Abstract As a remote and indirect recognition technology, human gait recognition has extensive applications in various fields, such as video-based surveillance systems. In this paper, the continuous density hidden Markov models (CD-HMM) is employed to perform gait recognition. Firstly, a feature extraction algorithm is proposed based on natural gait cycles,and the observation vector set is constructed using the extracted features. Then, the gait vector set extracted from the training sample set is used to estimate the parameters of CD-HMM. Finally, an adaptive algorithm is introduced based on Cox regression analysis to adaptively adjust parameters of the trained gait model. Experimental results show that the proposed method produces higher accuracies compared with other methods.
Fund:Supported by National Natural Science Foundation of China (No.61303146,61100160)
About author:: (WANG Xiuhui(Corresponding author), born in 1978, Ph.D., associate professor. His research interests include computer graphics and pattern recognition.)(YAN Ke, born in 1983, Ph.D., lecture. His research inte-rests include computer graphics, computational geometry, data mining and machine learning.)
[1] SARKAR S, PHILLIPS P J, LIU Z Y, 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. [2] 贲晛烨,徐 森,王科俊.行人步态的特征表达及识别综述.模式识别与人工智能, 2012, 25(1): 71-81. (BEN X Y, XU S, WANG K J. Review on Pedestrian Gait Feature Expression and Recognition. Pattern Recognition and Artificial Inte-lligence, 2012, 25(1): 71-81.) [3] MOUSTAKAS K, TZOVARAS D, STAVROPOULOS G. Gait Re-cognition Using Geometric Features and Soft Biometrics. IEEE Signal Processing Letters, 2010, 17(4): 367-370. [4] HUANG X X, BOULGOURIS N V. Gait Recognition with Shifted Energy Image and Structural Feature Extraction. IEEE Trans on Image Processing, 2012, 21(4): 2256-2268. [5] KUSAKUNNIRAN W, WU Q, ZHANG J, et al. Gait Recognition Across Various Walking Speeds Using Higher Order Shape Configuration Based on a Differential Composition Model. IEEE Trans on Systems, Man, and Cybernetics(Cybernetics), 2012, 42(6): 1654-1668. [6] 张元元,吴晓娟,阮秋琦.基于切向角特征的统计步态识别.模式识别与人工智能, 2010, 23(4): 539-545. (ZHANG Y Y, WU X J, RUAN Q Q. Statistical Gait Recognition Based on Tangent Angle Features. Pattern Recognition and Artificial Intelligence, 2010, 23(4): 539-545.) [7] HU M D, WANG Y H, ZHANG Z X, et al. Incremental Learning for Video-Based Gait Recognition with LBP Flow. IEEE Trans on Cybernetics, 2013, 43(1): 77-89. [8] BOULGOURIS N V, HUANG X X. Gait Recognition Using HMMs and Dual Discriminative Observations for Sub-dynamics Analysis. IEEE Trans on Image Processing, 2013, 22(9): 3636-3647. [9] HONG S J, LEE H S, KIM E. Probabilistic Gait Modeling and Recognition. IET Computer Vision, 2013, 7(1): 56-70. [10] 王科俊,阎 涛,吕卓纹,等.核稀疏保留投影及在步态识别中的应用.中国图象图形学报, 2013, 18(3): 257-263. (WANG K J, YAN T, L Z W, et al. Kernel Sparsity Preserving Projections and Its Application to Gait Recognition. Journal of Image and Graphics, 2013, 18(3): 257-263.) [11] LAI Z H, XU Y, JIN Z, et al. Human Gait Recognition via Sparse Discriminant Projection Learning. IEEE Trans on Circuits and Systems for Video Technology, 2014, 24(10): 1651-1662. [12] MURAMATSU D, MAKIHARA Y, YAGI Y. Cross-View Gait Recognition by Fusion of Multiple Transformation Consistency Measures. IET Biometrics, 2015, 4(2): 62-73. [13] ZHANG Y T, PAN G, JIA K, et al. Accelerometer-Based Gait Recognition by Sparse Representation of Signature Points with Clusters. IEEE Trans on Cybernetics, 2015, 45(9): 1864-1875. [14] MURAMATSU D, SHIRAISHI A, MAKIHARA Y, et al. Gait-Based Person Recognition Using Arbitrary View Transformation Model. IEEE Trans on Image Processing, 2015, 24(1): 140-154. [15] GUAN Y, LI C T, ROLI F. On Reducing the Effect of Covariate Factors in Gait Recognition: A Classifier Ensemble Method. IEEE Trans on Pattern Analysis and Machine Intelligence, 2015, 37(7): 1521-1528. [16] AMIN M G, AHMAD F, ZHANG Y M D, et al. Human Gait Reco-gnition with Cane Assistive Device Using Quadratic Time-Frequency Distributions. IET Radar, Sonar and Navigation, 2015, 9(9): 1224-1230. [17] RIDA I, JIANG X D, MARCIALIS G L. Human Body Part Selection by Group Lasso of Motion for Model-Free Gait Recognition. IEEE Signal Processing Letters, 2016, 23(1): 154-158. [18] LIU X M, CHEN T H. Video-Based Face Recognition Using Ada-ptive Hidden Markov Models // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2003, I: 340-345. [19] 杨 戈,刘 宏.视觉跟踪算法综述.智能系统学报, 2010, 5(2): 95-105. (YANG G, LIU H. Survey of Visual Tracking Algorithms. CAAI Transactions on Intelligent Systems, 2010, 5(2): 95-105.) [20] 杨 威,付耀文,潘晓刚,等.弱目标检测前跟踪技术研究综述.电子学报, 2014, 42(9): 1786-1793. (YANG W, FU Y W, PAN X G, et al. Track-Before-Detect Technique for Dim Targets: An Overview. Acta Electronica Sinica, 2014, 42(9): 1786-1793.) [21] THEEKHANONT P, KURUTACH W, MIGUET S. Gait Recognition Using GEI and Pattern Trace Transform // Proc of the IEEE International Symposium on Information Technology in Medicine and Education. New York, USA: IEEE, 2012: 936-940. [22] DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum Likelihood from Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society (Methodological), 1977, 39(1): 1-38. [23] SONG Y, LIANG W Q. Experimental Study of Discriminative Adaptive Training and MLLR for Automatic Pronunciation Evaluation. Tsinghua Science and Technology, 2011, 16(2): 189-193. [24] YU S Q, TAN D L, TAN T N. A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition // Proc of the 18th International Conference on Pattern Recognition.Hong Kong, China: IEEE, 2006, IV: 441-444.
2016, Vol. 29 
