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...
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...
Photometric registration is as important as geometric registration to generate a seamless augmented reality scene. Especially the difference in image quality between a real image ...
Abstract. The exploitation of video data requires to extract information at a rather semantic level, and then, methods able to infer "concepts" from low-level video featu...
We present a fully-automated method for real-time and marker-free 3D human motion capture. The system computes the 3D shape of the person filmed from a synchronized camera set. We...