Abstract A gait recognition method is proposed based on independent component analysis/support vector machine (ICA/SVM) and information fusion from multiple views. Human silhouette extraction is obtained by background subtraction and shadow elimination. Wavelet descriptor is applied to describe these silhouettes. Then, independent component analysis is employed to compress and extract their features, and gait classification is performed by support vector machine. The gait features from multiple views are fused, and recognition is finished. The method is evaluated on the National Laboratory of Pattern Recognition (NLPR) and Xi’an University of Technology (XAUT) gait database and the correct recognition rate is relatively high. The experimental results show that the proposed method has good recognition performance.
[1] Dawson M R. Gait Recognition. Ph.D Dissertation. London, UK: Imperial College of Science, Technology and Medicine. Department of Computing, 2002 [2] Tanawongsuwan R, Bobick A. Gait Recognition from TimeNormalized JointAngle Trajectories in the Walking Plane // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2001: 726731 [3] Wagg D K, Nixon M S. An Automated ModelBased Extraction and Analysis of Gait // Proc of the 6th International Conference on Automatic Face and Gesture Recognition. Seoul, Korea, 2004: 1116 [4] Yam C Y, Nixon M S, Carter J N. Gait Recognition by Walking and Running: A ModelBased Approach // Proc of the Asian Conference on Computer Vision. Melbourne, Australian, 2002: 16 [5] Kale A A, Cuntoor N, Krüger V. GaitBased Recognition of Human Using Continuous HMMs // Proc of the IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 336341 [6] Huang P S, Harris C J, Nixon M S. Comparing Different Template Features for Recognizing People by Their Gait // Proc of the British Machine Vision Conference. Southampton, UK, 1998: 639643 [7] Little J, Boyd J. Recognizing People by Their Gait: The Shape of Motion. IEEE Trans on Computer Vision Research, 1998, 2(1): 232 [8] Lee L. Gait Analysis for Classification. Technical Report, 2003014, Massachusetts, USA: Massachusetts Institute of Technology. Artificial Intelligence Laboratory, 2003 [9] Wang Liang. Gait Analysis and Recognition. Ph.D Dissertation. Beijing, China: Institute of Automation, Chinese Academy of Sciences, 2004 (in Chinese) (王 亮.步态分析与识别.博士学位论文.北京:中国科学院自动化研究所, 2004) [10] Zhang Yujin. Video Information Retrieval Based on Content. Beijing, China: Science Press, 2003: 102126 (in Chinese) (章毓晋.基于内容的视频信息检索.北京: 科学出版社, 2003: 102126) [11] Hyvarinen A, Oja E. Independent Component Analysis: Algorithm and Applications. Neural Networks, 2000, 13(4/5): 411430 [12] Yuen P C, Lai J H. Face Representation Using Independent Component Analysis. Pattern Recognition, 2002, 35(6): 12471257 [13] Deniz O, Catrillon M,Hernandez M. Face Recognition Using Independent Component Analysis and Support Vector Machines. Pattern Recognition Letters, 2003, 24(13): 21532157 [14] Pan Quan, Yu Xi, Cheng Yongmei, et al. Essential Methods and Progress of Information Fusion Theory. Acta Automatica Sinica, 2003, 29(4): 599615 (in Chinese) (潘 泉,于 昕,程咏梅,等.信息融合理论的基本方法与进展.自动化学报, 2003, 29(4): 599615)
2007, Vol. 20 
