An Effective and Fast Scene Change Detection Algorithm for MPEG Compressed Videos
In this paper, we propose an effective and fast scene change detection algorithm directly in MPEG compressed domain. The proposed scene change detection exploits the MPEG motion estimation and compensation scheme by examining the prediction status for each macro-block inside B frames and P frames. As a result, locating both abrupt and dissolved scene changes is operated by a sequence of comparison tests, and no feature extraction or histogram differentiation is needed. Therefore, the proposed algorithm can operate in compressed domain, and suitable for real-time implementations. Extensive experiments illustrate that the proposed algorithm achieves up to 94% precision for abrupt scene change detection and 100% for gradual scene change detection. In comparison with similar existing techniques, the proposed algorithm achieves superiority measured by recall and precision rates.
KeywordsMotion Estimation Precision Rate Scene Change Scene Change Detection Error Concealment Method
Unable to display preview. Download preview PDF.
- 1.Totterdell, A.: An algorithm for detecting and classifying scene breaks in MPEG video bit streams, Technical report, No.5 (September 1998)Google Scholar
- 3.Akrivas, G., Doulamis, N.D., Doulamis, A.D., Kollias, S.D.: Scene detection methods for MPEG-encoded video signals. In: Proceeding of the MELECON 2000 Mediterranean Electrotechnical Conference, Nicosia, Cyprus (May 2000)Google Scholar
- 4.Smeaton, A., et al.: An evaluation of alternative techniques for automatic detection of shot boundaries in digital video. In: Proc. Irish Machine Vision and Image Processing Conference (IMVIP 1999), Dublin, Ireland, September 8-9, pp. 45–62 (1999)Google Scholar
- 9.Saez, E., Benavides, J.I., Guil, N.: Reliabele time scene change detection in MPEG compressed video. In: ICME 2004, Taipei, June 27-30, pp. 567–570 (2004)Google Scholar
- 11.Kiranyaz, S., Caglar, K., Cramariuc, B., Gabbouj, M.: Unsupervised scene change detection techniques in features domain via clustering and elimination. In: Proc. of Tyrrhenian International Workshop on Digital Communications, Capri, Italy, September 8-11 (2002)Google Scholar
- 12.Fernando, W.A.C., Canagarajah, C.N., Bull, D.R.: Scene change detection algorithms for content-based video indexing and retrival. Electronics&communication engineering journal, 117–126 (June 2001)Google Scholar
- 14.Nang, J., Hong, S., Ihm, Y.: An efficient video segmentation scheme for MPEG video stream using macroblock information. In: Proceedings of the 7th ACM International Conference on Multimedia 1999, Orlando, FL, USA, October 30 - November 5, vol. 1, pp. 23–26. ACM, New York (1999)CrossRefGoogle Scholar
- 15.Chen, S.-C., Shyu, M.-L., Zhang, C.-C., Kashyap, R.L.: Video scene change detection method using unsuper segmentation and object tracking. In: IEEE International Conference on Multimedia and Expo. (ICME), pp. 57–60 (2001)Google Scholar
- 16.Oh, J., Hua, K.A., Liang, N.: A content-based scene change detection and classification technique using background tracking. In: Proc. of IS&T/SPIE Conference on Multimedia Computing and Networking 2000, San Jose, CA, January 2000, pp. 254–265 (2000)Google Scholar
- 17.Han, S.H.: Shot detection combining bayesian and structural information. In: Storage and Retrieval for Media Databases 2001, vol. 4315, December 2001, pp. 509–516 (2001)Google Scholar