View-Invariant Gait Recognition Based on Head and Shoulder Shape Analysis

Abstract:

To improve the recognition rate and resolve the view problem in gait analysis, a view-invariant method is presented. This method extracts the mean shape of the head and shoulder models in a gait cycle by using the Procrustes Shape Analysis (PSA) algorithm. Then, the mean shape is converted from 2-D space to 1-D space by unfolding the 2D mean shape from the top point of the head. Furthermore, the piecewise approximation (PA) of the unfolded mean shape is segmented corresponding to the average distance value. The obtained PA is adopted for estimating views and recognizing the gait. Finally, the presented method is conducted on the CASIA B database. The results illustrate that the PA is a powerful discriminative feature for view estimation and gait recognition, and the performance has been improved when there is view variation.

• Periodical: Applied Mechanics and Materials (Volumes 568-570)
• Pages: 705-709
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.568-570.705
• Online since: June 2014
• Authors: Guo Zhen Wang*, Hua Zhang, Li Jia Wang, Zhen Jie Wang
• Keywords: Gait Recognition, Mean Head and Shoulder Shape, Piecewise Approximation, Procrustes Shape Analysis

References

[1] M. Arantes and A. Gonzaga, Multimedia Tools and Applications, 55(2011)655-675.

[2] N. V. Boulgouris and Z. X. Chi, Pattern Recognition, 40(2007)1763-1770.

[3] J. Han and B. Bhanu, IEEE Transaction on Pattern Analysis and Machine Intelligence, 28(2006)316-322.

[4] T. H. W. Lan, R. S. T. Lee, and D. Zhang, Pattern Recognition, 40(2007) 2563-2573.

[5] Y. Pratheepan, J. V. Condell, and G. Prasad, The use of dynamic and static characteristics of gait for individual identification, in IMVIP'09 13th International, (2009), pp.111-116.

DOI: 10.1109/imvip.2009.27

[6] N. Liu and Y. P. Tan, View invariant gait recognition, in ICASSP 2012, (2012), pp.1410-1414.

[7] W. Kusakunniran, Q. Wu, H. Li and J. Zhang, Multiple views gait recognition using view transformation model based on optimized gait energy image, in Proceedings of IEEE Conference on Computer Vision Workshops, (2009), pp.1058-1064.

DOI: 10.1109/iccvw.2009.5457587

[8] M. H. Cheng, M. F. Ho and C. L. Huang, Pattern Recognition, 44(2008) 2541-2553.

[9] X. Han, J. Liu, L. Li and Z. Wang, gait recognition considering directions of walking, IEEE Conference on Cybernetics and Intelligent Systems, (2006), pp.1-5.

DOI: 10.1109/iccis.2006.252281

[10] E. J. Keogh, L. Wei, X. Xi, S. H. Lee and M. Vlachos, Keogh supports exact indexing of shapes under rotation invariance with arbitrary representations and distance measures, in 32rd Very Large Data Bases Conference, (2006).

[11] L. Liu, Y. Yin and W. Qin, Gait recognition based on outermost contour, in RSKT 2010, (2010), P. 395-402.

[12] CASIA B gait database, (http: /www. sinobiometric. com).