WAGL: Extreme Weather Adaptive Method for Robust and Generalizable UAV-based Cross-View Geo-localization

UAVM 2024

UAVs in Multimedia: Capturing the World from a New Perspective. This repository is the code for our paper WAGL: Extreme Weather Adaptive Method for Robust and Generalizable UAV-based Cross-View Geo-localization, Thank you for your kindly attention.

requirement

1. Download the University-1652-WX dataset
2. Prepare Data Folder

├── University-1652/
│   ├── readme.txt
│   ├── train/
│       ├── drone/                   /* drone-view training images 
│           ├── 0001
|           ├── 0002
|           ...
│       ├── street/                  /* street-view training images 
│       ├── satellite/               /* satellite-view training images       
│       ├── google/                  /* noisy street-view training images (collected from Google Image)
│   ├── test/
│       ├── query_drone/  
│       ├── gallery_drone/  
│       ├── query_street/  
│       ├── gallery_street/ 
│       ├── query_satellite/  
│       ├── gallery_satellite/ 
│       ├── 4K_drone/

Evaluation and Get the Results in Our Paper

You can download the trained embedding files (.mat)from the following link.

Download the trained files

Google Driver

Train and Test

We provide scripts to complete TriSSA training and testing

• Change the data_dir and test_dir paths and then run:

python train.py --gpu_ids 0 --name traied_model_name --train_all --batchsize 32  --data_dir your_data_path

python test.py --gpu_ids 0 --name traied_model_name --test_dir your_data_path  --batchsize 32 --which_epoch 120

Or simplely just try to run

python run_commond.py

The subbmit files for UAVM are in the dictionary acmm_files

python acmm2024_subbmit.py  # generate txt file for subbmit

python post_process.py  # ensemble different models 

Thanks

1. Zhedong Zheng, University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization
2. Xuanmeng Zhang, Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective

🔗 Citation

If you find our work helpful, please cite:

@inproceedings{sun2024wagl,
title={WAGL: Extreme Weather Adaptive Method for Robust and Generalizable UAV-based Cross-View Geo-localization},
author={Sun, Jian and Jiang, Xinyu and Xu, Xin and Vong, Chi-Man},
booktitle={Proceedings of the 2nd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective},
pages={14--18},
year={2024}
}

@inproceedings{zheng2020university,
title={University-1652: A multi-view multi-source benchmark for drone-based geo-localization},
author={Zheng, Zhedong and Wei, Yunchao and Yang, Yi},
booktitle={Proceedings of the 28th ACM international conference on Multimedia},
pages={1395--1403},
year={2020}
}

@article{wang2024multiple,
title={Multiple-environment Self-adaptive Network for Aerial-view Geo-localization},
author={Wang, Tingyu and Zheng, Zhedong and Sun, Yaoqi and Yan, Chenggang and Yang, Yi and Chua, Tat-Seng},
journal={Pattern Recognition},
volume={152},
pages={110363},
year={2024},
publisher={Elsevier}
}