Dynamic geodesic snakes for visual tracking Export

@inproceedings{citeulike:1937394, abstract = {Visual tracking using active contours is usually accomplished in a static framework. The active contour tracks the object of interest in a given frame of an image sequence, and then a subsequent prediction step ensures good initial placement for the next frame. This approach is unnatural, the curve evolution gets decoupled from the actual dynamics of the objects to be tracked. True dynamic approaches exist, all being marker particle based, and thus prone to the shortcomings of such particle-based implementations. In particular, topological changes are not handled naturally in this framework. The now "classical" level set approach is tailored for codimension one evolutions. However, dynamic curve evolution is at least of codimension two. We propose a natural, efficient, level set based approach for dynamic curve evolution which removes the artificial separation of segmentation and prediction, while retaining all the desirable properties of level set formulations. This is based on a new energy minimization functional which for the first time puts dynamics into the geodesic active contour framework.}, author = {Niethammer, M. and Tannenbaum, A.}, booktitle = {Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on}, citeulike-article-id = {1937394}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1315095}, journal = {Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on}, keywords = {active, contour, geodesic, occlusion, tracking}, pages = {I-660--I-667 Vol.1}, posted-at = {2007-11-19 10:54:58}, priority = {5}, title = {Dynamic geodesic snakes for visual tracking}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1315095}, volume = {1}, year = {2004} }

TY - CONF ID - citeulike:1937394 L3 - citeulike-article-id:1937394 N2 - Visual tracking using active contours is usually accomplished in a static framework. The active contour tracks the object of interest in a given frame of an image sequence, and then a subsequent prediction step ensures good initial placement for the next frame. This approach is unnatural, the curve evolution gets decoupled from the actual dynamics of the objects to be tracked. True dynamic approaches exist, all being marker particle based, and thus prone to the shortcomings of such particle-based implementations. In particular, topological changes are not handled naturally in this framework. The now "classical" level set approach is tailored for codimension one evolutions. However, dynamic curve evolution is at least of codimension two. We propose a natural, efficient, level set based approach for dynamic curve evolution which removes the artificial separation of segmentation and prediction, while retaining all the desirable properties of level set formulations. This is based on a new energy minimization functional which for the first time puts dynamics into the geodesic active contour framework. JF - Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on EP - I-667 Vol.1 TI - Dynamic geodesic snakes for visual tracking VL - 1 T2 - Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on SP - I-660 KW - active KW - contour KW - geodesic KW - occlusion KW - tracking AU - Niethammer, M AU - Tannenbaum, A PY - 2004/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1315095 ER -