A unified approach to scene change detection in uncompressed and compressed video

There is an urgent need to extract key information automatically from video for the purposes of indexing, fast retrieval and scene analysis. To support this vision, reliable scene change detection algorithms must be developed. This paper describes a novel unified algorithm for scene change detection in uncompressed and MPEG-2 compressed video sequences using statistical features of images. Results on video of various content types are reported and validated with the proposed scheme in uncompressed and MPEG-2 compressed video. Furthermore, results show that the accuracy of the detected transitions is above 95% and 90% for uncompressed and MPEG-2 compressed video respectively.