3D Gait Recognition Using Spatio-Temporal Motion Descriptors

We present a view independent algorithm for 3D human gait recognition. The identification of the person is achieved using motion data obtained by our markerless 3D motion tracking algorithm. We report its tracking accuracy using ground-truth data obtained by a marker-based motion capture system. The classification is done using SVM built on the proposed spatio-temporal motion descriptors. The identification performance was determined using 230 gait cycles performed by 22 persons. The correctly classified ratio achieved by SVM is equal to 93.5% for rank 1 and 99.6% for rank 3. We show that the recognition performance obtained with the spatio-temporal gait signatures is better in comparison to accuracy obtained with tensorial gait data and reduced by MPCA.

[1]  Shree K. Nayar,et al.  Computer Vision - ACCV 2006, 7th Asian Conference on Computer Vision, Hyderabad, India, January 13-16, 2006, Proceedings, Part I , 2006, ACCV.

[2]  Jirí Benes,et al.  On neural networks , 1990, Kybernetika.

[3]  Kinh Tieu,et al.  Learning pedestrian models for silhouette refinement , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[4]  Bogdan Kwolek,et al.  Swarm Intelligence Based Searching Schemes for Articulated 3D Body Motion Tracking , 2011, ACIVS.

[5]  Mark S. Nixon,et al.  Automatic Recognition by Gait , 2006, Proceedings of the IEEE.

[6]  D. Hatzinakos,et al.  Gait recognition: a challenging signal processing technology for biometric identification , 2005, IEEE Signal Processing Magazine.

[7]  B M Nigg,et al.  Three-dimensional measurement of rearfoot motion during running. , 1990, Journal of biomechanics.

[8]  Bogdan Kwolek,et al.  Gait recognition based on marker-less 3D motion capture , 2013, 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[9]  Pascal Fua,et al.  3D tracking for gait characterization and recognition , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[10]  Aaron F. Bobick,et al.  Gait recognition from time-normalized joint-angle trajectories in the walking plane , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[11]  Robert Bergevin,et al.  Towards view-invariant gait modeling: Computing view-normalized body part trajectories , 2009, Pattern Recognit..

[12]  Mark S. Nixon,et al.  Gender Classification in Human Gait Using Support Vector Machine , 2005, ACIVS.

[13]  Bogdan Kwolek,et al.  GPU-Accelerated Tracking of the Motion of 3D Articulated Figure , 2010, ICCVG.

[14]  Ryszard Tadeusiewicz,et al.  Computer Vision and Graphics , 2014, Lecture Notes in Computer Science.

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

[16]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[17]  Tieniu Tan,et al.  Modelling the Effect of View Angle Variation on Appearance-Based Gait Recognition , 2006, ACCV.

[18]  Junxia Gu,et al.  Action and Gait Recognition From Recovered 3-D Human Joints , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).