Efficient and reliable scene change detection in MPEG compressed video

This work presents a novel metric and a reliable algorithm for abrupt scene change detection. The new frame difference metric measures motion and content change across the video by using the motion vector and macroblock information in the MPEG compressed domain. With this new metric, a reliable scene change detection algorithm is discussed. Experimental results reveal that our scene change detection algorithm can successfully reduce the false alarms caused by local frame motion activity and at the same time increase the recall by amplifying the acceptance probability of the reliable scene change candidate.

[1]  Ajay Divakaran,et al.  MPEG-7 visual motion descriptors , 2001, IEEE Trans. Circuits Syst. Video Technol..

[2]  Hain-Ching Liu,et al.  Automatic determination of scene changes in MPEG compressed video , 1995, Proceedings of ISCAS'95 - International Symposium on Circuits and Systems.

[3]  Byoungchul Ahn,et al.  Robust algorithm for scene analysis on compressed video , 1999, 1999 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM 1999). Conference Proceedings (Cat. No.99CH36368).

[4]  Shih-Fu Chang,et al.  Scene change detection in an MPEG-compressed video sequence , 1995, Electronic Imaging.

[5]  Boon-Lock Yeo,et al.  Rapid scene analysis on compressed video , 1995, IEEE Trans. Circuits Syst. Video Technol..

[6]  Jurg Keller,et al.  Automatic video segmentation in the compressed domain , 2002, Proceedings, IEEE Aerospace Conference.

[7]  Xinying Wang,et al.  Scene abrupt change detection , 2000, 2000 Canadian Conference on Electrical and Computer Engineering. Conference Proceedings. Navigating to a New Era (Cat. No.00TH8492).

[8]  Jane Hunter,et al.  An overview of the MPEG-7 Description Definition Language (DDL) proposals , 2000, Signal Process. Image Commun..

[9]  SangKeun Lee,et al.  Efficient scene segmentation for content-based indexing in the compressed domain , 2001, 2001 IEEE Fourth Workshop on Multimedia Signal Processing (Cat. No.01TH8564).