|
|
|
| Gait Recognition Based on Spatio-Temporal HOG Feature of Plantar Pressure Distribution |
| XIA Yi1,2,MA Zu-Chang2,YAO Zhi-Ming2,SUN Yi-Ning 2 |
1.School of Information Science and Technology,University of Science and Technology of China,Hefei 230026
2.Research Centre for Information Technology of Sports and Health,Institute of Intelligent Machines,Chinese Academy of Sciences,Hefei 230031 |
|
|
|
|
Abstract A gait recognition method based on spatio-temporal histogram of oriented gradient (HOG) is proposed. Spatio-temporal HOG embodies the feature fusion of spatial and temporal plantar pressure information. Firstly,several key points,such as the maximum and the minimum points on the pressure-time curve,are picked out. Then,plantar pressure distribution images corresponding to the moment of key points are used to construct spatio-temporal HOG feature vector. Finally,support vector machine classification is applied to implement gait classification. Gait samples are collected from 30 persons at different walking speeds. When the walking speeds of the samples in the training and testing sets are not differentiated,the recognition rate is 93.5%. The experimental results demonstrate that spatio-temporal HOG feature accurately describes the dynamic plantar pressure distribution during walking,and it also has good speed-adaptable properties.
|
|
Received: 25 September 2012
|
|
|
|
|
|
[1\]Murakita T,Ikeda T,Ishiguro H. Human Tracking Using Floor Sensors Based on the Markov Chain Monte Carlo Method // Proc of the 17th International Conference on Pattern Recognition. Cambridge,UK,2004,IV: 917-920
[2]Liau W H,Wu Chaolin,Fu Lichen. Inhabitants Tracking System in a Cluttered Home Environment via Floor Load Sensors. IEEE Trans on Automation Science and Engineering,2008,5(1): 10-20
[3]Takeda T,Kuramoto K,Kobashi S,et al. Biometrics Security by Dynamics of Left and Right Sole Pressure While Walking［EB/OL］.［2012-07-1］.ttp://proceedings.spiedigitallibrary.org/data/Conferences/SPIEP/62093/805814_1.pdf
[4]Murray M P. Gait as a Total Pattern of Movement. American Journal of Physical Medicine,1967,46(1): 290-332
[5]Kale A,Sundaresan A,Rajagopalan A,et al. Identification of Humans Using Gait. IEEE Trans on Image Processing,2004,13(9): 1163-1173
[6]Shi Limin,Dong Jiaying,Li Taishan,et al. Primary Exploring of Incomplete Barefoot Test. Journal of Liaoning Police Academy,2005,(2): 6-9(in Chinese)
(史力民,董佳英,李泰山,等.赤足残缺足迹检验初探.辽宁警专学报,2005,(2): 6-9)
[7]Rodriguez R V,Evans N W D,Lewis R P,et al. An Experimental Study on the Feasibility of Footsteps as a Biometric［EB/OL］.［2012-07-01］. http://atvs.ii.uam.es/files/FootstepBiometri cEUSIPCO07.pdf
[8]Lin Erdong,Yao Zhiming,Zheng Zhong,et al. An Improved Gait Recognition Method Based on Ground Reaction Force. Pattern Recognition and Artificial Intelligence,2011,24(3): 353-359(in Chinese)
(林尔东,姚志明,郑 重,等.一种改进的基于地面反作用力的步态识别方法.模式识别与人工智能,2011,24(3): 353-359)
[9]2Vera R R,Mason J,Fierrez J,et al. Analysis of Time Domain Information for Footstep Recognition // Proc of the 6th International Symposium on Visual Computing. Las Vegas,USA,2010: 489-498
[10]Cho Y O,So B C,Jung J W. User Recognition Using Sequential Footprints under Shoes Based on Mat Type Floor Pressure Sensor. Advanced Science Letters,2012,9(1): 591-596
[11]Qian Gang,Zhang Jiqing,Kidane A. People Identification Using Floor Pressure Sensing and Analysis. IEEE Sensors Journal,2010,10(9): 1447-1460
[12]Mary H,Mitul V,Jason L,et al. Foot Pressure Distribution during Walking in Young and Old Adults. BMC Geriatrics,2005,5(1): 8-16
[13]de Cock A,Willems T,Witvrouw E,et al. A Functional Foot Type Classification with Cluster Analysis Based on Plantar Pressure Distribution during Jogging. Gait and Posture,2006,23(3): 339-347
[14]Razeghi M,Batt M E. Foot Type Classification: a Critical Review of Current Methods. Gait and Posture,2002,15(3): 282-291
[15]Lyons T E,Rosenblum B I,Veves A. The Diabetic Foot. New York,USA: Humana Press,2006
[16]Abdurakhmanov M A,Stolyarov I D,Il'vesa A G,et al. Measuring the Distribution of Plantar Pressures during Walking in Patients with Multiple Sclerosis to Evaluate Treatment Efficiency. Human Physiology,2006,32(2): 154-156
[17]Dalal N,Triggs B,Schmid C. Human Detection Using Oriented Histograms of Flow and Appearance // Proc of the 9th European Conference on Computer Vision. Graz,Austria,2006: 428-441
[18]Laptev I,Marszalek M,Schmid C,et al. Learning Realistic Human Actions from Movies // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos,USA,2008: 1-8
[19]Oliveira F P M,Sousa A,Santos R,et al. Spatio Temporal Alignment of Pedobarographic Image Sequences. Medical and Biological Engineering and Computing,2011,49(7): 843-850
[20]Tao Qing,Yao Sui. A New Kind of Machine Learning Algorithm: Support Vector Machines. Pattern Recognition and Artificial Intelligence,2000,13(3): 285-290(in Chinese)
(陶卿,姚穗.一种新的机器学习算法: Support Vector Machines.模式识别与人工智能,2000,13(3): 285-290)
[21]Jia Wei,Hu Rongxiang,Gui Jie,et al. Newborn Footprint Recognition Using Band Limited Phase Only Correlation // Proc of the 2nd International Conference on Medical Biometrics. Hong Kong,China,2010: 83-93
[22]Pataky T C,Goulermas J Y,Crompton R H. A Comparison of Seven Methods of Within Subjects Rigid Body Pedobarographic Image Registration. Journal of Biomechanics,2008,41(14): 3085-3089
[23]Suutala J,Rning J. Methods for Person Identification on a Pressure Sensitive Floor: Experiments with Multiple Classifiers and Reject Option. Information Fusion,2008,9(1): 21-40
[24]Turk M,Pentland A. Eigenfaces for Recognition. Journal of Cognitive Neuroscience,1991,3(1): 71-86
[25]Yun J,Woo W,Ryu J. User Identification Using User's Walking Pattern over the UbiFloorII // Proc of the International Conference on 2Computational Intelligence and Security. Xi'an,China,2005: 949-956 |
|
|
|
2013, Vol. 26 
