基于激光雷达的道路环境障碍物检测方法
|
摘要
激光雷达的环境感知是智能交通的一个关键环节。激光雷达以其数据量大、检测精度高等优点在该环节中发挥了重要作用。论文根据车体运动信息,对采集到的雷达数据进行数据转换、矫正,克服了高低起伏的路面带来的数据漂移问题;对矫正后的结果进行多密度聚类分析,得出障碍物信息;同时,基于雷达数据点的扫描角度和距离估计障碍物质心,根据相邻帧的惯导信息进行动态障碍物检测。在结构化道路环境中的实验结果表明所提出的方法对于单帧数据中的障碍物检测以及帧间的动态障碍物检测效果显著。
The environmental awareness of LIDAR is the key link in intelligent transportation. LIDAR with large amount of data and high detection precision has played an important role. In this paper,according to the body movement information,the collected LIDAR data are converted and corrected to overcome the data drift problem caused by high and low pavement. The results of the correction are analyzed by multi-density clustering to get the obstacle information. At the same time,based on the scanning angle and distance,the proposed method estimates the centroid of obstacles considering the inertial navigation information combined with the adjacent frame information to detect dynamic obstacles. The experimental results in the structured road environment show that the algorithms have significant improvement on the detection of obstacles in the single frame data and the dynamic obstacle detection between frames.
The environmental awareness of LIDAR is the key link in intelligent transportation. LIDAR with large amount of data and high detection precision has played an important role. In this paper,according to the body movement information,the collected LIDAR data are converted and corrected to overcome the data drift problem caused by high and low pavement. The results of the correction are analyzed by multi-density clustering to get the obstacle information. At the same time,based on the scanning angle and distance,the proposed method estimates the centroid of obstacles considering the inertial navigation information combined with the adjacent frame information to detect dynamic obstacles. The experimental results in the structured road environment show that the algorithms have significant improvement on the detection of obstacles in the single frame data and the dynamic obstacle detection between frames.
引文
[1]Zhu X,Gao M,Li S.A real-time Road Boundary Detection Algorithm Based on Driverless Cars[J].Journal of Beijing Union University,2015:843-848.
[2]史鹏波.基于单线激光雷达的道路特征检测[D].南京:南京理工大学,2013.SHI Pengbo.Road feature detection based on single-line lidar[D].Nanjing:Nanjing University of Science and Technology,2013.
[3]杨象军,项志宇,刘济林.基于四线激光雷达的校园道路的检测与跟踪[J].传感器与微系统,2013,32(9):134-138.YANG Xiangjun,XIANG Zhiyu,LIU Jilin.Detection and tracking of campus road based on four-line laser radar[J].Transducer and Microsystem Technologies,2013,32(9):134-138.
[4]Douillard B,Underwood J,Melkumyan N,et al.Hybrid elevation maps:3D surface models for segmentation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems,Taipei,IEEE,2010:1532-1538.
[5]胡铟,杨静宇.基于单目视觉的路面车辆检测及跟踪方法综述[J].公路交通科技,2007,24(12):127-131.HU Yin,YANG Jingyu.Vehicle Detection and Tracking Based on Monocular Vision[J].Journal of Highway and Transportation Research and Development,2007,24(12):127-131.
[6]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 Jianmin,LI Longjie,ZHENG Kaihua.Preceding Drivable Area Detection Based on Four-layer Laser Radar[J].Automobile Technology,2016(2):55-62.
[7]关超华,陈泳丹,陈慧岩,等.基于改进DBSCAN算法的激光雷达车辆探测方法[J].北京理工大学学报,2010,30(6):732-736.GUAN Chaohua,CHEN Yongdan,CHEN Huiyan,et al.Improved DBSCAN Clustering Algorithm Based Vehicle Detection Using a Vehicle-Mounted Laser Scanner[J].Transactions of Beijing Institute of Technology,2010,30(6):732-736.
[8]王新,刘永山,朱代春,等.三维点云配准算法的研究[J].燕山大学学报,2016,40(6):524-531.WANG Xin,LIU Yongshan,ZHU Daichun,et al.Research on registration algorithm of three-dimensional point cloud[J].Journal of Yanshan University,2016,40(6):524-531.
[9]王桂芝,王广亮.改进的快速DBSCAN算法[J].计算机应用,2009,29(9):2505-2508.WANG Guizhi,WANG Guangliang.Improved fast DB-SCAN algorithm[J].Journal of Computer Applications,2009,29(9):2505-2508.
[10]冯少荣,肖文俊.DBSCAN聚类算法的研究与改进[J].中国矿业大学学报,2008,37(1):105-111.FENG Shaorong,XIAO Wenjun.An Improved DBSCANClustering Algorithm[J].Journal of China University of Mining&Technology,2008,37(1):105-111.
[11]蔡颖琨,谢昆青,马修军.屏蔽了输入参数敏感性的DBSCAN改进算法[J].北京大学学报(自然科学版),2004,40(3):480-486.CAI Yinkun,XIE Kunqing,MA Xiujun.An Improved DBSCAN Algorithm which is Insensitive to Input Parameters[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2004,40(3):480-486.
[12]夏鲁宁,荆继武.SA-DBSCAN:一种自适应基于密度聚类算法[J].中国科学院大学学报,2009,26(4):530-538.XIA Lunning,XING Jiwu.SA-DBSCAN:A self-adaptive density-based clustering algorithm[J].Journal of the Graduate School of the Chinese Academy of Sciences,2009,26(4):530-538.
[13]包瑞胜,马新,崔熠明.基于优化DBSCAN算法的智能车载激光雷达数据处理技术研究[J].中国交通信息化,2017(3):135-140.BAO Ruisheng,MA Xin,CUI Yiming.Research on Data Processing Technology of Intelligent Vehicle-Mounted Lidar Based on Optimized DBSCAN Algorithm[J].Transportation Information Industry,2017(3):135-140.
[14]李龙杰.基于四线激光雷达的道路信息提取技术研究[D].北京:北京工业大学,2016.LI Longjie.Research on Road Information Extraction Technology Based on Four-line Laser Radar[D].Beijing:Beijing University of Technology,2016.
[15]Zhao G,Yuan J.Curb detection and tracking using3D-LIDAR scanner[C]//IEEE International Conference on Image Processing.Orlando,FL,USA,IEEE,2013:437-440.
[16]Aftatah M,Lahrech A,Abounada A.Fusion of GPS/INS/Odometer measurements for land vehicle navigation with GPS outage[C]//International Conference on Cloud Computing Technologies and Applications,Marrakech,Morocco,IEEE,2017:48-55.
[17]陆兴华.姿态融合滤波的无人机抗干扰控制算法[J].传感器与微系统,2016,35(7):116-119.LU Xinghua.Anti-interference control algorithm for UAV based on attitude fusion filtering.Transducer and Microsystem Technologies,2016,35(7):116-119.
[2]史鹏波.基于单线激光雷达的道路特征检测[D].南京:南京理工大学,2013.SHI Pengbo.Road feature detection based on single-line lidar[D].Nanjing:Nanjing University of Science and Technology,2013.
[3]杨象军,项志宇,刘济林.基于四线激光雷达的校园道路的检测与跟踪[J].传感器与微系统,2013,32(9):134-138.YANG Xiangjun,XIANG Zhiyu,LIU Jilin.Detection and tracking of campus road based on four-line laser radar[J].Transducer and Microsystem Technologies,2013,32(9):134-138.
[4]Douillard B,Underwood J,Melkumyan N,et al.Hybrid elevation maps:3D surface models for segmentation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems,Taipei,IEEE,2010:1532-1538.
[5]胡铟,杨静宇.基于单目视觉的路面车辆检测及跟踪方法综述[J].公路交通科技,2007,24(12):127-131.HU Yin,YANG Jingyu.Vehicle Detection and Tracking Based on Monocular Vision[J].Journal of Highway and Transportation Research and Development,2007,24(12):127-131.
[6]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 Jianmin,LI Longjie,ZHENG Kaihua.Preceding Drivable Area Detection Based on Four-layer Laser Radar[J].Automobile Technology,2016(2):55-62.
[7]关超华,陈泳丹,陈慧岩,等.基于改进DBSCAN算法的激光雷达车辆探测方法[J].北京理工大学学报,2010,30(6):732-736.GUAN Chaohua,CHEN Yongdan,CHEN Huiyan,et al.Improved DBSCAN Clustering Algorithm Based Vehicle Detection Using a Vehicle-Mounted Laser Scanner[J].Transactions of Beijing Institute of Technology,2010,30(6):732-736.
[8]王新,刘永山,朱代春,等.三维点云配准算法的研究[J].燕山大学学报,2016,40(6):524-531.WANG Xin,LIU Yongshan,ZHU Daichun,et al.Research on registration algorithm of three-dimensional point cloud[J].Journal of Yanshan University,2016,40(6):524-531.
[9]王桂芝,王广亮.改进的快速DBSCAN算法[J].计算机应用,2009,29(9):2505-2508.WANG Guizhi,WANG Guangliang.Improved fast DB-SCAN algorithm[J].Journal of Computer Applications,2009,29(9):2505-2508.
[10]冯少荣,肖文俊.DBSCAN聚类算法的研究与改进[J].中国矿业大学学报,2008,37(1):105-111.FENG Shaorong,XIAO Wenjun.An Improved DBSCANClustering Algorithm[J].Journal of China University of Mining&Technology,2008,37(1):105-111.
[11]蔡颖琨,谢昆青,马修军.屏蔽了输入参数敏感性的DBSCAN改进算法[J].北京大学学报(自然科学版),2004,40(3):480-486.CAI Yinkun,XIE Kunqing,MA Xiujun.An Improved DBSCAN Algorithm which is Insensitive to Input Parameters[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2004,40(3):480-486.
[12]夏鲁宁,荆继武.SA-DBSCAN:一种自适应基于密度聚类算法[J].中国科学院大学学报,2009,26(4):530-538.XIA Lunning,XING Jiwu.SA-DBSCAN:A self-adaptive density-based clustering algorithm[J].Journal of the Graduate School of the Chinese Academy of Sciences,2009,26(4):530-538.
[13]包瑞胜,马新,崔熠明.基于优化DBSCAN算法的智能车载激光雷达数据处理技术研究[J].中国交通信息化,2017(3):135-140.BAO Ruisheng,MA Xin,CUI Yiming.Research on Data Processing Technology of Intelligent Vehicle-Mounted Lidar Based on Optimized DBSCAN Algorithm[J].Transportation Information Industry,2017(3):135-140.
[14]李龙杰.基于四线激光雷达的道路信息提取技术研究[D].北京:北京工业大学,2016.LI Longjie.Research on Road Information Extraction Technology Based on Four-line Laser Radar[D].Beijing:Beijing University of Technology,2016.
[15]Zhao G,Yuan J.Curb detection and tracking using3D-LIDAR scanner[C]//IEEE International Conference on Image Processing.Orlando,FL,USA,IEEE,2013:437-440.
[16]Aftatah M,Lahrech A,Abounada A.Fusion of GPS/INS/Odometer measurements for land vehicle navigation with GPS outage[C]//International Conference on Cloud Computing Technologies and Applications,Marrakech,Morocco,IEEE,2017:48-55.
[17]陆兴华.姿态融合滤波的无人机抗干扰控制算法[J].传感器与微系统,2016,35(7):116-119.LU Xinghua.Anti-interference control algorithm for UAV based on attitude fusion filtering.Transducer and Microsystem Technologies,2016,35(7):116-119.