Real-time Video Quality Assessment for China Mobile Multimedia Broadcasting

A real-time system of objective quality assessment for compressed video over CMMB is creatively designed and implemented in this paper. It can evaluate the video quality of CMMB video streams and get a good corresponding with the subjective assessments results. At first, we extract features directly from the video streams as the inputs of our model. Then, using a linear algorithm, those extracted features from the video streams and the corresponding subjective assessments are linked in our method in order to obtain the reliable objective assessment. The experimental results show that our model can achieve good performance for the streaming video quality prediction over CMMB. In addition, since our model does not require the source picture, or the decoded processing, it is also suitable for many other real-time video applications.