Quality-aware video based on robust embedding of intra- and inter-frame reduced-reference features

With the rapid development of network visual communications, there is an urgent need of effective and efficient video quality assessment (VQA) methods for quality control and resource allocation purposes. In this paper, a spatial and temporal reduced-reference (RR) VQA measure is combined with a robust video watermarking approach, leading to a quality-aware video (QAV) system. At the sender side, both intra- and inter-frame RR features are calculated from the original video based on statistical models of natural video. This is followed by error control coding to improve robustness. The encoded features are then embedded invisibly into the same video signal using a robust angle quantization index modulation based watermarking method in 3D discrete cosine transform domain. At the receiver side, the RR features are extracted and decoded from the distorted video and employed to predict the perceptual degradation of the video signal. Experimental results demonstrate the applicability of the proposed approach to a wide range of distortion types and levels.