城市竣工测绘典型要素语义分割PointNet++深度学习模型适用性分析被引量：1

Analysis of the applicability of PointNet++deep learning model for semantic segmentation of typical elements of urban as-built mapping

在线阅读下载PDF

导出

摘要处理三维激光扫描仪获取的城市竣工测绘点云场景数据的传统方法存在较多局限性,无法适应信息化社会对产品高效处理的需求。基于此,本文分析了城市竣工测绘点云场景分类需求,研究了利用深度学习网络模型对点云场景进行自动化处理的方法。首先,对输入的城市竣工测绘数据进行预处理,以实现点云降采样、去噪、地面点与非地面点分割;然后,人工标注5个区域场景数据毫米级标签,进行数据增强;最后,测试PointNet++网络在城市竣工测绘点云场景下的语义分割性能和效果。测试结果表明,在少量样本下,PointNet++网络可以较好地实现城市竣工测绘点云场景的激光点云语义分割,总体mIoU达73.06%,能够满足城市竣工测绘点云语义自动化分割需求,为城市竣工测绘点云数据处理提供了新思路。 The traditional methods for processing urban completion mapping point cloud scene data obtained by 3D laser scanner have several limitations and cannot meet the demand for efficient processing of products in the information society.In this paper,we analyze the demand for classification of urban completion mapping point cloud scenes and study the automated processing of point cloud scenes using a deep learning network model.Firstly,we preprocess the input urban completion mapping data to achieve point cloud downsampling,denoising,and ground point and non-ground point segmentation.Secondly,manually labels five regional scenes with millimeter-level labels and performs data augmentation techniques.And finally tests the semantic segmentation performance and effect of the PointNet++network in urban completion mapping point cloud scenes.The test results show that the PointNet++network can achieve the semantic segmentation of laser point clouds in urban completion mapping point cloud scenes with a small number of samples,and the overall mIoU reaches 73.06%,meeting the demand for semantic automatic segmentation of urban completion mapping point clouds and offering a new approach to processing urban completion mapping point cloud data.

作者黄应华董振川李昊陈壮刘长睿张献州 HUANG Yinghua;DONG Zhenchuan;LI Hao;CHEN Zhuang;LIU Changrui;ZHANG Xianzhou(Faculty of Geosciences and Environmental Engineering,Southwest Jiaotong University,Chengdu 611756,China;Chengdu Institute of Survey&Investigation,Chengdu 610081,China;China Railway Design Group Corproratioin,Tianjin 300000,China)

机构地区西南交通大学地球科学与环境工程学院成都市勘察测绘研究院中国铁路设计集团有限公司

出处《测绘通报》 CSCD 北大核心 2024年第2期85-89,共5页 Bulletin of Surveying and Mapping

基金四川省测绘地理信息学会科技开放基金(CCX202216) 城市建设项目竣工测绘点云分类与特征信息提取(KY-B2-2022-001)。

关键词城市竣工测绘点云场景语义分割深度学习模型适用性 urban as-built mapping point cloud scenes semantic segmentation deep learning model applicability

分类号 P23 [天文地球—摄影测量与遥感]