Unsupervised Place Recognition With Deep Embedding Learning Over Radar Videos
Matthew Gadd, Daniele de Martini, Paul Newman . Arxiv 2021 – 1 citation
[Paper]
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.