Evaluation of different feature sets for gait recognition using skeletal data from Kinect

Gait is a persons manner of walking. It is a biometric that can be used for identifying humans. Gait is an unobtrusive metric that can be obtained from distance, and this is its main strength compared to other biometrics. In this paper we construct and evaluate feature sets with the purpose of finding out the role of different types of features and body parts in the recognition process. The feature sets were constructed from skeletal images in three dimensions made with a Kinect sensor. The Kinect is a low-cost device that includes RGB, depth and audio sensors. In our work automated gait cycle extraction algorithm was performed on the Kinect recordings. Metrics like angles and distances between joints were aggregated within a gait cycle, and from those aggregations the different feature datasets were constructed. Multilayer perceptron, support vector machine with sequential minimal optimization and J48 algorithms were used for classification on these datasets. At the end we give conclusions on which groups of features and body parts gave the best recognition rates.

[1]  R. Venkatesh Babu,et al.  Human gait recognition using depth camera: a covariance based approach , 2012, ICVGIP '12.

[2]  Björn W. Schuller,et al.  The TUM Gait from Audio, Image and Depth (GAID) database: Multimodal recognition of subjects and traits , 2014, J. Vis. Commun. Image Represent..

[3]  Haihong Hu,et al.  Frame difference energy image for gait recognition with incomplete silhouettes , 2009, Pattern Recognit. Lett..

[4]  Ran Gilad-Bachrach,et al.  Full body gait analysis with Kinect , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  Reza Safabakhsh,et al.  Model-based human gait recognition using leg and arm movements , 2010, Eng. Appl. Artif. Intell..

[6]  Bir Bhanu,et al.  Individual recognition using gait energy image , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Mark S. Nixon,et al.  Automated person recognition by walking and running via model-based approaches , 2004, Pattern Recognit..

[8]  G. Johansson.  Visual perception of biological motion and a model for its analysis , 1973 .

[9]  Thomas Villmann,et al.  Analysis of temporal Kinect motion capturing data , 2013 .

[10]  Ruigang Yang,et al.  Accuracy and repeatability of joint angles measured using a single camera markerless motion capture system. , 2014, Journal of biomechanics.

[11]  Kohei Arai,et al.  3D Skeleton model derived from Kinect Depth Sensor Camera and its application to walking style quality evaluations , 2013 .

[12]  Gian Luca Mariottini,et al.  Evaluating the accuracy of a mobile Kinect-based gait-monitoring system for fall prediction , 2013, PETRA '13.

[13]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[14]  James Nga-Kwok Liu,et al.  Gait flow image: A silhouette-based gait representation for human identification , 2011, Pattern Recognit..

[15]  Kingshuk Chakravarty,et al.  Person Identification using Skeleton Information from Kinect , 2013, ACHI 2013.

[16]  Kourosh Khoshelham,et al.  Accuracy analysis of kinect depth data , 2012 .

[17]  Claudia Linnhoff-Popien,et al.  Gait Recognition with Kinect , 2012 .

[18]  Wei Xiong,et al.  Active energy image plus 2DLPP for gait recognition , 2010, Signal Process..

[19]  Youbin Chen,et al.  Gait Recognition Based on Structural Gait Energy Image , 2013 .

[20]  Larry S. Davis,et al.  Stride and cadence as a biometric in automatic person identification and verification , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.