Performance analysis of time-distance gait parameters under different speeds

  • Authors:
  • Rawesak Tanawongsuwan;Aaron Bobick

  • Affiliations:
  • College of Computing, GVU Center, Georgia Institute of Technology, Atlanta, GA;College of Computing, GVU Center, Georgia Institute of Technology, Atlanta, GA

  • Venue:
  • AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper explores gait recognition for various walking speeds. Normal-constant speed is one of the assumptions being made in many current gait recognition techniques. However, some techniques do not scale well when certain gait conditions such as walking speed varies. We demonstrate the characteristics of time-distance gait parameters, stride length and cadence, with respect to walking speed at the inter-and intra-individual variation levels. The speed normalization or adjustment of gait features are studied and presented in details along with the expected recognition results. Our study of walking speed variations allows us to ascertain systematically the expected recognition-performance of time-distance gait parameters (stride length and cadence). In addition, we show the levels of measurement noise which can be tolerated in measuring these gait features without losing useful identity information.