Skip to main content
Presentation
Action recognition based on a bag of 3D points
Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops
  • Wanqing Li, University of Wollongong
  • Zhenyu Zhang, Microsoft Research, Redmond
  • Z Liu, Microsoft Research, Redmond
Document Type
Conference Paper
Publication Date
1-1-2010
Publication Details

Li, W., Zhang, Z. & Liu, Z. (2010). Action recognition based on a bag of 3D points. IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops (pp. 9-14). Piscataway, New Jersey, USA: IEEE.

Abstract
This paper presents a method to recognize human actions from sequences of depth maps. Specifically, we employ an action graph to model explicitly the dynamics of the actions and a bag of 3D points to characterize a set of salient postures that correspond to the nodes in the action graph. In addition, we propose a simple, but effective projection based sampling scheme to sample the bag of 3D points from the depth maps. Experimental results have shown that over 90% recognition accuracy were achieved by sampling only about 1% 3D points from the depth maps. Compared to the 2D silhouette based recognition, the recognition errors were halved. In addition, we demonstrate the potential of the bag of points posture model to deal with occlusions through simulation.
RIS ID
33987
Citation Information
Wanqing Li, Zhenyu Zhang and Z Liu. "Action recognition based on a bag of 3D points" Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops Vol. Piscataway, New Jersey, USA (2010) p. 9 - 14
Available at: http://works.bepress.com/wli/17/