Image hashing for loop closing in underwater visual SLAM

This article presents an experimental assessment of a hash-based loop closure detection methodology specially addressed to Multi-robot underwater visual Simultaneous Localization and Mapping (SLAM). This methodology uses two diferent top quality image global descriptors, one learned (NetVLAD) and on...

ver descrição completa

Detalhes bibliográficos
Autores: Bonin Font, Francisco, Burguera Burguera, Antoni, Oliver Codina, Gabriel Antonio
Tipo de documento: artigo
Data de publicação:2021
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/360402
Acesso em linha:https://hdl.handle.net/2117/360402
Access Level:Acceso aberto
Palavra-chave:Robotics
Visual loop closing detection
Underwater robotics
SLAM
Convolution neural networks
Robòtica
Àrees temàtiques de la UPC::Informàtica::Robòtica
Descrição
Resumo:This article presents an experimental assessment of a hash-based loop closure detection methodology specially addressed to Multi-robot underwater visual Simultaneous Localization and Mapping (SLAM). This methodology uses two diferent top quality image global descriptors, one learned (NetVLAD) and one handcrafted (HALOC). Complete tests were done to compare the performance of both hashing techniques applied in an extensive set of real underwater imagery.