采煤机作业区域人员精确检测方法研究

魏东; 王忠宾; 司垒; 谭超; 路绪良

doi:10.13272/j.issn.1671-251x.2021110069

采煤机作业区域人员精确检测方法研究

doi: 10.13272/j.issn.1671-251x.2021110069

魏东¹,
王忠宾^1,2,
司垒¹,
谭超¹,
路绪良¹

1.
1. 中国矿业大学机电工程学院, 江苏徐州 221116;
2.
2. 中国矿业大学江苏省矿山机电装备高校重点实验室, 江苏徐州 221116

基金项目:

国家重点研发计划资助项目（2020YFB1314200）；国家自然科学基金青年基金资助项目（52074271）；中国博士后科学基金特别资助项目（2020T130696）。

详细信息

作者简介:
魏东(1992-),男,辽宁阜新人,讲师,博士,研究方向为矿山装备智能化、煤矿人员安全保护,E-mail:weidongcmee@cumt.edu.cn。

中图分类号: TD421
计量
- 文章访问数: 354
- HTML全文浏览量: 35
- PDF下载量: 60
- 被引次数: 0
出版历程
- 收稿日期: 2021-11-29
- 修回日期: 2022-01-29
- 网络出版日期: 2022-03-01
- 刊出日期: 2022-03-01

Research on precise detection method of personnel in shearer operation area

1.
School of Mechatronic Engineering, China University of Mining and Technology, Xuzhou 221116, China;
2.
Jiangsu Key Laboratory of Mine Mechanical and Electrical Equipment, China University of Mining and Technology, Xuzhou 221116, China

摘要

摘要:
当前智能化采煤机已具有三维定位、记忆截割和远程监控等功能，但缺少采煤机作业区域误入人员的检测和预警保护功能，人员精确检测是亟待解决的关键问题之一。受综采工作面低照度、工况环境复杂多变影响，基于激光、射频、超声波等传感器的煤矿机电装备主动防撞预警技术应用受限，基于可见光传感器的防撞技术难以满足准确性和稳定性要求。搭建了基于红外热成像技术的采煤机作业区域人员精确检测系统架构，进而提出了人员精确检测方法：针对综采工作面红外图像噪声的高强度、不均匀特点，采用基于高斯掩码改进的多级导向滤波模型有效滤除红外图像噪声，并保留边缘信息；基于Lucas-Kanade光流法提取动态背景下的移动前景目标运动信息；采用基于图像局部信息权重的直觉模糊C均值聚类算法对采煤机作业区域红外图像信息进行分割，获取移动目标位置信息；基于形态学加权投票法对移动目标运动信息提取结果和红外图像信息分割结果进行融合，实现采煤机作业区域人员精确检测。在耿村矿21208综采工作面进行井下工业性试验，结果表明采煤机作业区域人员精确检测方法对现场人员的跟踪偏差平均值为0.106 5像素，重叠比平均值为96.10%，平均单次处理时间为0.490 8 s，满足现场应用需求。
- 综采智能化 /
- 采煤机 /
- 人员精确检测 /
- 红外热成像 /
- 光流法 /
- 运动信息提取 /
- 图像分割 /
- 图像形态学
Abstract:
The current intelligent shearer has the functions of three-dimensional positioning, memory cutting and remote monitoring, but it lacks the detection and early warning protection function of personnel entering the shearer operation area by mistake. Therefore, the precise detection of personnel is one of the key problems to be solved urgently. Affected by the low illumination and complex working conditions of fully mechanized working face, the application of active anti-collision warning technology for coal mine electromechanical equipment based on laser, radio frequency, ultrasonic and other sensors is limited, and the anti-collision technology based on visible light sensor cannot meet the requirements of accuracy and stability. The system architecture of precise detection of personnel in shearer operation area based on infrared thermal imaging technology is built, and then the precise detection method of personnel is proposed. Aiming at the high intensity and uneven characteristics of the infrared image noise in fully mechanized working face, an improved multi-layer guided filter model based on Gauss mask-code is used to filter out infrared image noise effectively and retain the edge information. The moving foreground target motion information under dynamic background is extracted by optical flow method that based on Lucas-Kanade. The intuitionistic fuzzy C-means clustering algorithm based on the weight of local image information is used to segment the infrared image information of the shearer operation area so as to obtain the position information of the moving target. Based on the morphological weighted voting method, the extraction results of the moving target motion information and the infrared image information segmentation results are fused to realize the precise detection of personnel in the shearer operation area. The underground industrial test is carried out in 21208 fully mechanized working face of Gengcun Coal Mine. The results show that the average tracking deviation of the precise detection method for personnel in the shearer operation area is 0.106 5 pixel, the average overlap ratio is 96.10%, and the average single processing time is 0.490 8 s, which meet the needs of field application.
- intelligent fully mechanized mining /
- shearer /
- precise personnel detection /
- infrared thermal imaging /
- optical flow method /
- motion information extraction /
- image segmentation /
- image morphology

HTML全文

参考文献(23)

[1]	关于加快煤矿智能化发展的指导意见[N].中国煤炭报,2020-03-05(2). The guiding opinions on accelerating the development of intelligent coal mines[N].China Coal News, 2020-03-05(2).
[2]	王国法,徐亚军,张金虎,等.煤矿智能化开采新进展[J].煤炭科学技术,2021,49(1):1-10. WANG Guofa,XU Yajun,ZHANG Jinhu,et al.New development of intelligent mining in coal mines[J].Coal Science and Technology,2021,49(1):1-10.
[3]	SCHIFFBAUER W H.Active proximity warning system for surface and underground mining applications[J].Mining Engineering,2002,54(12):40-48.
[4]	DU Jianxia.Design and implementation of underground locomotive collision avoidance system[J].Applied Mechanics & Materials,2015,741:744-748.
[5]	RUFF T M,HESSION-KUNZ D.Application of radio-frequency identification systems to collision avoidance in metal/nonmetal mines[J].IEEE Transactions on Industry Applications,2001,37(1):112-116.
[6]	HE Kai,MA Xianmin.Research on avoidance obstacle strategy of coal underground inspection robot based on binocular vision[C]//The 29th Chinese Control and Decision Conference,Chongqing,2017:6732-6737.
[7]	方崇全.基于激光扫描雷达的矿井机车障碍物检测方法研究[J].煤矿机械,2018,39(8):32-34. FANG Chongquan.Research on obstacle detection method for mine locomotive based on lidar[J].Coal Mine Machinery,2018,39(8):32-34.
[8]	周菲鑫.煤矿井下电机车无人驾驶测控系统研究[D].淮南:安徽理工大学,2019. ZHOU Feixin.Research on measurement and control system of unmanned electric locomotive in coal mine[D].Huainan:Anhui University of Science and Technology,2019.
[9]	李占利,陈佳迎,李洪安,等.安全时间模型下的井下运动目标防撞预警方法[J].西安科技大学学报,2016,36(6):875-881. LI Zhanli,CHEN Jiaying,LI Hongan,et al.An anti-collision early-warning method of coal mine underground moving objects based on security time model[J].Journal of Xi'an University of Science and Technology,2016,36(6):875-881.
[10]	王壬.基于机器视觉的井下机车防撞系统研究[D].重庆:重庆大学,2012. WANG Ren.Research on underground locomotive crashworthy system based on machine vision[D].Chongqing:Chongqing University,2012.
[11]	杨娟.煤矿井下机车防撞系统设计[J].煤炭技术,2014,33(11):197-199. YANG Juan.Design on anti-collision system of coalmine underground tramcar[J].Coal Technology,2014,33(11):197-199.
[12]	杨鑫.基于单目视觉的矿井电机车防撞预警系统的研究[D].徐州:中国矿业大学,2015. YANG Xin.Research on auti-collision warning system for the mine electric vehicle based on monocular vision[D]. Xuzhou:China University of Mining and Technology,2015.
[13]	GONG Lixiong,WANG Canlin.Research on moving target tracking based on FDRIG optical flow[J].Symmetry,2019,11(9):1122.
[14]	HE Kaiming,SUN Jian,TANG Xiaoou.Guided image filtering[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[15]	LUCAS B,KANADE T.An iterative technique of image registration and its application to stereo[C]//The 7th International Joint Conference on Artificial Intelligence,Vancouver,1981:674-679.
[16]	FISCHLER M A,BOLLES R C.Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J].Reading in Computer Vision, 1987:726-740.
[17]	HARTLEY R I.In defense of the eight-point algorithm[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(6):580-593.
[18]	WEI Dong,WANG Zhongbin,SI Lei,et al.An image segmentation method based on a modified local-information weighted intuitionistic fuzzy C-means clustering and gold-panning algorithm[J].Engineering Applications of Artificial Intelligence,2021,101:104209.
[19]	VIEILLE N.Random walks and voting theory[J]. Mathematics of Operations Research,2004,29(1):106-113.
[20]	GONZALEZ R C,WOODS R E.Digital image processing [M]. The 4th edition.Upper Saddle Rivel:Pearson Prentice Hall,2017.
[21]	HORN B,SCHUNCK B.Determining optical flow[J]. Artificial Intelligence,1980,17(1/2/3):185-203.
[22]	FARNEBÄCK G.Two-frame motion estimation based on polynomial expansion[J].Image Analysis,2003,2749:363-370.
[23]	JIANG Daihong,DAI Lei,LI Dan,et al.Moving-object tracking algorithm based on PCA-SIFT and optimization for underground coal mines[J]. IEEE Access,2019(7):35556-35563.