The distortion by using traditional video encoders (e.g. H.264) on the depth discontinuity can introduce disturbing effects on the synthesized view. The proposed scheme aims at preserving the most significantdepth transition for a better view synthesis. Furthermore, it has a scalable structure. The scheme extracts edge contours from a depth image and represents them by chain code. The chain code and the sampleddepth values on each side of the edge contour are encoded by differential and arithmetic coding. The depthimage is reconstructed by diffusion of edge samples and uniform sub-samples from the low quality depthimage. At low bit rates, the proposed scheme outperforms HEVC intra at the edges in the synthesized views, which correspond to the significant discontinuities in the depth image. The overall quality is also better with the proposed scheme at low bit rates for contents with distinct depth transition. © 2012 IEEE.

Multi-view three-dimensional television relies on view synthesis to reduce the number of views being transmitted.  Arbitrary views can be synthesized by utilizing corresponding depth images with textures. The depth images obtained from stereo pairs or range cameras may contain erroneous values, which entail artifacts in a rendered view. Post-processing of the data may then be utilized to enhance the depth image with the purpose to reach a better quality of synthesized views. We propose a Partial Differential Equation (PDE)-based interpolation method for a reconstruction of the smooth areas in depth images, while preserving significant edges. We modeled the depth image by adjusting thresholds for edge detection and a uniform sparse sampling factor followed by the second order PDE interpolation. The objective results show that a depth image processed by the proposed method can achieve a better quality of synthesized views than the original depth image. Visual inspection confirmed the results.

Multi-view three-dimensional television requires many views, which may be synthesized from two-dimensional images with accompanying pixel-wise depth information. This depth image, which typically consists of smooth areas and sharp transitions at object borders, must be consistent with the acquired scene in order for synthesized views to be of good quality. We have previously proposed a depth image coding scheme that preserves significant edges and encodes smooth areas between these. An objective evaluation considering the structural similarity (SSIM) index for synthesized views demonstrated an advantage to the proposed scheme over the High Efficiency Video Coding (HEVC) intra mode in certain cases. However, there were some discrepancies between the outcomes from the objective evaluation and from our visual inspection, which motivated this study of subjective tests. The test was conducted according to ITU-R BT.500-13 recommendation with Stimulus-comparison methods. The results from the subjective test showed that the proposed scheme performs slightly better than HEVC with statistical significance at majority of the tested bit rates for the given contents.

Advancements in three dimensional (3D) technologies are rapidly increasing. Three Dimensional Television (3DTV) aims at creating 3D experience for the home user. Moreover, multiview autostereoscopic displays provide a depth impression without the requirement for any special glasses and can be viewed from multiple locations. One of the key issues in the 3DTV processing chain is the content generation from the available input data format video plus depth and multiview video plus depth. This data allows for the possibility of producing virtual views using depth-image-based rendering. Although depth-image-based rendering is an efficient method, it is known for appearance of artifacts such as cracks, corona and empty regions in rendered images. While several approaches have tackled the problem, reducing the artifacts in rendered images is still an active field of research.   Two problems are addressed in this thesis in order to achieve a better 3D video quality in the context of view rendering: firstly, how to improve the quality of rendered views using a direct approach (i.e. without applying specific processing steps for each artifact), and secondly, how to fill the large missing areas in a visually plausible manner using neighbouring details from around the missing regions. This thesis introduces a new depth-image-based rendering and depth-based texture inpainting in order to address these two problems. The first problem is solved by an edge-aided rendering method that relies on the principles of forward warping and one dimensional interpolation. The other problem is addressed by using the depth-included curvature inpainting method that uses appropriate depth level texture details around disocclusions.   The proposed edge-aided rendering method and depth-included curvature inpainting methods are evaluated and compared with the state-of-the-art methods. The results show an increase in the objective quality and the visual gain over reference methods. The quality gain is encouraging as the edge-aided rendering method omits the specific processing steps to remove the rendering artifacts. Moreover, the results show that large disocclusions can be effectively filled using the depth-included curvature inpainting approach. Overall, the proposed approaches improve the content generation for 3DTV and additionally, for free view point television.

Traditional computer vision algorithms depend on information taken by visible-light cameras. But there are inherent limitations of this data source, e.g. they are sensitive to illumination changes, occlusions and background clutter. Range sensors give us 3D structural information of the scene and it’s robust to the change of color and illumination. In this thesis, we present a series of approaches which are developed using the depth information by Kinect to address the issues regarding human detection and action recognition. Taking the depth information, the basic problem we consider is to detect humans in the scene. We propose a model based approach, which is comprised of a 2D head contour detector and a 3D head surface detector. We propose a segmentation scheme to segment the human from the surroundings based on the detection point and extract the whole body of the subject. We also explore the tracking algorithm based on our detection result. The methods are tested on a dataset we collected and present superior results over the existing algorithms. With the detection result, we further studied on recognizing their actions. We present a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures. We extract the 3D skeletal joint locations from Kinect depth maps using Shotton et al.’s method. The HOJ3D computed from the action depth sequences are reprojected using LDA and then clustered into k posture visual words, which represent the prototypical poses of actions. The temporal evolutions of those visual words are modeled by discrete hidden Markov models (HMMs). In addition, due to the design of our spherical coordinate system and the robust 3D skeleton estimation from Kinect, our method demonstrates significant view invariance on our 3D action dataset. Our dataset is composed of 200 3D sequences of 10 indoor activities performed by 10 individuals in varied views. Our method is real-time and achieves superior results on the challenging 3D action dataset. We also tested our algorithm on the MSR Action3D dataset and our algorithm outperforms existing algorithm on most of the cases. / text

Due to the rapid development of 3D display market, the protection and authentication of the intellectual property rights of 3D multimedia has become an essential concern. As a consequence, the digital watermarking for 3D image and video is attracting considerable attention. The depth-image-based rendering (DIBR) technique has been playing a critical role in 3D contents representation because of its numerous advantages. A good digital watermarking algorithm should be robust to various possible attacks, including geometric distortions and compressions. And di erent from ordinary 2D digital watermarking, there are more speci c requirements for 3D watermarking, especially for DIBR 3D image watermarking. Not only the center view, but also the virtual left and right views can be illegally distributed. Therefore, the embedded watermark information should be accurately extracted from these three views individually for content authentication, even under attacks. In this thesis, we focus on the research of digital watermarking and watermarking based quality evaluation for DIBR 3D images. We first present a 2D image and video watermarking method based on contourlet transform, which is then extended to a robust contourlet-based watermarking algorithm for DIBR 3D images. The watermark is embedded into the center view by quantizing certain contourlet coe cients. The virtual left and right views are synthesized from the watermarked center view and the corresponding depth map. One advantage of our algorithm is its simplicity and practicality. However, the performance on watermark extraction needs to be further improved. As an improvement, a blind watermarking algorithm for DIBR 3D images based on feature regions and ridgelet transform is proposed. The watermarked view has good perceptual quality under both the objective and subjective image quality measures. Compared with other related and state-of-the-art methods, the proposed algorithm shows superiority in terms of watermark extraction and robustness to various attacks. Furthermore, as one of the most promising techniques for quality evaluation, a watermarking based quality evaluation scheme is developed for DIBR 3D images. The qualities of the watermarked center view and the synthesized left and right views under distortions can be estimated by examining the degradation of corresponding extracted watermarks. The simulation results demonstrate that our scheme has good performance of quality evaluation for DIBR 3D images under the attacks.

Three Dimensional Video (3DV) has become increasingly popular with the success of 3D cinema. Moreover, emerging display technology offers an immersive experience to the viewer without the necessity of any visual aids such as 3D glasses. 3DV applications, Three Dimensional Television (3DTV) and Free Viewpoint Television (FTV) are auspicious technologies for living room environments by providing immersive experience and look around facilities. In order to provide such an experience, these technologies require a number of camera views captured from different viewpoints. However, the capture and transmission of the required number of views is not a feasible solution, and thus view rendering is employed as an efficient solution to produce the necessary number of views. Depth-image-based rendering (DIBR) is a commonly used rendering method. Although DIBR is a simple approach that can produce the desired number of views, inherent artifacts are major issues in the view rendering. Despite much effort to tackle the rendering artifacts over the years, rendered views still contain visible artifacts. This dissertation addresses three problems in order to improve 3DV quality: 1) How to improve the rendered view quality using a direct approach without dealing each artifact specifically. 2) How to handle disocclusions (a.k.a. holes) in the rendered views in a visually plausible manner using inpainting. 3) How to reduce spatial inconsistencies in the rendered view. The first problem is tackled by an edge-aided rendering method that uses a direct approach with one-dimensional interpolation, which is applicable when the virtual camera distance is small. The second problem is addressed by using a depth-based inpainting method in the virtual view, which reconstructs the missing texture with background data at the disocclusions. The third problem is undertaken by a rendering method that firstly inpaint occlusions as a layered depth image (LDI) in the original view, and then renders a spatially consistent virtual view. Objective assessments of proposed methods show improvements over the state-of-the-art rendering methods. Visual inspection shows slight improvements for intermediate views rendered from multiview videos-plus-depth, and the proposed methods outperforms other view rendering methods in the case of rendering from single view video-plus-depth. Results confirm that the proposed methods are capable of reducing rendering artifacts and producing spatially consistent virtual views. In conclusion, the view rendering methods proposed in this dissertation can support the production of high quality virtual views based on a limited number of input views. When used to create a multi-scopic presentation, the outcome of this dissertation can benefit 3DV technologies to improve the immersive experience.

Depth-Image-Based Rendering (DIBR) of virtual views is a fundamental method in three dimensional 3-D video applications to produce dierent perspectives from texture and depth information, in particular the multi-viewplus-depth (MVD) format. Artifacts are still present in virtual views as a consequence of imperfect rendering using existing DIBR methods. In this paper, we propose an alternative DIBR method for MVD. In the proposed method we introduce an edge pixel and interpolate pixel values in the virtual view using the actual projected coordinates from two adjacent views, by which cracks and disocclusions are automatically lled. In particular, we propose a method to merge pixel information from two adjacent views in the virtual view before the interpolation; we apply a weighted averaging of projected pixels within the range of one pixel in the virtual view. We compared virtual view images rendered by the proposed method to the corresponding view images rendered by state-of-theart methods. Objective metrics demonstrated an advantage of the proposed method for most investigated media contents. Subjective test results showed preference to dierent methods depending on media content, and the test could not demonstrate a signicant dierence between the proposed method and state-of-the-art methods.

General 3D stereo vision is composed of two major phases. In the first phase, an image and its corresponding depth map are generated using stereo matching. In the second phase, depth-based image rendering (DIBR) is employed to generate images of different view angles. Stereo matching, a computation-intensive operation, generates the depth maps from two images captured at two different view positions. In this thesis, we present hardware designs of three different stereo matching methods: pixel-based, window-based, and dynamic programming (DP)-based. Pixel--based and window-based methods belong to the local optimization stereo matching methods while DP, one of the global optimization methods, consists of three main processing steps: matching cost computation, cost aggregation, and back-tracing. Hardware implementation of DP-based stereo matching usually requires large memory space to store the intermediate results, leading to large area cost. In this thesis, we propose a tile-based DP method by partition the original image into smaller tiles so that the processing of each tile requires smaller memory size.

Depth-Based Image Rendering (DIBR) is a popular method to generate 3D virtual image at different view positions using an image and a depth map. In general, DIBR consists of two major operations: image warping and hole filling. Image warping calculates the disparity from the depth map given some information of viewers and display screen. Hole filling is to calculate the color of pixel locations that do not correspond to any pixels in the original image after image warping. Although there are many different hole filling methods that determine the colors of the blank pixels, some undesirable artifacts are still observed in the synthesized virtual image. In this thesis, we present an approach that examines the geometry information near the region of blank pixels in order to reduce the artifacts near the edges of objects. Experimental results show that the proposed design can generate more natural shape around the edges of objects at the cost of more hardware and computation time.