基于车载16线激光雷达的障碍物检测方法

doi:10.3969/j.issn.1000-1158.2021.07.03

摘要
图/表
参考文献(22)
相关文章 (15)

全文: PDF (2872 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对目前车载16线激光雷达点云数据中障碍物检测算法准确率不高的问题,提出了一种基于自适应网格聚类的障碍物检测方法。首先,结合八叉树与随机抽样一致性算法(RANSAC)去除地面点;其次,投影点云至二维网格,依据各网格高程信息快速提取高结构物;然后,建立两级网格模型,按照粗网格聚类结果的分布信息自适应地确定子网格分辨率,对可能包含多目标的障碍物在子网格层进行准确检测;最后,结合相邻时刻障碍物的状态信息修正检测结果。在16线激光雷达城市道路环境测试集下的实验结果表明:该算法可准确检测行驶区域内障碍物目标,优化后的聚类算法较好地降低了欠分割与过分割错误率,检测准确率达91%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	孔德明
	段呈新
	巴特·古森斯
	王书涛

关键词 ：计量学, 障碍物检测, 网格聚类, 自适应, 八叉树算法, 随机抽样一致性算法

Abstract：Aiming at the issue of low accuracy of the existing in obstacle detection algorithm in the vehicle 16 line Lidar point cloud data, an obstacle detection algorithm based on adaptive grid is proposed. Firstly, octree and random sample consensus (RANSAC) algorithm is utilized to remove the ground point.Secondly, project the point cloud onto the 2D-grid, tall structure objects can be quickly extracted based on the elevation information in each grid.Thirdly, a two-level grid model is established, the sub-grid resolution is determined adaptively according to the distribution information of coarse grid clustering results, the obstacles that may contain multiple targets are detected precisely at the sub-grid layer.Finally, the clustering results are improved by combining the state information of two adjacent obstacles.The experimental results under urban road environment test sets show that the proposed method can precisely detect obstacles in driving area, the optimized clustering algorithm can reduce the error rates of under-segmentation and over-segmentation,the detection accuracy is 91%.

Key words： metrology obstacle detection grid clustering self-adaption;octree RANSAC

收稿日期: 2020-06-08 发布日期: 2021-07-15

PACS:

TB96

基金资助:国家自然科学基金(61501394,61771419);河北省自然科学基金(F2016203155,F2017203220)

作者简介: 孔德明(1983-),吉林公主岭人,燕山大学副教授,研究方向为激光雷达三维扫描测量技术。Email: demingkong@ysu.edu.cn

引用本文:

孔德明,段呈新,巴特·古森斯,王书涛. 基于车载16线激光雷达的障碍物检测方法[J]. 计量学报, 2021, 42(7): 846-852.
KONG De-ming,DUAN Cheng-xin,GOOSSENS Bart,WANG Shu-tao. Obstacle Detection Method Based on Vehicle 16-line Lidar. Acta Metrologica Sinica, 2021, 42(7): 846-852.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2021.07.03 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2021/V42/I7/846

［1］孔栋, 王晓原, 刘亚奇, 等. 基于车载32线激光雷达点云的车辆目标识别算法［J］. 科学技术与工程, 2018, 18 (5): 81-85.
Kong D, Wang X Y, Liu Y Q, et al.Vehicle target identification algorithm based on point cloud of vehicle 32-line laser lidar ［J］. Science Technology and Engineering, 2018, 18 (5) : 81-85.
［2］李博杨. 基于三维激光雷达的道路环境感知［D］.北京: 北京交通大学, 2019.
［3］李炯, 赵凯, 张志超, 等. 一种融合密度聚类与区域生长算法的快速障碍物检测方法［J］. 机器人, 2020, 42 (1): 60-70.
LI J, Zhao K, Zhang Z C, et al.A Fast Obstacle Detection Method by Fusion of Density-based Clustering and Region Growing Algorithms ［J］. Robot, 2020, 42 (1): 60-70.
［4］Charles R Q, Su H, Kaichun M, et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation［C］//Computer vision and pattern recognition, Honolulu, US, 2017: 77-85.
［5］Ren S, He K, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39 (6): 1137-1149.
［6］Yiakopoulos C, Gryllias K, Antoniadis I, et al.Rolling element bearing fault detection in industrial environments based on a K-means clustering approach ［J］. Expert Systems With Applications, 2011, 38 (3): 2888-2911.
［7］范小辉, 许国良, 李万林, 等. 基于深度图的三维激光雷达点云目标分割方法［J］. 中国激光, 2019, 46 (7): 292-299.
Fan X H, Xu G L, Li W L, v.Target Segmentation Method for Three-Dimensional LiDAR Point Cloud Based on Depth Image ［J］. Chinese Journal of Lasers, 2019, 46 (7): 292-299.
［8］李永强, 王文越, 郑艳慧, 等. 基于车载LiDAR数据的道路边界精细提取［J］. 河南理工大学学报自然科学版, 2014, 33 (4): 458-462.
Li Y Q, Wang W Y, Zheng H Y, et al.Refining extraction of road boundary from vehicle LiDAR date ［J］. Journal of Henan Polytechnic University (Nature Science), 2014, 33 (4): 458-462.
［9］段建民, 李龙杰, 郑凯华. 基于车载4线激光雷达的前方道路可行驶区域检测［J］. 汽车技术, 2016, (2): 55-62.
Duan J M, Li L J, Zheng K H.Preceding Drivable Area Detection Based on Four-layer Laser Radar ［J］. Automobile Technology, 2016, (2): 55-62.
［10］Sun Z, Bebis G, Miller R. On-road vehicle detection using Gabor filters and support vector machines ［C］//2002 14th International Conference on Digital Signal Processing Proceedings. IEEE, Santorini, Greece, 2002, 2: 1019-1022.
［11］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 F Y, 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.
［12］谢德胜, 徐友春, 王任栋, 等. 基于三维激光雷达的无人车障碍物检测与跟踪［J］. 汽车工程, 2018, 40 (8): 952-959.
Xie D S, Xu Y C, Wang R D, et al. Obstacle Detection and Tracking for Unmanned Vehicles Based on 3D Laser Radar ［J］. Automotive Engineering, 2018, 40 (8): 952-959.
［13］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.
［14］蔡怀宇, 陈延真, 卓励然, 等. 基于优化DBSCAN算法的激光雷达障碍物检测［J］. 光电工程, 2019, 46 (7): 83-90.
Cai H Y, Chen Y Z, Zhuo L R, et al. LiDAR object detection based on optimized DBSCAN algorithm ［J］. Opto-Electronic Engineering, 2019, 46 (7): 83-90.
［15］Chu P M, Cho S, Sim S, et al. A Fast Ground Segmentation Method for 3D Point Cloud ［J］. Journal of Information Processing Systems, 2017, 13 (3): 491-499.
［16］王育坚, 谭绍维, 荆文鹏, 等. 基于八叉树空间分割的NURBS曲面重构方法［J］. 计算机工程与设计, 2015, 36 (6): 1565-1570.
Wang Y J, Tan S W, Jing W P, et al. NURBS surface reconstruction based on space partitioning of octree ［J］. Computer Engineering and Design, 2015, 36 (6): 1565-1570.
［17］冯义从, 岑敏仪, 张同刚.地形自适应车载LiDAR点云滤波［J］. 测绘科学, 2015, 40 (10): 138-141, 152.
Feng Y C, Cen Y M, Zhang T G. Adaptive terrain based filter method for mobile LiDAR data ［J］. Science of Surveying and Mapping, 2015, 40 (10): 138-141, 152.
［18］唐菲菲, 阮志敏, 刘星, 等. 机载激光扫描数据粗差剔除新方法［J］. 激光杂志, 2011, 32 (1): 40-42.
Tang F F, Ruan Z M, Liu X, et al. A new method for outlier elimination of airborne LiDAR data ［J］. Laser Journal, 2011, 32 (1): 40-42.
［19］郑诚, 曹杨. 参数自适应的网格密度聚类算法［J］. 计算机应用研究, 2019, 36 (11): 3278-3281.
Zheng C, Cao Y.Self-adaptive based on grid density clustering algorithm ［J］. Application Research of Computers, 2019, 36 (11): 3278-3281.
［20］Sualeh M, Kim G W. Dynamic multi-lidar based mu-ltiple object detection and tracking ［J］. Sensors, 2019, 19 (6): 1474.
［21］程淑红, 高许, 程树春, 等. 基于计算机视觉的运动车辆检测［J］. 计量学报, 2017, 38 (3): 288-291.
Cheng S H, Gao X, Cheng S C, et al.Moving Vehicle Detection Based on Computer Vision ［J］. Acta Metrologica Sinica, 2017, 38 (3): 288-291.
［22］李海波, 曹云峰, 丁萌, 等. 基于三维点云聚类的坡度估计方法［J］. 计量学报, 2018, 39 (3): 304-309.
Li H B, Cao Y F, Ding M, et al. A Method of Slope Estimation Based on Clustering of Three-dimensional Point Cloud ［J］. Acta Metrologica Sinica, 2018, 39 (3): 304-309.