Content-aware video quality assessment: predicting human perception of quality using peak signal to noise ratio and spatial/temporal activity

Abstract

Since the end-user of video-based systems is often a human observer, prediction of human perception of quality (HPoQ) is an important task for increasing the user satisfaction. Despite the large variety of objective video quality measures, one problem is the lack of generalizability. This is mainly due to the strong dependency between HPoQ and video content. Although this problem is well-known, few existing methods directly account for the influence of video content on HPoQ. This paper propose a new method to predict HPoQ by using simple distortion measures and introducing video content features in their computation. Our methodology is based on analyzing the level of spatio-temporal activity and combining HPoQ content related parameters with simple distortion measures. Our results show that even very simple distortion measures such as PSNR and simple spatio-temporal activity measures lead to good results. Results over four different public video quality databases show that the proposed methodology, while faster and simpler, is competitive with current state-of-the-art methods, i.e., correlations between objective and subjective assessment higher than 80% and it is only two times slower than PSNR

Content-aware objective video quality assessment

“…First, we perform an extensive experimental evaluation based on a total of four VQMs, each tested on 696 distorted video sequences. The four tested VQMs comprise three newly presented here [structural similarity index measure (SSIM), 27 standardized method for objectively measuring video quality (SOVQM), 7 and video quality assessment by decoupling detail losses and additive impairments (VQAD) 10 26. Second, we describe the differences between the proposed methodology and other state-of-the-art methodologies which explicitly include content related indexes in their computation.…”

“…This can be seen as a disadvantage of their approach knowing that PVQ is affected by both spatial and temporal content related indexes 13 and that previous works have shown that PVQ and PSNR is better modeled by using an S-shape function which takes into account the saturation effect of the human vision. 15,26,31 Khan et al…”

“…26 in three main directions. First, we perform an extensive experimental evaluation based on a total of four VQMs, each tested on 696 distorted video sequences.…”

“…26. That approach involves offline training of the mapping functions' parameters and their relationship to video content characteristics.…”

“…28 In that work, an exponential function was used as mapping function that, unlike Ref. 26, does not take into account the saturation effect of human vision. In addition, Ref.…”