PCM 2002: Advances in Multimedia Information Processing — PCM 2002 pp 791-798 | Cite as
Segmenting People in Meeting Videos Using Mixture Background and Object Models
Abstract
We have developed a meeting recorder system which captures a panoramic video of a meeting room. Segmentation of people from this video is required for tracking and retrieval applications. However, the application scenario makes it difficult to rely on the usual solution of static background initialization and purely motion-based tracking for segmenting people. In this paper, we describe a novel framework for segmenting people in these videos using adaptive Gaussian mixtures for both background and object modeling. Based on a Bayesian formulation of the problem, results of object segmentation provide feedback to the background segmentation module. Experimental results on real meeting videos are presented.
Keywords
Object Model Background Model Object Segmentation Bayesian Formulation Segmentation ModulePreview
Unable to display preview. Download preview PDF.
References
- 1.Elgammal, A., Harwood, D. and Davis, L., “Non-parametric model for background subtraction,” Proc. 6th European Conference on Computer Vision, (2000).Google Scholar
- 2.Foote, J. and Kimber, D., “FlyCam: Practical panoramic video and automatic camera control,” Proc. of Int. Conf. on Multimedia & Expo, vol.3, (2000), 1419–1422.Google Scholar
- 3.Friedman, N. and Russell, S., “Image segmentation in video sequences: a probabilistic approach,” Proc. 13th Conf. Uncertainty in Artificial Intelligence, (1997).Google Scholar
- 4.Harville, M., Gordon, G. and Woodfill, J., “Foreground segmentation using adaptive mixture models in color and depth,” ICCV Workshop on Detection and Recognition of Events in Video, (2001), 3–11.Google Scholar
- 5.Gavrila, D. M., “The Visual Analysis of Human Movement: A Survey,” Computer Vision and Image Understanding, vol. 73(1), (1999), 82–98.MATHCrossRefGoogle Scholar
- 6.Haritaoglu, I., Harwood, D. and Davis, L., “W4: Real-Time Surveillance of People and Their Activities,” IEEE PAMI, vol. 22(8), (2000), 809–830.Google Scholar
- 7.Khan, S. and Shah, M., “Tracking People in Presence of Occlusion,” Proc. of ACCV, (2000).Google Scholar
- 8.Lee, D., Erol, B., Graham, J., Hull, J. and Murata, N., “Portable Meeting Recorder,” Proc. of ACM Multimedia, (2002).Google Scholar
- 9.Lee, D., “A Bayesian Framework for Background Segmentation Based on Adaptive Gaussian Mixtures,” Proc. of Conf. On Systemics, Cybernetics and Informatics, vol. 14, (2002), 76–81.Google Scholar
- 10.Rui, T., Gupta, A. and Cadiz, J., “Viewing meetings captured by an omni-directional camera”, ACM CHI, (2001), 450–457.Google Scholar
- 11.Stauffer, C. and Grimson, W.E.L., “Adaptive background mixture models for real-time tracking,” Proc. CVPR, vol. 2, (1999), 246–252.Google Scholar
- 12.Yang, J. and Waibel, A., “A Real-Time Face Tracker,” Proc. of WACV, (1996), 142–147.Google Scholar
- 13.Yang, J., Zhu, X., Gross, R., Kominek, J., Pan, Y. and Waibel, A., “Multimodal People ID for a Multimedia Meeting Browser,” Proc. of ACM Multimedia, (1999), 159–168.Google Scholar
- 14.Waibel, A., Bett, M., Metze, F., Ries, K., Schaaf, T., Schultz, T., Soltau, H., Yu, H. and Zechner, K., “Advances in automatic meeting record creation and access”, Proc. of ICASSP, (2001), 597–600.Google Scholar
- 15.Wren, C., Azarbayejani, A., Darrel, T. and Pentland, A., “Pfinder: Real-Time Tracking of the Human Body,” IEEE PAMI, vol. 19(7), (1997), 780–785.Google Scholar