Using Mutual Information for Multi-Anchor Tracking of Human Beings
Tracking of human beings represents a hot research topic in the field of video analysis. It is attracting an increasing attention among researchers thanks to its possible application in many challenging tasks. Among these, action recognition, human/human and human/computer interaction require body-part tracking. Most of the existing techniques in literature are model-based approaches, so despite their effectiveness, they are often unfit for the specific requirements of a body-part tracker. In this case it is very hard if not impossible to define a formal model of the target. This paper proposes a multi-anchor tracking system, which works on 8 bits color images and exploits the mutual information to track human body parts (head, hands, …) without performing any foreground/background segmentation. The proposed method has been designed as a component of a more general system aimed at human interaction analysis. It has been tested on a wide set of color video sequences and the very promising results show its high potential.
KeywordsMutual Information Augmented Reality Interest Point Video Summarization Anchor Position
Unable to display preview. Download preview PDF.
- 1.Bregler, C., Malik, J.: Tracking people with twists and exponential maps. In: IEEE Computer Vision and Pattern Recognition, pp. 8–15 (1998)Google Scholar
- 3.Dame, A., Marchand, E.: Accurate real-time tracking using mutual information. In: 9th IEEE International Symposium on Mixed and Augmented Reality, pp. 47–56 (2010)Google Scholar
- 4.Haritaoglu, I., Harwood, D., Davis, L.S.: W4: real-time surveillance of people and their activities. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(8), pp. 809–830 (2000)Google Scholar
- 8.Okada, R., Shirai, Y., Miura, J.: Tracking a person with 3D motion by integrating optical flow and depth. In: 4th IEEE International Conference on Automatic Face and Gesture Recognition, France, pp. 336–341 (2000)Google Scholar
- 9.Qian, R.J., Huang, T.S.: Estimating articulated motion by decomposition, Time-Varying Image Processing and Moving Object Recognition, 3-V. Cappellini (Ed.), pp. 275–286 (1994)Google Scholar
- 10.Sato, K., Aggarwal, J.K.: Tracking and recognizing two-person interactions in outdoor image sequences. In: IEEE Workshop on Multi-Object Tracking, Canada, pp. 87–94. (2001)Google Scholar
- 13.Wren, C., Azarbayejani, A., Darrell, T., Pentland, A.: Pfinder: real-time tracking of the human body. IEEE Trans. on Pattern Analysis and Machine Intelligence 19(7), 780–785 (1997)Google Scholar