测绘学报 ›› 2024, Vol. 53 ›› Issue (4): 736-749.doi: 10.11947/j.AGCS.2024.20230316

• 地图学与地理信息 • 上一篇    下一篇

基于图顶点深度聚类的建筑物合并方法

陈占龙1,2,3(), 鲁谢春1(), 徐永洋2,3   

  1. 1.中国地质大学(武汉)地质探测与评估教育部重点实验室,湖北 武汉 430074
    2.中国地质大学(武汉)计算机学院,湖北 武汉 430078
    3.国家地理信息系统工程技术研究中心,湖北 武汉 430078
  • 收稿日期:2023-08-07 修回日期:2024-02-04 发布日期:2024-05-13
  • 通讯作者: 鲁谢春 E-mail:chenzl@cug.edu.cn;xiechunlu@cug.edu.cn
  • 作者简介:陈占龙(1980—),男,博士,教授,研究方向为空间分析算法、空间推理、地理信息系统软件开发与应用。E-mail:chenzl@cug.edu.cn
  • 基金资助:
    基础加强计划重点项目;国家自然科学基金(41871305);地质探测与评估教育部重点实验室主任基金(CUG2022ZR06)

A building aggregation method based on deep clustering of graph vertices

Zhanlong CHEN1,2,3(), Xiechun LU1(), Yongyang XU2,3   

  1. 1.Key Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan 430074, China
    2.School of Computer Science, China University of Geoscience, Wuhan 430078, China
    3.National Engineering Research Center of Geographic Information System, Wuhan 430078, China
  • Received:2023-08-07 Revised:2024-02-04 Published:2024-05-13
  • Contact: Xiechun LU E-mail:chenzl@cug.edu.cn;xiechunlu@cug.edu.cn
  • About author:CHEN Zhanlong (1980—), male, PhD, professor, majors in spatial analysis algorithms, spatial reasoning, geographic information system software and application development. E-mail: chenzl@cug.edu.cn
  • Supported by:
    Key Projects of Foundation Improvement Program;The National Natural Science Foundation of China(41871305);The Opening Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education(CUG2022ZR06)

摘要:

建筑物要素合并是大比例尺地图缩编过程中实现空间结构简化的重要手段。基于综合规则的合并方法难以同时顾及要素形态、分布等诸多特征,受预设算法参数影响大,综合过程缺乏灵活性。针对这一问题,本文提出了一种基于图顶点深度聚类网络的建筑物合并模型,利用Delaunay三角网构建建筑物群组表征图模型,结合自编码器与图卷积网络学习剖分三角形的几何形态、空间分布特征,采用自监督学习方式实现三角形的聚类与分类(保留、删除),最终在不依赖样本条件下实现建筑物要素端到端智能化合并。试验表明,该方法对预设合并参数依赖低,能同时顾及建筑物要素的形态与分布特征。合并过程具有一定灵活性,合并结果能较好满足地图可视化要求。

关键词: 地图综合, 建筑物合并, 图神经网络, 自监督学习

Abstract:

Building element aggregation is pivotal for simplifying spatial structures in cartographic generalization. Conventional rule-based aggregation methods often cannot simultaneously consider the morphological and distributional characteristics of the features, because they are heavily influenced by preset algorithm parameters and lack flexibility in the cartographic generalizing process. To fill these limitations, this paper proposes a building aggregation model based on deep clustering of graph vertices. The model utilizes the Delaunay triangulation network to construct a representation graph model of building groups and combines an autoencoder and graph convolutional network to learn the subdivided triangles’ geometric shapes and spatial distribution features. A self-supervised learning approach is employed to cluster and classify the triangles into the categories of “retain” and “delete”. Consequently, it aggregates buildings intelligently in an end-to-end manner without relying on predefined samples. The experimental results demonstrate that the proposed method reduces reliance on preset aggregation parameters while simultaneously considering building elements’ morphology and distribution features. The aggregation process exhibits a certain degree of flexibility, resulting in aggregated buildings better aligning with the requirements of map visualization.

Key words: cartographic generalization, building aggregation, graph neural network, self-supervised learning

中图分类号: