Accurate, Robust, and Flexible Real-time Hand Tracking

被引:253
作者
Sharp, Toby [1 ]
Keskin, Cem [1 ]
Robertson, Duncan [1 ]
Taylor, Jonathan [1 ]
Shotton, Jamie [1 ]
Kim, David [1 ]
Rhemann, Christoph [1 ]
Leichter, Ido [1 ]
Vinnikov, Alon [1 ]
Wei, Yichen [1 ]
Freedman, Daniel [1 ]
Kohli, Pushmeet [1 ]
Krupka, Eyal [1 ]
Fitzgibbon, Andrew [1 ]
Izadi, Shahram [1 ]
机构
[1] Microsoft Res, Cambridge, England
来源
CHI 2015: PROCEEDINGS OF THE 33RD ANNUAL CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS | 2015年
关键词
POSE ESTIMATION; REGRESSION; VISION;
D O I
10.1145/2702123.2702179
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We present a new real-time hand tracking system based on a single depth camera. The system can accurately reconstruct complex hand poses across a variety of subjects. It also allows for robust tracking, rapidly recovering from any temporary failures. Most uniquely, our tracker is highly flexible, dramatically improving upon previous approaches which have focused on front-facing close-range scenarios. This flexibility opens up new possibilities for human-computer interaction with examples including tracking at distances from tens of centimeters through to several meters (for controlling the TV at a distance), supporting tracking using a moving depth camera (for mobile scenarios), and arbitrary camera placements (for VR headsets). These features are achieved through a new pipeline that combines a multi-layered discriminative reinitialization strategy for per-frame pose estimation, followed by a generative model-fitting stage. We provide extensive technical details and a detailed qualitative and quantitative analysis.
引用
收藏
页码:3633 / 3642
页数:10
相关论文
共 36 条
[1]  
[Anonymous], 2011, P CVPR
[2]  
[Anonymous], P ICCV
[3]  
[Anonymous], 2013, DECISION FORESTCOM, DOI DOI 10.1007/978-1-4471-4929-3
[4]  
[Anonymous], 2013, NIPS
[5]  
[Anonymous], P ICCV
[6]  
[Anonymous], 2013, P GRAPHICS INTERFACE
[7]  
[Anonymous], 2012, PROC CVPR IEEE
[8]  
Athitsos V, 2003, PROC CVPR IEEE, P432
[9]  
Ballan L, 2012, LECT NOTES COMPUT SC, V7577, P640, DOI 10.1007/978-3-642-33783-3_46
[10]   Smart particle filtering for 3D hand tracking [J].
Bray, M ;
Koller-Meier, E ;
Van Gool, L .
SIXTH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, PROCEEDINGS, 2004, :675-680