Cargando…

Cross-Spectral Local Descriptors via Quadruplet Network

This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input...

Descripción completa

Detalles Bibliográficos
Autores principales: Aguilera, Cristhian A., Sappa, Angel D., Aguilera, Cristhian, Toledo, Ricardo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5424750/
https://www.ncbi.nlm.nih.gov/pubmed/28420142
http://dx.doi.org/10.3390/s17040873
_version_ 1783235184758358016
author Aguilera, Cristhian A.
Sappa, Angel D.
Aguilera, Cristhian
Toledo, Ricardo
author_facet Aguilera, Cristhian A.
Sappa, Angel D.
Aguilera, Cristhian
Toledo, Ricardo
author_sort Aguilera, Cristhian A.
collection PubMed
description This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.
format Online
Article
Text
id pubmed-5424750
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-54247502017-05-12 Cross-Spectral Local Descriptors via Quadruplet Network Aguilera, Cristhian A. Sappa, Angel D. Aguilera, Cristhian Toledo, Ricardo Sensors (Basel) Article This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data. MDPI 2017-04-15 /pmc/articles/PMC5424750/ /pubmed/28420142 http://dx.doi.org/10.3390/s17040873 Text en © 2017 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Aguilera, Cristhian A.
Sappa, Angel D.
Aguilera, Cristhian
Toledo, Ricardo
Cross-Spectral Local Descriptors via Quadruplet Network
title Cross-Spectral Local Descriptors via Quadruplet Network
title_full Cross-Spectral Local Descriptors via Quadruplet Network
title_fullStr Cross-Spectral Local Descriptors via Quadruplet Network
title_full_unstemmed Cross-Spectral Local Descriptors via Quadruplet Network
title_short Cross-Spectral Local Descriptors via Quadruplet Network
title_sort cross-spectral local descriptors via quadruplet network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5424750/
https://www.ncbi.nlm.nih.gov/pubmed/28420142
http://dx.doi.org/10.3390/s17040873
work_keys_str_mv AT aguileracristhiana crossspectrallocaldescriptorsviaquadrupletnetwork
AT sappaangeld crossspectrallocaldescriptorsviaquadrupletnetwork
AT aguileracristhian crossspectrallocaldescriptorsviaquadrupletnetwork
AT toledoricardo crossspectrallocaldescriptorsviaquadrupletnetwork