In this paper we describe a dense motion segmentation method for wide baseline image pairs. Unlike many previous methods our approach is able to deal with deforming motions and lar...
Juho Kannala, Esa Rahtu, Sami S. Brandt, Janne Hei...
We present an efficient multi stage approach to detection of deformable objects in real, cluttered images given a single or few hand drawn examples as models. The method handles de...
Despite the ability of current GPU processors to treat heavy parallel computation tasks, its use for solving medical image segmentation problems is still not fully exploited and re...
This paper presents an approach to recognize human motion from singleviewed image sequencein order to realize a new man-computerinterface.Thehuman body is assumed to be linked mod...
Abstract. A new hybrid of feature-based and intensity-based registration is presented. The algorithm reflects a new understanding of the role of alignment error in the generation o...