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

doi:10.19562/j.chinasae.qcgc.2019.07.008

汽车工程 ›› 2019, Vol. 41 ›› Issue (7): 779-754.doi: 10.19562/j.chinasae.qcgc.2019.07.008

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

娄新雨¹, 王海^{1, 3}, 蔡英凤², 郑正扬¹, 陈龙²

1.江苏大学汽车与交通工程学院,镇江 212013;
2.江苏大学汽车工程研究院,镇江 212013;
3.香港大学机器人与自动化实验室,香港 999077

出版日期:2019-07-25 发布日期:2019-07-30
通讯作者: 蔡英凤,教授,博士生导师,E-mail:caicaixiao0304@126.com。
基金资助:
国家重点研发计划(2018YFB0105003)、国家自然科学基金(61601203,U1664258,U1764257,U1762264,61773184)、江苏省优秀青年基金(BK20180100)、江苏省重点研发计划(BE2016149)、江苏省战略性新兴产业发展重大专项(苏发改高技发(2016)1094号、(2015)1084号)、镇江市重点研发计划(GY2017006)和江苏高校境外研修计划资助。

A Research on an Algorithm for Real-time Detection and Classification of Road Obstacle by Using 64-line Lidar

Lou Xinyu¹, Wang Hai^1,3, Cai Yingfeng², Zheng Zhengyang¹ ,Chen Long²

1.School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013;
2.Institute of Automotive Engineering, Jiangsu University, Zhenjiang 212013;
3.Robotic and Automation Lab, University of Hongkong, Hongkong 999077

Online:2019-07-25 Published:2019-07-30

摘要/Abstract

摘要： 针对64线激光雷达数据量大,导致无人自主车的障碍物检测实时性差的问题,提出一种兼顾有效性和实时性的目标检测和分类算法。该算法首先通过多特征多层高度地图分离路面、障碍物和悬挂物;然后采用基于动态距离阈值的网格聚类算法对障碍物进行聚类,并结合相邻两个障碍物的运动状态信息对聚类结果进行修正,提高聚类的准确率;最后使用SVM对障碍物进行检测和分类。实验结果表明:该算法最优识别率达89.77%,耗时约为95 ms,在保证检测和分类准确率的基础上,满足无人自主车在道路行驶时检测障碍物的实时性要求,具有显著的工程实用价值。

关键词: 64线激光雷达, 目标检测, 目标分类, 实时性

Abstract: In view of the poor real-time performance of unmanned autonomous vehicle in detecting obstacles due to the huge volume of 64-line lidar data, an object detection and classification algorithm with good effectiveness and real-time performance is proposed. The algorithm separates the road, obstacle and suspended object by multi-feature / multi-layer elevation map. Then the grid clustering algorithm based on dynamic distance threshold is used to cluster the obstacles, with the clustering results corrected according to the motion state information of two adjacent obstacles to enhance clustering accuracy. Finally, SVM is adopted to detect and classify obstacles. The experiment results show that the algorithm attains a best identification rate of 89.77% with a duration of 95 ms, meeting the real-time requirements of unmanned vehicle in detecting obstacle on road, while ensuring the accuracy of detection and classification, having a significant engineering application value.

Key words: 64-line Lidar, object detection, object classification, real-time

娄新雨, 王海, 蔡英凤, 郑正扬, 陈龙. 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): 779-754.

Lou Xinyu, Wang Hai, Cai Yingfeng, Zheng Zhengyang , Chen Long. 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): 779-754.

参考文献

[1] QI C R, SU H, MO K, et al. PointNet: deep learning on point sets for 3D classification and segmentation[C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA,2016:77-85.
[2] 刘健.基于三维激光雷达的无人驾驶车辆环境建模关键技术研究[D].合肥:中国科学技术大学,2016.
[3] GOGA S, NEDEVSCHI S. An approach for segmenting 3D LiDAR data using multi-volume grid structures[C]. Intelligent Computer Communication and Processing (ICCP), Cluj-Napoca, Romania,2017:309-315.
[4] 肖克来提,邓志东.基于激光雷达的多属性栅格地图的创建[J].信息与电脑:理论版,2016(8):148-149.
[5] 邵帅,刘春晓,周光耀,等.基于车载LiDAR点云的地物分类方法的研究[J].测绘与空间地理信息,2017(2):198-201.
[6] SICILIANO B, KHATIB O. Springer handbook of robotics[J]. Robotics & Automation Magazine IEEE,2008,15(3):110.
[7] THRUN S, et al. Stanley: the robot that won the darpa grand challenge[J]. Journal of Field Robotics,2006,23(9):661-692.
[8] PENG Y, QU D, ZHONG Y, et al. The obstacle detection and obstacle avoidance algorithm based on 2-D lidar[C]. International Conference on Information & Automation, IEEE,2015.
[9] 苏致远,徐友春,李永乐.基于三维激光雷达的车辆目标检测方法[J].军事交通学院学报,2017,19(1):45-49.
[10] 杨成.无人驾驶智能车障碍检测方法研究[D].西安:西安工业大学,2015.
[11] 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].汽车电子,2016(2):55-61.
[12] 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.
[13] BEHLEY J, STEINHAGE V, CREMERS A B. Laser-based segment classification using a mixture of bag-of-words[C]. International Conference on Intelligent Robots & Systems, Tokyo, Japan,2013:4195-4200.
[14] BABAHAJIANI P. Object recognition in 3D point cloud of urban street scene[C]. Computer Vision-ACCV Workshops, Singapore, Singapore,2014:177-190.
[15] WIRGES S, FISCHER T, FRIAS J B, et al. Object detection and classification in occupancy grid maps using deep convolutional networks[J]. ar X iv:1805.08689v2.
[16] 甘志梅,王春香,杨明.基于激光雷达的车辆跟踪与识别算法[J].上海交通大学学报,2009,43(6):923-926.
[17] SKRZYPCZYNSKI P. Building geometrical map of environment using IR range finder data[C]. Intelligent Autonomous Systems,1995:408-412.
[18] 周俊静.基于激光雷达的智能车辆目标识别与跟踪[D].北京:北京工业大学,2014.
[19] BORGES G, ALDON M. Line extraction in 2D range images for mobile robotics[J]. Journal of Intelligent and Robotic Systems,2004,40:267-297.
[20] 赵一兵,王荣本,李琳辉,等.基于激光雷达的无人驾驶车前方障碍物检测[J].交通信息与安全,2007,25(2):9-13.

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

A Research on an Algorithm for Real-time Detection and Classification of Road Obstacle by Using 64-line Lidar

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

Metrics

本文评价

推荐阅读 10

[1]	程腾,倪昊,张强,王文冲,石琴. 基于虚拟点云的二阶段多模态融合网络[J]. 汽车工程, 2024, 46(2): 222-229.
[2]	马雷, 杨顺清, 王欢欢, 翟家琛, 徐健傲. 融合图像显著性特征的轻量级目标检测算法[J]. 汽车工程, 2024, 46(1): 84-91.
[3]	赵东宇, 赵树恩. 基于级联YOLOv7的自动驾驶三维目标检测[J]. 汽车工程, 2023, 45(7): 1112-1122.
[4]	韩勇,林旭洁,黄红武,蔡鸿瑜,罗金镕,李燕婷. 典型汽车碰撞事故场景中行人运动轨迹预测方法[J]. 汽车工程, 2023, 45(6): 1022-1030.
[5]	赵嘉豪,齐志权,齐智峰,王皓,何磊. 基于轮胎特征点的并行大型车辆朝向角计算[J]. 汽车工程, 2023, 45(6): 1031-1039.
[6]	陈妍妍,王海,蔡英凤,陈龙,李祎承. 基于检测的高效自动驾驶实例分割方法[J]. 汽车工程, 2023, 45(4): 541-550.
[7]	刘正发,吴亚,刘佩根,顾荣琦,陈广. 基于特征和标签联合分布匹配的智能驾驶跨域自适应目标检测[J]. 汽车工程, 2023, 45(11): 2082-2091.
[8]	胡杰,徐博远,熊宗权,昌敏杰,郭迪,谢礼浩. 基于多尺度掩码分类域自适应网络的跨域目标检测算法[J]. 汽车工程, 2022, 44(9): 1327-1338.
[9]	金立生,贺阳,王欢欢,霍震,谢宪毅,郭柏苍. 基于自适应阈值DBSCAN的路侧点云分割算法[J]. 汽车工程, 2022, 44(7): 987-996.
[10]	谢德胜,徐友春,陆峰,潘世举. 基于多传感器信息融合的3维目标实时检测[J]. 汽车工程, 2022, 44(3): 340-349.
[11]	刘子龙,沈祥飞. 融合Lite-HRNet的Yolo v5双模态自动驾驶小目标检测方法[J]. 汽车工程, 2022, 44(10): 1511-1520.
[12]	张炳力,秦浩然,江尚,郑杰禹,吴正海. 基于RetinaNet及优化损失函数的夜间车辆检测方法[J]. 汽车工程, 2021, 43(8): 1195-1202.
[13]	程腾,孙磊,侯登超,石琴,张峻宁,陈炯,黄鹤. 基于特征融合的多层次多模态目标检测[J]. 汽车工程, 2021, 43(11): 1602-1610.