基于多源数据的高精地图数据生产研究  

Research on High-Definition Map Data Production Based on Multi-Source Data

作　　者：李军 郑博 LI Jun;ZHENG Bo(Beijing Meida Zhida Technology Co.,Ltd.,Beijing,100020 China;Ditu(Beijing)Technology Co.,Ltd.,Beijing,100089 China)

机构地区：[1]北京美大智达科技有限公司,北京100020 [2]滴图(北京)科技有限公司,北京100089

出　　处：《科技资讯》2025年第1期24-26,共3页Science & Technology Information

摘　　要：高精地图(又被称为高分辨率地图)是自动驾驶汽车实现路径规划、道路场景认知、决策与控制的先决条件。与传统该地图和普通的导航电子地图相比,高精地图不仅包含地形地貌要素,还包含丰富的道路要素信息及语义信息。提出了综合利用无人机正射影像和车载移动扫描点云等多源异构数据提取高精地图的方法,探讨了高精地图数据模型的空间表达、属性分层和关联规则,以及实现高精地图制图的方式,提出了可行的技术方法,为高精地图的生产提供了参考。High-definition map,also known as high-resolution map,is a prerequisite for autonomous vehicle to realize path planning,road scene cognition,decision-making and control.Compared with traditional map and ordinary navigation electronic map,high-definition map not only contains topographic and geomorphic elements,but also contains rich road element information and semantic information.This paper proposes a method to extract highdefinition map from multi-source heterogeneous data such as UAV orthophoto and vehicle mobile scanning point cloud,discusses the spatial expression,attribute stratification and association rules of high-definition map data model,and proposes a feasible technical method to provide reference value for the production of high-precision map.

关 键 词：高精地图 车载点云数据 道路专题要素 车道线提取 

分 类 号：P208[天文地球—地图制图学与地理信息工程]