We introduce linear methods for model-based tracking of nonrigid 3D objects and for acquiring such models from video. 3D motions and flexions are calculated directly from image in...
We present an approach for efficiently recognizing all objects in a scene and estimating their full pose from multiple views. Our approach builds upon a state of the art single-vie...
Abstract. This paper concerns the exploration of a natural environment by a mobile robot equipped with both a video camera and a range sensor (stereo or laser range finder); we fo...
Carlos Parra, Rafael Murrieta-Cid, Michel Devy, Ma...
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
Extracting meaningful 3D human motion information from video sequences is of interest for applications like intelligent humancomputer interfaces, biometrics, video browsing and ind...