Real-time Hand Pose Recognition Using Low-Resolution Depth Images

Gesture recognition methods based on intensity or color images often suffer from low efficiency and lack of robustness. In this paper, we employ a new laser-based camera that produces reliable low-resolution depth images at video rates. By decomposing and recognizing hand poses as finger states (finger poses and finger inter-relations), we achieve robust hand pose recognition in real-time (30 frames/second).

• Type: Conference
• Year: 2006
• Where: CVPR
• Authors: Zhenyao Mo, Ulrich Neumann
• Keywords: Computer Vision, CVPR 2006, Finger Inter-relations, Gesture Recognition Methods, Hand Pose Recognition, Reliable Low-resolution Depth