TY - GEN
T1 - Hand pose estimation by combining fingertip tracking and articulated ICP
AU - Liang, Hui
AU - Yuan, Junsong
AU - Thalmann, Daniel
PY - 2012
Y1 - 2012
N2 - In this paper we present a model-based framework for hand pose estimation, which relies on the depth and color image sequence input. The proposed framework adopts a divide-and-conquer scheme, and combines fingertip tracking and articulated iterative closest point approach to restore the hand motion. The tracked fingertip positions are used to provide an initial estimation of the hand pose, and articulated ICP are adopted for further refinement. Experiments on both synthetic data and real-world sequences show the hand pose estimation scheme can accurately capture the natural hand motion.
AB - In this paper we present a model-based framework for hand pose estimation, which relies on the depth and color image sequence input. The proposed framework adopts a divide-and-conquer scheme, and combines fingertip tracking and articulated iterative closest point approach to restore the hand motion. The tracked fingertip positions are used to provide an initial estimation of the hand pose, and articulated ICP are adopted for further refinement. Experiments on both synthetic data and real-world sequences show the hand pose estimation scheme can accurately capture the natural hand motion.
KW - fingertip tracking
KW - hand pose estimation
KW - iterative closest point
UR - https://www.scopus.com/pages/publications/84872348237
U2 - 10.1145/2407516.2407543
DO - 10.1145/2407516.2407543
M3 - Conference contribution
AN - SCOPUS:84872348237
SN - 9781450318259
T3 - Proceedings - VRCAI 2012: 11th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry
SP - 87
EP - 90
BT - Proceedings - VRCAI 2012
T2 - 11th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry, VRCAI 2012
Y2 - 2 December 2012 through 4 December 2012
ER -