Identification of Multi-gait Using Spectral Analysis of Gravity Center Track

A new interference factor that may influencing accuracy of gait recognition system seriously is addressed in this paper. The gravity center track (GCT) of multi-gait is supposed to be the linear combination of single GCT of each participant. We decompose GCT of multi-gait by Fourier transformation and take the frequency distribution coefficient as the gait feature. As pedestrians will adjust their speed from walking alone to traveling together, we perform speed variation on GCT of single gait before matching with multi-gait. The experimental results show that GCT achieves good recognition effect on multi-gait, and has great robustness to dress.

[1]  Qiang Wu,et al.  Gait Recognition Under Various Viewing Angles Based on Correlated Motion Regression , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[2]  Yohan Dupuis,et al.  Feature subset selection applied to model-free gait recognition , 2013, Image Vis. Comput..

[3]  M. H. Habaebi,et al.  Gait recognition and effect of noise on the recognition rate , 2013, 2013 IEEE International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA).

[4]  Xin Chen,et al.  Extraction Method of Gait Feature Based on Human Centroid Trajectory , 2014 .

[5]  Kun Zhang,et al.  Application of Improved FCM on Classification of Multi-target Guided by AWACS , 2008, 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery.

[6]  Fredrik Gustafsson,et al.  Multi-target tracking with PHD filter using Doppler-only measurements , 2014, Digit. Signal Process..

[7]  Junping Du,et al.  PHD filter for multi-target tracking with glint noise , 2014, Signal Process..

[8]  D. S. Childress,et al.  The effect of step length, cadence, and walking speed on the trunk's vertical excursion , 2000, Proceedings of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Cat. No.00CH37143).

[9]  J. Little,et al.  Recognizing People by Their Gait: The Shape of Motion , 1998 .

[10]  Qilian Liang,et al.  Situation assessment via multi-target identification and classification in radar sensor networks , 2009, MILCOM 2009 - 2009 IEEE Military Communications Conference.

[11]  Koichi Shinoda,et al.  Robust Gait Recognition Against Speed Variation , 2010, 2010 20th International Conference on Pattern Recognition.

[12]  Tardi Tjahjadi,et al.  Gait recognition based on shape and motion analysis of silhouette contours , 2013, Comput. Vis. Image Underst..

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

[14]  Osama Masoud,et al.  View-independent human motion classification using image-based reconstruction , 2009, Image Vis. Comput..