基于激光点云的道路可通行区域检测方法

doi:10.19678/j.issn.1000-3428.0061717

摘要/Abstract

摘要： 以车载激光雷达获取的点云数据为研究对象，针对无人车道路环境感知的关键技术展开研究。为解决无人驾驶中道路可通行区域检测存在的地面不平整、缓坡、障碍物单一等问题，提出基于激光点云数据的道路可通行区域检测方法。通过基于分段校准的RANSAC算法进行地面分割，解决地面不平整导致的欠分割问题。使用多特征复合判据，利用基于体素化的DBSCAN聚类算法和基于结构特征的障碍物识别方法完成障碍物的分割与识别。结合道路结构以及数据高程突变特征，提取道路边界候选点并拟合得到完整的道路边界线。将道路区域栅格化，根据道路边界悬空障碍物判断并更新可通行区域，实现可通行区域的准确检测。实验结果表明，该方法在复杂道路场景中的边界检测准确率高于95%，可有效检测出障碍物及道路的可通行区域，具有良好的实时性与鲁棒性。

关键词: 无人驾驶, 分段校准, 障碍物分割与识别, 道路边界提取, 可通行区域

Abstract: This study focuses on several key technologies for unmanned vehicle road environment perception using the point cloud data obtained by vehicle lidar as the basis for the research.To solve the problems of uneven ground, gentle slope, and single obstacle when detecting passable areas in unmanned driving, this paper proposes a detection method for passable road areas based on laser point cloud data.The ground is segmented using the improved RANSAC algorithm based on sectional calibration to solve the problem of under-segmentation caused by uneven ground.Then, the multi-feature composite criterion is adopted to segment the obstacles.Obstacle recognition is performed by applying the DBSCAN clustering algorithm based on voxelization to structural features.Further, road boundary candidate points are extracted, and the road boundary line is fitted by combining the road structure and height mutation features.Finally, the passable area is updated by rasterizing the road area, combined with the judgment of suspended obstacles on the road boundary.The passable area can thus be accurately detected.The experimental results show that the boundary detection accuracy of this method in complex road scenes exceeds 95%, effectively detecting obstacles and passable areas of roads and displays good real-time performance and robustness.

Key words: unmanned driving, sectional calibration, obstacle segmentation and recognition, road boundary extraction, passable area

中图分类号:

TP391

宁小娟, 巩亮, 张金磊. 基于激光点云的道路可通行区域检测方法[J]. 计算机工程, 2022, 48(4): 22-29.

NING Xiaojuan, GONG Liang, ZHANG Jinlei. Detection Method of Passable Road Areas Based on Laser Point Clouds[J]. Computer Engineering, 2022, 48(4): 22-29.

https://www.ecice06.com/CN/Y2022/V48/I4/22

图/表 16

20230114133854

20230114133859

20230114133908

20230114133912

20230114133916

20230114133919

20230114133924

20230114133932

20230114133937

20230114133944

20230114133948

20230114133953

20230114133957

20230114134001

20230114134005

20230114134010

参考文献

[1] 赵凯, 朱愿, 王任栋.基于均值高程图的城市环境三维LiDAR点云地面分割方法[J].军事交通学院学报, 2018, 20(9):80-84. ZHAO K, ZHU Y, WANG R D.Mean elevation map-based ground segmentation method for 3D LiDAR point cloud under urban environment[J].Journal of Military Transportation University, 2018, 20(9):80-84.(in Chinese)
[2] KAMMEL S, PITZER B.Lidar-based lane marker detection and mapping[C]//Proceedings of 2008 IEEE Intelligent Vehicles Symposium.Washington D.C., USA:IEEE Press, 2008:1137-1142.
[3] 程子阳, 任国全, 张银.扫描线段特征用于三维点云地面分割[J].光电工程, 2019, 46(7):111-120. CHENG Z Y, REN G Q, ZHANG Y.Ground segmentation from 3D point cloud using features of scanning line segments[J].Opto-Electronic Engineering, 2019, 46(7):111-120.(in Chinese)
[4] ZHANG Y H, WANG J, WANG X N, et al.Road-segmentation-based curb detection method for self-driving via a 3D-LiDAR sensor[J].IEEE Transactions on Intelligent Transportation Systems, 2018, 19(12):3981-3991.
[5] 邱佳月, 赖际舟, 李志敏, 等.面向复杂场景的激光雷达地面分割算法[J].仪器仪表学报, 2020, 41(11):244-251. QIU J Y, LAI J Z, LI Z M, et al.A lidar ground segmentation algorithm for complex scenes[J].Chinese Journal of Scientific Instrument, 2020, 41(11):244-251.(in Chinese)
[6] KORAH T, MEDASANI S, OWECHKO Y.Strip histogram grid for efficient LIDAR segmentation from urban environments[C]//Proceedings of CVPR'11.Washington D.C., USA:IEEE Press, 2011:74-81.
[7] WANG X T, WANG W D, YIN X F, et al.A new grid map construction method for autonomous vehicles[J].IFAC-PapersOnLine, 2018, 51(31):377-382.
[8] PANG C, ZHONG X Y, HU H S, et al.Adaptive obstacle detection for mobile robots in urban environments using downward-looking 2D LiDAR[J].Sensors, 2018, 18(6):1749.
[9] CHENG J, XIANG Z Y, CAO T, et al.Robust vehicle detection using 3D Lidar under complex urban environment[C]//Proceedings of 2014 IEEE International Conference on Robotics and Automation.Washington D.C., USA:IEEE Press, 2014:691-696.
[10] 娄新雨, 王海, 蔡英凤, 等.采用64线激光雷达的实时道路障碍物检测与分类算法的研究[J].汽车工程, 2019, 41(7):779-784. LOU X Y, WANG H, CAI Y F, et al.A research on an algorithm for real-time detection and classification of road obstacle by using 64-line lidar[J].Automotive Engineering, 2019, 41(7):779-784.(in Chinese)
[11] 霍占强, 王勇杰, 雒芬, 等.基于超点图网络的三维点云室内场景分割模型[J].计算机工程, 2021, 47(12):308-315. HUO Z Q, WANG Y J, LUO F, et al.Indoor scene segmentation model using three-dimensional point cloud based on super point graph network[J].Computer Engineering, 2021, 47(12):308-315.(in Chinese).
[12] ZHOU Y, TUZEL O.VoxelNet:end-to-end learning for point cloud based 3D object detection[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:4490-4499.
[13] HE C H, ZENG H, HUANG J Q, et al.Structure aware single-stage 3D object detection from point cloud[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:11870-11879.
[14] LIANG M, YANG B, CHEN Y, et al.Multi-task multi-sensor fusion for 3D object detection[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:7337-7345.
[15] 贾锋, 薛潺涓, 王欣.用于肺结节检测和分类的两阶段深度学习方法[J].吉林大学学报(理学版), 2020, 58(2):329-336. JIA F, XUE C J, WANG X.Two-stage deep learning method for detection and classification of pulmonary nodules[J].Journal of Jilin University(Science Edition), 2020, 58(2):329-336.(in Chinese).
[16] 刘健, 梁华为, 梅涛, 等.基于道路形态分析的道路边界提取[J].机器人, 2016, 38(3):322-328. LIU J, LIANG H W, MEI T, et al.Road curb extraction based on road shape analysis[J].Robot, 2016, 38(3):322-328.(in Chinese)
[17] WANG G J, WU J, HE R, et al.A point cloud-based robust road curb detection and tracking method[J].IEEE Access, 2019, 7:24611-24625.
[18] 闫明, 蔡云飞, 陈盟.一种新的非结构化环境可通行区域检测算法[J].计算机与数字工程, 2019, 47(7):1652-1661. YAN M, CAI Y F, CHEN M.A new accessible area detection algorithm in unstructured environment[J].Computer and Digital Engineering, 2019, 47(7):1652-1661.(in Chinese)
[19] DOUILLARD B, UNDERWOOD J, KUNTZ N, et al.On the segmentation of 3D LIDAR point clouds[C]//Proceedings of 2011 IEEE International Conference on Robotics and Automation.Washington D.C., USA:IEEE Press, 2011:2798-2805.
[20] ESTER M, KRIEGEL H P, SANDER J, et al.A density-based algorithm for discovering clusters in large spatial databases with noise[C]//Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining.Palo Alto, USA:AAAI Press, 1996:226-231.
[21] ZERMAS D, IZZAT I, PAPANIKOLOPOULOS N.Fast segmentation of 3D point clouds:a paradigm on LiDAR data for autonomous vehicle applications[C]//Proceedings of 2017 IEEE International Conference on Robotics and Automation.Washington D.C., USA:IEEE Press, 2017:5067-5073.
[22] ZHANG Y H, WANG J, WANG X N, et al.3D LIDAR-based intersection recognition and road boundary detection method for unmanned ground vehicle[C]//Proceedings of the 18th International Conference on Intelligent Transportation Systems.Washington D.C., USA:IEEE Press, 2015:499-504.

选择文件类型/文献管理软件名称

选择包含的内容