Method for detecting the status of retaining walls in intelligent mines
-
摘要: 无人驾驶车辆在矿山行驶过程中,如果矿区挡墙出现破损而没有被及时发现并修复,车辆在行驶或卸载时超出挡墙安全范围,易造成安全事故。现有的挡墙状态检测方法多是基于车端、无人机传感设备采集的点云数据,视野有限,稀疏性较大,稳定性差,且缺乏针对挡墙状态完整性检测的方法。针对上述问题,提出了一种基于路侧激光雷达传感器的挡墙状态完整性检测方法。采用分辨率较高的路侧激光雷达传感器采集车辆行驶区域的挡墙点云数据,采用多边形区域滤波及体素栅格化获得完整的挡墙点云数据。采用滑动寻迹搜索技术,沿着挡墙延伸方向将其划分成子单元,以适应不同形状挡墙。针对矿区场地不平整及远处点云数据稀疏带来的误检问题,采用高度差阈值和密度阈值双阈值法,通过检测子单元的缺陷情况得到整个挡墙状态的完整性检测。采集了内蒙古某矿区“L”型、“S”型挡墙的点云数据,并在有遮挡和无遮挡的场景下进行现场试验,结果表明,该检测方法对不同形状挡墙的缺陷均具有较强的检测能力,能够实时识别并标记出点云数据的破损部位。Abstract: During the driving process of unmanned vehicles in mines, if the retaining wall in the mining area is damaged and not detected and repaired in a timely manner, the vehicle may exceed the safety range of the retaining wall during driving or unloading. It can easily cause safety accidents. The existing methods for detecting the status of retaining walls are mostly based on point cloud data collected by vehicle and drone sensing devices. The methods have limited field of view, high sparsity and poor stability. There is a lack of detection methods for the integrity status of retaining walls. In order to solve the above problems, a method for detecting the integrity of retaining wall status based on roadside LiDAR sensors is proposed. A high-resolution roadside LiDAR sensor is used to collect point cloud data of the retaining wall in the driving area of the vehicle. Polygonal area filtering and voxel rasterization are used to obtain complete point cloud data of the retaining wall. A sliding trace search technique is used to divide the retaining wall into sub units along its extension direction to accommodate the different shaped retaining walls. In response to the problem of false detection caused by uneven mining sites and sparse remote point cloud data, a dual threshold method of height difference threshold and density threshold is adopted. It detects the integrity of the entire retaining wall status by detecting the defects of sub units. The method collects point cloud data of "L" and "S" type retaining walls in a mining area in Inner Mongolia. The on-site experiments are conducted in both occluded and unobstructed scenarios. The results show that this detection method has strong detection capability for defects in different shapes of retaining walls. The method can identify and mark the damaged parts of point cloud data in real-time.
-
表 1 “L”型挡墙缺陷区域采样统计
Table 1. Sampling and statistics of defect areas in the "L" type retaining wall
m 序号 hk-max hk-min Δh 挡墙状态 1 0.70 0.18 0.52 塌方 2 1.19 0.59 0.60 塌方 3 1.28 0.65 0.63 塌方 4 1.10 0.76 0.34 塌方 5 1.54 1.15 0.39 塌方 6 2.27 1.65 0.62 塌方 表 2 “S”型挡墙缺陷区域采样统计
Table 2. Sampling and statistics of defect areas in the "S" type retaining wall
m 序号 hk-max hk-min Δh 挡墙状态 1 −0.02 −0.61 0.59 塌方 2 −0.08 −0.54 0.46 塌方 3 −0.04 −0.66 0.62 塌方 4 −0.27 −0.58 0.31 塌方 5 −0.52 −0.62 0.10 塌方 6 −0.38 −0.94 0.56 塌方 表 3 被遮挡场景挡墙缺陷区域采样统计
Table 3. Sampling and statistics of retaining wall defect areas in occluded scenarios
m 序号 hk-max hk-min Δh 挡墙状态 1 −0.11 −0.58 0.47 塌方 2 −0.04 −0.65 0.61 塌方 3 −0.29 −0.62 0.33 塌方 4 −0.49 −0.70 0.21 塌方 5 −0.33 −0.93 0.60 塌方 -
[1] 戴亨,张巴图. 露天矿山运输无人驾驶系统作业方式[J]. 露天采矿技术,2020,35(5):20-24. doi: 10.13235/j.cnki.ltcm.2020.05.006DAI Heng,ZHANG Batu. Operation modes of driverless system in open-pit mine haulage[J]. Opencast Mining Technology,2020,35(5):20-24. doi: 10.13235/j.cnki.ltcm.2020.05.006 [2] 于海旭,杜志勇,魏志丹,等. 我国矿区无人驾驶技术现状与发展趋势分析[J]. 工矿自动化,2022,48(增刊2):82-87.YU Haixu,DU Zhiyong,WEI Zhidan,et al. Analysis on the current situation and development trend of unmanned driving technology in mining areas in China[J]. Journal of Mine Automation,2022,48(S2):82-87. [3] 孙溥茜. 推进矿区无人驾驶,矿山生态圈协同共赢[J]. 机器人产业,2021(5):52-55. doi: 10.3969/j.issn.2096-0182.2021.05.011SUN Puqian. Promote unmanned driving in mining areas and win-win collaboration in mine ecosystem[J]. Robot Industry,2021(5):52-55. doi: 10.3969/j.issn.2096-0182.2021.05.011 [4] LU Xiaowei,AI Yunfeng,TIAN Bin. Real-time mine road boundary detection and tracking for autonomous truck[J]. Sensors,2020,20(4):1121. doi: 10.3390/s20041121 [5] 黄立明, 李华志, 余贵珍. 一种基于激光雷达的露天矿区可行驶区域检测方法: CN202110581104.6[P]. 2021-06-25.HUANG Liming, LI Huazhi, YU Guizhen. A driving area detection method based on LiDAR in open-pit mining area: CN202110581104.6[P]. 2021-06-25. [6] 任良才, 赵斌, 杨超, 等. 一种无人矿卡行驶场景的路面及两侧挡墙检测方法: CN202111174666.5[P]. 2022-01-14.REN Liangcai, ZHAO Bin, YANG Chao, et al. The invention relates to a detection method of road surface and retaining wall on both sides of the driving scene of unmanned mining truck: CN202111174666.5[P]. 2022-01-14. [7] 孟德将, 田滨, 潘子宇, 等. 自动驾驶车辆在露天煤矿排土场的挡墙检测方法[C]. IEEE国际智能交通系统会议(ITSC), 印第安纳波利斯, 2021: 2829-2834.MENG Dejiang, TIAN Bin, PAN Ziyu, et al. Berm detection for autonomous truck in surface mine dump area[C]. IEEE International Intelligent Transporta- tion Systems Conference (ITSC), Indianapolis, 2021: 2829-2834. [8] 王植,安世缘,邹俊,等. 露天矿点云数据中台阶线提取[J]. 东北大学学报(自然科学版),2021,42(9):1323-1328.WANG Zhi,AN Shiyuan,ZOU Jun,et al. Step line extraction from point cloud data of open-pit mine[J]. Journal of Northeastern University(Natural Science),2021,42(9):1323-1328. [9] 杨荣明,丁震,杨健健,等. 基于平行控制理论的矿区无人驾驶卡车仿真系统[J]. 工矿自动化,2022,48(11):80-83,100. doi: 10.13272/j.issn.1671-251x.17999YANG Rongming,DING Zhen,YANG Jianjian,et al. Simulation system of mine unmanned vehicle based on parallel control theory[J]. Journal of Mine Automation,2022,48(11):80-83,100. doi: 10.13272/j.issn.1671-251x.17999 [10] 闫凌,黄佳德. 矿用卡车无人驾驶系统研究[J]. 工矿自动化,2021,47(4):19-29.YAN Ling,HUANG Jiade. Research on unmanned driving system of mine-used truck[J]. Industry and Mine Automation,2021,47(4):19-29. [11] FRANKLIN W R. Pnpoly-point inclusion in polygon test[EB/OL]. [2023-08-18]. https://wrfranklin.org/Research/Short_Notes/pnpoly.html. [12] HORMANNK,AGATHOS A. The point in polygon problem for arbitrary polygons[J]. Computational Geometry:Theory and Applications,2001,20(3):131-144. doi: 10.1016/S0925-7721(01)00012-8 [13] 白运波. 无人驾驶车辆多目标检测与跟踪研究[D]. 重庆: 重庆理工大学, 2021.BAI Yunbo. Research on multi target detection and tracking of driverless vehicle[D]. Chongqing: Chongqing University of Technology, 2021. [14] 葛淑,王福云,杨军,等. 智能采矿作业制定标准:用于自主采矿运输的智能车辆[J]. IEEE智能汽车学报,2022,7(3):413-416. doi: 10.1109/TIV.2022.3197820GE Shu,WANG Fuyun,YANG Jun,et al. Making standards for smart mining operations:intelligent vehicles for autonomous mining transportation[J]. IEEE Transactions on Intelligent Vehicles,2022,7(3):413-416. doi: 10.1109/TIV.2022.3197820 [15] 阮顺领,焦鑫,景莹,等. 一种露天矿区非结构化道路分割检测方法[J]. 测绘科学,2022,47(6):204-212. doi: 10.16251/j.cnki.1009-2307.2022.06.026RUAN Shunling,JIAO Xin,JING Ying,et al. Road detection in mining area based on bilateral segmentation optimization network[J]. Science of Surveying and Mapping,2022,47(6):204-212. doi: 10.16251/j.cnki.1009-2307.2022.06.026 [16] 李宏刚,王云鹏,廖亚萍,等. 无人驾驶矿用运输车辆感知及控制方法[J]. 北京航空航天大学学报,2019,45(11):2335-2344.LI Honggang,WANG Yunpeng,LIAO Yaping,et al. Perception and control method of driverless mining vehicle[J]. Journal of Beijing University of Aeronautics and Astronautics,2019,45(11):2335-2344. [17] 刘旭, 黄轩, 王国军. 自动驾驶的挡墙检测方法, 装置及车辆: CN202211100104.0[P]. 2022-12-09.LIU Xu, HUANG Xuan, WANG Guojun. Retaining wall detection method, device and vehicle for automatic driving: CN202211100104.0[P]. 2022-12-09. [18] 赵斌, 李金铭, 唐建林. 一种适用于自动驾驶车辆的挡土墙检测方法及系统: CN202111424 522.0[P]. 2022-04-12.ZHAO Bin, LI Jinming, TANG Jianlin. The invention relates to a retaining wall detection method and system suitable for automatic driving vehicles: : CN202111424 522.0[P]. 2022-04-12. [19] 张明, 周晓阳, 郭勇, 等. 改进U-Net模型训练方法、露天矿道路挡墙缺口检测方法及装置: CN202211497613.1[P]. 2023-03-10.ZHANG Ming, ZHOU Xiaoyang, GUO Yong, et al. Improved U-Net model training method, open pit road retaining wall gap detection method and device: CN202211497613.1[P]. 2023-03-10. [20] 赖观其,郭文敬. 挡土墙无损检测方法介绍[J]. 路基工程,2004(1):12-14.LAI Guanqi,GUO Wenjing. Introduction of nondestructive testing method for retaining wall[J]. Subgrade Engineering,2004(1):12-14.