基于相对运动特征的步态识别方法

系统仿真学报 ›› 2015, Vol. 27 ›› Issue (10): 2299-2304.

基于相对运动特征的步态识别方法

杨科, 窦勇, 吕绍和

并行与分布处理重点实验室国防科学技术大学,长沙 410073

收稿日期:2015-06-14 修回日期:2015-07-31 出版日期:2015-10-08 发布日期:2020-08-07
作者简介:杨科(1990-),男,河南,硕士,研究方向为模式识别;窦勇(1966-),男,吉林,博士,研究方向为可重构计算,人工智能;吕绍和(1982-),男,博士,研究方向为无线通信,人工智能。
基金资助:
国家863计划主题项目子课题(2012AA012706)

Gait Recognition Based-on Relative Motion Features and Kinect

Yang Ke, Dou Yong, Lv Shaohe

National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha 410073, China

Received:2015-06-14 Revised:2015-07-31 Online:2015-10-08 Published:2020-08-07

摘要/Abstract

摘要： 步态识别是一项很重要的生物识别技术。步态特征分为静态与运动两类。一些工作发现,尽管步态的本质特性在于运动,但运动特征的识别能力较为有限。究竟是运动本身的区分能力有限,还是现有特征未能充分捕获运动特性目前尚不清楚。基于Kinect骨骼模型,相对运动特征被提出,特定关节点之间的距离及其变化被用来刻画步态。相对运动特征的获取无需计算步态周期,鲁棒性好。实验结果显示,相对运动特征的识别精度达84%,与静态特征相当;与已有运动特征相比,精度提高10%以上。

关键词: 动态步态特征, 相对运动特征, 步态识别, 生物识别技术

Abstract: Gait recognition Kinect is a very important biometric technology. Gait feature can be divided into two categories: static and dynamic. Some work found that although the essential characteristics of gait are motion, but the motion feature's recognition capability is limited. However, is the distinguishing ability of the motion itself limited, or existing features doesn't adequately capture the characteristics of motion? Relative distance-based motion features were proposed, and distances between the particular skeleton points and their changes were used to characterize the gait. The relative motion features were extracted without calculating the gait cycle, and with robustness. Experimental results show that the relative motion features' recognition accuracy is up to 84%, which is equivalent to static characteristic.

Key words: dynamic gait feature, relative motion feature, gait recognition, biometrics

中图分类号:

TP391.9

杨科, 窦勇, 吕绍和. 基于相对运动特征的步态识别方法[J]. 系统仿真学报, 2015, 27(10): 2299-2304.

Yang Ke, Dou Yong, Lv Shaohe. Gait Recognition Based-on Relative Motion Features and Kinect[J]. Journal of System Simulation, 2015, 27(10): 2299-2304.

参考文献

[1] Xiaofei He, Shuicheng Yan, Yuxiao Hu, et al. Face Recognition using Laplacianfaces[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on (S0162-8828), 2005, 27(3): 328-340.
[2] Jain Anil K, Hong L, Bolle R.An identity-authentication system using fingerprints[C]// Proceedings of the IEEE 85.9 (1997). USA: IEEE, 1997: 1365-1388.
[3] Bouchrika I, Goffredo M, Carter J, et al. On using gait in forensic biometrics[J]. Journal of Forensic Sciences (S1556-4029), 2011, 56(4): 882-889
[4] Phillips P J, Sarkar S., Robledo I, et al. The gait identification challenge problem: data sets and baseline algorithm[C]// Pattern Recognition, 2002, Proceedings 16th International Conference on. Vol. 1. USA: IEEE, 2002.
[5] Han Ju, Bir Bhanu.Individual recognition using gait energy image[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on (S0162-8828), 2006, 28(2): 316-322.
[6] Bashir Khalid, Tao Xiang, Shaogang Gong.Gait recognition using gait entropy image[C]// IET Conference Proceedings. London, UK: IET, 2009: 1-6.
[7] Wang Chen, Junping Zhang, Jian Pu, et al. Chrono-gait image: a novel temporal template for gait recognition[C]// Computer Vision-ECCV 2010. Germany: Springer Berlin Heidelberg, 2010: 257-270.
[8] Cunado David, Mark S Nixon, John N Carter.Using gait as a biometric, via phase-weighted magnitude spectra[C]// Audio-and Video-based Biometric Person Authentication. Germany: Springer Berlin Heidelberg, 1997.
[9] Yoo Jang-Hee, Mark S Nixon, Chris J Harris.Extracting gait signatures based on anatomical knowledge[C]// Proceedings of BMVA Symposium on Advancing Biometric Technologies, London, UK: BMVA, 2002: 1-2.
[10] Lombardi S, Nishino K, Makihara Y, et al. Two-Point Gait: Decoupling Gait from Body Shape[C]// Computer Vision (ICCV), 2013 IEEE International Conference on. USA: IEEE, 2013: 1041-1048.
[11] Veeraraghavan Ashok, Amit K Roy-Chowdhury, Rama Chellappa. Matching shape sequences in video with applications in human movement analysis[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on (S0162-8828), 2005, 27(12): 1896-1909.
[12] Andersson V, R Araujo. Person identification using anthropometric and gait data from kinect sensor[C]// Proceedings of the Twenty-Ninth Association for the Advancement of Artificial Intelligence Conference, AAAI, 2015. USA: AIAA, 2015.
[13] Araujo Ricardo M, Gustavo Graña, Virginia Andersson.Towards skeleton biometric identification using the microsoft kinect sensor[C]// Proceedings of the 28th Annual ACM Symposium on Applied Computing. USA: ACM, 2013.
[14] Preis Johannes, Mortiz Kessel, Martin Werner, et al. Gait recognition with kinect[C]// 1st International Workshop on Kinect in Pervasive Computing, 2012.
[15] Ball Adrian, David Rye, Fabio Ramos, et al. Unsupervised clustering of people from 'skeleton' data[C]// Proceedings of the Seventh Annual ACM/IEEE International Conference on Human-Robot Interaction. USA: ACM, 2012.
[16] Ahmed Mohammed, Naseer Al-Jawad, Azhin Sabir.Gait recognition based on Kinect sensor[C]// SPIE Photonics Europe. Brussels, Belgium: International Society for Optics and Photonics, 2014.
[17] Gianaria Elena, Balossino Nello, Grangetto Marco, et al. Gait characterization using dynamic skeleton acquisition[C]// Multimedia Signal Processing (MMSP), 2013 IEEE 15th International Workshop on. USA: IEEE, 2013.
[18] Chattopadhyay Pratik, Shamik Sural, Jayanta Mukherjee. Frontal Gait Recognition from Incomplete Sequences using RGB-D Camera [C]// (2014) Information Forensics and Security, IEEE Transactions on. USA: IEEE, 2014.