In this work1 a combination of depth and silhouette information is presented to track the motion of a human from a single view. Depth data is acquired from a Photonic Mixer Device ...
State-of-the-art methods for human detection and pose estimation require many training samples for best performance. While large, manually collected datasets exist, the captured v...
Leonid Pishchulin, Arjun Jain, Mykhaylo Andriluka,...
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
The extrinsic camera parameters from video stream images can be accurately estimated by tracking features through the image sequence and using these features to compute parameter ...
A novel method unifying viewer and model centered approaches for representing structurally complex 3-D objects like human faces is presented. The uni ed 3D frequency-domain repres...