Publicación:
CROSS-SPECTRAL LOCAL DESCRIPTORS VIA QUADRUPLET NETWORK

Vista sencilla de ítem
dc.creatorCRISTHIAN ALEJANDRO AGUILERA CARRASCO
dc.date2017
dc.date.accessioned2025-01-10T14:35:37Z
dc.date.available2025-01-10T14:35:37Z
dc.date.issued2017
dc.description.abstractTHIS 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.
dc.formatapplication/pdf
dc.identifier.doi10.3390/s17040873
dc.identifier.issn1424-8220
dc.identifier.issn1424-8220
dc.identifier.urihttps://repositorio.ubiobio.cl/handle/123456789/8106
dc.languagespa
dc.publisherSENSORS
dc.relation.uri10.3390/s17040873
dc.rightsPUBLICADA
dc.titleCROSS-SPECTRAL LOCAL DESCRIPTORS VIA QUADRUPLET NETWORK
dc.title.alternativeDESCRIPTORES LOCALES ESPECTRALES CRUZADOS A TRAVÉS DE LA RED CUÁDRUPLE
dc.typeARTÍCULO
dspace.entity.typePublication
ubb.EstadoPUBLICADA
ubb.Otra ReparticionDEPARTAMENTO DE INGENIERIA ELECTRICA Y ELECTRONICA
ubb.SedeCONCEPCIÓN
Archivos
Colecciones
Artículos científicos