Browse > Article

A Real-Time Head Tracking Algorithm Using Mean-Shift Color Convergence and Shape Based Refinement  

Jeong Dong-Gil (Agency for Defense Development)
Kang Dong-Goo (Department of EECS and Image Information Research Center, Korea Advanced Institute of Science and Technology)
Yang Yu Kyung (KTF Technologies)
Ra Jong Beom (Department of EECS and Image Information Research Center, Korea Advanced Institute of Science and Technology)
Publication Information
Abstract
In this paper, we propose a two-stage head tracking algorithm adequate for real-time active camera system having pan-tilt-zoom functions. In the color convergence stage, we first assume that the shape of a head is an ellipse and its model color histogram is acquired in advance. Then, the min-shift method is applied to roughly estimate a target position by examining the histogram similarity of the model and a candidate ellipse. To reflect the temporal change of object color and enhance the reliability of mean-shift based tracking, the target histogram obtained in the previous frame is considered to update the model histogram. In the updating process, to alleviate error-accumulation due to outliers in the target ellipse of the previous frame, the target histogram in the previous frame is obtained within an ellipse adaptively shrunken on the basis of the model histogram. In addition, to enhance tracking reliability further, we set the initial position closer to the true position by compensating the global motion, which is rapidly estimated on the basis of two 1-D projection datasets. In the subsequent stage, we refine the position and size of the ellipse obtained in the first stage by using shape information. Here, we define a robust shape-similarity function based on the gradient direction. Extensive experimental results proved that the proposed algorithm performs head hacking well, even when a person moves fast, the head size changes drastically, or the background has many clusters and distracting colors. Also, the propose algorithm can perform tracking with the processing speed of about 30 fps on a standard PC.
Keywords
Head tracking; mean-shift; color histogram similarity; gradient-based shape similarity;
Citations & Related Records
연도 인용수 순위
  • Reference
1 S. Birchfield, 'Elliptical head tracking using intensity gradient and color histograms,' IEEE Conf. Computer Vision and Pattern Recognition, Santa Barbara, California, June 1998   DOI
2 T. Kailath, 'The divergence and. Bhattacharyya distance measures in signal selection,' IEEE Trans. Communication Technology. vol. 15, no. 1, pp. 52-60, Feb. 1996
3 I. Grinias and G. Tziritas, 'Robust pan, tilt and zoom estimation,' IEEE Int'l Conf. Digital Signal Processing, vol. 2, pp. 679-682, July 2002   DOI
4 D. Comaniciu and P. Meer, 'Mean Shift: A robust approach toward feature space analysis,' IEEE Trans. Pattern Analysis and Machine Intelligence. vol. 24, no. 5 May 2002   DOI   ScienceOn
5 S. M Smith and J. M Brady, 'ASSET-2: Real-time motion segmentation and shape tracking,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 8, pp. 814-820. Aug. 1995   DOI   ScienceOn
6 A. Lipton, 'Local application of optic flow to analyze rigid versus non-rigid motion,' Technical report CMU-RI- TR-99-13, Robotics Institute, Carnegie Mellon University, Dec. 1999.
7 A. Baumberg and D. Hogg, 'An efficient method for contour tracking using active shape models,' Proc. Workshop on Motion of Nonrigid and Articulated Objects., pp. 194-199, Los Alamitos, Calif.: IEEE CS Press, Nov. 1994   DOI
8 Comaniciu, 'Robust detection and tracking of human faces with an active camera,' IEEE Int'l Workshop on Visual Surveillance, pp. 11-18, July 2000   DOI
9 D. Comaniciu, 'Kernel-based object tracking,' IEEE Trans. Pattern Analysis and Machine Intelligence. vol. 25, no. 5, pp.564-577, May 2003   DOI   ScienceOn