Cargando…

Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

Place recognition is critical for both offline mapping and online localization. However, current single-sensor based place recognition still remains challenging in adverse conditions. In this paper, a heterogeneous measurement based framework is proposed for long-term place recognition, which retrie...

Descripción completa

Detalles Bibliográficos
Autores principales: Yin, Huan, Xu, Xuecheng, Wang, Yue, Xiong, Rong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8166203/
https://www.ncbi.nlm.nih.gov/pubmed/34079825
http://dx.doi.org/10.3389/frobt.2021.661199
_version_ 1783701457798692864
author Yin, Huan
Xu, Xuecheng
Wang, Yue
Xiong, Rong
author_facet Yin, Huan
Xu, Xuecheng
Wang, Yue
Xiong, Rong
author_sort Yin, Huan
collection PubMed
description Place recognition is critical for both offline mapping and online localization. However, current single-sensor based place recognition still remains challenging in adverse conditions. In this paper, a heterogeneous measurement based framework is proposed for long-term place recognition, which retrieves the query radar scans from the existing lidar (Light Detection and Ranging) maps. To achieve this, a deep neural network is built with joint training in the learning stage, and then in the testing stage, shared embeddings of radar and lidar are extracted for heterogeneous place recognition. To validate the effectiveness of the proposed method, we conducted tests and generalization experiments on the multi-session public datasets and compared them to other competitive methods. The experimental results indicate that our model is able to perform multiple place recognitions: lidar-to-lidar (L2L), radar-to-radar (R2R), and radar-to-lidar (R2L), while the learned model is trained only once. We also release the source code publicly: https://github.com/ZJUYH/radar-to-lidar-place-recognition.
format Online
Article
Text
id pubmed-8166203
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-81662032021-06-01 Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning Yin, Huan Xu, Xuecheng Wang, Yue Xiong, Rong Front Robot AI Robotics and AI Place recognition is critical for both offline mapping and online localization. However, current single-sensor based place recognition still remains challenging in adverse conditions. In this paper, a heterogeneous measurement based framework is proposed for long-term place recognition, which retrieves the query radar scans from the existing lidar (Light Detection and Ranging) maps. To achieve this, a deep neural network is built with joint training in the learning stage, and then in the testing stage, shared embeddings of radar and lidar are extracted for heterogeneous place recognition. To validate the effectiveness of the proposed method, we conducted tests and generalization experiments on the multi-session public datasets and compared them to other competitive methods. The experimental results indicate that our model is able to perform multiple place recognitions: lidar-to-lidar (L2L), radar-to-radar (R2R), and radar-to-lidar (R2L), while the learned model is trained only once. We also release the source code publicly: https://github.com/ZJUYH/radar-to-lidar-place-recognition. Frontiers Media S.A. 2021-05-17 /pmc/articles/PMC8166203/ /pubmed/34079825 http://dx.doi.org/10.3389/frobt.2021.661199 Text en Copyright © 2021 Yin, Xu, Wang and Xiong. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Robotics and AI
Yin, Huan
Xu, Xuecheng
Wang, Yue
Xiong, Rong
Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
title Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
title_full Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
title_fullStr Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
title_full_unstemmed Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
title_short Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
title_sort radar-to-lidar: heterogeneous place recognition via joint learning
topic Robotics and AI
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8166203/
https://www.ncbi.nlm.nih.gov/pubmed/34079825
http://dx.doi.org/10.3389/frobt.2021.661199
work_keys_str_mv AT yinhuan radartolidarheterogeneousplacerecognitionviajointlearning
AT xuxuecheng radartolidarheterogeneousplacerecognitionviajointlearning
AT wangyue radartolidarheterogeneousplacerecognitionviajointlearning
AT xiongrong radartolidarheterogeneousplacerecognitionviajointlearning