Performance evaluation of scene change detection algorithms

Scene change detection algorithms become the key issues especially for video information in many digital video applications such as digital libraries and video servers. The accuracy and execution speed of the scene change detection algorithm is critical if large amounts of video data are to be processed. In this paper, we discuss the performance of the three previous proposed methods and present a new algorithm to use the histogram difference of DC images incorporating the HVS (human visual system) for fast and accurate detection. The simulation results are also presented for two test video sequences, commercials and news, to show that the proposed algorithm works better than the previous ones.