Back to Search
Start Over
Learning Multi-level Features For Sensor-based Human Action Recognition
- Source :
- Pervasive and Mobile Computing, Volume 40, September 2017, Pages 324-338
- Publication Year :
- 2016
-
Abstract
- This paper proposes a multi-level feature learning framework for human action recognition using a single body-worn inertial sensor. The framework consists of three phases, respectively designed to analyze signal-based (low-level), components (mid-level) and semantic (high-level) information. Low-level features capture the time and frequency domain property while mid-level representations learn the composition of the action. The Max-margin Latent Pattern Learning (MLPL) method is proposed to learn high-level semantic descriptions of latent action patterns as the output of our framework. The proposed method achieves the state-of-the-art performances, 88.7%, 98.8% and 72.6% (weighted F1 score) respectively, on Skoda, WISDM and OPP datasets.<br />Comment: 26 pages, 23 figures
- Subjects :
- Computer Science - Computer Vision and Pattern Recognition
I.5.2
Subjects
Details
- Database :
- arXiv
- Journal :
- Pervasive and Mobile Computing, Volume 40, September 2017, Pages 324-338
- Publication Type :
- Report
- Accession number :
- edsarx.1611.07143
- Document Type :
- Working Paper