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

• URL: http://arxiv.org/abs/2603.21222v1
• Date: Sun, 22 Mar 2026 13:26:28 GMT
• Title: A Large-Scale Remote Sensing Dataset and VLM-based Algorithm for Fine-Grained Road Hierarchy Classification
• Abstract summary: We present SYSU-HiRoads, a large-scale hierarchical road dataset, and RoadReasoner, a vision-language-geometry framework.<n> 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.<n>RoadReasoner is designed to generate robust road surface masks, topology-preserving road networks, and semantically coherent hierarchy assignments.
• Score: 7.761005954075427
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction [54.19939140744149]
  RoadGIE establishes a novel interactive paradigm for road extraction in remote sensing.<n>WorldRoadSeg-360K is the largest and most diverse road segmentation dataset to date.<n>RoadGIE achieves state-of-the-art performance in both segmentation accuracy and topological consistency.
  arXiv  Detail & Related papers  (2026-05-26T11:20:27Z)
• Beyond Endpoints: Path-Centric Reasoning for Vectorized Off-Road Network Extraction [9.833728353188132]
  We release WildRoad, a global off-road road network dataset constructed efficiently with a dedicated interactive annotation tool.<n>We introduce MaGRoad, a path-centric framework that aggregates multi-scale visual evidence along candidate paths to infer connectivity robustly.<n>MaGRoad achieves state-of-the-art performance on our challenging WildRoad benchmark while generalizing well to urban datasets.
  arXiv  Detail & Related papers  (2025-12-11T08:29:27Z)
• Neural Semantic Map-Learning for Autonomous Vehicles [85.8425492858912]
  We present a mapping system that fuses local submaps gathered from a fleet of vehicles at a central instance to produce a coherent map of the road environment. Our method jointly aligns and merges the noisy and incomplete local submaps using a scene-specific Neural Signed Distance Field. We leverage memory-efficient sparse feature-grids to scale to large areas and introduce a confidence score to model uncertainty in scene reconstruction.
  arXiv  Detail & Related papers  (2024-10-10T10:10:03Z)
• Brightearth roads: Towards fully automatic road network extraction from satellite imagery [2.446672595462589]
  We propose a fully automated pipeline for extracting road networks from satellite imagery. Our approach directly generates road line-strings that are seamlessly connected and precisely positioned.
  arXiv  Detail & Related papers  (2024-06-21T07:55:15Z)
• Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting [70.66710698485745]
  We propose an Adaptive Hierarchical SpatioTemporal Network (AHSTN) to promote traffic forecasting. AHSTN exploits the spatial hierarchy and modeling multi-scale spatial correlations. Experiments on two real-world datasets show that AHSTN achieves better performance over several strong baselines.
  arXiv  Detail & Related papers  (2023-06-15T14:50:27Z)
• MGL2Rank: Learning to Rank the Importance of Nodes in Road Networks Based on Multi-Graph Fusion [7.835154677901744]
  Existing methods for evaluating the importance of nodes in traffic networks only consider topological information and traffic volumes. We propose a graph learning-based framework (MGL2Rank) that integrates the rich characteristics of road networks to rank the importance of nodes.
  arXiv  Detail & Related papers  (2023-05-20T13:46:44Z)
• Semi-supervised Road Updating Network (SRUNet): A Deep Learning Method for Road Updating from Remote Sensing Imagery and Historical Vector Maps [3.350048575501172]
  We propose a road detection method based on semi-supervised learning (SRUNet) specifically for road-updating applications. The proposed SRUNet can provide stable, up-to-date, and reliable prediction results for a wide range of road renewal tasks.
  arXiv  Detail & Related papers  (2023-04-28T16:51:35Z)
• SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving [64.10636296274168]
  Road extraction is an essential step in building autonomous navigation systems. Using just convolution neural networks (ConvNets) for this problem is not effective as it is inefficient at capturing distant dependencies between road segments in the image. We propose a Spatial and Interaction Space Graph Reasoning (SPIN) module which when plugged into a ConvNet performs reasoning over graphs constructed on spatial and interaction spaces projected from the feature maps.
  arXiv  Detail & Related papers  (2021-09-16T03:52:17Z)
• GANav: Group-wise Attention Network for Classifying Navigable Regions in Unstructured Outdoor Environments [54.21959527308051]
  We present a new learning-based method for identifying safe and navigable regions in off-road terrains and unstructured environments from RGB images. Our approach consists of classifying groups of terrain classes based on their navigability levels using coarse-grained semantic segmentation. We show through extensive evaluations on the RUGD and RELLIS-3D datasets that our learning algorithm improves the accuracy of visual perception in off-road terrains for navigation.
  arXiv  Detail & Related papers  (2021-03-07T02:16:24Z)
• Convolutional Recurrent Network for Road Boundary Extraction [99.55522995570063]
  We tackle the problem of drivable road boundary extraction from LiDAR and camera imagery. We design a structured model where a fully convolutional network obtains deep features encoding the location and direction of road boundaries. We showcase the effectiveness of our method on a large North American city where we obtain perfect topology of road boundaries 99.3% of the time.
  arXiv  Detail & Related papers  (2020-12-21T18:59:12Z)
• PP-LinkNet: Improving Semantic Segmentation of High Resolution Satellite Imagery with Multi-stage Training [4.694536172504848]
  Road network and building footprint extraction is essential for many applications such as updating maps, traffic regulations, city planning, ride-hailing, disaster response textitetc.
  arXiv  Detail & Related papers  (2020-10-14T10:23:48Z)
• Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene [76.4183572058063]
  We present a richly-annotated 3D point cloud dataset for multiple outdoor scene understanding tasks. The dataset has been point-wisely annotated with both hierarchical and instance-based labels. We formulate a hierarchical learning problem for 3D point cloud segmentation and propose a measurement evaluating consistency across various hierarchies.
  arXiv  Detail & Related papers  (2020-08-11T19:10:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.