Unsupervised place recognition with deep embedding learning over radar videos
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 ti...
Hlavní autoři: | Gadd, M, De Martini, D, Newman, P |
---|---|
Médium: | Conference item |
Jazyk: | English |
Vydáno: |
IEEE
2021
|
Podobné jednotky
-
Contrastive learning for unsupervised radar place recognition
Autor: Gadd, M, a další
Vydáno: (2022) -
Look around you: sequence-based radar place recognition with learned rotational invariance
Autor: Gadd, M, a další
Vydáno: (2020) -
Open-RadVLAD: fast and robust radar place recognition
Autor: Gadd, M, a další
Vydáno: (2024) -
Off the radar: uncertainty-aware radar place recognition with introspective querying and map maintenance
Autor: Yuan, J, a další
Vydáno: (2023) -
Kidnapped radar: topological radar localisation using rotationally-invariant metric learning
Autor: Gadd, M, a další
Vydáno: (2020)