Obstacle detection and tracking method based on millimeter wave radar and LiDAR

被引：0

作者：

Niu G. ^{[1
,2
]}

Tian Y. ^{[1
]}

Xiong Y. ^{[1
]}

机构：

[1] Institute of Robotics, Civil Aviation University of China, Tianjin

[2] Key Laboratory of Smart Airport Theory and System, CAAC, Tianjin

来源：

Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics | 2024年 / 50卷 / 05期

关键词：

LiDAR; millimeter wave radar; obstacle tracking; sensor fusion; unmanned vehicle;

D O I：

10.13700/j.bh.1001-5965.2022.0541

中图分类号：

学科分类号：

摘要：

Limited detecting range, low precision, and poor stability are just a few of the issues with obstacle detection and tracking that arise when using a single millimeter wave radar, or LiDAR, on an unmanned vehicle in a park. An obstacle-detecting and tracking approach based on the fusion of radar and LiDAR is proposed. Firstly, the improved Euclidean clustering algorithm is adopted to extract the objects in the road boundary from LiDAR point clouds. Furthermore, effective objects can be obtained from millimeter wave radar data which is handled based on an information filtering strategy. Then, the adaptive fusion of two kinds of objects described above is carried out based on the intersection over union and reliability analysis of objectdetection. The tracking gate and the joint probabilistic data association (JPDA) algorithm are performed to match sequence frames. In order to achieve obstacle tracking, the interacting multiple model and unscented Kalman filter method are finally put into practice. The experimental results show that the proposed method has higher accuracy and stability than using a single sensor for obstacle detection and tracking. © 2024 Beijing University of Aeronautics and Astronautics (BUAA). All rights reserved.

引用

页码：1481 / 1490

页数：9

共 18 条

[1]

LI Y, IBANEZ-GUZMAN J., Lidar for autonomous driving: The principles, challenges, and trends for automotive lidar and perception systems, IEEE Signal Processing Magazine, 37, 4, pp. 50-61, (2020)

[2]

GUO X M, LI B J, LONG J Y, Et al., Path planning of urban autonomous driving using laser point cloud data, China Journal of Highway and Transport, 33, 4, pp. 182-190, (2020)

[3]

LIM W, LEE S, SUNWOO M, Et al., Hierarchical trajectory planning of an autonomous car based on the integration of a sampling and an optimization method, IEEE Transactions on Intelligent Transportation Systems, 19, 2, pp. 613-626, (2018)

[4]

CHEN J F, WANG C C, CHOU C F., Multiple target tracking in occlusion area with interacting object models in urban environments, Robotics and Autonomous Systems, 103, pp. 68-82, (2018)

[5]

PU L, ZHANG X J., Deep learning based UAV vision object detection and tracking, Journal of Beijing University of Aeronautics and Astronautics, 48, 5, pp. 872-880, (2022)

[6]

FENG D., Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges, IEEE Transactions on Intelligent Transportation Systems, 22, 3, pp. 1341-1360, (2021)

[7]

LI J, ZHAO K, ZHANG Z C, A fast obstacle detection method by fusion of density-based clustering and region growing algorithms, Robot, 42, 1, pp. 60-70, (2020)

[8]

XU S, WANG R, WANG H, Et al., An optimal hierarchical clustering approach to mobile LiDAR point clouds, IEEE Transactions on Intelligent Transportation Systems, 21, 7, pp. 2765-2776, (2020)

[9]

RAVINDRAN R, SANTORA M J, JAMALI M J, Et al., Multiobject detection and tracking, based on DNN, for autonomous vehicles: A review, IEEE Sensors Journal, 21, 5, pp. 5668-5677, (2021)

[10]

KIM J, CHOI Y, PARK M, Et al., Multi-sensor-based detection and tracking of moving objects for relative position estimation in autonomous driving conditions, Journal of Supercomputing, 76, 10, pp. 8225-8247, (2020)

← 1 2 →