Tracking of Moving Heads in Cluttered Scenes from Stereo Vision
Tracking a number of persons moving in cluttered scenes is an important issue in computer vision. It is the first step of automatic video-based surveillance systems. In this paper we present a binocular vision system using stereo information for moving head detection and tracking. After background subtraction, the remained foreground disparity image is used as a mask to delete background clutter as well as to reduce the search space, which greatly improve the tracking performance when occlusion happens. With a local sampling method together with the stereo information obtained, we are now able to reliably detect and track people in cluttered natural environments at about 5 Hz on standard PC hardware.
Unable to display preview. Download preview PDF.
- 1.C. Wren, A. Azarbayejani, T. Darrell, A. Pentland: Pfinder: real-time tracking of the human body. In Proc. 2nd Int. Conf. on Automatic Face and Gesture Recognition (1996) 51–56. 148Google Scholar
- 2.J. Costeira, T. Kanade: A multi-body factorization method for motion analysis. In Proc. 5th Int. Conf. on Computer Vision (1995) 1071–1076. 148Google Scholar
- 3.P.H. S. Torr: An assessment of information criteria for motion model selection. In Proc. Conf. Computer Vision and Pattern Recognition (1997) 148Google Scholar
- 4.G. Hager, K. Toyama: X vision: combining image warping and geometric constraints for fast visual tracking. In Proc. 4th European Conf. Computer Vision, Vol. 12, (1996) 507–517. 148Google Scholar
- 5.A. Blake, M. Isard, D. Reynard: Learning to track the visual motion of contours. J. Artificial Intelligence 78, (1995), 101–134. 148Google Scholar
- 6.M. Isard. A. Blake: Contour tracking by stochastic propagation of conditional density. In Proc. 4th European Conf. Computer Vision, Cambridge, England, (April 1996) 343–356. 148Google Scholar
- 7.C. Rasmussen, G. D. Hager: Joint probabilistic techniques for tracking multi-part objects. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Santa Barbara, CA (1998) 16–21. 148Google Scholar
- 8.C. Eveland, K. Konolige, R. C. Bolles: Background modeling for segmentation of video-rate stereo sequences. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (June 1998) 266–271. 149Google Scholar
- 10.A. Blake, M. Isard: “Active Contours”. Berlin, New York: Springer, (1998), 74–79. 152Google Scholar