We present a method for the simultaneous detection and segmentation of objects from static images. We employ lowlevel contour features that enable us to learn the coarse object sh...
3D video, which consists of a sequence of 3D mesh models, can provide detailed 3D information both in spatial and temporal domain. In this paper, a key frame extraction method has...
A prototype system has been built to navigate a walking robot into a ship structure. The 8-legged robot is equipped with a stereo head. From the CAD-model of the ship good viewpoi...
Markus Vincze, Minu Ayromlou, Carlos Beltran, Anto...
An automatic human shape-motion analysis method based on a fusion architecture is proposed for human action recognition in videos. Robust shape-motion features are extracted from h...
In this paper we suggest an approach to describing and tracking the deformation of facial features. We concentrate on the mouth since its shape is important in detecting emotion, ...