局部阈值自适应的地面点云分割  

Ground point cloud segmentation based on local threshold adaptive method

作　　者：张佩翔 王奇 高仁璟[1,2] 夏阳 万振中 ZHANG Peixiang;WANG Qi;GAO Renjing;XIA Yang;WAN Zhenzhong(State Key Laboratory of Structural Analysis,Optimization and CAE Software for Industrial Equipment,School of Automotive Engineering,Dalian University of Technology,Dalian 116024,China;Ningbo Institute of Dalian University of Technology,Ningbo 315000,China;BYD Auto Industry Company Limited,Shenzhen 518118,China)

机构地区：[1]大连理工大学汽车工程学院工业装备结构分析优化与CA E软件全国重点实验室,辽宁大连116024 [2]大连理工大学宁波研究院,浙江宁波315000 [3]比亚迪汽车工业有限公司,广东深圳518118

出　　处：《光学精密工程》2023年第17期2564-2572,共9页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.12172076);深圳市科创委项目(No.JSGG20200102155001779)。

摘　　要：为了进一步提高自动驾驶感应模块中激光雷达点云地面分割算法的分割精度,提出一种基于种子点距离阈值和路面波动加权幅值自适应的地面点云分割算法。该算法在极坐标栅格地图划分的基础上,将种子点的选取判断阈值与二维平面的水平距离特征相关联,通过点云间的水平距离变化控制种子点集的更新;在道路模型拟合过程中,为解决斜坡路面模型更新停滞问题引入坡度连续性判断准则,根据路面波动加权幅值的变化建立点云的分割阈值方程,最终实现关于点云距离特征的自适应阈值分割。对开源数据集Semantic KITTI进行点云二分类数据处理,并在此基础上测试算法性能。实验结果表明:与现有算法相比,本文所述地面分割算法的精确率和召回率均提升了2%~4%,具有较高的准确性。The LIDAR point cloud ground segmentation algorithm in the autonomous driving sensing mod⁃ule has low segmentation accuracy that requires further improvement.To address this problem,a ground point cloud segmentation algorithm is proposed based on a seed point distance threshold and road fluctua⁃tion weighted amplitude adaptive approach.Firstly,the method establishes a correlation between the se⁃lection threshold of seed points and the horizontal distance feature of the two-dimensional plane based on polar coordinate raster map division and controls the update of the seed point set through the change in hori⁃zontal distance between point clouds.Subsequently,in the process of road model fitting,the slope conti⁃nuity judgment criterion is introduced to solve the stagnation problem of the slope pavement model update.Finally,the segmentation threshold equation of point clouds is established according to the change in the weighted amplitude of road surface fluctuation.This enables the achievement of adaptive threshold seg⁃mentation with respect to the distance feature of point clouds.In this paper,point cloud binary classifica⁃tion data processing on the open-source dataset Semantic KITTI is performed,and the performance of the algorithm is tested.The experimental results demonstrate that the ground segmentation algorithm de⁃scribed in this paper exhibits an improvement of 2%-4%in precision and recall when compared to existing algorithms.This substantiates the high accuracy of the algorithm proposed in this study.

关 键 词：点云 地面分割 种子点距离 自适应阈值分割 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TN952[自动化与计算机技术—计算机科学与技术]