Unifying boundary and region-based information for geodesic active tracking

This paper addresses the problem of tracking several non-rigid objects over a sequence of frames acquired from a static observer using boundary and region-based information under a coupled geodesic active contour framework. Given the current frame, a statistical analysis is performed on the observed difference frame which provides a measurement that distinguishes between the static and mobile regions in terms of conditional probabilities. An objective function is defined that integrates boundary-based and region-based module by seeking curves that attract the object boundaries and maximize the a posteriori segmentation probability on the interior curve regions with respect to intensity and motion properties. This function is minimized using a gradient descent method. The associated Euler-Lagrange PDE is implemented using a Level-Set approach, where a very fast front propagation algorithm evolves the initial curve towards the final tracking result. Very promising experimental results are provided using real video sequences.

[1]  Patrick Bouthemy,et al.  Region-Based Tracking Using Affine Motion Models in Long Image Sequences , 1994 .

[2]  Anthony J. Yezzi,et al.  Gradient flows and geometric active contour models , 1995, Proceedings of IEEE International Conference on Computer Vision.

[3]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[4]  Larry S. Davis,et al.  3-D model-based tracking of humans in action: a multi-view approach , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Rachid Deriche,et al.  Region tracking through image sequences , 1995, Proceedings of IEEE International Conference on Computer Vision.

[6]  Stanley T. Birchfield,et al.  Elliptical head tracking using intensity gradients and color histograms , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[7]  Frederic Fol Leymarie,et al.  Tracking Deformable Objects in the Plane Using an Active Contour Model , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Alan L. Yuille,et al.  Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Rachid Deriche,et al.  A PDE-based level-set approach for detection and tracking of moving objects , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[10]  Georgios Tziritas,et al.  Adaptive detection and localization of moving objects in image sequences , 1999, Signal Process. Image Commun..

[11]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[12]  Rachid Deriche,et al.  Geodesic Active Regions for Motion Estimation and Tracking , 1999, ICCV.

[13]  R. Deriche,et al.  Geodesic Active Regions for Texture Segmentation , 1998 .

[14]  Michael Isard,et al.  Contour Tracking by Stochastic Propagation of Conditional Density , 1996, ECCV.

[15]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Dimitris N. Metaxas,et al.  Constrained deformable superquadrics and nonrigid motion tracking , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.