Human gait recognition based on frontal view using kinect features and orthogonal least square selection
This paper discussed the recognition of human gait for both frontal and oblique view based on orthogonal least square (OLS) as feature selection and Multi-Layer perceptron (MLP) as classifier. Firstly, kinect sensor was used to acquire several frames of human gait in both oblique and frontal view. N...
| Published in: | 2017 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2017 |
|---|---|
| Main Author: | |
| Format: | Conference paper |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2018
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050139746&doi=10.1109%2fISSPIT.2017.8388674&partnerID=40&md5=19e81929d1ef607ee4e8a52eaaf4c8c9 |
| Summary: | This paper discussed the recognition of human gait for both frontal and oblique view based on orthogonal least square (OLS) as feature selection and Multi-Layer perceptron (MLP) as classifier. Firstly, kinect sensor was used to acquire several frames of human gait in both oblique and frontal view. Next, feature extraction is conducted via skeleton joint point in the 3D space known as direct-gait (D-G) feature. Further, feature selection is performed in identifying the significant D-G features using OLS labeled as OLS-G features. Then, the effectiveness of the OLS-G features in recognition of human based on their gait is evaluated using neural network classifier. Result attained proven that OLS-G feature in frontal view is indeed apt for recognition of human based on their gait with recognition accuracy of 90.6%. © 2017 IEEE. |
|---|---|
| ISSN: | |
| DOI: | 10.1109/ISSPIT.2017.8388674 |