Scene Detection in Videos Using Mutual Information

Abstract:

In this paper, the new detection algorithm of scene detection based on mutual information has been presented. Our approach first detect shot boundary using mutual information. Then key frames are selected from different shots. To cluster similar shots into groups, we present a novel clustering method based on mutual information. Experiments on test video indicate that the proposed scene detection method accurately detects most of the scene boundaries while preserving a good tradeoff between recall and precision.

• Periodical: Applied Mechanics and Materials (Volumes 34-35)
• Pages: 920-926
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.34-35.920
• Online since: October 2010
• Authors: Shao Nian Huang, Zhi Yong Zhang
• Keywords: Clustering, Key Frame, Mutual Information (MI), Scene Detection

References

[1] N. Johnson and D. Hogg. Learning the distribution of object trajectories for event recognition. In BMVC '95: Proceedings of the 6th British conference on Machine vision (Vol. 2), pages583-592, Surrey, UK, UK, 1995. BMVA Press.

DOI: 10.5244/c.9.58

[2] C. Stauffer andW. E. L. Grimson. Learning patterns of activity using real-time tracking. Transactions on Pattern Analysis and Machine Intelligence, 22(8): 747-757, (2000).

DOI: 10.1109/34.868677

[3] Z. Rasheed and M. Shah, Detection and representation of scenes in videos, IEEE Trans. Multimedia, vol. 7, no. 6, pp.1097-1105, Dec. (2005).

DOI: 10.1109/tmm.2005.858392

[4] ]A. Hanjalic, R. L. Lagendijk, and J. Biemond, Automated high-level movie segmentation for advanced video-retrieval systems, IEEE Trans. Circuits Syst. Video Technol., vol. 9, no. 4, pp.580-588, June1999.

DOI: 10.1109/76.767124

[5] .

[5] M. Yeung, B. Yeo, and B. Liu, Segmentation of videos by clustering and graph analysis, Comput. Vis. Image Understand., vol. 71, no. 1, pp.94-109, July (1998).

[6] T. M. Cover and J.A. Thomas. Elements of Information Theory. John Wiley and Sons, New York, 1991. ）.

[7] Z. Cernekova,I. Pitas, and C. Nikou. Information theory-based shot cut/fade detection and video summarization[J]. IEEE Transactions on Circuits and Systems for Video Technology, 16(1): pp.82-91, (2006).

DOI: 10.1109/tcsvt.2005.856896

[8] T. Lin and H. -J. Zhang. Automatic video scene extraction by shot grouping[C]. in Proc 15th Int Conf Pattern Recognition, vol. 4. Spain, Sept. 2000. 39-42.

DOI: 10.1109/icpr.2000.902860

[9] T. Liu, H. J. Zhang, and F. Qi, A novel video key-frame extraction algorithm based on perceived motion energy model, IEEE Trans. Circuits Syst. Video Technol., vol. 13, no. 10, pp.1006-1013, Oct. (2003).

DOI: 10.1109/tcsvt.2003.816521

[10] H. C. Shih and C. L. Huang, Content-based multi-functional video retrieval system, Int. Conf. Computers in Education, pp.383-384, Jan. (2005).

[11] T. Lin and H. -J. Zhang. Automatic video scene extraction by shot grouping[C]. in Proc 15th Int Conf Pattern Recognition, vol. 4. Spain, Sept. 2000. 39-42.

DOI: 10.1109/icpr.2000.902860

[12] (Alan Hanjalic. Automated High-Level Movie Segmentation for Advanced Video-Retrieval Systems[J]. IEEE transactions on circuits and systems for video technology . 1999, (9): 580－588.

DOI: 10.1109/76.767124