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...
Abstract— Mobile wireless sensor networks have to be robust against the limitations of the underlying platform. While lightweight form factor makes them an attractive choice for ...
Lun Jiang, Jyh-How Huang, Ankur Kamthe, Tao Liu, I...
We present a computer vision system for robust object tracking in 3D by combining evidence from multiple calibrated cameras. This kernel-based 3D tracker is automatically bootstra...
Ambrish Tyagi, Mark A. Keck, James W. Davis, Geras...
In this paper we perform 3D face tracking on corrupted video sequences. We use a deformable model, combined with a predictive filter, to recover both the rigid transformations and...
Siome Goldenstein, Christian Vogler, Dimitris N. M...
Monocular SLAM has the potential to turn inexpensive cameras into powerful pose sensors for applications such as robotics and augmented reality. However, current implementations l...