We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving place recognition problem using complex radar data. We experiment on 280 km of data and show performance exceeding state-of-the-art supervised approaches, localising correctly 98.38% of the time when using just the nearest database candidate.
@article{arxiv.2106.06703,
title = {Unsupervised Place Recognition with Deep Embedding Learning over Radar Videos},
author = {Matthew Gadd and Daniele De Martini and Paul Newman},
journal= {arXiv preprint arXiv:2106.06703},
year = {2021}
}
Comments
to be presented at the Workshop on Radar Perception for All-Weather Autonomy at the IEEE International Conference on Robotics and Automation (ICRA) 2021