浏览全部资源
扫码关注微信
面向地铁场景的激光雷达目标检测研究
Research on lidar target detection for metro scene
- 机车电传动 2022年第2期 页码：89-96
- 作者机构：
1.中车株洲电力机车研究所有限公司，湖南 株洲 412001
2.湖南大学 汽车车身先进设计制造国家重点实验室，湖南 长沙;410082
- 作者简介：
潘文波（1986—），男，博士，高级工程师，主要从事雷达感知、定位与建图、多传感器融合感知方面的研究； E-mail：panwb1@csrzic.com
- 基金信息：国家自然科学青年基金项目(5210120159);国家重大技术装备攻关工程项目（系列化中国标准地铁列车研制及试验）
DOI：10.13890/j.issn.1000-128X.2022.02.013
中图分类号： U231;TN958.98纸质出版日期：2022-03-10，
收稿日期：2022-02-15，
修回日期：2022-03-02，
- 稿件说明：
扫 描 看 全 文
潘文波, 李程, 袁希文, 等. 面向地铁场景的激光雷达目标检测研究[J]. 机车电传动, 2022,(2):89-96.
PAN Wenbo, LI Cheng, YUAN Xiwen, et al. Research on lidar target detection for metro scene[J]. Electric drive for locomotives, 2022,(2):89-96.
潘文波, 李程, 袁希文, 等. 面向地铁场景的激光雷达目标检测研究[J]. 机车电传动, 2022,(2):89-96. DOI： 10.13890/j.issn.1000-128X.2022.02.013.
PAN Wenbo, LI Cheng, YUAN Xiwen, et al. Research on lidar target detection for metro scene[J]. Electric drive for locomotives, 2022,(2):89-96. DOI： 10.13890/j.issn.1000-128X.2022.02.013.
摘要
针对列车运行前方限界难以实时构建、非结构化轨道道路环境目标聚类检测复杂等问题，提出一种基于激光雷达的目标检测及前方界限实时构建系统。首先，采用了空间换时间的策略提升轨道提取效率，利用轨道局部高程信息、全局几何平行信息并融合多帧信息实现轨道稳定提取，从而基于提取的轨道位置实时构建列车通行的前方限界；其次，基于点云深度图、梯度与距离特征解决了非平铺路场景下的障碍物聚类问题，采用航迹信息进行多目标跟踪提高目标跟踪的稳定性。通过在地铁场景实车测试验证，结果表明该方法能够准确可靠地提取轨道位置和进行目标检测与跟踪。
Abstract
Aiming at the problems of difficult real-time construction of train running forward boundary and complex cluster detection of unstructured track and road environment targets
a lidar based on target detection and forward boundary real-time construction system was proposed. Firstly
the strategy of space for time was adopted to improve the efficiency of rail track extraction
and the rail track was extracted steadily by using the local elevation information
global geometric parallel information and multi-frame information of the rail track. Then
the forward limit of train passage was constructed based on the extracted rail track position in real time. Secondly
based on the point cloud depth map and gradient and distance characteristics
the obstacle clustering problem in non-paved road scenarios was solved
and the track information was used for multi-target tracking to improve the stability of target tracking. By real train test on metro scene
it was proved that the proposed method could extract track position accurately and reliably
it also could detect and track targets.
关键词
地铁车辆激光雷达轨道提取分割聚类目标检测城市轨道交通
Keywords
metro trainslidartrack extractionsegmentation and clusteringtarget detectionurban rail transit
references
MOHAMAD M, KUSEVIC K, MRSTIK P, et al. Automatic rail extraction in terrestrial and airborne LiDAR data[C]//IEEE. 2013 International Conference on 3D Vision-3DV 2013. Seattle: IEEE, 2013: 303-309.
LOU Yidong, ZHANG Tian, TANG Jian, et al. A fast algorithm for rail extraction using mobile laser scanning data[J]. Remote Sensing, 2018, 10(12): 1-22.
AMARAL V, MARQUES F, LOURENÇO A, et al. Laser-based obstacle detection at railway level crossings[J]. Journal of Sensors, 2016, 4(2)：1-11
曲越. 城轨列车非接触式障碍物检测系统的研究[D]. 北京: 北京交通大学, 2017.
QU Yue. The research of non-contact obstacle detection system for urban rail vehicle[D]. Beijing: Beijing Jiaotong University, 2017.
张博, 陈慧岩, 席军强. 智能车辆非结构化路面障碍检测[J]. 汽车工程, 2009, 31(6): 526-530.
ZHANG Bo, CHEN Huiyan, XI Junqiang. Obstacle detection on unstructured terrain for unmanned ground vehicles[J]. Automotive Engineering, 2009, 31(6): 526-530.
SHANG Erke, AN Xiangjing, WU Tao, et al. Lidar based negative obstacle detection for field autonomous land vehicles[J]. Journal of Field Robotics, 2016, 33(5): 591-617.
LUO Zhongzhen, MOHRENSCHILDT M V, HABIBI S. A probability occupancy grid based approach for real-time lidar ground segmentation[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(3): 998-1010.
MOOSMANN F, PINK O, STILLER C. Segmentation of 3D lidar data in non-flat urban environments using a local convexity criterion[C]//IEEE. 2009 IEEE Intelligent Vehicles Symposium. Xi'an: IEEE, 2009: 215-220.
CHENG Ziyang, REN Guoquan, ZHANG Yin. Ground segmentation algorithm based on 3D lidar point cloud[C]//Proceedings of the 2018 International Conference on Mechanical, Electrical, Electronic Engineering & Science (MEEES 2018). Paris: Atlantis Press, 2018: 16-21.
何秉高, 孙向阳, 史丽娟, 等. 基于激光雷达与机器视觉融合的轨道交通障碍物检测方法研究[J]. 轻工科技, 2019, 35(9): 80-82.
HE Binggao, SUN Xiangyang, SHI Lijuan, et al. Research on rail transit obstacle detection method based on lidar and machine vision fusion[J]. Light Industry Science and Technology, 2019, 35(9): 80-82.
胡云卿, 冯江华, 龙腾, 等. 智轨电车多源环境感知系统[J]. 控制与信息技术, 2020(1): 13-18.
HU Yunqing, FENG Jianghua, LONG Teng, et al. Multi-source environment perception system for autonomous-rail rapid tram[J]. Control and Information Technology, 2020(1): 13-18.
曾祥, 蒋国涛, 鲍纪宇, 等. 基于车载激光雷达的隧道内障碍物检测[J]. 控制与信息技术, 2021(1): 1-8.
ZENG Xiang, JIANG Guotao, BAO Jiyu, et al. Detection of obstacles in tunnel based on vehicle-borne lidar[J]. Control and Information Technology, 2021(1): 1-8.
黄世泽, 杨玲玉, 陶婷, 等. 基于实例分割的有轨电车障碍物入侵检测及轨道识别方法[J]. 上海公路, 2021(2): 89-94.
HUANG Shize, YANG Lingyu, TAO Ting, et al. A method of tram obstacle intrusion detection and track recognition based on instance segmentation[J]. Shanghai Highways, 2021(2): 89-94.
中华人民共和国住房和城乡建设部. 地铁限界标准: CJJ/T 96—2018[S]. 北京: 中国建筑工业出版社, 2018.
Ministry of Housing and Urban-Rural Development of the People's Republic of China. Standard for metro gauges: CJJ/T 96—2018[S]. Beijing: China Architecture & Building Press, 2018.
龚轩, 乐孜纯, 王慧, 等. 多目标跟踪中的数据关联技术综述[J]. 计算机科学, 2020, 47(10): 136-144.
GONG Xuan, LE Zichun, WANG Hui, et al. Survey of data association technology in multi-target tracking[J]. Computer Science, 2020, 47(10): 136-144.
0
浏览量
37
下载量
0
CSCD
7
CNKI被引量
- 网络PDF下载
- WORD下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 湘ICP备20010475号-1
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies