Abstract
A new approach for tracking a non-rigid target is presented. Tracking is formulated as a Maximum A Posteriori (MAP) segmentation problem where each pixel is assigned a binary label indicating whether it belongs to the target or not. The label field is modeled as a Markov Random Field whose Gibbs energy comprises three terms. The first term quantifies the error in matching the object model with the object’s appearance as given by the current segmentation. Coping with the deformations of the target while avoiding optical flow computation is achieved by marginalizing this likelihood over all possible motions per pixel. The second term penalizes the lack of continuity in the labels of the neighbor pixels, thereby encouraging the formation of a smoothly shaped object mask, without holes. Finally, for the sake of increasing robustness, the third term constrains the object mask to assume an elliptic shape model with unknown parameters. MAP optimization is performed iteratively, alternating between estimating the shape parameters and recomputing the segmentation using updated parameters. The latter is accomplished by discriminating each pixel via a simple hypothesis test. We demonstrate the efficiency of our approach on synthetic and real video sequences.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hager, G., Belhumeur, P.: Efficient region tracking with parametric models of geometry and illumination. IEEE T-PAMI 20, 1025–1039 (1998)
Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE T-PAMI 25, 564–575 (2003)
Zhang, H., Huang, W., Huang, Z., Li, L.: Affine object tracking with kernel-based spatial-color representation. Comp. Vision and Pattern Recog.(CVPR) 1, 200–293 (2005)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. Intl. Journal Comp. Vis. 1, 321–332 (1988)
Moelich, M., Chan, T.: Tracking objects with the Chan-Vese algorithm. Technical report 03-14, Computational Applied Mathematics, UCLA, Los Angeles (2003)
Mansouri, A.: Region tracking via level set PDEs without motion computation. IEEE T-PAMI 24, 947–961 (2002)
Paragios, N., Deriche, R.: Variational Principles in Optical Flow Estimation and Tracking. In: Osher, S., Paragios, N. (eds.) Geometric Level Set Methods in Imaging, Vision, and Graphics, pp. 299–317. Springer, Heidelberg (2003)
Freedman, D., Zhang, T.: Active contours for tracking distributions. IEEE T-IP 13, 518–526 (2004)
Yilmaz, A., Li, X., Shah, M.: Contour-based object tracking with occlusion handling in video acquired using mobile cameras. IEEE T-PAMI 26, 1531–1536 (2004)
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Intl. Journal Comp. Vis. 22, 61–79 (1997)
Malladi, R., Sethian, J., Vemuri, B.: Shape modeling with front propagation: A level set approach. IEEE T-PAMI 17, 158–175 (1995)
Zhu, S., Yuille, A.: Region competition: Unifying snakes, region growing, and bayes/MDL for multiband image segmentation. IEEE T-PAMI 18, 884–900 (1996)
Chan, T., Vese, L.: Active contours without edges. IEEE T-IP 10, 266–277 (2001)
Cremers, D.: Dynamical statistical shape priors for level set-based tracking. IEEE T-PAMI 28, 1262–1273 (2006)
Li, S.Z.: Markov Random Field Modeling in Computer Vision. Springer, Heidelberg (1995)
Freedman, D., Zhang, T.: Interactive graph cut based segmentation with shape priors. Comp. Vision Pattern Recog. (CVPR) 1, 755–762 (2005)
Slabaugh, G., Unal, G.: Graph cuts segmentation using an elliptical shape prior. In: Intl. Conf. Image Proc. pp. 1222–1225 (2005)
Boykov, Y., Jolly, M.: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: Intl. Conf. Comp. Vision (ICCV), vol. 1, pp. 105–112 (2001)
Leichter, I., Lindenbaum, M., Rivlin, E.: Bittracker - a bitmap tracker for visual tracking under very general conditions. Technion, Computer Science Department, Technical Report CIS-2006-03.revised (2006)
Besag, J.: On the statistical analysis of dirty pictures. J. Royal Stat. Soc. B 48, 259–302 (1986)
Greig, D., Porteous, B., Seheult, A.: Exact maximum a posteriori estimation for binary images. J. Royal Stat. Soc. B 51, 271–279 (1989)
Aach, T., Kaup, A.: Bayesian algorithms for adaptive change detection in image sequences using Markov random fields. Signal Proc. Image Communic. 7, 147–160 (1995)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Enescu, V., Ravyse, I., Sahli, H. (2007). Visual Tracking by Hypothesis Testing. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2007. Lecture Notes in Computer Science, vol 4678. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74607-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-540-74607-2_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74606-5
Online ISBN: 978-3-540-74607-2
eBook Packages: Computer ScienceComputer Science (R0)