Available from: http://hdl.handle.net/10948/39720

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

Hong Kong University of Science and Technology

25. Li, Haohan MATH. Algorithms for image processing.

Degree: 2018, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-96216 ; https://doi.org/10.14711/thesis-991012655669003412 ; http://repository.ust.hk/ir/bitstream/1783.1-96216/1/th_redirect.html

► In this thesis, we introduce connections between diffuse interface models, total variation models, and the threshold dynamics scheme. We show that it is a natural… (more)

▼ In this thesis, we introduce connections between diffuse interface models, total variation models, and the threshold dynamics scheme. We show that it is a natural extension of many continuum diffuse interface models to the discrete graph based models. The Ginzburg-Landau functional is close connected to total variation minimization via classical Laplacian operator and is often used to describe two terms with a sharp interface between them. The Merriman-Bence-Osher (MBO) algorithm is efficient in minimizing these diffuse interface models on graphs. In Chapter 2, we review the classical diffuse interface models. Such continuum PDEs involve a front propagating by mean curvature on each of its point. We also study the definition of mean curvature flow as well as discrete version of mean curvature flow on arbitrary graphs. Since the diffuse interface models and mean curvature flow are all closely related to the MBO scheme, we also review the classical MBO method and extend it for arbitrary graphs. In Chapter 3, an algorithm based on point integral method is introduced. Inspired by diffuse interface models that have been used in variety of problems, like fluid dynamics and image processing, we introduce an algorithm to solve heat equation over a point cloud which is believed to lie on a low dimensional manifold for most natural data sets. Due to the complicated geometrical structure of the manifold, it is not easy to solve PDEs on arbitrary manifold. However, utilizing the point integral method with proper kernel function [1], we can solve heat equation on the point cloud efficiently. We also use the Merriman-Bence-Osher (MBO) [2] scheme to speed up the scheme. In Chapter 4, we proposed an efficient iterative thresholding method for multi-phase image segmentation. The algorithm is based on minimizing piecewise constant Mumford-Shah functional in which the contour length (or perimeter) is approximated by a non-local multi-phase energy. The minimization problem is solved by an iterative method. Each iteration consists of computing simple convolutions followed by a thresholding step. The algorithm is easy to implement and has the optimal complexity O(N log N) per iteration. We also show that the iterative algorithm has the total energy decaying property. We present some numerical results to show the efficiency of our method. In Chapter 5, a novel weighted nonlocal total variation (WNTV) method is proposed. Compared to the classical nonlocal total variation methods, our method modifies the energy functional to introduce a weight to balance between the labeled sets and unlabeled sets. With extensive numerical examples in semi-supervised clustering, image inpaiting and image colorization, we demonstrate that WNTV provides an effective and efficient method in many image processing and machine learning problems.

Subjects/Keywords: Image processing ; Data processing ; Mathematical models ; Image segmentation ; Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Li, H. M. (2018). Algorithms for image processing. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-96216 ; https://doi.org/10.14711/thesis-991012655669003412 ; http://repository.ust.hk/ir/bitstream/1783.1-96216/1/th_redirect.html

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):

Li, Haohan MATH. “Algorithms for image processing.” 2018. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-96216 ; https://doi.org/10.14711/thesis-991012655669003412 ; http://repository.ust.hk/ir/bitstream/1783.1-96216/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Li, Haohan MATH. “Algorithms for image processing.” 2018. Web. 07 Mar 2021.

Vancouver:

Li HM. Algorithms for image processing. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2018. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-96216 ; https://doi.org/10.14711/thesis-991012655669003412 ; http://repository.ust.hk/ir/bitstream/1783.1-96216/1/th_redirect.html.

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

Council of Science Editors:

Li HM. Algorithms for image processing. [Thesis]. Hong Kong University of Science and Technology; 2018. Available from: http://repository.ust.hk/ir/Record/1783.1-96216 ; https://doi.org/10.14711/thesis-991012655669003412 ; http://repository.ust.hk/ir/bitstream/1783.1-96216/1/th_redirect.html

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

Hong Kong University of Science and Technology

26. Wang, Zhexi. Street view data segmentation and modelling.

Degree: 2013, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-62297 ; https://doi.org/10.14711/thesis-b1255216 ; http://repository.ust.hk/ir/bitstream/1783.1-62297/1/th_redirect.html

► Large scale urban scene scanned data processing attracts much attention these years. There are many research topics along the whole process, including data capturing, alignment,… (more)

▼ Large scale urban scene scanned data processing attracts much attention these years. There are many research topics along the whole process, including data capturing, alignment, registration, segmentation, and modelling. My research work is related to data capturing, segmentation and modelling. First we present a real-time stereo reconstruction system which can be used for data capturing. It is used on airplane mounted capturing system and do real-time structure-from-motion by using monocular or stereo cameras, which provides camera pose estimation and similarity reconstruction or metric reconstruction respectively. Then we address the problem of separating objects from 3D scanned point clouds of urban scene. The proposed approach hierarchically performs the grouping from the 3D points to curve segments, object elements, and finally objects. We introduce the relation attributes that describe relations for pairs of object primitives, learn a preference function over such attributes via ranking-SVM which is used to compute the degree that two object primitives belong to an object, and finally merge object elements that are very likely to be contained in the same object. Unlike previous 3D points segmentation algorithms that require object priors to annotate 3D points, our approach only exploits the relation prior that is not limited to any specific object and can separate general urban objects. At last, we present an automatic approach to reconstruct 3D road network models as a part of city models from terrestrial LiDAR and photo data. Terrestrial data provide much higher resolution then aerial data, however, the common terrestrial LiDAR data suffers from occlusion, inconsistency between multiple scans, and the lack of topology information. We introduce the prior knowledge of roads in the form of 2D topology maps, which are widely available on Internet, to assist the reconstruction of roads. A cross-domain alignment method is designed to align the captured data and 2D topology maps. Topology-aware partitioning helps splitting captured data into manageable partitions so that a model for each partition can be generated individually. Finally, all partitions are merged to a global consistent model. Our pipelines are tested in large scale datasets such as San Francisco, New York City, and Paris.

Subjects/Keywords: Image processing ; Digital techniques ; Digital images ; Data processing ; Computer vision

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Wang, Z. (2013). Street view data segmentation and modelling. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-62297 ; https://doi.org/10.14711/thesis-b1255216 ; http://repository.ust.hk/ir/bitstream/1783.1-62297/1/th_redirect.html

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):

Wang, Zhexi. “Street view data segmentation and modelling.” 2013. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-62297 ; https://doi.org/10.14711/thesis-b1255216 ; http://repository.ust.hk/ir/bitstream/1783.1-62297/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Wang, Zhexi. “Street view data segmentation and modelling.” 2013. Web. 07 Mar 2021.

Vancouver:

Wang Z. Street view data segmentation and modelling. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2013. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-62297 ; https://doi.org/10.14711/thesis-b1255216 ; http://repository.ust.hk/ir/bitstream/1783.1-62297/1/th_redirect.html.

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

Council of Science Editors:

Wang Z. Street view data segmentation and modelling. [Thesis]. Hong Kong University of Science and Technology; 2013. Available from: http://repository.ust.hk/ir/Record/1783.1-62297 ; https://doi.org/10.14711/thesis-b1255216 ; http://repository.ust.hk/ir/bitstream/1783.1-62297/1/th_redirect.html

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

Hong Kong University of Science and Technology

27. Kwok, Chun Wing. Digital image forensics and anti-forensics.

Degree: 2014, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-71021 ; https://doi.org/10.14711/thesis-b1333743 ; http://repository.ust.hk/ir/bitstream/1783.1-71021/1/th_redirect.html

► Nowadays, images are commonly found in Facebook, YouTube, WeChat and WWW all over the world due to the prevalence of digital cameras, smart phones, 3G/4G,… (more)

Subjects/Keywords: Digital images ; Data processing ; Editing ; Image processing ; Digital techniques ; Forensic sciences

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Kwok, C. W. (2014). Digital image forensics and anti-forensics. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-71021 ; https://doi.org/10.14711/thesis-b1333743 ; http://repository.ust.hk/ir/bitstream/1783.1-71021/1/th_redirect.html

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):

Kwok, Chun Wing. “Digital image forensics and anti-forensics.” 2014. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-71021 ; https://doi.org/10.14711/thesis-b1333743 ; http://repository.ust.hk/ir/bitstream/1783.1-71021/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Kwok, Chun Wing. “Digital image forensics and anti-forensics.” 2014. Web. 07 Mar 2021.

Vancouver:

Kwok CW. Digital image forensics and anti-forensics. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2014. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-71021 ; https://doi.org/10.14711/thesis-b1333743 ; http://repository.ust.hk/ir/bitstream/1783.1-71021/1/th_redirect.html.

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

Council of Science Editors:

Kwok CW. Digital image forensics and anti-forensics. [Thesis]. Hong Kong University of Science and Technology; 2014. Available from: http://repository.ust.hk/ir/Record/1783.1-71021 ; https://doi.org/10.14711/thesis-b1333743 ; http://repository.ust.hk/ir/bitstream/1783.1-71021/1/th_redirect.html

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

Hong Kong University of Science and Technology

28. Ng, Tsz Yeung. Background extraction via sampling.

Degree: 2015, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-78852 ; https://doi.org/10.14711/thesis-b1514769 ; http://repository.ust.hk/ir/bitstream/1783.1-78852/1/th_redirect.html

► Background extraction, which is to compute a background image given a set of images, has real life applications in computer vision such as video surveillance… (more)

Subjects/Keywords: Image processing ; Digital techniques ; Digital video ; Data processing

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Ng, T. Y. (2015). Background extraction via sampling. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-78852 ; https://doi.org/10.14711/thesis-b1514769 ; http://repository.ust.hk/ir/bitstream/1783.1-78852/1/th_redirect.html

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):

Ng, Tsz Yeung. “Background extraction via sampling.” 2015. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-78852 ; https://doi.org/10.14711/thesis-b1514769 ; http://repository.ust.hk/ir/bitstream/1783.1-78852/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Ng, Tsz Yeung. “Background extraction via sampling.” 2015. Web. 07 Mar 2021.

Vancouver:

Ng TY. Background extraction via sampling. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2015. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-78852 ; https://doi.org/10.14711/thesis-b1514769 ; http://repository.ust.hk/ir/bitstream/1783.1-78852/1/th_redirect.html.

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

Council of Science Editors:

Ng TY. Background extraction via sampling. [Thesis]. Hong Kong University of Science and Technology; 2015. Available from: http://repository.ust.hk/ir/Record/1783.1-78852 ; https://doi.org/10.14711/thesis-b1514769 ; http://repository.ust.hk/ir/bitstream/1783.1-78852/1/th_redirect.html

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

Hong Kong University of Science and Technology

29. Zhang, Bo ECE. Computational photography for efficient image and video acquisition.

Degree: 2019, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-99555 ; https://doi.org/10.14711/thesis-991012717868003412 ; http://repository.ust.hk/ir/bitstream/1783.1-99555/1/th_redirect.html

► Image sensors have become ubiquitous because of the increasing need for entertainment demand, mobile applications, Internet of things (IoTs) and auto-driving vehicles. In addition to… (more)

▼ Image sensors have become ubiquitous because of the increasing need for entertainment demand, mobile applications, Internet of things (IoTs) and auto-driving vehicles. In addition to the requirement for improved image quality, the power consumption is also becoming a key design factor especially for the wireless sensor networks (WSNs) where sensors need to be deployed at large scale. Substantial research work has already been proposed for low power CMOS image sensors. Unlike previous work that optimizes the power consumption through circuitry techniques, this dissertation rethinks the imaging system and introduces methods to achieve extremely low power image acquisition through computational photography techniques. First, we propose a lossy image compression algorithm called Microshift which achieves state-of-the-art on-chip compression performance while preserving hardware friendliness. To implement this algorithm, we propose a hardware architecture and validate it on FPGA. The results on the ASIC design further validates the power efficiency. The sensor achieves power as low as 59.7 pJ/(pixel frame) while running on 1530 frames per second. To enable high-performance decompression, we propose Markov random field method which provides PSNR > 34dB for a 1.25bit/pixel image. Second, we propose DenResUnet to enhance the bit-depth information so that ADCs for the image sensor quantize fewer bits. The DenResUnet adopts extensive residual learning structure, which greatly improves the perceptual visual quality. Furthermore, we develop an extension which decompresses the Microshift images in real-time. Extensive experiments demonstrate that high-quality results can be obtained even from 1 bit/pixel images. Third, we propose to adaptively change the sensor sampling rate for aggressive power saving and interpolate the intermediate frames computationally. We propose to establish the dense correspondence between two frames through halfway domain optimization. To account for large displacement, sparse correspondence is jointly considered for the correspondence optimization. This method is validated on real scene images and demonstrates superior robustness to large displacement and image noises than other methods. Last but not least, we further propose to colorize the videos by propagating the color from a reference image to the subsequent frames. Since the image sensor only needs to capture one color frame, the transmission bandwidth can be greatly reduced. To reconstruct high quality colorized videos, we propose the ColorNet. To further improve the perceptual quality we adopt generative adversarial network (GAN) technique. Our method can also generate consistent improved video results. Our work outperforms previous methods both quantitatively and quantitatively, demonstrating photo-realistic reconstruction quality.

Subjects/Keywords: Computational photography ; Image processing ; Digital techniques ; Digital video ; Data processing ; Technique

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Zhang, B. E. (2019). Computational photography for efficient image and video acquisition. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-99555 ; https://doi.org/10.14711/thesis-991012717868003412 ; http://repository.ust.hk/ir/bitstream/1783.1-99555/1/th_redirect.html

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):

Zhang, Bo ECE. “Computational photography for efficient image and video acquisition.” 2019. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-99555 ; https://doi.org/10.14711/thesis-991012717868003412 ; http://repository.ust.hk/ir/bitstream/1783.1-99555/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Zhang, Bo ECE. “Computational photography for efficient image and video acquisition.” 2019. Web. 07 Mar 2021.

Vancouver:

Zhang BE. Computational photography for efficient image and video acquisition. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2019. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-99555 ; https://doi.org/10.14711/thesis-991012717868003412 ; http://repository.ust.hk/ir/bitstream/1783.1-99555/1/th_redirect.html.

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

Council of Science Editors:

Zhang BE. Computational photography for efficient image and video acquisition. [Thesis]. Hong Kong University of Science and Technology; 2019. Available from: http://repository.ust.hk/ir/Record/1783.1-99555 ; https://doi.org/10.14711/thesis-991012717868003412 ; http://repository.ust.hk/ir/bitstream/1783.1-99555/1/th_redirect.html

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

Hong Kong University of Science and Technology

30. Yuan, Yuan ECE. Weakly-supervised video visual knowledge learning.

Degree: 2018, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-105608 ; https://doi.org/10.14711/thesis-991012637268803412 ; http://repository.ust.hk/ir/bitstream/1783.1-105608/1/th_redirect.html

► Learning video visual representation for detection has emerged as one of the fundamental problems toward general video understanding. It requires rich knowledge for spatial and/or… (more)

▼ Learning video visual representation for detection has emerged as one of the fundamental problems toward general video understanding. It requires rich knowledge for spatial and/or temporal localization; however, manually collecting fully-supervised annotations is extremely expensive and not scalable. This thesis has made progress toward effectively employing weakly-labeled data in learning video representations for detection tasks. Specifically, we focus on video object detection with human action descriptions, and temporal action detection with video-level action categories. For the weakly-supervised video object detection task, we propose a temporal dynamic graph long short-term memory network. This enables global temporal reasoning by constructing a dynamic graph that is based on temporal correlations of object proposals and spans the entire video. It significantly alleviates the missing label issue for each individual frame by transferring knowledge across correlated objects proposals in the whole video. Extensive evaluations on a large-scale daily-life action dataset demonstrates the superiority of our proposed method. For the weakly-supervised temporal action detection task, we propose three different approaches. (1) We propose an end-to-end framework to simultaneously update feature representation for classification and generate temporal proposals with a gated recurrent unit for detection. (2) We propose a novel structure-and-relation network, which includes a local structure module to leverage the context information for improving localization, and a global relation module to process all instances simultaneously through exploiting their interactions. These modules are integrated from a probabilistic perspective and can be learned in an end-to-end fashion. (3) We propose a marginalized dropout attention (MDA) mechanism for video feature aggregation in order to learn a more accurate action probability for each frame from classification networks. The MDA module is performed as a structural regularization, alleviating an existing problem of only attending on the most salient frames. Our proposed methods outperform the previous weakly-supervised approaches on several challenging video benchmarks.

Subjects/Keywords: Optical data processing ; Digital video ; Image processing ; Digital techniques

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Yuan, Y. E. (2018). Weakly-supervised video visual knowledge learning. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-105608 ; https://doi.org/10.14711/thesis-991012637268803412 ; http://repository.ust.hk/ir/bitstream/1783.1-105608/1/th_redirect.html

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):

Yuan, Yuan ECE. “Weakly-supervised video visual knowledge learning.” 2018. Thesis, Hong Kong University of Science and Technology. Accessed March 07, 2021. http://repository.ust.hk/ir/Record/1783.1-105608 ; https://doi.org/10.14711/thesis-991012637268803412 ; http://repository.ust.hk/ir/bitstream/1783.1-105608/1/th_redirect.html.

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

MLA Handbook (7^th Edition):

Yuan, Yuan ECE. “Weakly-supervised video visual knowledge learning.” 2018. Web. 07 Mar 2021.

Vancouver:

Yuan YE. Weakly-supervised video visual knowledge learning. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2018. [cited 2021 Mar 07]. Available from: http://repository.ust.hk/ir/Record/1783.1-105608 ; https://doi.org/10.14711/thesis-991012637268803412 ; http://repository.ust.hk/ir/bitstream/1783.1-105608/1/th_redirect.html.

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

Council of Science Editors:

Yuan YE. Weakly-supervised video visual knowledge learning. [Thesis]. Hong Kong University of Science and Technology; 2018. Available from: http://repository.ust.hk/ir/Record/1783.1-105608 ; https://doi.org/10.14711/thesis-991012637268803412 ; http://repository.ust.hk/ir/bitstream/1783.1-105608/1/th_redirect.html

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

Open Access Theses and Dissertations