Video quality

About: Video quality is a research topic. Over the lifetime, 13143 publications have been published within this topic receiving 178307 citations.

Performance bounds for peer-assisted live streaming

Abstract: Peer-assisted streaming is a promising way for service providers to offer high-quality IPTV to consumers at reasonable cost. In peer-assisted streaming, the peers exchange video chunks with one another, and receive additional data from the central server as needed. In this paper, we analyze how to provision resources for the streaming system, in terms of the server capacity, the video quality, and the depth of the distribution trees that deliver the content. We derive the performance bounds for minimum server load, maximum streaming rate, and minimum tree depth under different peer selection constraints. Furthermore, we show that our performance bounds are actually tight, by presenting algorithms for constructing trees that achieve our bounds.

CloudStream: Delivering high-quality streaming videos through a cloud-based SVC proxy

Abstract: Existing media providers such as YouTube and Hulu deliver videos by turning it into a progressive download. This can result in frequent video freezes under varying network dynamics. In this paper, we present CloudStream: a cloud-based video proxy that can deliver high-quality streaming videos by transcoding the original video in real time to a scalable codec which allows streaming adaptation to network dynamics. The key is a multi-level transcoding parallelization framework with two mapping options (Hallsh-based Mapping and Lateness-first Mapping) that optimize transcoding speed and reduce the transcoding jitters while preserving the encoded video quality. We evaluate the performance of CloudStream on our campus cloud testbed.

Statistical multiplexed video encoding using pre-encoding a priori statistics and a priori and a posteriori statistics

Abstract: A statistical multiplexing apparatus and method for generating and combining a plurality of encoded video bit streams. A storage device contains pre-stored a priori statistics indicative of the encoding complexity of the video signals from which the encoded video bit streams will be generated. The pre-stored a priori statistics may include inter-pixel differences in the same picture or between multiple pictures or pre-encoding a priori statistics generated during a preliminary encoding of the video signals. Examples of pre-encoding a priori statistics include the number of bits per picture at a given quantization level, an average quantization level, picture types, scene change locations and repeat field for one or more of the video bit streams. The video signals are applied to encoders which compress the signals in accordance with bit allocation decisions generated by a statistics computer. The statistics computer uses only pre-encoding a priori statistics from the storage device to generate bit allocation decisions. Alternatively, the statistics computer may use any type of a priori statistics in conjunction with a posteriori statistics received from the encoders in allocating bits. The resulting compressed video bit streams are applied to a multiplexer and combined into a single multiplexed bit stream for transmission on a single channel. The statistics computer thus has access to additional information regarding the encoding complexity of the video bit streams to be encoded and combined, and can therefore generate more accurate bit allocations and better maintain consistent video quality across multiple encoded bit streams.

Quality analysis for 3D video using 2D video quality models

Abstract: The 3D (3-dimensional) video technologies are emerging to provide more immersive media content compared to conventional 2D (2-dimensional) video applications. More often 3D video quality is measured using rigorous and time-consuming subjective evaluation test campaigns. This is due to the fact that 3D video quality can be described as a combination of several perceptual attributes such as overall image quality, perceived depth, presence, naturalness and eye strain, etc. Hence this paper investigates the relationship between subjective quality measures and several objective quality measures like PSNR, SSIM, and VQM for 3D video content. The 3D video content captured using both stereo camera pair (two cameras for left and right views) and colour-and-depth special range cameras are considered in this study. The results show that, VQM quality measures of individual left and right views (rendered left and right views for colour-and-depth sequences) can be effectively used in predicting the overall image quality and statistical measures like PSNR and SSIM of left and right views illustrate good correlations with depth perception of 3D video.

Quality Assessment of In-the-Wild Videos

Abstract: Quality assessment of in-the-wild videos is a challenging problem because of the absence of reference videos and shooting distortions. Knowledge of the human visual system can help establish methods for objective quality assessment of in-the-wild videos. In this work, we show two eminent effects of the human visual system, namely, content-dependency and temporal-memory effects, could be used for this purpose. We propose an objective no-reference video quality assessment method by integrating both effects into a deep neural network. For content-dependency, we extract features from a pre-trained image classification neural network for its inherent content-aware property. For temporal-memory effects, long-term dependencies, especially the temporal hysteresis, are integrated into the network with a gated recurrent unit and a subjectively-inspired temporal pooling layer. To validate the performance of our method, experiments are conducted on three publicly available in-the-wild video quality assessment databases: KoNViD-1k, CVD2014, and LIVE-Qualcomm, respectively. Experimental results demonstrate that our proposed method outperforms five state-of-the-art methods by a large margin, specifically, 12.39%, 15.71%, 15.45%, and 18.09% overall performance improvements over the second-best method VBLIINDS, in terms of SROCC, KROCC, PLCC and RMSE, respectively. Moreover, the ablation study verifies the crucial role of both the content-aware features and the modeling of temporal-memory effects. The PyTorch implementation of our method is released at https://github.com/lidq92/VSFA.