A Method for Intelligent Road Network Selection Based on Graph Neural Network
Open Access
- 11 August 2023
- journal article
- research article
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 12 (8) , 336
Abstract
As an essential role in cartographic generalization, road network selection produces basic geographic information across map scales. However, the previous selection methods could not simultaneously consider both attribute characteristics and spatial structure. In light of this, an intelligent road network selection method based on a graph neural network (GNN) is proposed in this paper. Firstly, the selection case is designed to construct a sample library. Secondly, some neighbor sampling and aggregation rules are developed to update road features. Then, a GNN-based selection model is designed to calculate classification labels, thus completing road network selection. Finally, a few comparative analyses with different selection methods are conducted, verifying that most of the accuracy values of the GNN model are stable over 90%. The experiments indicate that this method could aggregate stroke nodes and their neighbors together to synchronously preserve semantic, geometric, and topological features of road strokes, and the selection result is closer to the reference map. Therefore, this paper could bridge the distance between deep learning and cartographic generalization, thus facilitating a more intelligent road network selection method.Keywords
Funding Information
- National Natural Science Foundation of China (42271463, 212300410014, 232102211026, SKLGIE2023-M-4-1)
- the Excellent Youth Foundation of Henan Scientific Committee (42271463, 212300410014, 232102211026, SKLGIE2023-M-4-1)
- the Key Research and Development Project of Henan Province (Science and Technology) (42271463, 212300410014, 232102211026, SKLGIE2023-M-4-1)
- State Key Laboratory of Geo-Information Engineering (42271463, 212300410014, 232102211026, SKLGIE2023-M-4-1)
This publication has 29 references indexed in Scilit:
- A comparative study of various strategies to concatenate road segments into strokes for map generalizationInternational Journal of Geographical Information Science, 2012
- A Road Network Selection Process Based on Data Enrichment and Structure DetectionTransactions in GIS, 2010
- Selective omission of road features based on mesh density for automatic map generalizationInternational Journal of Geographical Information Science, 2009
- Experiential hierarchies of streetsComputers, Environment and Urban Systems, 2008
- A Structural Approach to the Model Generalization of an Urban Street Network*GeoInformatica, 2004
- Selection of Streets from a Network Using Self‐Organizing MapsTransactions in GIS, 2004
- Topographic Map Generalization: Association of Road Elimination with Thematic AttributesThe Cartographic Journal, 2002
- A Dynantic Decision Tree Structure Supporting Urban Road Network Automated GeneralizationThe Cartographic Journal, 1996
- Integrating Thematic, Geometric, and Topological Information in the Generalization of Road NetworksCartographica, 1996
- Analysis of Urban Road Networks to Support Cartographic GeneralizationCartography and Geographic Information Science, 1995