Cross-View Gait Recognition in 3-D Space Based on Gravity Center Track

Abstract:

We propose in this paper a novel cross-view gait recognition method based on gravity center trajectory (GCT). Inspired by the finding that if the GCT of human in walking process has regularity, the representation coefficients of the trajectory are generally consistent across different views. We propose to project the coefficients of GCT to different view plane (VP) which is the normal plane of view angle direction vector to achieve view-invariant features for gait recognition. Firstly, we obtain the GCT under different views by summation of pixel coordinates in body area. Then, we use the least square method to eliminate the upward or downward trend of GCT caused by view variance. Then, we project the GCT function to the corresponding VP. Lastly, we perform recognition by using a simple cluster method. Experimental results on the widely used CASIA-B gait database demonstrate the effectiveness and practicability of the proposed method.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 4210-4215
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.4210
• Online since: September 2014
• Authors: Xin Chen*, Tian Qi Yang
• Keywords: 3-D Projection, Cross-View, Gait Recognition, GCT

References

[1] N.N. Liu Y.P. Tan, View Invariant Gait Recognition, in IEEE International Conference on Acoustics, Speech, and Signal Processing, 2010, p.1410–1413.

DOI: 10.1109/icassp.2010.5495466

[2] M. Goffredo et al., Self-calibrating view-invariant gait biometrics, IEEE Trans. Syst., Man, Cybern. B, vol. 40, no. 4, p.997–1008, (2010).

DOI: 10.1109/tsmcb.2009.2031091

[3] W. Kusakunniran et al., Support vector regression for multi-view gait recognition based on local motion feature selection, in IEEE Computer Soc. Conf. Computer Vision and Pattern Recognition, 2010, p.974–981.

DOI: 10.1109/cvpr.2010.5540113

[4] N. Liu, J. Lu, and Y.P. Tan, Joint Subspace Learning for View-Invariant Gait Recognition, IEEE Signal Processing Letters, vol. 18, pp.431-434, (2011).

DOI: 10.1109/lsp.2011.2157143

[5] R. Bodor et al., View-independent human motion classification using image-based reconstruction, Image Vis. Comput., vol. 27, no. 8, p.1194–1206, (2009).

DOI: 10.1016/j.imavis.2008.11.008

[6] I. Bouchrika and M.S. Nixon, Model-Based Feature Extraction for Gait Analysis and Recognition, Lecture Notes in Computer Science, vol. 4418, pp.150-160, (2007).

DOI: 10.1007/978-3-540-71457-6_14

[7] X. Chen and T. Yang, Extraction Method of Gait Feature Based on Human Centroid Trajectory, Proceedings of the 2013 International Conference on Computer Engineering and Network (CENet2013), vol. 277, pp.515-523, (2014).

DOI: 10.1007/978-3-319-01766-2_59

[8] W. Kusakunniran, Q. Wu, J. Zhang, H. Li , Cross-view and multi-view gait recognitions based on view transformation model using multi-layer perceptron, Pattern Recognition Letters, vol. 33, pp.882-889, (2012).

DOI: 10.1016/j.patrec.2011.04.014

[9] G. Shakhnarovich, L. Lee, and T. Darrell, Integrated face and gait recognition from multiple views, in IEEE Computer Soc. Conf. Computer Vision and Pattern Recognition, 2001, p.439–446.

DOI: 10.1109/cvpr.2001.990508

[10] W. Kusakunniran,Q. Wu, A New View-Invariant Feature for Cross-View Gait Recognition, IEEE Transactions on Information Forensics and Security, vol. 8, SI, pp.1642-1653, (2013).

DOI: 10.1109/tifs.2013.2252342

[11] H.F. Hu, Enhanced Gabor Feature Based Classification Using a Regularized Locally Tensor Discriminant Model for Multiview Gait Recognition, IEEE Transcations on Circuits and Systerms for Video Technology, vol. 23, no. 7, pp.1274-1286, Jul (2013).

DOI: 10.1109/tcsvt.2013.2242640

[12] M. Goffredo et al., Self-calibrating view-invariant gait biometrics, IEEE Trans. Syst., Man, Cybern. B, vol. 40, no. 4, p.997–1008, (2010).

DOI: 10.1109/tsmcb.2009.2031091

[13] J. Lu and Y. Tan, Uncorrelated discriminant simplex analysis for view-invariant gait signal computing, Pattern Recognit. Lett., vol. 31, no. 5, p.382–393, (2010).

DOI: 10.1016/j.patrec.2009.11.006