罗俊奇;叶勤;张绍明;史鹏程;

• 1:同济大学测绘与地理信息学院
• 2:武汉大学计算机学院

摘要(Abstract)：

针对稀疏点云道路分割与路障检测，特别是低矮路障检测方法中存在严重阈值依赖，从而受限于特定应用场景的问题，提出了一种自适应阈值的道路分割与低矮路障检测方法。通过坡度自适应算法与局部平面拟合，改进LineFit道路地面提取算法以实现斜率阈值自适应。利用基于曲率突变的点云分割算法实现道路边界提取。在道路分割的基础上，引入目标点云的局部相对密度实现了欧式聚类低矮路障检测的半径阈值自适应，提高了不同道路场景低矮路障检测的鲁棒性。实验表明，与传统的点云道路分割与路障检测方法相比，该方法对稀疏点云的道路分割与路障检测精度达到90%,对低矮路障具备更高的检测召回率与精确率，适用于低线束LiDAR自动驾驶平台的道路环境感知。

关键词(KeyWords)： 稀疏点云;低矮路障;阈值自适应;点云分割;目标检测

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41771480);; 上海市自然科学基金项目(22ZR1465700)

作者(Authors): 罗俊奇;叶勤;张绍明;史鹏程;

参考文献(References)：

• [1] XIE Y,TIAN J,ZHU X X.Linking points with labels in 3D:a review of point cloud semantic segmentation[J].IEEE geoscience and remote sensing magazine,2020,8(4):38-59.
• [2] 李德仁，洪勇，王密，等.测绘遥感能为智能驾驶做什么?[J].测绘学报，2021,50(11):1421-1431.
• [3] BICHSEL R,BORGES P V K.Low-obstacle detection using stereo vision[C]//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).Daejeon,Korea (South):IEEE,2016:4054-4061.
• [4] YANG G,MENTASTI S,BERSANI M,et al.LiDAR point-cloud processing based on projection methods:a comparison[C]//Proceedings of AEIT International Conference of Electrical and Electronic Technologies for Automotive (AEIT AUTOMOTIVE).Turin,Italy:IEEE,2020:1-6.
• [5] 张硕，叶勤，史婧，等.改进RangeNet++损失函数的车载点云小目标语义分割方法[J].计算机辅助设计与图形学学报，2021,33(5):704-711.
• [6] QI C R,SU H,MO K,et al.PointNet:deep learning on point sets for 3D classification and segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA:IEEE,2017:77-85.
• [7] B?RCS A,NAGY B,BENEDEK C.Instant object detection in LiDAR point clouds[J].IEEE geoscience and remote sensing letters,2017,14(7):992-996.
• [8] LIU Y,ZHONG R.Buildings and terrain of urban area point cloud segmentation based on PCL[C]//Proceedings of 35th International Symposium on Remote Sensing of Environment (ISRSE35).Beijing,China:IOP Conference Series-Earth and Environmental Science,2014,17(1):012238.
• [9] WANG C,JI M,WANG J,et al.An improved DBSCAN method for LiDAR data segmentation with automatic EPS estimation[J].Sensors,2019,19(1):172.
• [10] DOUILLARD B,UNDERWOOD J,KUNTZ N,et al.On the segmentation of 3D LIDAR point clouds[C]//Proceedings of IEEE International Conference on Robotics and Automation (ICRA).Shanghai,China:IEEE,2011:2798-2805.
• [11] 邹斌，王磊.基于激光雷达道路可通行区域的检测与提取[J].自动化与仪表，2018,33(2):33-38,49.
• [12] ZHANG Y,REN G,CHENG Z,et al.A target detection algorithm for 3D LiDAR point cloud[C]//Proceedings of 2019 2nd International Conference on Information Systems and Computer Aided Education (ICISCAE).Dalian,China:IEEE,2019:405-410.
• [13] HIMMELSBACH M,HUNDELSHAUSEN F V,WUENSCHE H J.Fast segmentation of 3D point clouds for ground vehicles[C]//Proceedings of IEEE Intelligent Vehicles Symposium (IV).La Jolla,CA,USA:IEEE,2010:560-565.
• [14] 景庄伟，管海燕，臧玉府，等.基于深度学习的点云语义分割研究综述[J].计算机科学与探索，2021,15(1):1-26.
• [15] GU J,WANG Y,CHEN L,et al.A reliable road segmentation and edge extraction for sparse 3D LiDAR data[C]//Proceedings of IEEE Intelligent Vehicles Symposium (IV).Changshu,China:IEEE,2018:1452-1457.
• [16] 鲁小伟.矿山道路边界线实时检测与跟踪[D].北京：中国科学院大学，2020.
• [17] SUN P,ZHAO X,XU Z,et al.A 3D LiDAR data-based dedicated road boundary detection algorithm for autonomous vehicles[J].IEEE access,2019,7:29623-29638.