Statistical Gait Recognition Based on Tangent Angle Features
ZHANG Yuan-Yuan1,WU Xiao-Juan1,RUAN Qiu-Qi2
1.School of Information Science and Engineering,Shandong University,Jinan 250100 2.Institute of Information Science,Beijing Jiaotong University,Beijing 100044
Abstract A statistical gait recognition algorithm based on tangent angle features is proposed in this paper. Firstly, the method of Procrustes shape analysis is used to produce Procrustes compact Mean Shape (PMS) from the continuous posture variation of human body profile outline in gait sequence. The PMS is utilized as the primitive gait feature in this paper. Then the tangent angle corresponding to the tangential vector at each sample point on the PMS is computed. The tangent angle is considered to reflect the local appearance and tendency at that particular point of the outline and is treated as a local discriminative gait feature called Tangent Angle Feature (TAF). Finally, the Local Tangent angle Dissimilarity is used to measure the distance between two different TAFs, and the simplest standard classifiers are used to implement gait recognition. The experimental results on CASIA database and SOTON database show that the proposed algorithm is simple and effective and outperforms other existing approaches in terms of recognition accuracy.
[1] BenAbdelkader C, Cutler R G, Davis L S. Gait Recognition Using Image Self-Similarity. EURASIP Journal on Applied Signal Processing, 2004, 4: 572-585 [2] Lee L, Grimson W E L. Gait Analysis for Recognition and Classification // Proc of the 5th IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 148-155 [3] Yang Jun, Wu Xiaojuan, Peng Zhang, et al. Gait Representation and Classification Algorithm Based on Multi Area Segmentation. Chinese Journal of Computers, 2006, 29(10): 1876-1881 (in Chinese) (杨 军,吴晓娟,彭 彰,等.基于多区域分割的步态表示与识别算法研究.计算机学报, 2006, 29(10): 1876-1881) [4] Wang Liang, Hu Weiming, Tan Tieniu. Gait-Based Human Identification. Chinese Journal of Computers, 2003, 26(3): 353-360 (in Chinese) (王 亮,胡卫明,谭铁牛.基于步态的身份识别.计算机学报, 2003, 26(3): 353-360) [5] Wang Liang, Tan Tieniu, Hu Weiming, et al. Automatic Gait Recognition Based on Statistical Shape Analysis. IEEE Trans on Image Processing, 2003, 12(9): 1120-1131 [6] Zhao Zijian, Wu Xiaojuan, Liu Yuncai. A Gait Recognition Algorithm Based on Angle Histogram. Computer Engineering Science, 2006, 28(6): 73-76 (in Chinese) (赵子健,吴晓娟,刘允才.基于角度直方图的步态识别算法.计算机工程与科学, 2006, 28(6): 73-76) [7] Zhao Zijian, Wu Xiaojuan. Research on Gait Recognition Based on Approximate Space-Time Slice Vectors. Pattern Recognition and Artificial Intelligence. 2005, 18(5): 608-614 (in Chinese) (赵子健,吴晓娟.基于近似时空切片向量的步态识别方法研究.模式识别与人工智能, 2005, 18(5): 608-614) [8] Peng Zhang, Wu Xiaojuan, Yang Jun. A Multi-View Method for Gait Recognition Based on the Length of Bodys Parts. Acta Automatica Sinica, 2007, 33(2): 210-213 (in Chinese) (彭 彰,吴晓娟,杨 军.基于肢体长度参数的多视角步态识别算法,自动化学报, 2007, 33(2):210-213) [9] Sarkar S, Phillips P J, Liu Z, et al. The HumanID Gait Challenge Problem: Data Sets, Performance, and Analysis. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(2): 162-177 [10] Han Ju, Bhanu B. Individual Recognition Using Gait Energy Image. IEEE Trans on Pattern Analysis and Machine Intelligence, 2006, 28(2): 316-322 [11] Ma Qinyong, Wang Shenkang, Nie Dongdong, et al. Moment Gait Energy Image Based Human Recognition at a Distance. Acta Electrnica Sinica, 2007, 35(11): 2078-2082 (in Chinese) (马勤勇,王申康,聂栋栋,等.基于瞬时步态能量图的远距离身份识别.电子学报, 2007, 35(11): 2078-2082) [12] CASIA Gait Database [DB/OL]. [2006-06-10]. http://www.cbsr.ia.ac.cn/China/index%20.CH.asp [13] Shutler J D, Grant M G, Nixon M S, et al. On a Large Sequence-Based Human Gait Database // Proc of the International Conference on Recent Advances in Soft Computing. Nottingham, UK, 2002: 66-71 [14] Guo Dajun. Handbook of Mathematics. Jinan, China: Shandong Science and Technology Press, 1985 (in Chinese) (郭大钧.大学数学手册.济南:山东科学技术出版社, 1985) [15] Papadimitriou C H, Steiglitz K. Combinatorial Optimization: Algorithms and Complexity. Upper Saddle River, USA: Prentice Hall, 1982 [16] Phillips P J, Moon H, Rizvi S A, et al. The FERET Evaluation Methodology for Face Recognition Algorithms. IEEE Trans on Pattern Analysis and Machine Intelligence. 2000, 22(10): 1090-1104 [17] Chen Shi, Ma Tianjun, Huang Wanhong, et al. Gait Recognition Based on Shape Context Descriptor. Pattern Recognition and Artificial Intelligence, 2007, 20(6): 794-799 (in Chinese) (陈 实,马天骏,黄万红,等.基于形状上下文描述子的步态识别.模式识别与人工智能, 2007, 20(6): 794-799) [18] Wang Liang, Ning Huazhong, Tan Tieniu, et al. Fusion of Static and Dynamic Body Biometrics for Gait Recognition. IEEE Trans on Circuits and Systems for Video Technology, 2004, 14(2): 149-158 [19] Wagg D K, Nixon M S. On Automated Model-Based Extraction and Analysis of Gait // Proc of the IEEE International Conference on Automatic Face and Gesture Recognition. Seoul, South Korea, 2004: 11-16 [20] Chen Shi, Ma Tianjun, Huang Wanhong, et al. A Multi-Layer Windows Method of Moments for Gait Recognition. Journal of Electronics Information Technology, 2009, 31(1): 116-119 (in Chinese) (陈 实,马天骏,黄万红,等.用于步态识别的多层窗口图像矩.电子与信息学报, 2009, 31(1): 116-119)
2010, Vol. 23 
