Rajiv Soundararajan

Study of Subjective and Objective Quality Assessment of Video

We present the results of a recent large-scale subjective study of video quality on a collection of videos distorted by a variety of application-relevant processes. Methods to assess the visual quality of digital videos as perceived by human observers are becoming increasingly important, due to the large number of applications that target humans as the end users of video. Owing to the many approaches to video quality assessment (VQA) that are being developed, there is a need for a diverse independent public database of distorted videos and subjective scores that is freely available. The resulting Laboratory for Image and Video Engineering (LIVE) Video Quality Database contains 150 distorted videos (obtained from ten uncompressed reference videos of natural scenes) that were created using four different commonly encountered distortion types. Each video was assessed by 38 human subjects, and the difference mean opinion scores (DMOS) were recorded. We also evaluated the performance of several state-of-the-art, publicly available full-reference VQA algorithms on the new database. A statistical evaluation of the relative performance of these algorithms is also presented. The database has a dedicated web presence that will be maintained as long as it remains relevant and the data is available online.

Making a “Completely Blind” Image Quality Analyzer

An important aim of research on the blind image quality assessment (IQA) problem is to devise perceptual models that can predict the quality of distorted images with as little prior knowledge of the images or their distortions as possible. Current state-of-the-art “general purpose” no reference (NR) IQA algorithms require knowledge about anticipated distortions in the form of training examples and corresponding human opinion scores. However we have recently derived a blind IQA model that only makes use of measurable deviations from statistical regularities observed in natural images, without training on human-rated distorted images, and, indeed without any exposure to distorted images. Thus, it is “completely blind.” The new IQA model, which we call the Natural Image Quality Evaluator (NIQE) is based on the construction of a “quality aware” collection of statistical features based on a simple and successful space domain natural scene statistic (NSS) model. These features are derived from a corpus of natural, undistorted images. Experimental results show that the new index delivers performance comparable to top performing NR IQA models that require training on large databases of human opinions of distorted images. A software release is available at http://live.ece.utexas.edu/research/quality/niqe_release.zip.

RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment

We study the problem of automatic “reduced-reference” image quality assessment (QA) algorithms from the point of view of image information change. Such changes are measured between the reference- and natural-image approximations of the distorted image. Algorithms that measure differences between the entropies of wavelet coefficients of reference and distorted images, as perceived by humans, are designed. The algorithms differ in the data on which the entropy difference is calculated and on the amount of information from the reference that is required for quality computation, ranging from almost full information to almost no information from the reference. A special case of these is algorithms that require just a single number from the reference for QA. The algorithms are shown to correlate very well with subjective quality scores, as demonstrated on the Laboratory for Image and Video Engineering Image Quality Assessment Database and the Tampere Image Database. Performance degradation, as the amount of information is reduced, is also studied.

A subjective study to evaluate video quality assessment algorithms

Automatic methods to evaluate the perceptual quality of a digital video sequence have widespread applications wherever the end-user is a human. Several objective video quality assessment (VQA) algorithms exist, whose performance is typically evaluated using the results of a subjective study performed by the video quality experts group (VQEG) in 2000. There is a great need for a free, publicly available subjective study of video quality that embodies state-of-the-art in video processing technology and that is effective in challenging and benchmarking objective VQA algorithms. In this paper, we present a study and a resulting database, known as the LIVE Video Quality Database, where 150 distorted video sequences obtained from 10 different source video content were subjectively evaluated by 38 human observers. Our study includes videos that have been compressed by MPEG-2 and H.264, as well as videos obtained by simulated transmission of H.264 compressed streams through error prone IP and wireless networks. The subjective evaluation was performed using a single stimulus paradigm with hidden reference removal, where the observers were asked to provide their opinion of video quality on a continuous scale. We also present the performance of several freely available objective, full reference (FR) VQA algorithms on the LIVE Video Quality Database. The recent MOtion-based Video Integrity Evaluation (MOVIE) index emerges as the leading objective VQA algorithm in our study, while the performance of the Video Quality Metric (VQM) and the Multi-Scale Structural SIMilarity (MS-SSIM) index is noteworthy. The LIVE Video Quality Database is freely available for download1 and we hope that our study provides researchers with a valuable tool to benchmark and improve the performance of objective VQA algorithms.

Video Quality Assessment by Reduced Reference Spatio-Temporal Entropic Differencing

We present a family of reduced reference video quality assessment (QA) models that utilize spatial and temporal entropic differences. We adopt a hybrid approach of combining statistical models and perceptual principles to design QA algorithms. A Gaussian scale mixture model for the wavelet coefficients of frames and frame differences is used to measure the amount of spatial and temporal information differences between the reference and distorted videos, respectively. The spatial and temporal information differences are combined to obtain the spatio-temporal-reduced reference entropic differences. The algorithms are flexible in terms of the amount of side information required from the reference that can range between a single scalar per frame and the entire reference information. The spatio-temporal entropic differences are shown to correlate quite well with human judgments of quality, as demonstrated by experiments on the LIVE video quality assessment database.

Wireless Video Quality Assessment: A Study of Subjective Scores and Objective Algorithms

Evaluating the perceptual quality of video is of tremendous importance in the design and optimization of wireless video processing and transmission systems. In an endeavor to emulate human perception of quality, various objective video quality assessment (VQA) algorithms have been developed. However, the only subjective video quality database that exists on which these algorithms can be tested is dated and does not accurately reflect distortions introduced by present generation encoders and/or wireless channels. In order to evaluate the performance of VQA algorithms for the specific task of H.264 advanced video coding compressed video transmission over wireless networks, we conducted a subjective study involving 160 distorted videos. Various leading full reference VQA algorithms were tested for their correlation with human perception. The data from the paper has been made available to the research community, so that further research on new VQA algorithms and on the general area of VQA may be carried out.

Hybrid coding for Gaussian broadcast channels with Gaussian sources

This paper considers a degraded Gaussian broadcast channel over which Gaussian sources are to be communicated. When the sources are independent, this paper shows that hybrid coding achieves the optimal distortion region, the same as that of separate source and channel coding. It also shows that uncoded transmission is not optimal for this setting. For correlated sources, the paper shows that a hybrid coding strategy has a better distortion region than separate source-channel coding below a certain signal to noise ratio threshold. Thus, hybrid coding is a good choice for Gaussian broadcast channels with correlated Gaussian sources.

Communicating Linear Functions of Correlated Gaussian Sources Over a MAC

This paper considers the problem of transmitting linear functions of two correlated Gaussian sources over a two-user additive Gaussian noise multiple access channel. The goal is to recover this linear function within an average mean squared error distortion criterion. Each transmitter has access to only one of the two Gaussian sources and is limited by an average power constraint. In this paper, a lattice coding scheme and two lower bounds on the achievable distortion are presented. The lattice scheme achieves within a constant of a distortion lower bound if the signal-to-noise ratio is greater than a threshold. Furthermore, for the difference of correlated Gaussian sources, uncoded transmission is shown to be worse in performance to lattice coding methods for correlation coefficients above a threshold.

Adaptive Sum Power Iterative Waterfilling for MIMO Cognitive Radio Channels

In this paper, the sum capacity of the Gaussian multiple input multiple output (MIMO) cognitive radio channel (MCC) is expressed as a convex problem with finite number of linear constraints, allowing for polynomial time interior point techniques to find the solution. In addition, a specialized class of sum power iterative waterfilling algorithms is determined that exploits the inherent structure of the sum capacity problem. These algorithms not only determine the maximizing sum capacity value, but also the transmit policies that achieve this optimum. The paper concludes by providing numerical results which demonstrate that the algorithm takes very few iterations to converge to the optimum.

Estimation with a helper who knows the interference

We consider the problem of estimating a signal corrupted by independent interference with the assistance of a cost-constrained helper who knows the interference causally or noncausally. When the interference is known causally, we characterize the minimum distortion incurred in estimating the desired signal. In the noncausal case, we present a general achievable scheme for discrete memoryless systems and novel lower bounds on the distortion for the binary and Gaussian settings. Our Gaussian setting coincides with that of assisted interference suppression introduced by Grover and Sahai. Our lower bound for this setting is based on the relation recently established by Verdú between divergence and minimum mean squared error. We illustrate with a few examples that this lower bound can improve on those previously developed. Our bounds also allow us to characterize the optimal distortion in several interesting regimes. Moreover, we show that causal and noncausal estimation are not equivalent for this problem. Finally, we consider the case where the desired signal is also available at the helper. We develop new lower bounds for this setting that improve on those previously developed, and characterize the optimal distortion up to a constant multiplicative factor for some regimes of interest.