Extracting multilane roads from OpenStreetMap through graph convolutional neural network and road mesh relationship analysis

Abstract

Multilane roads in vector data are comprised of parallel line features that represent the same road. The extraction of these features is crucial for updating maps and cartographic generalization. This article addresses previous object-level extraction limitations by introducing a mesh-based method that employs a GCNN model to classify them based on geometric features and proximity relationship. A bidirectional region growing clustering method (BRGC) is designed to cluster the identified multilane road meshes belonging to the same road into groups considering their spatial relationships. The object-level multilane roads are extracted based on the clustering results. Validation using road data from OpenStreetMap in Chengdu and Zhengzhou achieved a classification f1-score >90% for multilane road mesh. Moreover, the object-level multilane detection precision and recall were 88.05% and 92.72% on the Chengdu dataset, and 86.99% and 91.37% on the Zhengzhou dataset, which demonstrates the proposed method effectively extracts multilane roads at the object level, aligning with real-world scenarios and human cognition.

Keywords

• Cartographic generalization
• road network
• multilane road extraction
• graph convolutional neural network