Incremental level set tracking

We consider the problem of contour tracking in the level set framework. Level set methods rely on low level image features, and very mild assumptions on the shape of the object to be tracked. To improve their robustness to noise and occlusion, one might consider adding shape priors that give additional weight to contours that are more likely than others. This works well in practice, but assumes that the class of object to be tracked is known in advance so that the proper shape prior is learned. In this work we propose to learn the shape priors on the fly. That is, during tracking we learn an eigenspace of the shape contour and use it to detect and handle occlusions and noise. Experiments on a number of sequences reveal the advantages of our method.