Saliency Based Assessment of Videos from Frame-Wise Quality Measures

Video quality assessment aims to compute the formalmeasure of perceived video degradation when video is passedthrough a video transmission/processing system. Most of theexisting video quality measures extend Image Quality Measuresby applying them on each frame and later combining the qualityvalues of each frame to get the quality of the entire video. Whencombining the quality values of frames, a simple average or invery few metrics, weighted average has been traditionally used. In this work, saliency of a frame has been used to compute theweight required for each frame to obtain the quality value ofvideo. The goal of every objective quality metric is to correlateas closely as possible to the perceived quality, and the objectiveof saliency is parallel to this as the saliency values should matchthe human perception. Hence we have experimented by usingsaliency to get the final video quality. The idea is demonstratedby using a number of state of art quality metrics on some of thebenchmark datasets.