期刊论文

中文

计算机应用研究

1001-3695

2023

40

3

909-913

10.19734/j.issn.1001-3695.2022.05.0345

本校为第一机构

低线束激光雷达扫描的点云数据较为稀疏，导致无人驾驶环境感知系统中三维目标检测效果欠佳，通过多帧点云配准可实现稀疏点云稠密化，但动态环境中的行人与移动车辆会降低激光雷达的定位精度，也会造成融合帧中运动目标上的点云偏移较大。针对上述问题，提出了一种动态环境中多帧点云融合算法，并利用该算法在园区道路实况下进行了三维目标检测，提高了低线束激光雷达的三维目标检测精度。利用16线与40线激光雷达采集的行驶路况数据进行实验，结果表明该算法能够增强稀疏点云密度，改善低成本激光雷达的环境感知能力。

The point cloud data scanned by the low-beam LiDAR is relatively sparse, resulting in poor 3D object detection in the unmanned environment perception system.Multi-frame point cloud registration can achieve sparse point cloud densification, however, pedestrians and movin...MORE The point cloud data scanned by the low-beam LiDAR is relatively sparse, resulting in poor 3D object detection in the unmanned environment perception system.Multi-frame point cloud registration can achieve sparse point cloud densification, however, pedestrians and moving vehicles in a dynamic environment will reduce the ...