Title: A 3D target detection algorithm for low-speed unmanned vehicles in closed parks based on redundant fusion of multi-sensor information

Authors: Zhiqun Yuan; Jiayue Li; Jian Jiang; Xiujing Gao

Addresses: School of Mechanical and Automotive Engineering, Xiamen University of Technology, Fujian Provincial Key Laboratory of Advanced Design and Manufacture for Bus Coach, Xiamen, Fujian, 361024, China ' School of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen, Fujian, 361024, China ' School of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen King Long United Automotive Industry Co., Ltd., Fujian Provincial Key Laboratory of Intelligent Connected Commercial Vehicle, Xiamen, Fujian, 361024, China ' School of Smart Marine Science and Technology, Fujian University of Technology, Fujian Provincial Key Laboratory of Marine Smart Equipment, Fuzhou, Fujian, 350118, China

Abstract: To address the issues of object segmentation and pedestrian mis-detection, this paper proposes a redundant target detection method based on multi-level Euclidean clustering and view cone point cloud fusion. First, the joint calibration of LiDAR and camera is completed. Then, the pedestrian information and point cloud fusion are used to form a pedestrian cone point cloud, in addition, the multi-level threshold Euclidean clustering algorithm and the optimal 3D bracket selection method are designed. Finally, the pedestrian 3D bounding box is obtained by solving the point cloud confidence function, and fusion matching with the LiDAR detection results is performed to output the multi-sensor fusion perception results. Real-vehicle experimental data show that this method improves the accuracy of the whole sensing module, reduces the number of missed and misdetected boxes, and achieves 94.94% detection accuracy, which is 8.68% higher than the LiDAR detection algorithm, demonstrating its effectiveness and reliability.

Keywords: autonomous driving; closed park; multi-level Euclidean clustering; multi-sensor fusion; point cloud target detection.

DOI: 10.1504/IJVSMT.2025.147901

International Journal of Vehicle Systems Modelling and Testing, 2025 Vol.19 No.3, pp.217 - 242

Received: 03 Jul 2024
Accepted: 30 Sep 2024
Published online: 07 Aug 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article