Sensing of human hand motion is very important for a variety of applications, such as CG animation and athletic performance measurement. Tracking a hand is difficult because the hand has high degree of freedom articulated mechanisms. This paper presents a 3-D model-based hand tracking method which is robust to occlusions and local minima. Tracking is performed minimizing estimation error of an optical flow and maximizing the overlap between a projected model and a silhouette image. We employ stochastic optimization to solve them, which are generally difficult. We present experimental results on tracking from synthetic and real image sequences.
|出版ステータス||Published - 1996 12月 1|
|イベント||Proceedings of the 1996 IEEE 22nd International Conference on Industrial Electronics, Control, and Instrumentation, IECON. Part 3 (of 3) - Taipei, Taiwan|
継続期間: 1996 8月 5 → 1996 8月 10
|Other||Proceedings of the 1996 IEEE 22nd International Conference on Industrial Electronics, Control, and Instrumentation, IECON. Part 3 (of 3)|
|Period||96/8/5 → 96/8/10|
ASJC Scopus subject areas