智轨电车多传感器融合检测与跟踪研究

潘文波; 袁希文; 林军; 谢国涛; 龙腾; 黄文宇

doi:10.13890/j.issn.1000-128X.2022.04.023

您当前的位置：

首页 >

文章列表页 >

智轨电车多传感器融合检测与跟踪研究

检测技术 | 更新时间：2024-08-02

- 智轨电车多传感器融合检测与跟踪研究
- Research on multi-sensor fusion detection and tracking technology for autonomous-rail rapid transit tram
- 机车电传动 2022年第4期页码：157-165
- 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，主要研究方向为智能驾驶环境感知与建图定位； E-mail: panwb1@csrzic.com
- 基金信息：
  
  国家自然科学青年基金项目(5210120159);湖南省自然科学青年基金项目(2020JJ5091)
- DOI：10.13890/j.issn.1000-128X.2022.04.023
  中图分类号： U239.5;TP391.4
- 纸质出版日期：2022-07-10，
  
  收稿日期：2022-02-15，
  
  修回日期：2022-06-22，
- 稿件说明：
扫描看全文
潘文波, 袁希文, 林军, 等. 智轨电车多传感器融合检测与跟踪研究[J]. 机车电传动, 2022,(4):157-165.

PAN Wenbo, YUAN Xiwen, LIN Jun, et al. Research on multi-sensor fusion detection and tracking technology for autonomous-rail rapid transit tram[J]. Electric drive for locomotives, 2022,(4):157-165.
潘文波, 袁希文, 林军, 等. 智轨电车多传感器融合检测与跟踪研究[J]. 机车电传动, 2022,(4):157-165. DOI： 10.13890/j.issn.1000-128X.2022.04.023.

PAN Wenbo, YUAN Xiwen, LIN Jun, et al. Research on multi-sensor fusion detection and tracking technology for autonomous-rail rapid transit tram[J]. Electric drive for locomotives, 2022,(4):157-165. DOI： 10.13890/j.issn.1000-128X.2022.04.023.

摘要

为了保证智轨电车的运行安全，提高结构化道路环境下多种路况障碍物检测与跟踪的高效性和鲁棒性，文章提出一种基于激光雷达与毫米波雷达融合的多目标检测与跟踪方法。该方法首先基于毫米波雷达与激光雷达进行单传感器感知，然后通过多源融合算法融合单传感器感知结果，以获取更精确的感知结果。基于虚警滤除算法解决了毫米波雷达虚警引起误报问题，基于点云深度图和梯度与距离特征解决了多变场景下的障碍物聚类问题，基于分区点云特点设计代价函数提高了形状估计算法的鲁棒性，基于航迹信息进行多目标跟踪提高了目标跟踪的稳定性。为了克服异构传感器融合难题，设计了多源传感器异步融合策略，提升了结构化道路环境下目标检测与跟踪能力。最后，基于ROS框架在智轨电车上进行实车测试，试验结果表明，该方法能够稳定可靠地检测目标并实现跟踪。

Abstract

To ensure the operational safety of the autonomous-rail rapid transit (ART) trams on the structured roads

it is necessary to improve the efficiency and robustness of obstacle detection and tracking under different road conditions. This paper proposed a multi-target detection and tracking approach based on the fusion of LiDAR and millimeter-wave radar. Firstly

a millimeter-wave radar and LiDAR are used to perceive by single sensor

and the sensing results were merged by using a multi-source fusion algorithm

to generate more accurate detection results. Based on the false alarm filtering algorithm

the problem of false alarm probably caused by the millimeter wave radar was solved. The approach was based on the point cloud range image

and the gradient and distance characteristics to solve the problem of clustering obstacles in changing scenes. The cost function was derived from the characteristics of the segmented point clouds

which improves the robustness of the shape estimation algorithm. The multi-target tracking based on the track information raised the stability of target tracking. To overcome the challenge of heterogeneous sensor fusion

a multi-source sensor asynchronous fusion strategy was applied

which improved the target detection and tracking capabilities on the structured roads. The proposed approach was verified on the real ART trams based on the ROS framework. The test results demonstrate the stability

accuracy and reliability of the proposed approach.

关键词

智轨电车分割聚类形状估计交互式多模型多源信息融合

Keywords

autonomous-rail rapid transit (ART) tramsegmentation clusteringshape estimationinteractive multi-modelmulti-source information fusion

references

THRUN S, MONTEMERLO M, DAHLKAMP H, et al. Stanley: the robot that won the DARPA grand challenge[J]. Journal of Field Robotics, 2006, 23(9): 661-692.

LEONARD J, HOW J, TELLER S, et al. A perception-driven autonomous urban vehicle[J]. Journal of Field Robotics, 2008, 25(10): 727-774.

王海, 刘明亮, 蔡英凤, 等. 基于激光雷达与毫米波雷达融合的车辆目标检测算法[J]. 江苏大学学报(自然科学版), 2021, 42(4): 389-394.

WANG Hai, LIU Mingliang, CAI Yingfeng, et al. Vehicle target detection algorithm based on fusion of lidar and millimeter wave radar[J]. Journal of Jiangsu University (Natural Science Edition), 2021, 42(4): 389-394.

YAN Zhi, DUCKETT T, BELLOTTO N. Online learning for 3D LiDAR-based human detection: experimental analysis of point cloud clustering and classification methods[J]. Autonomous Robots, 2020, 44(2): 147-164.

ZERMAS D, IZZAT I, PAPANIKOLOPOULOS N. Fast segmentation of 3D point clouds: a paradigm on LiDAR data for autonomous vehicle applications[C]//IEEE. 2017 IEEE International Conference on Robotics and Automation (ICRA). Singapore: IEEE, 2017: 5067-5073.

GUO Yulan, WANG Hanyun, HU Qingyong, et al. Deep learning for 3D point clouds: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(12): 4338-4364.

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.

邱枫. 车载毫米波雷达多目标稳定跟踪算法研究[D]. 哈尔滨: 哈尔滨工业大学, 2018.

QIU Feng. Research on stable multi-target tracking algorithm of vehicle-borne millimeter wave radar[D]. Harbin: Harbin Institute of Technology, 2018.

DICKMANN J, KLAPPSTEIN J, HAHN M, et al. Automotive radar the key technology for autonomous driving: from detection and ranging to environmental understanding[C]//IEEE. 2016 IEEE Radar Conference. Philadelphia: IEEE, 2016: 1-6.

FARAGHER R. Understanding the basis of the Kalman filter via a simple and intuitive derivation [lecture notes][J]. IEEE Signal Processing Magazine, 2012, 29(5): 128-132.

龚迅. 汽车防撞雷达多目标跟踪算法研究[D]. 南京: 南京理工大学, 2017.

GONG Xun. Research on multi-target tracking algorithm of automotive anti-collision radar[D]. Nanjing: Nanjing University of Science and Technology, 2017.

姬存慧. 基于交互多模型的机动目标跟踪算法研究及硬件实现[D]. 南京: 南京理工大学, 2013.

JI Cunhui. Research and hardware implementation of maneuvering target tracking algorithm based on interactive multi-model[D]. Nanjing: Nanjing University of Science and Technology, 2013.

SINGER R A, STEIN J J. An optimal tracking filter for processing sensor data of imprecisely determined origin in surveillance systems[C]//IEEE. 1971 IEEE Conference on Decision and Control. Miami Beach: IEEE, 1971: 171-175.

李朝. 基于激光雷达和毫米波雷达融合的目标检测方法研究[D]. 太原: 中北大学, 2021.

LI Chao. Research on object detection method based on fusion of lidar and millimeter wave radar[D]. Taiyuan: North University of China, 2021.

LIU Haitao, PAN Wenbo, HU Yunqing, et al. A detection and tracking method based on heterogeneous multi-sensor fusion for unmanned mining trucks[J]. Sensors, 2022, 22(16): 5989.

SHIN K, KWON Y P, TOMIZUKA M. RoarNet: a robust 3D object detection based on Region approximation refinement[C]//IEEE. 2019 IEEE Intelligent Vehicles Symposium (IV). Paris: IEEE, 2019: 2510-2515.

CHEN Xiaozhi, MA Huimin, WAN Ji, et al. Multi-view 3D object detection network for autonomous driving[C]//IEEE. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 6526-6534.

QI C R, LIU Wei, WU Chenxia, et al. Frustum pointnets for 3D object detection from rgb-d data[C]//IEEE. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 918-927.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据