基于Kinect的人体危险动作检测
Human Dangerous Action Detection Based on Kinect

作者: 李晓林 :淄博职业学院,山东 淄博 ; 吕周南 , 孙凤池 :南开大学软件学院,天津 ;

关键词: 危险动作骨骼跟踪跌倒检测模式分类支持向量机Dangerous Action Skeletal Tracking Fall Detection Pattern Classification Support Vector Machine

摘要: 针对家庭环境中老年人的健康安全问题,提出了一种基于Kinect骨骼数据的人体危险动作检测方法。对日常生活中的人体动作模式进行分析,将对人体直接造成伤害和预示着人体即将受到伤害的两种动作定义为危险动作。利用Kinect传感器提供的骨骼跟踪获取人体的头部位置,对不同动作模式下人体头部位置的变化规律进行分析。根据头部位置变化作为危险动作检测的特征,通过支持向量机分类器对人体的动作模式进行分类,可以有效检测出日常家居环境中的危险动作,与基于头部运动速度的方法相比,误判、漏判现象明显减少,识别正确率较高,且具有良好的可扩展性。

Abstract: In view of the health and safety of the elderly in the family environment, a human dangerous action detection method based on Kinect skeletal data is proposed. The action that will directly damage human body or presage the happening of dangerous situation is defined as dangerous action by the analysis of human behavior in daily life. The head position of human body is obtained by using Kinect sensor and the change of head position in different action modes is analyzed. The action mode of human body is classified by support vector machine classifier according to the changes of head position as hazardous motion detection features so that the dangerous action in daily home environment can be effectively detected. Compared with the method based on the velocity of the head, misjudgment and false negative phenomenon are significantly reduced, and this method has good scalability and high recognition accuracy.

文章引用: 李晓林 , 吕周南 , 孙凤池 (2016) 基于Kinect的人体危险动作检测。 传感器技术与应用, 4, 8-14. doi: 10.12677/JSTA.2016.41002

参考文献

[1] 杨冬叶, 赵勇. 我国空巢老年人的现状与对策[J]. 现代临床护理, 2004, 3(5): 60-62.

[2] 徐光佑, 曹媛媛. 动作识别与行为理解综述[J]. 中国图像图形学报, 2009, 14(2): 189-195.

[3] Alwan, M., Rajendran, P.J., Kell, S., et al. (2006) A Smart and Passive Floor-Vibration Based Fall Detector for Elderly. Information & Communication Technol-ogies, ICTTA, 1, 1003-1007.

[4] Sixsmith, A. and Johnson, N. (2004) A Smart Sensor to Detect the Falls of the El-derly. IEEE Pervasive Computing, 3, 42-47.

[5] Li, Q., Zhou, G. and Stankovic, J.A. (2008) Accurate, Fast Fall De-tection Using Posture and Context Information. Proceedings of the 6th ACM Conference on Embedded Network Sensor Systems, Raleigh, 5-7 November 2008, 443- 444.

[6] Nait-Charif, H. and Mckenna, S.J. (2004) Activity Summarisa-tion and Fall Detection in a Supportive Home Environment. International Conference on Pattern Recognition, IEEE Computer Society, Cambridge, UK, 23-26 August 2004, 323-326.

[7] Gritti, A.P., Tarabini, O., Guzzi, J., Di Caro, G.A., Caglioti, V., Gambardella, L.M. and Giusti, A. (2014) Kinect-Based People Detection and Tracking from Small-Footprint Ground Robot. IEEE/RSJ International Conference on Intelligent Robots and Systems, Chicago, 14-18 September 2014, 4096-4013.

[8] Wang, K., Wang, X., Pan, Z. and Liu, K. (2013) A Two-Stage Framework for 3D Face Reconstruction from RGBD Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 1493-1504.

[9] 范宝华, 王秀平. 老年人的跌倒问题及护理对策[J]. 解放军护理杂志, 2001, 18(2): 24.

[10] 赵海勇. 基于视频流的运动人体行为识别研究[D]: [博士论文]. 西安: 西安电子科技大学, 2011.

[11] Hazelhoff, L., Han, J.G. and De With, P.H.N. (2008) Video-Based Fall Detection in the Home Using Principal Component Analysis. Advanced Concepts for Intelligent Vision Systems, 5259, 298-309.

[12] 余涛. Kinect应用开发实战: 最自然的方式与机器对话[M]. 北京: 机械工程出版社, 2012: 57-60.

分享
Top