建筑物合并是地图综合中的复杂决策问题,基于规则的合并方法试图通过一系列认知参数和约束条件来解决“哪些合并”“如何合并”等问题,但是由于区域环境的复杂性、算子选择的多样性以及参量调整的多变性,基于规则的合并结果总是不尽人意。在人工智能技术支持下,将深度学习方法引入,则是从数据驱动视角通过样本训练以期突破规则方法的局限。本研究即是基于图卷积神经网络构建的一种建筑物分组及合并的方法。利用约束Delaunay三角网和最小生成树构建图结构,从图结构中提取建筑物节点特征和距离特征。通过图卷积层和点积运算得到的节点余弦相似度与距离特征拼接作为连接边特征,最后通过全连接层得到二分类结果。通过对比实验分析,本方法的ARI指数高于现有的方法 (从0.674到0.800)。
Yan Xiongfeng,Ai Tinghua,Yang Min,Tong Xiaohua,Liu Qian.A graph deep learning approach for urban building grouping[J].Geocarto International,2022.
Zhao Rong,Ai Tinghua,Yu Wenhao,He Yakun,Shen Yilang.Recognition of building group patterns using graph convolutional network[J].Cartography and Geographic Information Science,2020.
Yu Feng,Frank Thiemann,Monika Sester.Learning Cartographic Building Generalization with Deep Convolutional Neural Networks[J].ISPRS International Journal of Geo-Information,2019.
Xianjin He,Xinchang Zhang,Jie Yang.Progressive Amalgamation of Building Clusters for Map Generalization Based on Scaling Subgroups[J].ISPRS International Journal of Geo-Information,2018.
Thomas N. Kipf,Max Welling.Semi-Supervised Classification with Graph Convolutional Networks.[J].CoRR,2016.
Boyan Cheng,Qiang Liu,Xiaowen Li.Local Perception-Based Intelligent Building Outline Aggregation Approach with Back Propagation Neural Network[J].Neural Processing Letters,2015.
Haowen Yan,Robert Weibel,Bisheng Yang.A Multi-parameter Approach to Automated Building Grouping and Generalization[J].GeoInformatica,2008.
Manuel Cámara,Francisco López.Mathematical Morphology Applied to Raster Generalization of Urban City Block Maps[J].Cartographica: The International Journal for Geographic Information and Geovisualization,2000.
BO SU,ZHILIN LI,GRAHAM LODWICK,JEAN-CLAUDE MULLER.Algebraic models for the aggregation of area features based upon morphological operators[J].International Journal of Geographical Information Science,1997(3).
JonathanRichardShewchuk.Triangle: Engineering a 2D quality mesh generator and Delaunay triangulator[J].Lecture Notes in Computer Science,1996(1).
J.MarkWare,ChristopherB.Jones,GeraintLl.Bundy.A triangulated spatial model for cartographic generalisation of areal objects[J].Lecture Notes in Computer Science,1995(1).
艾廷华.深度学习赋能地图制图的若干思考[J].测绘学报,2021(09).
钱海忠,武芳,谭笑,邓红艳.基于ABTM的城市建筑物合并算法[J].中国图象图形学报,2005(10).
0
浏览量
295
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621