JCSE, vol. 12, no. 1, pp.1-11, March, 2018

DOI: http://dx.doi.org/10.5626/JCSE.2018.12.1.1

Human Activities Recognition Based on Skeleton Information via Sparse Representation

Suolan Liu, Lizhi Kong, and Hongyuan Wang
School of Information Science and Engineering, Changzhou University, Changzhou, China; University of Texas at Dallas, Richardson, TX, USA School of Materials Science and Engineering, Changzhou University, Changzhou, China School of Information Science and Engineering, Changzhou University, Changzhou, China

Abstract: Human activities recognition is a challenging task due to its complexity of human movements and the variety performed by different subjects for the same action. This paper presents a recognition algorithm by using skeleton information generated from depth maps. Concatenating motion features and temporal constraint feature produces feature vector. Reducing dictionary scale proposes an improved fast classifier based on sparse representation. The developed method is shown to be effective by recognizing different activities on the UTD-MHAD dataset. Comparison results indicate superior performance of our method over some existing methods.

Keyword: Activity recognition; Skeleton feature; Temporal feature; Sparse representation

Full Paper:   670 Downloads, 1520 View