In order to speedup the encoding process of H.264/AVC and Scalable Video Coding (SVC), Temporal and Spatial Correlation-based Merging and Splitting (TSCMS) fast mode decision algorithm and Coded Block Pattern (CBP)-based fast mode decision algorithm are proposed in this thesis. TSCMS and CBP-based fast mode decision algorithms are applied to H.264/AVC and SVC, respectively. In TSCMS, Temporal Correlation (TC) is used to predict the Motion Vectors (MVs) of 8¡Ñ8 blocks in each macroblock. In addition, the merging and splitting procedure is adopted to predict the motion vectors of other blocks. Afterwards, the spatial correlation is performed to merge 16¡Ñ16 blocks instead of the conventional merge scheme. CBP value is the syntax used at each Macroblock (MB) header to indicate whether an MB contains residual information or not in CBP-based fast mode decision algorithm. The proposed algorithm can exclude the invalid modes for the mode prediction of the current MB in Enhancement Layer (EL) through the CBP values and MB modes of adjacent MBs in EL and the co-located Base Layer (BL) MB modes. Experimental results show that the proposed algorithms reduce computations significantly with negligible PSNR degradation and bit increase when compared to JM 12.3, JSVM 9.12, and the other existing methods.

Thesis (M.Eng.)--Memorial University of Newfoundland, 2001. / Bibliography: leaves 108-112.

Thesis (Ph. D.)--University of Washington, 2001. / Vita. Includes bibliographical references (p. 169-184).

Thesis (M. Phil.)--Hong Kong University of Science and Technology, 2003. / Includes bibliographical references (leaves 57-58). Also available in electronic version. Access restricted to campus users.

Thesis (M. Phil.)--Hong Kong University of Science and Technology, 2003. / Includes bibliographical references (leaves 66-68). Also available in electronic version. Access restricted to campus users.

Includes bibliographical references (p. 65-67).

Bandwidth-intensive video streaming applications occupy an overwhelming fraction of bandwidth-limited wireless network traffic. Compressed video data are highly structured and the psycho-visual perception of distortions and losses closely depends on that structure. This dissertation exploits the inherent video data structure to develop perceptually-optimized transmission paradigms at different protocol layers that improve video quality of experience, introduce error resilience, and enable supporting more video users. First, we consider the problem of network-wide perceptual quality optimization whereby different video users with (possibly different) real-time delay constraints are sharing wireless channel resources. Due to the inherently stochastic nature of wireless fading channels, we provide statistical delay guarantees using the theory of effective capacity. We derive the resource allocation policy that maximizes the sum video quality and show that the optimal operating point per user is such that the rate-distortion slope is the inverse of the supported video source rate per unit bandwidth, termed source spectral efficiency. We further propose a scheduling policy that maximizes the number of scheduled users that meet their QoS requirement. Next, we develop user-level perceptual quality optimization techniques for non-scalable video streams. For non-scalable videos, we estimate packet loss visibility through a generalized linear model and use for prioritized packet delivery. We solve the problem of mapping video packets to MIMO subchannels and adapting per-stream rates to maximize the total perceptual value of successfully delivered packets per unit time. We show that the solution enables jointly reaping gains in terms of improved video quality and lower latency. Optimized packet-stream mapping enables transmission of more relevant packets over more reliable streams while unequal modulation opportunistically increases the transmission rate on the stronger streams to enable low latency delivery of high priority packets. Finally, we develop user-level perceptual quality optimization techniques for scalable video streams. We propose online learning of the mapping between packet losses and quality degradation using nonparametric regression. This quality-loss mapping is subsequently used to provide unequal error protection for different video layers with perceptual quality guarantees. Channel-aware scalable codec adaptation and buffer management policies simultaneously ensure continuous high-quality playback. Across the various contributions, analytic results as well as video transmission simulations demonstrate the value of perceptual optimization in improving video quality and capacity. / text

published_or_final_version / Electrical Engineering / Master / Master of Philosophy

No description available.

The ability to track articulated human motion in video sequences is essential for applications ranging from biometrics, virtual reality, human-computer interfaces and surveillance. The work presented in this thesis focuses on tracking and analysing human motion in terms of MPEG-4 Body Animation Parameters, in the context of a model-based coding scheme. Model-based coding has emerged as a potential technique for very low bit-rate video compression. This study emphasises motion reconstruction rather than photorealistic human body modelling, consequently a 3-D skeleton with 31 degrees-of-freedom was used to model the human body. Compression is achieved by analysing the input images in terms of the known 3-D model and extracting parameters that describe the relative pose of each segment. These parameters are transmitted to the decoder which synthesises the output by transforming the default model into the correct posture. The problem comprises two main aspects: 3-D human motion capture and pose description. The goal of the 3-D human motion capture component is to generate 3-D locations of key joints on the human body without the use of special markers or sensors placed on the subject. The input sequence is acquired by three synchronised and calibrated CCD cameras. Digital image matching techniques including cross-correlation and least squares matching are used to find spatial correspondences between the multiple views as well as temporal correspondences in subsequent frames with sub-pixel accuracy. The tracking algorithm automates the matching process examining each matching result and adaptively modifying matching parameters. Key points must be manually selected in the first frame, following which the tracking commences without the intervention of the user, employing the recovered 3-D motion of the skeleton model for prediction of future states. Epipolar geometry is exploited to verify spatial correspondences in each frame before the 3-D locations of all joints are computed through triangulation to construct the 3-D skeleton. The pose of the skeleton is described by the MPEG-4 Body Animation Parameters. The subject's motion is reconstructed by applying the animation parameters to a simplified version of the default MPEG-4 skeleton. The tracking algorithm may be adapted to 2-D tracking in monocular sequences. An example of 2-D tracking of facial expressions demonstrates the flexibility of the algorithm. Further results involving tracking separate body parts demonstrate the advantage of multiple views and the benefit of camera calibration, which simplifies the generation of 3-D trajectories and the estimation of epipolar geometry. The overall system is tested on a walking sequence where full body motion capture is performed and all 31 degrees-of freedom of the tracked model are extracted. Results show adequate motion reconstruction (i.e. convincing to most human observers), with slight deviations due to lack of knowledge of the volumetric property of the human body. / Thesis (M.Sc.Eng.)-University of KwaZulu-Natal, Durban, 2005.