Hybrid Gait Recognition Method Based on Phase Trajectory

Pinjie Li, Tao Xue, Tao Zhang, Huangang Wang, Ming Zhang

Research output: Chapter in Book/Published conference outputConference publication

Abstract

Gait recognition is critical to the activity monitoring, health management, assistance control of prostheses and exoskeletons, etc. This study aims to improve the gait classification performance on daily hybrid locomotions. We found the hip angle phase trajectories present significantly gait-dependent patterns, whereas the phase patterns show repeated limit cycles for periodic gaits while half-cycles or dots for aperiodic gaits. By converting the gait recognition issue into an image classification problem, we propose to use a convolution neural network (CNN) to learn the gait-dependent phase pattern images. Besides, to enhance the gait transition stability, we further integrate the prior state transition probability with category likelihood via dynamic Bayesian network. The proposed method has been experimented with 6 healthy subjects on standing, sitting, stand-to-sit, sit-to-stand, walking, running, stair ascending, and stair descending gaits. The overall leave-one-out cross-validation accuracy in continuous time is 96.15%.
Original languageEnglish
Title of host publication2022 27th International Conference on Automation and Computing (ICAC)
PublisherIEEE
Number of pages6
ISBN (Electronic)978-1-6654-9807-4
ISBN (Print)978-1-6654-9808-1
DOIs
Publication statusPublished - 10 Oct 2022
Event2022 27th International Conference on Automation and Computing (ICAC) - Bristol, United Kingdom
Duration: 1 Sep 20223 Sep 2022

Conference

Conference2022 27th International Conference on Automation and Computing (ICAC)
Period1/09/223/09/22

Keywords

  • Convolution Neural Network
  • Dynamic Bayesian Network
  • Gait Recognition
  • Phase Trajectory

Fingerprint

Dive into the research topics of 'Hybrid Gait Recognition Method Based on Phase Trajectory'. Together they form a unique fingerprint.

Cite this