Action recognition based on a bag of 3D points

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.

DOI: 10.1109/CVPRW.2010.5543273

Extracted Key Phrases

7 Figures and Tables

01002002011201220132014201520162017
Citations per Year

811 Citations

Semantic Scholar estimates that this publication has 811 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Li2010ActionRB, title={Action recognition based on a bag of 3D points}, author={Wanqing Li and Zhengyou Zhang and Zicheng Liu}, journal={2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops}, year={2010}, pages={9-14} }