A Large-Scale Remote Sensing Dataset and VLM-based Algorithm for Fine-Grained Road Hierarchy Classification

2026-03-22

AI Summary

This study addresses the challenge of fine-grained hierarchical classification of roads in remote sensing imagery by proposing RoadReasoner, a novel framework that uniquely integrates vision-language models with geometric descriptors to jointly perform road segmentation, topological reconstruction, and three-level hierarchical classification. Key innovations include frequency-sensitive feature enhancement, multi-scale contextual modeling, skeleton-segment-level geometric descriptors, and geometry-aware textual prompts, enabling semantically interpretable hierarchical mapping. The authors also introduce SYSU-HiRoads, the first large-scale hierarchical road dataset, featuring dense masks, vectorized centerlines, and three-tier semantic labels. Experimental results demonstrate that the proposed method achieves 72.6% overall accuracy, 64.2% F1 score, and 60.6% SegAcc on SYSU-HiRoads and CHN6-CUG, respectively, significantly outperforming existing approaches.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

In this work, we present SYSU-HiRoads, a large-scale hierarchical road dataset, and RoadReasoner, a vision-language-geometry framework for automatic multi-grade road mapping from remote sensing imagery. SYSU-HiRoads is built from GF-2 imagery covering 3631 km2 in Henan Province, China, and contains 1079 image tiles at 0.8 m spatial resolution. Each tile is annotated with dense road masks, vectorized centerlines, and three-level hierarchy labels, enabling the joint training and evaluation of segmentation, topology reconstruction, and hierarchy classification. Building on this dataset, RoadReasoner is designed to generate robust road surface masks, topology-preserving road networks, and semantically coherent hierarchy assignments. We strengthen road feature representation and network connectivity by explicitly enhancing frequency-sensitive cues and multi-scale context. Moreover, we perform hierarchy inference at the skeleton-segment level with geometric descriptors and geometry-aware textual prompts, queried by vision-language models to obtain linguistically interpretable grade decisions. Experiments on SYSU-HiRoads and the CHN6-CUG dataset show that RoadReasoner surpasses state-of-the-art road extraction baselines and produces accurate and semantically consistent road hierarchy maps with 72.6% OA, 64.2% F1 score, and 60.6% SegAcc. The dataset and code will be publicly released to support automated transport infrastructure mapping, road inventory updating, and broader infrastructure management applications.

Problem

• road hierarchy classification
• remote sensing
• fine-grained
• automated mapping
• infrastructure management

Innovation

• vision-language model
• road hierarchy classification
• remote sensing
• topology-preserving road extraction
• geometric-aware prompting