Graph cut is a popular technique for interactive image segmentation. However, it has certain shortcomings. In particular, graph cut has problems with segmenting thin elongated obj...
Abstract. We introduce a non-linear shape prior for the deformable model framework that we learn from a set of shape samples using recent manifold learning techniques. We model a c...
Abstract. Autonomous collision avoidance in vehicles requires an accurate seperation of obstacles from the background, particularly near the focus of expansion. In this paper, we p...
Andreas Wedel, Thomas Schoenemann, Thomas Brox, Da...
In the last decade, graph-cut optimization has been popular for a variety of pixel labeling problems. Typically graph-cut methods are used to incorporate a smoothness prior on a l...
To segment a whole object from an image is an essential and challenging task in image processing. In this paper, we propose a hybrid segmentation algorithm which combines prior sh...