Action Recognition Based on Depth Motion Map and Hybrid Classifier
Joint Authors
Li, Wenhui
Wang, Qiuling
Wang, Ying
Source
Mathematical Problems in Engineering
Issue
Vol. 2018, Issue 2018 (31 Dec. 2018), pp.1-10, 10 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2018-11-14
Country of Publication
Egypt
No. of Pages
10
Main Subjects
Abstract EN
In order to efficiently extract and encode 3D information of human action from depth images, we present a feature extraction and recognition method based on depth video sequences.
First, depth images are projected continuously onto three planes of Cartesian coordinate system, and differential images of the respective projection surfaces are accumulated to obtain the complete 3D information of the depth motion maps (DMMs).
Then, discriminative completed LBP (disCLBP) encodes depth motion maps to extract effective human action information.
A hybrid classifier combined with Extreme Learning Machine (ELM) and collaborative representation classification (CRC) is employed to reduce the computational complexity while reducing the impact of noise.
The proposed method is tested on the MSR-Action3D database; the experimental results show that it achieves 96.0% accuracy and well performs better robustness comparing to other popular approaches.
American Psychological Association (APA)
Li, Wenhui& Wang, Qiuling& Wang, Ying. 2018. Action Recognition Based on Depth Motion Map and Hybrid Classifier. Mathematical Problems in Engineering،Vol. 2018, no. 2018, pp.1-10.
https://search.emarefa.net/detail/BIM-1209481
Modern Language Association (MLA)
Li, Wenhui…[et al.]. Action Recognition Based on Depth Motion Map and Hybrid Classifier. Mathematical Problems in Engineering No. 2018 (2018), pp.1-10.
https://search.emarefa.net/detail/BIM-1209481
American Medical Association (AMA)
Li, Wenhui& Wang, Qiuling& Wang, Ying. Action Recognition Based on Depth Motion Map and Hybrid Classifier. Mathematical Problems in Engineering. 2018. Vol. 2018, no. 2018, pp.1-10.
https://search.emarefa.net/detail/BIM-1209481
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1209481