Gait recognition based on multiple views fusion of wavelet descriptor and human skeleton model

Authors:
Dong Ming;Cong Zhang;Yanru Bai;Baikun Wan;Yong Hu;KDK Luk
Affiliations:
Department of Biomedical Engineering, Tianjin University, Tianjin, China;Department of Biomedical Engineering, Tianjin University, Tianjin, China;Department of Biomedical Engineering, Tianjin University, Tianjin, China;Department of Biomedical Engineering, Tianjin University, Tianjin, China;Department of Orthopaedics and Traumatology, University of Hong Kong, Hong Kong, China;Department of Orthopaedics and Traumatology, University of Hong Kong, Hong Kong, China
Venue:
VECIMS'09 Proceedings of the 2009 IEEE international conference on Virtual Environments, Human-Computer Interfaces and Measurement Systems
Year:
2009

Citing 10
Cited 0

Support-Vector Networks

Machine Learning
How good are support vector machines?

Neural Networks
The HumanID Gait Challenge Problem: Data Sets, Performance, and Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Biometrics: Personal Identification in Networked Society

Biometrics: Personal Identification in Networked Society
Classification of Electrocardiogram Signals With Support Vector Machines and Particle Swarm Optimization

IEEE Transactions on Information Technology in Biomedicine
Automatic gait recognition via statistical approaches for extendedtemplate features

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Integrating Face and Gait for Human Recognition at a Distance in Video

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Gait Recognition Using Radon Transform and Linear Discriminant Analysis

IEEE Transactions on Image Processing
Marginal Fisher Analysis and Its Variants for Human Gait Recognition and Content- Based Image Retrieval

IEEE Transactions on Image Processing
Kernel Component Analysis Using an Epsilon-Insensitive Robust Loss Function

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gait recognition is a relatively new subfield in biometric recognition, which attempts to recognize people from the way they walk or run. This paper discusses silhouette-based feature descriptor. Human silhouette geometry is generated by boundary tracking approach and resampled to a normalized format. Boundary-centroid distance is proposed to describe gait modality. Then, we apply wavelet transform to boundary-centroid distance, and extract wavelet descriptor. At the same time, we obtain the human skeleton model and extract body's dynamic parameters to express gait modality. We carry out human identification based on SVM using the two kinds of gait feature. The performances based on the two features are compared. Multiple feature fusion and multiple views fusion are carried out and the recognition results demonstrate that the performance of multiple features and multiple views recognition is better than any single feature and single view recognition.