A Method for Human Gait Recognition Using SpatialTemporal Analysis
SU Han1,2, HUANG FengGang1
1.School of Computer Science and Technology, Harbin Engineering University, Harbin 150001 2.School of Computer Science, Sichuan Normal University, Chengdu 610068
Abstract A new method for modelfree recognition of gait based on silhouette in computer vision sequences is proposed. The silhouette shape is represented by a novel approach which includes not only the spatial body contour but also the temporal information. Using this shape representation, the temporal information is extracted with low cost of computation. First, a background subtraction is used to separate objects from background, and gait cycle is obtained by analyzing the variety of the silhouette width and height. Then, the spatial shape of walker and their motion by the temporal matrix are presented, and Discrete Fourier analysis is used to analyze the gait feature. The nearest neighbor classifier is used to distinguish the different gaits of human. The performance of the proposed approach is tested on different gait databases. Recognition results show it is efficient.
[1] Murary M P. Gait as a Total Pattern of Movement. American Journal of Physical Medicine, 1967, 46(1): 290332 [2] Zhang Daxu, Dai Kerong, Peng Jiaxiong. A Self Adaptive Object Extraction and Tracking Method for Complex Image Sequence. Acta Electronical Sinica,1994, 22(10): 4651 (in Chinese) (张大序,戴可荣,彭嘉雄.复杂图像序列的自适应目标提取和跟踪方法.电子学报, 1994, 22(10): 4651) [3] Wang Liang, Hu Weiming, Tan Tieniu. GaitBased Human Identification. Chinese Journal of Computers, 2003, 26(3): 353360 (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): 353360) [4] Wang Liang, Tan Tieniu, Hu Weiming, et al. Automatic Gait Recognition Based on Statistical Shape Analysis. IEEE Trans on Image Processing, 2003, 12(9): 11201131 [5] Wang Liang, Tan Tieniu, Ning Huazhong, et al. Silhouette AnalysisBased Gait Recognition for Human Identification. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(12): 15051518 [6] Niyogi S A, Adelson E H. Analyzing and Recognizing Walking Figures in XYT // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Seattle, USA, 1994: 469474 [7] Nixon M S, Carter J N. Advances in Automatic Gait Recognition // Proc of IEEE Conference on Face and Gesture Analysis. Seoul, Korea, 2004: 1116 [8] BenAbdelkader C, Cutler R, Nanda H, et al. Eigengait: MotionBased Recognition of People Using Image SelfSimilarity // Proc of the 3rd International Conference on Audio and VideoBased Biometric Person Authentication. Halmstad, Sweden, 2001: 284294 [9] HayfronAcquah J B, Nixon M S, Carter J N. Automatic Gait Recognition by Symmetry Analysis. Pattern Recognition Letters, 2003, 24(13): 21752183 [10] Murase H, Sakai R. Moving Object Recognition in Eigenspace Representation: Gait Analysis and Lip Reading. Pattern Recognition Letters, 1996, 17(2): 155162 [11] Little J, Boyd J. Recognizing People by Their Gait: The Shape of Motion. Journal of Computer Vision Research, 1998, 1(2): 232 [12] Huang P, Harris C, Nixon M. Human Gait Recognition in Canonical Space Using Temporal Templates. Vision Image and Signal Processing, 1999, 146(2): 93100 [13] Cunado D, Nixon M S, Carter J N. Gait Extraction and Description by EvidenceGathering // Proc of the 2nd International Conference on Audio and VideoBased Biometric Person Authentication. Nixon, USA, 1999: 4348 [14] Yam C Y, Nixon M S, Carter J N. Automated Person Recognition by Walking and Running via ModelBased Approaches. Pattern Recognition, 2004, 37(5): 10571072 [15] Su Han, Huang Fenggang. Markerless Human Gait Recognition by Shape and Motion Analysis // Proc of the International Conference on Intelligent Sensing and Information Processing. Chennai, India, 2005: 161165
2007, Vol. 20 
