Human gait recognition using depth camera: a covariance based approach

Authors:
M. S. Naresh Kumar;R. Venkatesh Babu
Affiliations:
Indian Institute of Science, Bangalore, India;Indian Institute of Science, Bangalore, India
Venue:
Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing
Year:
2012

Citing 8
Cited 1

Moving object recognition in eigenspace representation: gait analysis and lip reading

Pattern Recognition Letters
A Multi-view Method for Gait Recognition Using Static Body Parameters

AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
Human gait recognition by the fusion of motion and static spatio-temporal templates

Pattern Recognition
Frame difference energy image for gait recognition with incomplete silhouettes

Pattern Recognition Letters
Unsupervised clustering of people from 'skeleton' data

HRI '12 Proceedings of the seventh annual ACM/IEEE international conference on Human-Robot Interaction
Region covariance: a fast descriptor for detection and classification

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
A shape- and texture-based enhanced Fisher classifier for face recognition

IEEE Transactions on Image Processing
Gait energy volumes and frontal gait recognition using depth images

IJCB '11 Proceedings of the 2011 International Joint Conference on Biometrics

UbiHeld: ubiquitous healthcare monitoring system for elderly and chronic patients

Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gait is an important biometric modality for recognizing humans. Unlike other biometrics, human gait can be captured at a distance which makes it an unobtrusive method for recognition. In this paper, an unrestricted gait recognition algorithm is proposed which uses 3D skeleton information and trajectory covariance of joint points. 3-D skeleton is generated from the depth images that are captured using Kinect sensor. The temporal tracking of skeleton points is used for gait analysis. The covariance measure between these skeleton point trajectories are computed and the covariance matrices form the gait model. The gait is recognized by computing the minimum dissimilarity measure between the gait models of the training data and the testing data. Recognition accuracy of over 90% has been achieved for a data set consisting of fixed and moving camera scenarios of 20 subjects.