GNSS拒止环境下无人机视觉地理定位汇总

开源工作：

1. Leveraging Map Retrieval and Alignment for Robust UAV Visual Geo-Localization

paper：Leveraging Map Retrieval and Alignment for Robust UAV Visual Geo-Localization | IEEE Journals & Magazine | IEEE Xplore

code: GitHub - hmf21/UAVLocalization: Implementation of visual based UAV geo-localization using satellite imagery

2. A Visual Navigation Algorithm for UAV Based on Visual-Geography Optimization

code:GitHub - XuWeibo-code/UAV_Visual_Navigation: This is part of the code for visual navigation algorithms, which fuses VO with localization method based on heterogeneous image matching.

paper:A Visual Navigation Algorithm for UAV Based on Visual-Geography Optimization

与ORB-SLAM3结合，代码似乎没有完全开源

3. Jointly Optimized Global-Local Visual Localization of UAVs

code: GitHub - lihaoling/GLVL: This is a PyTorch implementation of the paper "Jointly Optimized Global-Local Visual Localization of UAVs".

paper: https://arxiv.org/pdf/2310.08082

4. Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments

code:GitHub - Dmmm1997/DenseUAV: 「TIP」Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments

paper:Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments | IEEE Journals & Magazine | IEEE Xplore

5. Drone Referring Localization: An Efficient Heterogeneous Spatial Feature Interaction Method For UAV Self-Localization

code:GitHub - Dmmm1997/DRL: official repo of paper: Drone Referring Localization: An Efficient Heterogeneous Spatial Feature Interaction Method For UAV Self-Localization

paper:https://arxiv.org/pdf/2208.06561

6. Visual place recognition for aerial imagery: A survey

code: GitHub - prime-slam/aero-vloc: Framework for aerial imagery localization using different VPR systems

paper:https://arxiv.org/pdf/2406.00885

7. LoD-Loc_Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment（NeurIPS）

code:GitHub - VictorZoo/LoD-Loc: This repository is an implementation of the paper "LoD-Loc: Visual Localization using LoD 3D Map with Neural Wireframe Alignment".

paper:[2410.12269] LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment

8.The First Large-scale Benchmark for UAV Visual Localization under Low-altitude Multi-view Observation Condition

GitHub - UAV-AVL/Benchmark: UAV Visual Localization

论文：

数据集：

1.ALTO:貌似是一个比赛的数据集，看了一下测试集，基本全是绿色区域（村庄、草地、山）挑战性应该挺大
https://github.com/MetaSLAM/ALTO.git