In this paper, a semi-automatic method to capture motion data from a single-camera video is proposed. The input video is first segmented and analyzed, and a 3D character model wit...
This paper presents an approach to recover body motions from multiple views using a 3D skeletal model. It takes, as input, foreground silhouette sequences from multiple viewpoints...
We combine detection and tracking techniques to achieve robust 3?D motion recovery of people seen from arbitrary viewpoints by a single and potentially moving camera. We rely on d...
Andrea Fossati, Miodrag Dimitrijevic, Vincent Lepe...
A challenge for 3D motion capture by monocular vision is 3D-2D projection ambiguities that may bring incorrect poses during tracking. In this paper, we propose improving 3D motion ...
One basic observation for pedestrian detection in video sequences is that both appearance and motion information are important to model the moving people. Based on this observatio...