Virtual snakes for occlusion analysis

We introduce virtual snakes for generating occlusion hypotheses. Initially, snakes are clustered based on their motion to form object hypotheses-a type of motion segmentation. When two snakes intersect, four virtual snakes are generated-a background and a foreground snake for each of the original two. The two foreground virtual snakes are allowed to relax, while the two background virtual snakes move in accordance with their previous motion. The combined energies of the snakes in the two colliding objects are examined after the collision to determine the occlusion relationship, and the inconsistent virtual snakes are deleted. We show that this heuristic can be used to correctly track objects in the presence of strong occlusion.

[1]  Hans-Hellmut Nagel,et al.  Tracking of complex driving manoeuvres in traffic image sequences , 1998, Image Vis. Comput..

[2]  Alex Pentland,et al.  Cooperative Robust Estimation Using Layers of Support , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Ryohei Nakatsu,et al.  Automatic extraction and tracking of contours , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[4]  M. Isard,et al.  Statistical models of visual shape and motion , 1998, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[5]  Naonori Ueda,et al.  Tracking Moving Contours Using Energy-Minimizing Elastic Contour Models , 1992, Int. J. Pattern Recognit. Artif. Intell..

[6]  Valdis Berzins,et al.  Dynamic Occlusion Analysis in Optical Flow Fields , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Edward H. Adelson,et al.  Representing moving images with layers , 1994, IEEE Trans. Image Process..

[8]  Amir A. Amini,et al.  Snakes and Splines for Tracking Non-Rigid Heart Motion , 1996, ECCV.

[9]  Stephen M. Smith,et al.  ASSET-2: Real-Time Motion Segmentation and Shape Tracking , 1995, IEEE Trans. Pattern Anal. Mach. Intell..