|本期目录/Table of Contents|

[1]卢颖,吕希凡,郭良杰,等.基于Kinect的地铁乘客不安全行为识别方法与实验*[J].中国安全生产科学技术,2021,17(12):162-168.[doi:10.11731/j.issn.1673-193x.2021.12.026]
　LU Ying,LYU Xifan,GUO Liangjie,et al.Kinect-based recognition method and experiments on unsafe behavior of subway passengers[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(12):162-168.[doi:10.11731/j.issn.1673-193x.2021.12.026]
点击复制

基于Kinect的地铁乘客不安全行为识别方法与实验*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
17
期数:
2021年12期
页码:
162-168
栏目:
职业安全卫生管理与技术
出版日期:
2021-12-31

文章信息/Info

Title:
Kinect-based recognition method and experiments on unsafe behavior of subway passengers
文章编号:
1673-193X(2021)-12-0162-07
作者:
卢颖; 吕希凡; 郭良杰 ; 仇乐; 路越茗
（1.武汉科技大学 资源与环境学院，湖北 武汉 430081；
2.中国地质大学（武汉） 工程学院，湖北 武汉 430074)
Author(s):
LU Ying;  LYU Xifan;  GUO Liangjie;  QIU Le;  LU Yueming
(1.School of Resource & Environmental Engineering,Wuhan University of Science and Technology,Wuhan Hubei 430081,China;
2.Faculty of Engineering,China University of Geosciences,Wuhan Hubei 430074,China)
关键词:
不安全行为识别; 特征矢量; 关节角度; 动态时间规整算法（DTW）; 地铁乘客
Keywords:
unsafe behavior recognition;  characteristic vector;  joint angle;  dynamic time warping algorithm (DTW);  subway passengers
分类号:
X913.4
DOI:
10.11731/j.issn.1673-193x.2021.12.026
文献标志码:
A
摘要:
为解决地铁视频监控技术对乘客不安全行为只记录不识别且较少考虑识别精确度的问题，提出1种基于Kinect传感器的高效识别方法。以Pelvis为向量起点和动作活动高频关节为终点构建识别特征向量；运用余弦定理获得标准动作与测试动作关节的最大角度差序列；以最大角度差为动作特征量建立相似度计算模型，运用动态时间规整算法（DTW）将初始结果转换为动作相似度。以相连关节法为对照组开展对比实验，结果表明：前者在抽烟、挥拳、挥手呼救等行为识别的准确度分别为91.7%，86.9%，89.2%，平均比对照组高4%以上，显著提高了地铁乘客不安全行为的识别率，可为地铁智能安全管控提供理论与技术依据。
Abstract:
In order to solve the problem that the subway video surveillance technology only records but does not recognize the unsafe behavior of passengers and considers the recognition accuracy less,an efficient recognition method based on Kinect sensor was proposed.The characteristic vectors of recognition were constructed by taking Pelvis as the starting point of the vector and the high-frequency joints of the motive action as the end point,and the maximum angle difference sequence between the standard motion and the test motion joint was obtained through the law of cosines.A similarity calculation model with the maximum angle difference as the motion characteristic quantity was established,then the dynamic time warping algorithm (DTW) was used to convert the initial results into the motion similarity,and the comparative experiments were carried out with the connected joint method as the control group.The results showed that the accuracies of the former on behavior recognition such as smoking,punching,and calling for help were 91.7%,86.9%,and 89.2%,respectively,which were on average 4% higher than the control group.It significantly improves the recognition rate of the unsafe behaviors of subway passengers,and can provide theoretical and technical basis for the intelligent safety management and control of subway.

参考文献/References:

［1］吉根林,许振,李欣璐,等.监控视频中异常事件检测技术研究进展［J］.南京航空航天大学学报,2020,52(5):685-694. JI Genlin,XU Zhen,LI Xinlu,et al.Progress on abnormal event detection technology in video surveillance［J］.Journal of Nanjing University of Aeronautics & Astronautics,2020,52(5):685-694.
［2］李志欣,魏海洋,黄飞成,等.结合视觉特征和场景语义的图像描述生成［J］.计算机学报,2020,43(9):1624-1640. LI Zhixin,WEI Haiyang,HUANG Feicheng,et al.Combine visual features and scene semantics for image captioning［J］.Chinese Journal of Computers,2020,43(9):1624-1640.
［3］丁重阳,刘凯,李光,等.基于时空权重姿态运动特征的人体骨架行为识别研究［J］.计算机学报,2020,43(1):29-40. DING Chongyang,LIU Kai,LI Guang,et al.Spatio-temporal weighted posture motion features for human skeleton action recognition research ［J］.Chinese Journal of Computers,2020,43(1):29-40.
［4］KORCHI A E,GHANOU Y.2D geometric shapes dataset-for machine learning and pattern recognition［J］.Data in Brief,2020,(32):106090.
［5］MA Y,LIU D,CAI L.Deep learning-based upper limb functional assessment using a single Kinect v2 sensor［J］.Sensors,2020,20(7):1903.
［6］乔少杰,李天瑞,韩楠,等.大数据环境下移动对象自适应轨迹预测模型［J］.软件学报,2015,26(11):2869-2883. QIAO Shaojie,LI Tianrui,HAN Nan,et al.Self-adaptive trajectory prediction model for moving objects in big data environment［J］.Journal of Software,2015,26(11):2869-2883.
［7］GIUROIU M C,MARITA T.Gesture recognition toolkit using a Kinect sensor［C］// IEEE International Conference on Intelligent Computer Communication & Processing.IEEE,2015:317-324.
［8］LI B,HAN C,BAI B.Hybrid approach for human posture recognition using anthropometry and BP neural network based on Kinect V2［J］.Eurasip Journal on Image and Video Processing,2019（8）：1-15.
［9］YU X,XIONG S.A dynamic time warping based algorithm to evaluate Kinect-enabled home based physical rehabilitation exercises for older people ［J］.Sensors,2019,19(13):2882-2898.
［10］ABDELBAKY A,ALY S.Human action recognition using short-time motion energy template images and PCANet features［J］.Neural Computing and Applications,2020(3):12561-12574.
［11］杨思燕,贺国旗,刘如意.基于SIFT算法的大场景视频拼接算法及优化［J］.计算机科学,2019,46(7):286-291. YANG Siyan,HE Guoqi,LIU Ruyi.Video stitching algorithm based on SIFT and its optimization［J］.Computer Science,2019,46(7):286-291.
［12］于瑞云,苏展,谢青,等.基于空间分割的人体模型骨骼提取算法［J］.计算机学报,2019,42(9):2049-2061. YU Ruiyun,SU Zhan,XIE Qing,et al.Skeleton extraction of character model based on space segmentation［J］.Chinese Journal of Computers,2019,42(9):2049-2061.
［13］陆中秋,侯振杰,陈宸,等.基于深度图像与骨骼数据的行为识别［J］.计算机应用,2016,36(11):2979-2984,2992. LU Zhongqiu,HOU Zhenjie,CHEN Chen,et al.Action recognition based on depth images and skeleton data［J］.Journal of Computer Applications,2016,36(11):2979-2984,2992.
［14］陈冲,白硕,黄丽达,等.基于视频分析的人群密集场所客流监控预警研究［J］.中国安全生产科学技术,2020,16(4):143-148. CHEN Chong,BAI Shuo,HUANG Lida,et al.Research on monitoring and early-warning of passenger flow in crowded places based on video analysis［J］.Journal of Safety Science and Technology,2020,16(4):143-148.
［15］赵江平,王垚.基于图像识别技术的不安全行为识别［J］.安全与环境工程,2020,27(1):158-165. ZHAO Jiangping,WANG Yao.Unsafe behavior recognition based on image recognition technology［J］.Safety and Environmental Engineering,2020,27(1):158-165.
［16］赵小虎,黄程龙.基于Kinect的矿井人员违规行为识别算法研究［J］.湖南大学学报(自然科学版),2020,47(4):92-98. ZHAO Xiaohu,HUANG Chenglong.Research on identification algorithm of mine person’s violation behavior based on Kinect［J］.Journal of Hunan University(Natural Sciences),2020,47(4):92-98.
［17］吕周南.基于Kinect的人体危险行为检测研究［D］.天津：南开大学，2015.
［18］王如冰,万欣,毛鹏,等.乘客不安全行为与地铁事故关联性的fsQCA［J］.中国安全科学学报,2020,30(7):156-162. WANG Rubing,WAN Xin,MAO Peng,et al.Relevance study between unsafe behaviors of passengers and metro accidents based on fsQCA［J］.China Safety Science Journal,2020,30(7):156-162.
［19］刘艳,汪彤,吴宗之.地铁运营事故风险中的乘客因素分析［J］.应用基础与工程科学学报,2006,14:329-334. LIU Yan,WANG Tong,WU Zongzhi.Analysis on passenger factors in accident risks of subway operation［J］.Journal of Basic Science and Engineering,2006,14:329-334.
［20］中国电科电子科技研究院.人工智能在公安视频大数据分析领域的前沿应用［EB/OL］.(2019-01-12)［2021-12-17］.http://app.myzaker.com/news/article.php?pk=5c393a611bc8e05c1b000025.
［21］丁伟利,胡博,张焱鑫.基于规则的连续动作识别［J］.高技术通讯,2019,345(9):41-47. DING Weili,HU Bo,ZHANG Yanxin.Rule-based continuous action recognition［J］.High Technology Letters,2019,345(9):41-47.
［22］LIU,WU X,WU L,et al.Static human gesture grading based on Kinect［C］//5th International Congress on Image and Signal Processing.IEEE,2012:1390-1393.
［23］SU C J,CHIANG C Y,HUANG J Y.Kinect-enabled home-based rehabilitation system using Dynamic Time Warping and fuzzy logic［J］.Applied Soft Computing.2014(22):652-666.
［24］RYBARCZYK Y,DETERS J K,GONZALO A A,et.al.Recognition of physiotherapeutic exercises through DTW and low-cost vision-based motion capture［C］// International Conference on Applied Human Factors and Ergonomics,2017,592:348-360.
［25］SHOKOOHI M,WANG J,KEOGH E.On the non-trivial generalization of dynamic time warping to the multi-dimensional case［C］// Proceedings of the 2015 SIAM International Conference on Data Mining,2015:289-297.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期： 2021-03-04
* 基金项目： 国家自然科学基金项目（51874213）；湖北省自然科学基金青年项目（2018CFB186）；湖北省应急管理厅安全生产专项（KJZX201907011）
作者简介： 卢颖，博士，讲师，主要研究方向为城市公共安全风险理论与控制技术、消防安全管理等。
通信作者： 郭良杰，博士，讲师，主要研究方向为人的行为捕捉及分析，人体跌倒风险评估及干预等。
更新日期/Last Update: 2022-01-16