https://github.com/mttgdd/open-radvlad

Open-RadVLAD: Shift and Rotation Invariant Radar Place Recognition with the Fourier Transform and VLAD
https://github.com/mttgdd/open-radvlad

Last synced: 26 days ago
JSON representation

Open-RadVLAD: Shift and Rotation Invariant Radar Place Recognition with the Fourier Transform and VLAD

• Host: GitHub
• URL: https://github.com/mttgdd/open-radvlad
• Owner: mttgdd
• License: mit
• Created: 2023-10-19T14:02:07.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-17T19:38:23.000Z (9 months ago)
• Last Synced: 2024-02-17T20:34:45.841Z (9 months ago)
• Language: Python
• Size: 14.6 KB
• Stars: 7
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Open-RadVLAD: Fast and Robust Radar Place Recognition

This is an open implementation and benchmark from the paper 

**Open-RadVLAD: Fast and Robust Radar Place Recognition** 


M. Gadd and P. Newman 


*IEEE Radar Conference (RadarConf), 2024* 


[https://arxiv.org/abs/2401.15380](https://arxiv.org/abs/2401.15380)

If you use this code in your research, please cite the following paper:

```bash

@inproceedings{gadd2024openradvlad,

title={{Open-RadVLAD: Fast and Robust Radar Place Recognition}},

author={Gadd, Matthew and Newman, Paul},

booktitle={IEEE Radar Conference (RadarConf)},

year={2024}

}

```

An example use is shown below, for the FFT-RadVLAD method

```bash

python -m launch.fft_vlad

```

This runs over all pairs of trajectories from [The Oxford Radar RobotCar Dataset](https://oxford-robotics-institute.github.io/radar-robotcar-dataset/).