Abstract
In this paper the idea of Intelligent scissors is adopted for contour tracking in dynamic image sequence. Tracking contour of human can therefore be converted to tracking seed points in images by making use of the properties of the optimal path (Intelligent Edge). The main advantage of the approach is that it can handle correctly occlusions that occur frequently when human is moving. Non-Uniform Rational B-Spline (NURBS) is used to represent parametrically the contour that one wants to track. In order to track robustly the contour in images, similarity and compatibility measurements of the edge are computed as the weighting functions of optimal estimator. To reduce dramatically the computational load, an efficient method for extracting the region interested is proposed. Experiments show that the approach works robustly for sequences with frequent occlusions.
Similar content being viewed by others
References
Aggarwal J, Cai Q. Human motion analysis — A review.Computer Vision and Image Understanding, 1999, 73: 428–440.
Moeslnd T B, Granum E. A survey of computer visionbased human motion capture.Computer Vision and Image Understanding, 2001, 81: 231–236.
Hogg D. Model-based vision: A program to see a walking person.Image and Vision Computing, 1983, 1(1): 5–20.
Niyogi S A, Adelson E H. Analyzing and recognizing walking figures in XYT. InProc. Conf. Computer Vision and Pattern Recognition, 1994, pp. 469–474.
Rohr K. Human Movement Analysis Based on Explicit Motion Models. Kluwer Academic, Dordrecht/Boston, 1997, Chapter 8, pp. 171–198.
Wachter S, Nagel H-H. Tracking persons in monocular image sequences.Computer Vision and Image Understanding, 1999, 74: 174–192.
MacCormick J, Isard M. Partitioned sampling, articulated objects, and interface-quality hand tracking. InProc. ECCV, Dublin, 2000, 2: 13–19.
Kakadiaris I, Metaxas D. Model-based estimation of 3D human motion with occlusion based on active multiviewpoint selection. InProc. Conf. Computer Vision and Pattern Recognition, 1996, pp. 81–87.
Deutscher J, Davison A, Reid I. Automatic partitioning of high dimensional search spaces associated with articulated body motion capture. InProc. Conf. Computer Vision and Pattern Recognition, 2001, pp. 187–193.
Sullivan J, Blake A, MacCormick J. Object localization by Bayesian correlation. InProc. the 6th European Conference on Computer Vision, Dublin, 2000.
Chen Y, Rui Y, Huang T S. JPDAF based HMM for real-time contour tracking. InProc. Conf. Computer Vision and Pattern Recognition, Kauai, Hawaii, 2001, pp. 203–209.
Ricquebourg Y, Bouthemy P. Real-time tracking of moving persons by exploiting spatial-temporal image slices.IEEE Trans. Pattern Analysis and Machine Intelligence, 2000, 22: 797–808.
Kass M, Witkin A, Terzopoulos D. Snakes: Active contour models.Int. J. Computer Vision, 1988, 1: 321–331.
Peterfreund N. Robust tracking of position and velocity with Kalman snakes.IEEE Trans. Pattern Analysis and Machine Intelligence, 1999, 21: 564–569.
Mortensen E N, Barrett W A. Intelligent scissors for image composition. InProc. the ACM SIGGRAPH'95, Los Angeles, CA, USA, 1995, pp. 191–198.
Isard M, Blake A. Condensation — Conditional density propagation for visual tracking.International Journal of Computer Vision, 1998, 29: 2–28.
Mundy J L, Zissermann A. Geometric Invariance in Computer Vision. Artificial Intelligence Series, MIT Press, Cambridge, USA, 1992.
Wren C R, Azarbaeyjani A, Darrell T, Pentland A P. Pfinder: Real-time tracking of the human body.IEEE Trans. Pattern Analysis and Machine Intelligence, 1997, 19: 780–785.
Suauffer C, Grimson W E L. Learning patterns of activity using real-time tracking.IEEE Trans. Pattern Analysis and Machine Intelligence, 2000, 22: 747–757.
Deutscher J, Blake A, North B, Bascle B. Tracking through singularities and discontinuities by random sampling. InProc. 7th Int. Conf. Computer Vision, 1999, 2: 1144–1149.
Piegl L, Tiller W. The NURES Book, 2nd ed., Springer-Verlag, Berlin, Heidelberg, 1997.
Hearn D, Baker M P. Computer Graphics. 2nd ed., Prentice Hall, Englewood Cliffs, NJ, 1994.
Xu G, Zhang Z. Epiploar Geometry in Stereo, Motion and Object Recognition. Kluwer Academic Publisher, Boston, MA, 1996.
Saint-Marc P, Rom H, Medioni G. B-spline contour representation and symmetry detection.IEEE Trans. Pattern Analysis and Machine Intelligence, 1993, 15: 1191–1197.
Author information
Authors and Affiliations
Corresponding author
Additional information
Chun-Hong Pan received his Ph.D. degree in pattern recognition and intelligent system from Institute of Automation, the Chinese Academy of Sciences (CAS), in 2000. Then he worked on computer vision in University of Southern California in USA for one and a half years as a visiting scholar. Currently he works at National Laboratory of Pattern Recognition, Institute of Automation, CAS. His main research interest is computer vision, pattern recognition, and remote sensing.
Hong-Ping Yan received her Ph.D. degree in pattern recognition and intelligent system from Institute of Automation, CAS, in 2002. After that, she spent one year in Iwate University as an invited scientific researcher in plant modeling and visualization. Currently she works in INRIA in France as a post-doctoral. Her research topic lies in plant modeling and visualization, computer graphics, and pattern recognition.
Song-De Ma received his Ph.D. degree in image processing and computer vision from University of Paris 6 in 1983. Since 1986, he has been a professor at National Laboratory of Pattern Recognition, Institute of Automation, CAS. He has been the vice-minister of the Ministry of Science and Technology (MOST) of China since April 2000. His research interests include computer vision, computer graphics, and pattern recognition.
Rights and permissions
About this article
Cite this article
Pan, CH., Yan, HP. & Ma, SD. Parametric tracking of legs by exploiting Intelligent Edge. J. Comput. Sci. & Technol. 19, 674–683 (2004). https://doi.org/10.1007/BF02945594
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02945594