View-invariant gait recognition method by three-dimensional convolutional neural network

Authors:

Abstract
Gait as an important biometric feature can identify a human at a long distance. View change is one of the most challenging factors for gait recognition. To address the cross view issues in gait recognition, we propose a view-invariant gait recognition method by three-dimensional (3-D) convolutional neural network. First, 3-D convolutional neural network (3DCNN) is introduced to learn view-invariant feature, which can capture the spatial information and temporal information simultaneously on normalized silhouette sequences. Second, a network training method based on cross-domain transfer learning is proposed to solve the problem of the limited gait training samples. We choose the C3D as the basic model, which is pretrained on the Sports-1M and then fine-tune C3D model to adapt gait recognition. In the recognition stage, we use the fine-tuned model to extract gait features and use Euclidean distance to measure the similarity of gait sequences. Sufficient experiments are carried out on the CASIA-B dataset and the experimental results demonstrate that our method outperforms many other methods.
Funding Information
  • China Postdoctoral Science Foundation
  • National Natural Science Foundation of China (61601021)
  • National Natural Science Foundation of China (61601021)
  • National Natural Science Foundation of China (61370128)
  • Natural Science Foundation of Beijing Municipality (L172022)
  • United Foundation of Beijing Natural Science and Haidian Original Innovation (L172022)
  • Program for New Century Excellent Talents in University (NCET-13-0659)
  • Program for New Century Excellent Talents in University (NCET-13-0659)
  • Fundamental Research Funds for the Central Universities (2016RC015)
  • Fundamental Research Funds for the Central Universities (2017JBM078)

This publication has 32 references indexed in Scilit: