TY - GEN
T1 - A hand pose tracking benchmark from stereo matching
AU - Zhang, Jiawei
AU - Jiao, Jianbo
AU - Chen, Mingliang
AU - Qu, Liangqiong
AU - Xiaobin, XU
AU - Yang, Qingxiong
PY - 2017/9
Y1 - 2017/9
N2 - In this paper we establish a long-term 3D hand pose tracking benchmark1. It contains 18,000 stereo image pairs as well as the ground-truth 3D positions of palm and finger joints from different scenarios. Meanwhile, to accurately segment hand from stereo images, we propose a novel stereo-based hand segmentation and depth estimation algorithm specially tailored for hand tracking here. The experiments indicate the effectiveness of the proposed algorithm by demonstrating that its tracking performance is comparable to the use of an active depth sensor under various of challenging scenarios.
AB - In this paper we establish a long-term 3D hand pose tracking benchmark1. It contains 18,000 stereo image pairs as well as the ground-truth 3D positions of palm and finger joints from different scenarios. Meanwhile, to accurately segment hand from stereo images, we propose a novel stereo-based hand segmentation and depth estimation algorithm specially tailored for hand tracking here. The experiments indicate the effectiveness of the proposed algorithm by demonstrating that its tracking performance is comparable to the use of an active depth sensor under various of challenging scenarios.
UR - https://scholars.cityu.edu.hk/en/publications/a-hand-pose-tracking-benchmark-from-stereo-matching(f9ae6c73-5463-475b-a26c-10d791566d16).html
U2 - 10.1109/ICIP.2017.8296428
DO - 10.1109/ICIP.2017.8296428
M3 - Conference contribution
SN - 978-1-5090-2175-8
BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
ER -