Exploiting pose dynamics for human recognition from their gait signatures
- PDF / 1,757,813 Bytes
- 19 Pages / 439.642 x 666.49 pts Page_size
- 69 Downloads / 184 Views
Exploiting pose dynamics for human recognition from their gait signatures Sanjay Kumar Gupta1
· Pratik Chattopadhyay1
Received: 21 February 2020 / Revised: 16 June 2020 / Accepted: 9 October 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Computer vision-based gait recognition has evolved into an active area of research since the past decade, and a number of useful algorithms have been proposed over the years. Among the existing gait recognition techniques, pose-based approaches have gained more popularity due to their inherent capability of capturing the silhouette shape variation during walking at a high resolution. However, a short-coming of the existing pose-based gait recognition approaches is that their effectiveness depends on the accuracy of a pre-defined set of key poses and are, in general, not robust against varying walking speeds. In this work, we propose an improvement to the existing pose-based approaches by considering a gallery of key pose sets corresponding to varying walking speeds instead of just a single key pose set. This gallery is generic and is constructed from a large set of subjects that may/may not include the subjects present in the gait recognition data set. Comparison between a pair of training and test sequences is done by mapping each of these into the individual key pose sets present in the above gallery set, computing the Active Energy Image for each key pose, and next observing the frequency of matched key poses in all the sets. Our approach has been evaluated on two popular gait data sets, namely the CASIA B data and the TUMGAID data. A thorough experimental evaluation along with comparison with state-of-the-art techniques verify the effectiveness of our approach. Keywords Gait recognition · walking speed invariant · Active energy image · Video surveillance
1 Introduction Gait is one of the important biometric features that is used to identify a person from his/her walking video. Computer vision-based gait recognition has been an active research area since the past decade and it has significant potential for application in digital forensics Sanjay Kumar Gupta
[email protected] Pratik Chattopadhyay [email protected] 1
Pattern Recognition Laboratory, Department of Computer Science and Engineering, Indian Institute of Technology (Banaras Hindu University), Varanasi, India
Multimedia Tools and Applications
and video surveillance. An advantage of gait-based human recognition over other biometrics such as fingerprints, iris, and face recognition is that gait recognition can work with high accuracy even if the surveillance camera is positioned at a distance from the monitoring zone, thereby enabling capturing of low-resolution videos only [19, 30, 32]. Previous studies show that key pose-based gait feature extraction techniques such as [10, 11, 32] preserve information about the silhouette shape changes during walking at a higher resolution than the feature aggregation-based methods such as [19, 34, 46]. However, a d
Data Loading...
