一种基于关节点信息的人体行为识别新方法

doi:10.3724/SP.J.1218.2014.00285

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (617 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
田国会, 尹建芹, 韩旭, 于静. 一种基于关节点信息的人体行为识别新方法[J]. 机器人, 2014, 36(3): 285-292.DOI: 10.3724/SP.J.1218.2014.00285. TIAN Guohui, YIN Jianqin, HAN Xu, YU Jing. A Novel Human Activity Recognition Method Using Joint Points Information. ROBOT, 2014, 36(3): 285-292. DOI: 10.3724/SP.J.1218.2014.00285.

摘要

为了提高机器人服务的主动性与智能性，使用Kinect体感设备获取人体的关节点数据解决人体行为识别问题．首先，利用Kinect采集人体关节点坐标，构造用于表示人体结构的3维空间向量，然后计算结构向量之间的角度和向量模的比值，进行人体姿态描述，同时以一段时间内连续的姿态序列作为行为表示特征量，最后选用动态时间规整（DTW）算法计算测试行为模板与参考行为模板之间的相似度以实现行为识别．实验结果表明，选用的行为表示特征量具有旋转与平移不变性．另外，对人在日常生活中的6种行为进行了识别实验，结果表明本文的行为识别算法可以取得较好的识别效果．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	田国会
	尹建芹
	韩旭
	于静

关键词 ：人体行为识别, 人体关节点, 行为表示, 动态时间规整

Abstract：

In order to increase the activeness and intelligence of robot services, Kinect is used to collect the joint point information for the recognition of human activities. Firstly, coordinates of human joint points are acquired by Kinect, and the three-dimensional structure vector is constructed to represent the human body structure. Then, the angles and the ratios of structure vector lengths between the space vectors are computed to represent the human postures. Meanwhile, the behavior is represented by continuous posture sequences within a limited timespan. At last, dynamic time warping (DTW) algorithm is applied to implementing the activity recognition by calculating the similarity between test behavior sequence and reference activity template. The experimental results show that the behavior representation scheme is invariant to rotation and translation. Moreover, experiments are conducted to recognize 6 kinds of human activities in daily living, and the results show that better recognition results can be acquired by the proposed algorithm.

Key words： human activity recognition human joint point activity representation dynamic time warping

收稿日期: 2013-07-17 录用日期: 2014-04-29

TP391

基金资助:

国家自然科学基金资助项目（61075092，61203341）；山东省自然科学基金资助项目（ZR2011FM011）；山东大学自主创新基金资助项目（2011JC017）

通讯作者: 尹建芹，ise_yinjq@ujn.edu.cn E-mail: ise_yinjq@ujn.edu.cn

作者简介: 李睿（1986- ），女，博士．研究领域：工业机器人，精密光电测量．
曲兴华（1956- ），男，博士，教授．研究领域：精密光电测量．

链接本文:

https://robot.sia.cn/CN/10.3724/SP.J.1218.2014.00285 或 https://robot.sia.cn/CN/Y2014/V36/I3/285

[1] Aggarwal J K, RyooMS. Human activity analysis: A review[J]. ACM Computing Surveys, 2011, 43(3): No.16.

[2] 谷军霞,丁晓青,王生进.行为分析算法综述[J].中国图象图形学报,2009,14(3):377-387. Gu J X, Ding X Q,Wang S J. A survey of activity analysis algorithms[J]. Journal of Image and Graphics, 2009, 14(3): 377-387.

[3] Weinland D, Ronfard R, Boyer E. A survey of visionbased methods for action representation, segmentation and recognition[J]. Computer Vision and Image Understanding, 2011,115(2): 224-241.

[4] 杜友田,陈峰,徐文立,等.基于视觉的人的运动识别综述[J].电子学报,2007,35(1):84-90. Du Y T, Chen F, Xu W L, et al. A survey on the vision-based human motion recognition[J]. Acta Electronica Sinica, 2007, 35(1): 84-90.

[5] Cheng L Y, Sun Q, Su H, et al. Design and implementation of human-robot interactive demonstration system based on Kinect[C]//Proceedings of the 24th Chinese Control and Decision Conference. Piscataway, USA: IEEE, 2012: 971-975.

[6] 尹建芹,田国会,姜海涛,等.面向家庭服务的人体动作识别[J].四川大学学报:工程科学版,2011,43(4):101-107. Yin J Q, Tian G H, Jiang H T, et al. Human action recognition oriented to family service[J]. Journal of Sichuan University: Engineering Science Edition, 2011, 43(4): 101-107.

[7] 尹建芹,田国会,周风余.智能空间下基于时序直方图的人体行为表示与理解[J].计算机学报,2014,37(2):470-479. Yin J Q, Tian G H, Zhou F Y. Human activity representation and recognition based on temporal order histogram in intelligent space[J]. Chinese Journal of Computers, 2014, 37(2): 470-479.

[8] Wu J X, Osuntogun A, Choudhury T, et al. A scalable approach to activity recognition based on object use[C]//IEEE International Conference on Computer Vision. Piscataway, USA: IEEE, 2007: 1-8.

[9] Li C C, Chen Y Y. Human posture recognition by simple rules[C]//2006 IEEE International Conference on Systems, Man, and Cybernetics. Piscataway, USA: IEEE, 2007: 3237-3240.

[10] Rodriguez M D, Ahmed J, Shah M. Action MACH: A spatiotemporal maximum average correlation height filter for action recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2008: 3001-3008.

[11] Biswas J, Veloso M. Depth camera based indoor mobile robot localization and navigation[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2012: 1697-1702.

[12] 杨东方,王仕成,刘华平,等.基于Kinect 系统的场景建模与机器人自主导航[J].机器人,2012,34(5):581-589. Yang D F, Wang S C, Liu H P, et al. Scene modeling and autonomous navigation for robots based on Kinect system[J]. Robot, 2012, 34(5): 581-589.

[13] Noel R R, Salekin A, Islam R. A natural user interface classroom based on Kinect[J]. IEEE Learning Technology, 2011, 13(4): 59-61.

[14] Rogers III J G, Christensen H I. A conditional random field model for place and object classification[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2012: 1766-1772.

[15] Izadi S, Kim D, Hilliges O, et al. KinectFusion: Real-time 3D reconstruction and interaction using a moving depth camera[C]//24th Annual ACM Symposium on User Interface Software and Technology. New York, USA: ACM, 2011: 559-568.

[16] Thanh T T, Chen F, Kotani K, et al. Extraction of discriminative patterns from skeleton sequences for human action recognition[C]//IEEE International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future. Piscataway, USA: IEEE, 2012: 6pp.

[17] Girshick R, Shotton J, Kohli P, et al. Efficient regression of general-activity human poses from depth images[C]//IEEE International Conference on Computer Vision. Piscataway, USA: IEEE, 2011: 415-422.

[18] Sempena S, Maulidevi N U, Aryan P R. Human action recognition using dynamic time warping[C]//2011 International Conference on Electrical Engineering and Informatics. Piscataway, USA: IEEE, 2011: 5pp.

[19] Raptis M, Kirovski D, Hoppe H. Real-time classification of dance gestures from skeleton animation[C]//ACM SIGGRAPH/ Eurographics Symposium on Computer Animation. New York, USA: ACM, 2011: 147-156.

[20] Xia L, Chen C C, Aggarwal J K. View invariant human action recognition using histograms of 3D joints[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2012: 20-27.

[21] Packer B, Saenko K, Koller D. A combined pose, object, and feature model for action understanding[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2012: 1378-1385.

[22] Lai K, Konrad J, Ishwar P. A gesture-driven computer interface using Kinect[C]//IEEE Southwest Symposium on Image Analysis and Interpretation. Piscataway, USA: IEEE, 2012: 185-188.

[23] Sanchez-Riera J, Cech J, Horaud R. Action recognition robust to background clutter by using stereo vision[C]//12th European Conference on Computer Vision. Berlin, Germany: Springer, 2012: 332-341.

[24] Misumi H, Fujimura W, Kosaka T, et al. GAMIC: Exaggerated real time character animation control method for full-body gesture interaction systems[C]//ACM SIGGRAPH 2011. New York, USA: ACM, 2011: 5.

[25] Lin S Y, Shie C K, Chen S C, et al. Human action recognition using action trait code[C]//21st International Conference on.Pattern Recognition. Piscataway, USA: IEEE, 2012: 3456-3459.

[26] Patsadu O, Nukoolkit C, Watanapa B. Human gesture recognition using Kinect camera[C]//9th International Joint Conference on Computer Science and Software Engineering. Piscataway, USA: IEEE, 2012: 28-32.

[27] Yang X D, Zhang C Y, Tian Y L. Recognizing actions using depth motion maps-based histograms of oriented gradients[C]//Proceedings of the 20th ACM International Conference on Multimedia. New York, USA: ACM, 2012: 1057-1060.

[28] Lallee S, Lemaignan S, Lenz A, et al. Towards a platformindependent cooperative human-robot interaction system: I. Perception[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2010: 4444-4451.

[29] Lallée S, Pattacini U, Boucher J D, et al. Towards a platformindependent cooperative human-robot interaction system: II. Perception, execution and imitation of goal directed actions[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2011: 2895-2902.