Research on Video Quality Assessment

Abstract

Objective quality assessment plays a very important role in the video applications, as they promise the means to evaluate the performance of acquisition, display, coding and communication systems. Objective video quality assessment still has a long way to go before it reaches the level of success. Perception video sequences quality metrics are of great potential benefit to the video industry. Many researchers have focused on developing digital video sequences quality metrics which produce results that accurately emulate subjective responses. However, to be widely applicable a metric must also work over a wide range of quality, and be useful for in-service quality monitoring. In this paper, we propose novel quality metrics for video sequences. The temporal correlations of video frames and the visual interest feature are considered in this method. Meanwhile the metrics are capable of capturing spatial distortions in video sequences. And they can quantify the spatial distortions and differentiate the type of distortion. Furthermore the metrics correlate well with the subjective quality measures because perception distortions of human have been taken into consideration. Experimental results show that our perceptual quality metrics performs better than the existing methods.