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。
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.
作者
许联航
李曦
郭叙森
李静
XU Lianhang;LI Xi;GUO Xusen;LI Jing(CHN Energy Shendong Coal Group Co.,Ltd.,Ordos 017209,China;Aerospace Heavy Industry Co.,Ltd.,Xiaogan 432000,China)
出处
《工矿自动化》
CSCD
北大核心
2023年第8期121-126,共6页
Journal Of Mine Automation
关键词
智慧矿山
无人驾驶矿车
道路挡墙
点云
体素栅格化
路侧激光雷达传感器
intelligent mine
unmanned mining vehicle
road retaining walls
point cloud
voxel rasterization
roadside LiDAR sensor
