现代雷达2026，Vol.48Issue(1)：48-54,7.DOI:10.16592/j.cnki.1004-7859.20240809002
基于Mask R-CNN的激光雷达测量数据特征点识别
Feature Point Recognition of LiDAR Measurement Data Based on Mask R-CNN
摘要
Abstract
Directly using LiDAR measurement data to extract key information for feature point recognition cannot directly distinguish whether points belong to the same target.Only extracting local feature points can lead to a decrease in data feature recognition ac-curacy.A LiDAR measurement data feature point recognition based on Mask R-CNN is proposed.Firstly,PointNet++is selected as the backbone network of Mask R-CNN to extract feature vectors,and a feature pyramid network is constructed next to the back-bone branch to extract multi-scale features.A three-dimensional candidate box is generated by the region suggestion network,which is input into the classifier network through ROI Align.Target category prediction,candidate box position regression,and bi-nary mask are carried out to output the target segmentation results.Then,based on the segmented target point cloud,a 4D Shepard surface estimation is used.Target point cloud curvature,Obtain the volume integral invariants and normalize them.Finally,cluster the volume integral invariants using the K-means algorithm to achieve feature point recognition in LiDAR measurement data.The experimental results show that the proposed method can effectively segment targets in LiDAR measurement data with a simplification rate of 37.68%.The data feature point recognition performance and quality are high,and the detection results of AP,AP50,and AP75 are all above 90%,indicating good application effects.关键词
卷积神经网络掩膜/激光雷达测量数据/特征点识别/体积积分不变量/K-means算法Key words
Mask R-CNN/LiDAR measurement data/feature point recognition/volume integral invariants/K-means algorithm分类
信息技术与安全科学引用本文复制引用
幸荔芸,李珊枝..基于Mask R-CNN的激光雷达测量数据特征点识别[J].现代雷达,2026,48(1):48-54,7.基金项目
重庆市职业教育教学改革研究基金资助项目(Z233094) （Z233094）
"重庆市教育科学"十四五"规划2023年度重点课题基金资助项目(K23YC3070047) （K23YC3070047）
