We propose a new approach for integrating geometric scene knowledge into a level-set tracking framework. Our approach is based on a novel constrained-homography transformation mode...
Abstract. We propose a novel Multiple Instance Learning (MIL) framework to perform target localization from image sequences. The proposed approach consists of a softmax logistic re...
We consider a team of mobile agents where a leader has to monitor battery levels of all other agents. Only the leader is capable to transmit information to other agents. Every now...
Visual Hull (VH) construction from silhouette images is a popular method of shape estimation. The method, also known as Shape-From-Silhouette (SFS), is used in many applications s...
We introduce a new approach to modelling gradient flows of contours and surfaces. While standard variational methods (e.g. level sets) compute local interface motion in a different...
Yuri Boykov, Vladimir Kolmogorov, Daniel Cremers, ...