Gait Recognition
Novel features for silhouette based gait recognition systems
|Arhiant Kochhar |Divyesh Gupta |M. Hanmandlu |Shantaram Vasikarla |
|N. S. Institute of Technology New Delhi,|N. S. Institute of Technology |Dept. of Electrical Engineering |Dept. of Computer Science |
|India |New Delhi, India |Indian Institute of Technology |California State University |
|arihant8kochhar@gmail.com |divyesh.gupta@gmail.com |New Delhi, India |Carson, CA 90747 |
| | |mhmandlu@gmail.com |shantaram@computer.org |
Abstract- This paper proposes certain features for human gait cycle detection and recognition. The features cover both the categories of holistic and model-based approaches for human gait recognition. A unique feature vector is formed from the spatial-temporal silhouettes and Support Vector Machine (SVM) classifier is used for the identification of individuals through their gait. The present work is concerned with the efficiency of the extracted features. Experimentation on the silhouette samples of publicly available CASIA database has given furnishes promising results.
1. INTRODUCTION
Human gait can be simply defined as the way one walks. It is the pattern of movement of the limbs constituting the locomotion of an individual. Identifying a person just by the way of walk is a natural methodology which we do everyday spontaneously. With the initial studies on biomechanics, physical medicine for therapy and the associated techniques using markers to joints (and other parts) in the body providing encouraging results, the recognition of human through gait has been
|Arhiant Kochhar |Divyesh Gupta |M. Hanmandlu |Shantaram Vasikarla |
|N. S. Institute of Technology New Delhi,|N. S. Institute of Technology |Dept. of Electrical Engineering |Dept. of Computer Science |
|India |New Delhi, India |Indian Institute of Technology |California State University |
|arihant8kochhar@gmail.com |divyesh.gupta@gmail.com |New Delhi, India |Carson, CA 90747 |
| | |mhmandlu@gmail.com |shantaram@computer.org |
Abstract- This paper proposes certain features for human gait cycle detection and recognition. The features cover both the categories of holistic and model-based approaches for human gait recognition. A unique feature vector is formed from the spatial-temporal silhouettes and Support Vector Machine (SVM) classifier is used for the identification of individuals through their gait. The present work is concerned with the efficiency of the extracted features. Experimentation on the silhouette samples of publicly available CASIA database has given furnishes promising results.
1. INTRODUCTION
Human gait can be simply defined as the way one walks. It is the pattern of movement of the limbs constituting the locomotion of an individual. Identifying a person just by the way of walk is a natural methodology which we do everyday spontaneously. With the initial studies on biomechanics, physical medicine for therapy and the associated techniques using markers to joints (and other parts) in the body providing encouraging results, the recognition of human through gait has been