吉林大学学报(工学版) ›› 2021, Vol. 51 ›› Issue (3): 1067-1072.doi: 10.13229/j.cnki.jdxbgxb20200160

• 计算机科学与技术 • 上一篇    

基于连续密度隐马尔可夫模型的矿下异常行为识别算法

王淑敏(),陈伟   

  1. 哈尔滨工程大学 经济管理学院,哈尔滨 150001
  • 收稿日期:2020-03-16 出版日期:2021-05-01 发布日期:2021-05-07
  • 作者简介:王淑敏(1980-),女,博士研究生. 研究方向:企业经营与管理,信息与控制工程. E-mail:dxh123521@163.com
  • 基金资助:
    国家社科基金项目(17CSH016);国家社科基金一般项目(19BJL008);国家自然科学基金项目(61371178)

Algorithm for identifying abnormal behavior in underground mines based on continuous density hidden Markov model

Shu-min WANG(),Wei CHEN   

  1. School of Economics and Management,Harbin Engineering University,Harbin 150001,China
  • Received:2020-03-16 Online:2021-05-01 Published:2021-05-07

摘要:

针对当前方法识别精度不高的问题,提出了基于连续密度隐马尔可夫模型的矿下异常行为识别算法。获取待识别矿下视频帧数据,通过级联分类器实现运动区域的初步检测,并读入下帧数据,直到所有帧检测完毕。引入连续密度隐马尔可夫(HMM)模型,将人体图像分解成若干相等区域,获取图像区域中的标准差值特征,对连续密度HMM进行训练,完成异常行为识别。实验结果证明,本文算法的识别结果具有精度高和检测率高的特性,说明其具有可靠性。

关键词: 计算机应用, 连续密度, 马尔可夫模型, 矿下异常, 识别

Abstract:

In the current research of abnormal behaviors in underground mines the result accuracy needs improvement. In order to solve this problem and improve the safety of underground mines, a continuous density hidden Markov model is proposed to identify abnormal behaviors in underground mines. In the detection of human motion area under the mine, first, the video frame data to be identified is obtained; the human motion area is preliminarily extracted for each image, and the preliminary detection of human motion area is realized by cascading classifiers to get more accurate human motion area. Then the next frame data is read in, and this process is iterated until all frames are detected. According to the preliminary detection results, the continuous density hidden Markov model is introduced to decompose the human body image into several equal areas. The representative color features and the standard difference features in the image area are obtained. The continuous density HMM of the target is trained through the obtained feature data. The abnormal behavior recognition of the human body target under the mine is completed according to the training model. The experimental results show that the proposed algorithm has the characteristics of high accuracy and high detection rate in different number of human behavior recognition, which shows that the algorithm is reliable.

Key words: computer application, continuous density, Markov model, underground anomaly, identification

中图分类号: 

  • TP39

图1

二值图像模板连接操作示意图"

图2

级联分类器示意图"

图3

人体运动区域检测结果"

1 王恬, 李庆武, 刘艳, 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.
Wang Tian, Li Qing-wu, Liu Yan, et al. Abnormal human body behavior recognition using pose estimation[J]. Chinese Journal of Scientific Instrument, 2016, 37(10):2366-2372.
2 林玲, 廖德, 高阳, 等. 基于加权样本选择与主动学习的视频异常行为检测算法[J]. 模式识别与人工智能, 2016, 29(4):341-349.
Lin Ling, Liao De, Gao Yang, et al. Video anomaly detection algorithm based on weighted sample selection and active learning[J]. Pattern Recognition and Artificial Intelligence, 2016, 29(4):341-349.
3 杨振宏, 丁光灿, 张涛, 等. 基于SEM的建筑工人不安全行为传播影响因素研究[J]. 安全与环境学报, 2018, 18(3):987-992.
Yang Zhen-hong, Ding Guang-can, Zhang Tao, et al. Investigation and analysis of the influential factors on the spreading reckless behaviors of the building workers based on the SEM[J]. Journal of Safety and Environment, 2018, 18(3):987-992.
4 杨超宇, 李策, 苏剑臣. 基于视频的煤矿安全监控行为识别系统研究[J]. 煤炭工程, 2016, 48(4):111-113.
Yang Chao-yu, Li Ce, Su Jian-chen. Research on video-based system of activity recognition for coal mine safety surveillance[J]. Coal Engineering, 2016, 48(4):111-113.
5 佟瑞鹏, 张艳伟. 人工智能技术在矿工不安全行为识别中的融合应用[J]. 中国安全科学学报, 2019, 29(1):7-12.
Tong Rui-peng, Zhang Yan-wei. Integration between artificial intelligence technologies for miners' unsafe behavior identification[J]. China Safety Science Journal, 2019, 29(1):7-12.
6 原渊. Mahout策略下矿井监控视频异常行为推荐[J]. 煤炭技术, 2017, 36(10):218-220.
Yuan Yuan. Mahout strategy under mine monitoring video abnormal behavior recommendation[J]. Coal Technology, 2017, 36(10):218-220.
7 周柚, 杨森, 李大琳,等. 基于现场可编程门电路的人脸检测识别加速平台[J]. 吉林大学学报:工学版, 2019, 49(6):2051-2057.
Zhou You, Yang Sen, Li Da-lin, et al. Acceleration platform for face detection and recognition based on field-programmable gate array[J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6):2051-2057.
8 宋丹妮, 王平, 张晓华, 等. 基于视频监控的中小群体异常行为检测[J]. 计算机工程与设计, 2016, 37(9):2507-2514.
Song Dan-ni, Wang Ping, Zhang Xiao-hua, et al. Abnormal behavior detection of small and medium crowd based on video surveillance[J]. Computer Engineering and Design, 2016, 37(9):2507-2514.
9 王松,党建武,王阳萍,等. 基于3D运动历史图像和多任务学习的动作识别[J]. 吉林大学学报:工学版,2020,50(4):1495-1502.
Wang Song, Dang Jian-wu, Wang Yang-ping, et al. Action recognition based on 3D motion history image and multi-task learning[J]. Journal of Jilin University(Engineering and Technology Edition), 2020,50(4):1495-1502.
10 丁松涛, 曲仕茹. 基于改进时空兴趣点检测的人体行为识别算法[J]. 西北工业大学学报, 2016, 34(5):886-892.
Ding Song-tao, Qu Shi-ru. An improved interest point detector for human action recognition[J]. Journal of Northwestern Polytechnical University, 2016, 34(5):886-892.
11 周宏宇,宋旭,刘国英.Haar特征耦合级联分类器的车道线检测算法[J].计算机工程与设计,2020,41(6):1719-1724.
Zhou Hong-yu, Song Xu, Liu Guo-ying. Lane detection algorithm based on Haar feature based coupled cascade classifer[J]. Computer Engineering and Design, 2020,41(6):1719-1724.
[1] 刘元宁,吴迪,朱晓冬,张齐贤,李双双,郭书君,王超. 基于YOLOv3改进的用户界面组件检测算法[J]. 吉林大学学报(工学版), 2021, 51(3): 1026-1033.
[2] 朱小龙,谢忠. 基于机器学习的地理空间数据抽取算法[J]. 吉林大学学报(工学版), 2021, 51(3): 1011-1016.
[3] 欧阳丹彤,刘扬,刘杰. 故障响应指导下基于测试集的故障诊断方法[J]. 吉林大学学报(工学版), 2021, 51(3): 1017-1025.
[4] 钱榕,张茹,张克君,金鑫,葛诗靓,江晟. 融合全局和局部特征的胶囊图神经网络[J]. 吉林大学学报(工学版), 2021, 51(3): 1048-1054.
[5] 沈淑涛,尼玛扎西. 基于区块链技术的双混沌可识篡改图像加密方法[J]. 吉林大学学报(工学版), 2021, 51(3): 1055-1059.
[6] 朱晓冬,张齐贤,刘元宁,吴迪,吴祖慷,王超群,李昕龙. 基于多方向局部二值模式与稳定特征的虹膜识别[J]. 吉林大学学报(工学版), 2021, 51(2): 650-658.
[7] 顾天奇,胡晨捷,涂毅,林述温. 基于移动最小二乘法的稳健重构方法[J]. 吉林大学学报(工学版), 2021, 51(2): 685-691.
[8] 许骞艺,秦贵和,孙铭会,孟诚训. 基于改进的ResNeSt驾驶员头部状态分类算法[J]. 吉林大学学报(工学版), 2021, 51(2): 704-711.
[9] 魏晓辉,周长宝,沈笑先,刘圆圆,童群超. 机器学习加速CALYPSO结构预测的可行性[J]. 吉林大学学报(工学版), 2021, 51(2): 667-676.
[10] 王伟达,武燕杰,史家磊,李亮. 基于驾驶员意图识别的电子液压制动助力系统控制策略[J]. 吉林大学学报(工学版), 2021, 51(2): 406-413.
[11] 周炳海,吴琼. 基于多目标的机器人装配线平衡算法[J]. 吉林大学学报(工学版), 2021, 51(2): 720-727.
[12] 方明,陈文强. 结合残差网络及目标掩膜的人脸微表情识别[J]. 吉林大学学报(工学版), 2021, 51(1): 303-313.
[13] 宋元,周丹媛,石文昌. 增强OpenStack Swift云存储系统安全功能的方法[J]. 吉林大学学报(工学版), 2021, 51(1): 314-322.
[14] 刘富,刘璐,侯涛,刘云. 基于优化MSR的夜间道路图像增强方法[J]. 吉林大学学报(工学版), 2021, 51(1): 323-330.
[15] 王小玉,胡鑫豪,韩昌林. 基于生成对抗网络的人脸铅笔画算法[J]. 吉林大学学报(工学版), 2021, 51(1): 285-292.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!