Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph Traversal

Accurate clustering of buildings is a prerequisite for map generalization in densely populated urban data. Edge buildings at the edge of building groups, identified through human-eye recognition, may serve as boundary constraints for clustering. This paper proposes the use of seven Gestalt factors t...

Full description

Saved in:
Bibliographic Details
Main Authors: Hesheng Huang, Yijun Zhang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/14/6/222
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850167455624724480
author Hesheng Huang
Yijun Zhang
author_facet Hesheng Huang
Yijun Zhang
author_sort Hesheng Huang
collection DOAJ
description Accurate clustering of buildings is a prerequisite for map generalization in densely populated urban data. Edge buildings at the edge of building groups, identified through human-eye recognition, may serve as boundary constraints for clustering. This paper proposes the use of seven Gestalt factors to distinguish edge buildings from other buildings. Employing the DGI model to produce high-quality node embeddings, optimize the mutual information between the local node representation and the global summary vector. We then conduct training to identify edge buildings in the two test datasets using eight feature combinations. This research introduces a modified distance metric called the ‘m_dis’ feature, which is used to describe the closeness between two adjacent buildings. Finally, the clusters of edge and inner buildings are determined through a constrained graph traversal that is based on the ‘m_dis’ feature. This method is capable of effectively identifying and distinguishing densely distributed building groups in Chengdu City, China, as demonstrated by experimental results. It offers novel concepts for edge building recognition in dense urban areas, confirms the significance of the LOF factor and the ‘m_dis’ feature, and achieves superior clustering results in comparison to other methods. Additionally, this semi-supervised clustering method (DGI-EIC) has the potential to achieve an ARI index of approximately 0.5.
format Article
id doaj-art-c8b36f6b96f4412fbd4bf4dd02f35042
institution OA Journals
issn 2220-9964
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-c8b36f6b96f4412fbd4bf4dd02f350422025-08-20T02:21:12ZengMDPI AGISPRS International Journal of Geo-Information2220-99642025-06-0114622210.3390/ijgi14060222Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph TraversalHesheng Huang0Yijun Zhang1Key Laboratory of Poyang Lake Watershed Agricultural Resources and Ecology of Jiangxi Province, School of Land Resources and Environment, Jiangxi Agricultural University, Nanchang 330045, ChinaChengdu Planning Research and Application Technology Center, Chengdu 610041, ChinaAccurate clustering of buildings is a prerequisite for map generalization in densely populated urban data. Edge buildings at the edge of building groups, identified through human-eye recognition, may serve as boundary constraints for clustering. This paper proposes the use of seven Gestalt factors to distinguish edge buildings from other buildings. Employing the DGI model to produce high-quality node embeddings, optimize the mutual information between the local node representation and the global summary vector. We then conduct training to identify edge buildings in the two test datasets using eight feature combinations. This research introduces a modified distance metric called the ‘m_dis’ feature, which is used to describe the closeness between two adjacent buildings. Finally, the clusters of edge and inner buildings are determined through a constrained graph traversal that is based on the ‘m_dis’ feature. This method is capable of effectively identifying and distinguishing densely distributed building groups in Chengdu City, China, as demonstrated by experimental results. It offers novel concepts for edge building recognition in dense urban areas, confirms the significance of the LOF factor and the ‘m_dis’ feature, and achieves superior clustering results in comparison to other methods. Additionally, this semi-supervised clustering method (DGI-EIC) has the potential to achieve an ARI index of approximately 0.5.https://www.mdpi.com/2220-9964/14/6/222building groupsDGI modelclusteringedge buildingmodified-distance
spellingShingle Hesheng Huang
Yijun Zhang
Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph Traversal
ISPRS International Journal of Geo-Information
building groups
DGI model
clustering
edge building
modified-distance
title Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph Traversal
title_full Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph Traversal
title_fullStr Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph Traversal
title_full_unstemmed Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph Traversal
title_short Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph Traversal
title_sort clustering method for edge and inner buildings based on dgi model and graph traversal
topic building groups
DGI model
clustering
edge building
modified-distance
url https://www.mdpi.com/2220-9964/14/6/222
work_keys_str_mv AT heshenghuang clusteringmethodforedgeandinnerbuildingsbasedondgimodelandgraphtraversal
AT yijunzhang clusteringmethodforedgeandinnerbuildingsbasedondgimodelandgraphtraversal