基于Kinect传感器的跌倒行为的检测与分析

高危作业现场环境复杂,危险系数高,容易发生跌倒事故,造成人员伤亡。为了检测工人跌倒行为,提出了一种基于Kinect传感器的人体跌倒检测方法。利用Kinect获取深度图像,提取关节点信息,通过计算关节点相对位置熵和速度的变化,判断人体是否发生跌倒。通过对比实验,确定了一组跌倒识别率最高的骨架关节点:头、双肩、双膝、中心点。实验数据表明该方法可以更快速准确地检测出跌倒行为。

Abstract

High-risk work site environments are complex and dangerous and responsible for many fall accidents and casualties. To detect the fall behavior of workers, a human fall detection method using a Kinect sensor was proposed. Based on depth images obtained using a Kinect, we extracted body joint points information and determined whether a human body fell by calculating the changes of the relative position entropy and speed of the joint points. Through comparative experiments, a set of skeleton joint points with the highest fall recognition rate were determined: head, shoulders, knees, and center points. Experimental data show that the method can detect fall behaviors more quickly and accurately compared with the conventional methods.

参考文献

[1] . 刍议建筑施工现场安全管理[J]. 中国安全生产科学技术, 2012, 8(7): 222-225.

. Discussion on safety management of construction site[J]. Journal of Safety Science and Technology, 2012, 8(7): 222-225.

[2] . 中国地下工程安全风险管理的现状、问题及相关建议[J]. 岩石力学与工程学报, 2008, 27(4): 649-655.

. State, issues and relevant recommendations for security risk management of China's underground engineering[J]. Chinese Journal of Rock Mechanics and Engineering, 2008, 27(4): 649-655.

[3] , 等. 基于穿戴式平台的老人摔倒监测系统设计[J]. 传感器与微系统, 2017, 36(7): 130-133.

, et al. Design of elderly tumble monitoring system based on wearable platform[J]. Transducer and Microsystem Technologies, 2017, 36(7): 130-133.

[4] . 基于室内无线传感器网络射频信号的老年人跌倒检测研究[J]. 电子学报, 2011, 39(1): 195-200.

. Fall detection using radio signals of home wireless sensor networks[J]. Acta Electronica Sinica, 2011, 39(1): 195-200.

[5] , 等. 利用姿势估计实现人体异常行为识别[J]. 仪器仪表学报, 2016, 37(10): 2366-2372.

, et al. Abnormal human body behavior recognition using pose estimation[J]. Chinese Journal of Scientific Instrument, 2016, 37(10): 2366-2372.

[6] . 基于主题隐马尔科夫模型的人体异常行为识别[J]. 计算机科学, 2012, 39(3): 251-255, 275.

. Human abnormal behavior recognition based on topic hidden Markov model[J]. Computer Science, 2012, 39(3): 251-255, 275.

[7] . 基于阈值与PSO-SVM的人体跌倒检测研究[J]. 计算机工程, 2016, 42(5): 317-321.

. Research on human fall detection based on threshold and PSO-SVM[J]. Computer Engineering, 2016, 42(5): 317-321.

[8] ShiX, XiongQ, LeiL. Research on fall detection system based on pressure sensor[J]. Chinese Journal of Scientific Instrument, 2010( 3): 237- 242.

[9] . Introducing the use of depth data for fall detection[J]. Personal and Ubiquitous Computing, 2013, 17(6): 1063-1072.

[10] , 等. 基于流形学习的人体动作识别[J]. 中国图象图形学报, 2014, 19(6): 914-923.

, et al. Human action recognition based on manifold learning[J]. Journal of Image and Graphics, 2014, 19(6): 914-923.

[11] . 基于Kinect的姿势识别与应用研究[J]. 计算机技术与发展, 2013, 23(5): 258-260.

. Recognition and application research of kinect-based gesture[J]. Computer Technology and Development, 2013, 23(5): 258-260.

[12] , et al. Validity of the microsoft kinect system in assessment of compensatory stepping behavior during standing and treadmill walking[J]. European Review of Aging and Physical Activity, 2017, 14(1): 1-11.

[13] 卞紫阳. RGB-D视频人体异常行为检测方法研究[D]. 北京: 北京理工大学, 2016.

Bian ZY. Research on detection method of human abnormal behavior based on RGB-D video[D]. Beijing: Beijing Institute of Technology, 2016.

[14] , 等. 一种基于深度和信息熵的人体运动检测方法[J]. 小型微型计算机系统, 2014, 35(2): 388-392.

, et al. A human motion detection method based on depth and information entropy[J]. Journal of Chinese Computer Systems, 2014, 35(2): 388-392.

[15] . 基于Kinect V2的跌倒行为检测与分析[J]. 现代电子技术, 2019, 42(6): 142-145.

. Detection and analysis on fall behavior based on Kinect V2[J]. Modern Electronics Technique, 2019, 42(6): 142-145.

马宗方, 李静, 曹陇鑫. 基于Kinect传感器的跌倒行为的检测与分析[J]. 激光与光电子学进展, 2020, 57(21): 210402. Ma Zongfang, Li Jing, Cao Longxin. Fall Behavior Detection and Analysis Using a Kinect Sensor[J]. Laser & Optoelectronics Progress, 2020, 57(21): 210402.

基于Kinect传感器的跌倒行为的检测与分析

关于本站 Cookie 的使用提示

全站搜索

基于Kinect传感器的跌倒行为的检测与分析

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索