IRSAMap:Towards Large-Scale, High-Resolution Land Cover Map Vectorization

2025-08-22

AI Summary

Remote sensing land cover mapping is shifting from pixel-wise segmentation to object-level vector modeling; however, existing datasets suffer from three critical bottlenecks: sparse class annotations, limited scale, and absence of spatial structural information. To address these, we introduce RS-Vecto—the first globally representative, high-resolution, multi-feature remote sensing vector geospatial dataset—spanning 79 regions across six continents, covering over 1,000 km² and containing >1.8 million instances across 10 land-cover classes. We propose an innovative hybrid annotation pipeline integrating human verification with AI-assisted labeling to jointly enforce semantic accuracy and topological consistency. RS-Vecto supports unified benchmarking across diverse tasks, including pixel classification, building footprint extraction, road centerline detection, and panoptic segmentation. Experimental results demonstrate substantial improvements in boundary precision and structural plausibility. RS-Vecto establishes a foundational infrastructure for vectorized geospatial modeling and digital twin applications.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Representation, semantic annotation, enhancement, enrichments, access and/or integration of a variety of data on the Web
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

With the enhancement of remote sensing image resolution and the rapid advancement of deep learning, land cover mapping is transitioning from pixel-level segmentation to object-based vector modeling. This shift demands more from deep learning models, requiring precise object boundaries and topological consistency. However, existing datasets face three main challenges: limited class annotations, small data scale, and lack of spatial structural information. To overcome these issues, we introduce IRSAMap, the first global remote sensing dataset for large-scale, high-resolution, multi-feature land cover vector mapping. IRSAMap offers four key advantages: 1) a comprehensive vector annotation system with over 1.8 million instances of 10 typical objects (e.g., buildings, roads, rivers), ensuring semantic and spatial accuracy; 2) an intelligent annotation workflow combining manual and AI-based methods to improve efficiency and consistency; 3) global coverage across 79 regions in six continents, totaling over 1,000 km; and 4) multi-task adaptability for tasks like pixel-level classification, building outline extraction, road centerline extraction, and panoramic segmentation. IRSAMap provides a standardized benchmark for the shift from pixel-based to object-based approaches, advancing geographic feature automation and collaborative modeling. It is valuable for global geographic information updates and digital twin construction. The dataset is publicly available at https://github.com/ucas-dlg/IRSAMap

Problem

• Addresses limited class annotations in land cover mapping
• Overcomes small data scale for vector modeling
• Resolves lack of spatial structural information in datasets

Innovation

• Global vector dataset for land cover mapping
• AI-assisted annotation workflow for efficiency
• Multi-task adaptability across diverse geographic features