Obstacle detection in underground mines using multiple LiDARs based on grid method
-
摘要:
针对井工矿障碍物检测中因高程结构点云过滤困难和地面分割精度不足导致的误识别与漏识别问题，提出了一种基于栅格法的井工矿多激光雷达障碍物检测方法。首先，采用条件滤波进行点云的裁剪和去噪，将条件滤波后的多激光雷达点云数据进行融合，再进行体素降采样，完成点云预处理。其次，将预处理后的点云投影到二维栅格，依据栅格与车体的距离划分远近距离栅格，并分别计算各栅格的巷道地面高度和顶部高度特征，更新车体附近栅格和每行栅格特征，基于点云分布和前后行栅格的连续性，采用由近到远、逐行更新的策略进行全局栅格特征更新，实现对巷道地面和顶部特征的精准计算。最后，基于栅格特征进行地面分割，从非地面点云中过滤掉高程结构点云，再对剩余点云进行欧氏聚类，从中检测出障碍物。井下测试结果表明：该方法可有效过滤上下坡及点云稀疏工况中的高程结构点云；对信号箱、锥形桶、低矮支架和车辆等低矮目标检测的准确率分别为92.3%，90.9%，96.5%和100%；在不同工况巷道中，有效减少了误识别和漏识别，具有较高的障碍物检测准确率。
Abstract:To address the issues of false and missed detections in obstacle detection within underground mines caused by difficulties in filtering elevated structural point clouds and insufficient ground segmentation accuracy, a multi-LiDAR obstacle detection method based on grid method for underground mines was proposed. Firstly, conditional filtering was employed to crop and denoise the point clouds. The point cloud data from multiple LiDARs, after conditional filtering, were fused and subsequently downsampled through voxelization to accomplish point cloud preprocessing. Secondly, the preprocessed point clouds were projected onto a two-dimensional grid, which was divided into near and far regions based on the distance to the vehicle. The tunnel ground and ceiling heights for each grid were then calculated separately, and the features of nearby grids and row-wise grids were updated. Based on the point cloud distribution and inter-row grid continuity, a strategy of updating the global grid characteristics was implemented from near to far and row by row, enabling precise estimation of tunnel ground and ceiling characteristics. Finally, ground segmentation was performed based on the grid features, elevated structural point clouds were filtered out from the non-ground point clouds, and Euclidean clustering was applied to the remaining point clouds to detect obstacles. Field test results demonstrated that the proposed method could effectively filter out elevated structural point clouds in uphill/downhill and sparse point cloud conditions. Detection accuracies for low-profile targets, including signal boxes, traffic cones, low supports, and vehicles reached 92.3%, 90.9%, 96.5%, and 100%, respectively. Across various tunnel conditions, the approach significantly reduces false and missed detections, achieving high obstacle detection accuracy.
-
-
![]()
图 1 基于栅格法的井工矿多激光雷达障碍物检测流程
Figure 1. Obstacle detection process of multi-LiDAR based on grid method for underground mines
![]()
图 3 相邻行栅格地面附近点云分布
Figure 3. Distribution of ground-proximate point clouds in adjacent grid rows
![]()
图 5 点云稀疏工况下高程结构点云过滤效果
Figure 5. Filtering effect of elevated structural point clouds under sparse point cloud condition
![]()
图 6 上下坡工况下高程结构点云过滤效果
Figure 6. Filtering effect of elevated structural point clouds under uphill and downhill working conditions
![]()
图 7 积水工况下障碍物车辆检测效果
Figure 7. Detection effect of vehicle obstacles under waterlogging condition
表 1 低矮目标检测结果
Table 1 Detection results of low-profile targets
类别 标记数/个 检测数/个 准确率/% 信号箱 52 48 92.3 锥形桶 66 60 90.9 低矮支架 86 83 96.5 车辆 70 70 100 
下载: 导出CSV
-
[1] 阮顺领,李少博,顾清华,等. 基于双向特征融合的露天矿区道路障碍检测[J]. 煤炭学报,2023,48(3):1425-1438. RUAN Shunling,LI Shaobo,GU Qinghua,et al. Road obstacle detection in open-pit mines based on bidirectional feature fusion[J]. Journal of China Coal Society,2023,48(3):1425-1438.
[2] 顾清华,李佳威,陈露,等. 基于固态激光雷达的露天矿非结构化运输道路小尺寸落石检测方法[J]. 激光与光电子学进展,2024,61(8):229-234. GU Qinghua,LI Jiawei,CHEN Lu,et al. Small-scale rockfall detection method based on solid-state lidar for unstructured transportation roads in open-pit mines[J]. Laser & Optoelectronics Progress,2024,61(8):229-234.
[3] 骆彬. 井下蓄电池无轨胶轮车无人驾驶系统设计研究[D]. 徐州:中国矿业大学,2019. LUO Bin. Design of driverless system of underground battery trackless rubber tire vehicle[D]. Xuzhou:China University of Mining and Technology,2019.
[4] 蔡晓晴. 煤矿井下无轨胶轮车无人驾驶技术研究[J]. 能源与节能,2025(4):144-146,150. CAI Xiaoqing. Unmanned driving technology for trackless rubber-tired vehicles in underground coal mines[J]. Energy and Energy Conservation,2025(4):144-146,150.
[5] 田子建,阳康,吴佳奇,等. 基于LMIENet图像增强的矿井下低光环境目标检测方法[J]. 煤炭科学技术,2024,52(5):222-235. DOI: 10.12438/cst.2023-0675 TIAN Zijian,YANG Kang,WU Jiaqi,et al. LMIENet enhanced object detection method for low light environment in underground mines[J]. Coal Science and Technology,2024,52(5):222-235. DOI: 10.12438/cst.2023-0675
[6] 袁稼轩. 基于深度学习的井下巷道行人检测与距离估计[D]. 合肥:合肥工业大学,2019. YUAN Jiaxuan. Pedestrian detection and distance estimation of underground roadway based on deep learning[D]. Hefei:Hefei University of Technology,2019.
[7] 曹多美,庄秀丽. 煤矿井巷环境下机器人视觉图像增强及障碍识别研究[J]. 煤矿机械,2017,38(2):39-41. CAO Duomei,ZHUANG Xiuli. Mine rescue robot visual image enhancement and extraction of obstacles[J]. Coal Mine Machinery,2017,38(2):39-41.
[8] 周钦全,孙希平,余晓洁,等. 高分辨毫米波雷达与摄像融合目标跟踪方法[J]. 电子信息对抗技术,2024,39(4):47-55. ZHOU Qinquan,SUN Xiping,YU Xiaojie,et al. Target tracking method for fusion of high-resolution millimeter-wave radar and camera[J]. Electronic Information Warfare Technology,2024,39(4):47-55.
[9] 王新竹,李骏,李红建,等. 基于三维激光雷达和深度图像的自动驾驶汽车障碍物检测方法[J]. 吉林大学学报(工学版),2016,46(2):360-365. WANG Xinzhu,LI Jun,LI Hongjian,et al. Obstacle detection based on 3D laser scanner and range image for intelligent vehicle[J]. Journal of Jilin University (Engineering and Technology Edition),2016,46(2):360-365.
[10] 王涛,曾文浩,于琪. 基于激光雷达的无人驾驶障碍物检测和跟踪[J]. 西南交通大学学报,2021,56(6):1346-1354. WANG Tao,ZENG Wenhao,YU Qi. Obstacle detection and tracking for driverless cars based on lidar[J]. Journal of Southwest Jiaotong University,2021,56(6):1346-1354.
[11] 杨春雨,张鑫. 煤矿机器人环境感知与路径规划关键技术[J]. 煤炭学报,2022,47(7):2844-2872. YANG Chunyu,ZHANG Xin. Key technologies of coal mine robots for environment perception and path planning[J]. Journal of China Coal Society,2022,47(7):2844-2872.
[12] CHEN Xiaozhi,MA Huimin,WAN Ji,et al. Multi-view 3D object detection network for autonomous driving[C]. IEEE Conference on Computer Vision and Pattern Recognition,Honolulu,2017:6526-6534.
[13] 贺海涛,廖志伟,郭卫. 煤矿井下无轨胶轮车无人驾驶技术研究与探索[J]. 煤炭科学技术,2022,50(增刊1):212-217. HE Haitao,LIAO Zhiwei,GUO Wei. Research and exploration on driverless technology of trackless rubbertyred vehicle in coal mine[J]. Coal Science and Technology,2022,50(S1):212-217.
[14] 蒲德全,高振刚,李鹏洲. 基于传感器融合的矿井运输车辆环境感知研究[J]. 金属矿山,2024(10):176-181. PU Dequan,GAO Zhengang,LI Pengzhou. Study on environmental perception of mine transportation vehicles based on sensor fusion[J]. Metal Mine,2024(10):176-181.
[15] 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.
[16] 王紫临,张达. 井下障碍物激光雷达动态识别技术[J]. 矿冶,2023,32(1):104-108,114. WANG Zilin,ZHANG Da. Research on underground obstacle dynamic detection based on LiDAR[J]. Mining and Metallurgy,2023,32(1):104-108,114.
[17] 贺思奎. 矿用电机车无人驾驶环境感知系统研究[D]. 徐州:中国矿业大学,2023. HE Sikui. Research on the unmanned environment sensing system of mining electric locomotive[D]. Xuzhou:China University of Mining and Technology,2023.
[18] 何艳. 煤矿辅助运输机器人目标感知识别技术研究[D]. 徐州:中国矿业大学,2024. HE Yan. Research on target perception and recognition technology of coal mine auxiliary transport robot[D]. Xuzhou:China University of Mining and Technology,2024.
[19] PENG Ping'an,PAN Jin,ZHAO Ziyu,et al. A novel obstacle detection method in underground mines based on 3D LiDAR[J]. IEEE Access,2024,12:106685-106694. DOI: 10.1109/ACCESS.2024.3437784
[20] 孟春蕾. 矿井无人驾驶三维目标检测方法研究[D]. 徐州:中国矿业大学,2024. MENG Chunlei. Research on detection method of mine unmanned three-dimensional target[D]. Xuzhou:China University of Mining and Technology,2024.
[21] 秦沛霖,张传伟,周李兵,等. 煤矿井下无人驾驶无轨胶轮车目标3D检测研究[J]. 工矿自动化,2022,48(2):35-41. QIN Peilin,ZHANG Chuanwei,ZHOU Libing,et al. Research on 3D target detection of unmanned trackless rubber-tyred vehicle in coal mine[J]. Industry and Mine Automation,2022,48(2):35-41.
[22] 杨志方. 基于雷达与视觉融合的双模态煤矿井下环境感知技术[J]. 工矿自动化,2023,49(11):67-75. YANG Zhifang. Bimodal environment perception technology for underground coal mine based on radar and visual fusion[J]. Journal of Mine Automation,2023,49(11):67-75.
[23] 刁秀强. 基于图像与激光点云的煤矿井下2D/3D目标识别算法研发[D]. 徐州:中国矿业大学,2024. DIAO Xiuqiang. Research and development of 2D/3D target recognition algorithm in coal mine based on image and laser point cloud[D]. Xuzhou:China University of Mining and Technology,2024.
-
期刊类型引用(6)
1. 于南南，王祥青. 基于LoRa无线扩频通信技术的过程测量系统的研究与应用. 科技资讯. 2024(21): 4-7 . 
百度学术
2. 洪志鑫，蒋伟，贾文琪，韩朝晖. OOIP设计在煤矿控制系统的研究与应用. 煤矿机电. 2023(06): 38-42 . 百度学术
3. 汪伟. 基于MPLSVPN架构与AR技术的三层组网传输方法. 辽东学院学报(自然科学版). 2022(01): 63-68 . 百度学术
4. 莫言迟，刘占省，张安山，王广. 融合BIM技术和物联网的消防安全数据管理方法. 建筑技术. 2021(06): 710-713 . 百度学术
5. 张洪光，刘亭亭，吕秀莎，张莹，聂剑红，李青. 三维露天矿山场景中异构分簇组网协议研究. 工矿自动化. 2021(12): 68-74 . 本站查看
6. 底伟. 基于无线传感网络的水源井集中监控系统设计. 机电信息. 2020(20): 116-117 . 百度学术
其他类型引用(7)
计量
- 文章访问数: 24
- HTML全文浏览量: 4
- PDF下载量: 2
- 被引次数: 13
