This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Region Tracking via Level Set PDEs without Motion Computation
July 2002 (vol. 24 no. 7)
pp. 947-961

Tracking regions in an image sequence is a challenging and difficult problem in image processing and computer vision and at the same time, one that has many important applications: automated video surveillance, video database search and retrieval, automated video editing, etc. So far, numerous approaches to region tracking have been proposed. Many of them suffer from excessive constraints imposed on the motion of the region being tracked and need an explicit motion model (e.g., affine, Euclidean). Some, which do not need a parametrized motion model, rely instead on a dense motion field. By and large, most rely on some kind or other of motion information. Those which do not use any motion information instead use a model of the region being tracked, typically by assuming strong intensity boundaries, or constraining the shape of the region to belong to a parametrized family of shapes. In this paper, we propose a novel approach to region tracking that is derived from a Bayesian formulation. The novelty of the approach is twofold: First, no motion field or motion parameters need to be computed. This removes a major burden since accurate motion computation has been and remains a challenging problem and the quality of region tracking algorithms based on motion critically depends on the computed motion fields and parameters. The second novelty of this approach, is that very little a priori information about the region being tracked is used in the algorithm. In particular, unlike numerous tracking algorithms, no assumption is made on the strength of the intensity edges of the boundary of the region being tracked, nor is its shape assumed to be of a certain parametric form. The problem of region tracking is formulated as a Bayesian estimation problem and the resulting tracking algorithm is expressed as a level set partial differential equation. We present further extensions to this partial differential equation, allowing the possibility of including additional information in the tracking process, such as priors on the region's intensity boundaries and we present the details of the numerical implementation. Very promising experimental results are provided using numerous real image sequences with natural object and camera motion.

[1] I.K. Sethi and R. Jain, “Finding Trajectories of Feature Points in a Monocular Image Sequence,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 1, pp. 56-73, 1987.
[2] J.L. Crowley, P. Stelmaszyk, and C. Discours, “Measuring Image Flow by Tracking Edge Lines,” Proc. Second Int'l Conf. Computer Vision, pp. 658-664, Dec. 1988.
[3] R. Deriche and O.D. Faugeras, “Tracking Line Segments,” Proc. First European Conf. Computer Vision, pp. 259-268, Apr. 1990.
[4] D.G. Lowe, “Robust Model-Based Motion Tracking through the Integration of Search and Estimation,” Int'l J. Computer Vision, vol. 8, no. 2, pp. 113-122, 1992.
[5] F. Leymarie and M. Levine, "Tracking deformable objects in the plane using an active contour model, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 6, pp. 617-634, June 1993.
[6] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Proc. First Int'l Conf. Computer Vision, pp. 259-268, 1987.
[7] R. Curwen and A. Blake, Active Vision. MIT Press, pp. 39-57, 1992.
[8] D. Terzopoulos and R. Szeliski, Active Vision. MIT Press, pp. 3-20, 1992.
[9] A. Blake, R. Curwen, and A. Zisserman, "Affine-Invariant Contour Tracking with Automatic Control of Spatiotemporal Scale," IEEE Proc. Fourth Int'l Conf. Computer Vision, pp. 66-75,Berlin, Germany, May 1993.
[10] R. Deriche and T. Blaszka, "Recovering and Characterizing Image Features Using an Efficient Model Based Approach," Proc. Computer Vision and Pattern Recognition, pp. 530-535,New York, June 1993.
[11] M. Bertalmio, G. Sapiro, and G. Randall, “Morphing Active Contours: A Geometric Approach to Topology-Independent Image Segmentation and Tracking,” Proc. Int'l Conf. Image Processing, vol. III, pp. 318-322, 1998.
[12] A.-R. Mansouri, A. Olivier, and J. Konrad, “Topology-Independent Region Tracking with Level Sets,” Proc. Int'l Conf. Image Processing, vol. III, pp. 66-69, 2000.
[13] N. Paragios and R. Deriche, Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, pp. 1-15, 2000.
[14] S.C. Zhu and A. Yuille, “Region Competition: Unifying Snakes, Region Growing and Bayes/MDL for Multiband Image Segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, pp. 884-900, 1996.
[15] J.A. Sethian, Level Set Methods. Cambridge Univ. Press, 1998.
[16] A.-R. Mansouri, T. Chomaud, and J. Konrad, “A Comparative Evaluation of Algorithms for Fast Computation of Level Set PDEs with Applications to Motion Segmentation,” Proc. Int'l Conf. Image Processing, vol. III, pp. 636-639, 2001.
[17] D. Comaniciu and V. Ramesh, “Mean Shift Optimal Prediction for Efficient Object Tracking,” Proc. Int'l Conf. Image Processing, vol. III, pp. 70-73, 2000.
[18] S. C. Zhu, “Embedding Gestalt Laws in Markov Random Fields,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 11, Nov. 1999.

Index Terms:
Region tracking, Bayesian estimation, level set equations, image sequence analysis.
Citation:
Abdol-Reza Mansouri, "Region Tracking via Level Set PDEs without Motion Computation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 947-961, July 2002, doi:10.1109/TPAMI.2002.1017621
Usage of this product signifies your acceptance of the Terms of Use.