Hierarchical Image Matching for UAV Absolute Visual Localization via Semantic and Structural Constraints

2025-06-11

AI Summary

Absolute visual localization of UAVs in GNSS-denied environments remains challenging due to poor matching robustness caused by cross-source (satellite-to-aerial) and cross-temporal image discrepancies. Method: We propose a hierarchical cross-source image matching framework: first, semantic-guided coarse matching at the region level, leveraging vision foundation model features and geometric structure constraints; second, lightweight fine-grained feature alignment for pixel-level accurate matching—both stages operate without prior relative pose estimation. Contribution/Results: We introduce the first “semantic-aware + structure-constrained” dual-granularity matching paradigm, enabling an end-to-end purely visual absolute localization pipeline. Evaluated on multiple public benchmarks and our newly constructed CS-UAV dataset, our method achieves significant improvements in localization accuracy and robustness—especially under challenging conditions including illumination variation, large viewpoint shifts, and seasonal changes.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Localization, Mapping, and Navigation
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Absolute localization, aiming to determine an agent's location with respect to a global reference, is crucial for unmanned aerial vehicles (UAVs) in various applications, but it becomes challenging when global navigation satellite system (GNSS) signals are unavailable. Vision-based absolute localization methods, which locate the current view of the UAV in a reference satellite map to estimate its position, have become popular in GNSS-denied scenarios. However, existing methods mostly rely on traditional and low-level image matching, suffering from difficulties due to significant differences introduced by cross-source discrepancies and temporal variations. To overcome these limitations, in this paper, we introduce a hierarchical cross-source image matching method designed for UAV absolute localization, which integrates a semantic-aware and structure-constrained coarse matching module with a lightweight fine-grained matching module. Specifically, in the coarse matching module, semantic features derived from a vision foundation model first establish region-level correspondences under semantic and structural constraints. Then, the fine-grained matching module is applied to extract fine features and establish pixel-level correspondences. Building upon this, a UAV absolute visual localization pipeline is constructed without any reliance on relative localization techniques, mainly by employing an image retrieval module before the proposed hierarchical image matching modules. Experimental evaluations on public benchmark datasets and a newly introduced CS-UAV dataset demonstrate superior accuracy and robustness of the proposed method under various challenging conditions, confirming its effectiveness.

Problem

• Absolute UAV localization without GNSS signals
• Cross-source image matching challenges in localization
• Semantic and structural constraints for accurate matching

Innovation

• Hierarchical cross-source image matching for UAV localization
• Semantic-aware coarse matching with structural constraints
• Lightweight fine-grained matching for pixel-level accuracy