Dynamical statistical shape priors for level set-based tracking

@article{citeulike:1873456, abstract = {In recent years, researchers have proposed introducing statistical shape knowledge into level set-based segmentation methods in order to cope with insufficient low-level information. While these priors were shown to drastically improve the segmentation of familiar objects, so far the focus has been on statistical shape priors which are static in time. Yet, in the context of tracking deformable objects, it is clear that certain silhouettes (such as those of a walking person) may become more or less likely over time. In this paper, we tackle the challenge of learning dynamical statistical models for implicitly represented shapes. We show how these can be integrated as dynamical shape priors in a Bayesian framework for level set-based image sequence segmentation. We assess the effect of such shape priors "with memory" on the tracking of familiar deformable objects in the presence of noise and occlusion. We show comparisons between dynamical and static shape priors, between models of pure deformation and joint models of deformation and transformation, and we quantitatively evaluate the segmentation accuracy as a function of the noise level and of the camera frame rate. Our experiments demonstrate that level set-based segmentation and tracking can be strongly improved by exploiting the temporal correlations among consecutive silhouettes which characterize deforming shapes.}, author = {Cremers, D. }, booktitle = {Transactions on Pattern Analysis and Machine Intelligence}, citeulike-article-id = {1873456}, doi = {http://dx.doi.org/10.1109/TPAMI.2006.161}, journal = {Transactions on Pattern Analysis and Machine Intelligence}, keywords = {active, contour, level-set, pde, shape, statistical, tracking}, number = {8}, pages = {1262--1273}, posted-at = {2007-11-06 10:21:45}, priority = {5}, title = {Dynamical statistical shape priors for level set-based tracking}, url = {http://dx.doi.org/10.1109/TPAMI.2006.161}, volume = {28}, year = {2006} }

TY - JOUR ID - citeulike:1873456 L3 - citeulike-article-id:1873456 TI - Dynamical statistical shape priors for level set-based tracking T2 - Transactions on Pattern Analysis and Machine Intelligence JF - Transactions on Pattern Analysis and Machine Intelligence VL - 28 IS - 8 SP - 1262 EP - 1273 N2 - In recent years, researchers have proposed introducing statistical shape knowledge into level set-based segmentation methods in order to cope with insufficient low-level information. While these priors were shown to drastically improve the segmentation of familiar objects, so far the focus has been on statistical shape priors which are static in time. Yet, in the context of tracking deformable objects, it is clear that certain silhouettes (such as those of a walking person) may become more or less likely over time. In this paper, we tackle the challenge of learning dynamical statistical models for implicitly represented shapes. We show how these can be integrated as dynamical shape priors in a Bayesian framework for level set-based image sequence segmentation. We assess the effect of such shape priors "with memory" on the tracking of familiar deformable objects in the presence of noise and occlusion. We show comparisons between dynamical and static shape priors, between models of pure deformation and joint models of deformation and transformation, and we quantitatively evaluate the segmentation accuracy as a function of the noise level and of the camera frame rate. Our experiments demonstrate that level set-based segmentation and tracking can be strongly improved by exploiting the temporal correlations among consecutive silhouettes which characterize deforming shapes. KW - active KW - contour KW - level-set KW - pde KW - shape KW - statistical KW - tracking AU - Cremers, D PY - 2006/// UR - http://dx.doi.org/10.1109/TPAMI.2006.161 ER -