Abstract:To realize real-time and non-intrusive quality monitoring for networked video, a content-adaptive packet-layer model for quality assessment is proposed. Considering the fact that the coding distortion of a video is dependent not only on the bit-rate but also on the motion characteristic of the video content, temporal complexity is evaluated and incorporated in quality assessment in the proposed model. Since very limited information is available for a packet-layer model, an adaptive method for frame type detection is first applied. Then the temporal complexity which reflects the motion characteristic of the video content is estimated using the ratio of the bit-rate for coding I frames and P frames. The estimated temporal complexity is incorporated in the proposed model, making it adaptive to different video content. Experimental results show that the proposed model achieves an advanced performance in comparison with the ITU-T G.1070 model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.