Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/74529
Registro completo de metadatos
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor | Reconocimiento de Formas e Inteligencia Artificial | es_ES |
dc.contributor | Automática, Robótica y Visión Artificial | es_ES |
dc.contributor.author | Gallego, Antonio-Javier | - |
dc.contributor.author | Pertusa, Antonio | - |
dc.contributor.author | Gil, Pablo | - |
dc.contributor.other | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos | es_ES |
dc.contributor.other | Universidad de Alicante. Departamento de Física, Ingeniería de Sistemas y Teoría de la Señal | es_ES |
dc.date.accessioned | 2018-03-26T06:33:45Z | - |
dc.date.available | 2018-03-26T06:33:45Z | - |
dc.date.issued | 2018-03-24 | - |
dc.identifier.citation | Gallego A-J, Pertusa A, Gil P. Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks. Remote Sensing. 2018; 10(4):511. doi:10.3390/rs10040511 | es_ES |
dc.identifier.issn | 2072-4292 | - |
dc.identifier.uri | http://hdl.handle.net/10045/74529 | - |
dc.description.abstract | The automatic classification of ships from aerial images is a considerable challenge. Previous works have usually applied image processing and computer vision techniques to extract meaningful features from visible spectrum images in order to use them as the input for traditional supervised classifiers. We present a method for determining if an aerial image of visible spectrum contains a ship or not. The proposed architecture is based on Convolutional Neural Networks (CNN), and it combines neural codes extracted from a CNN with a k-Nearest Neighbor method so as to improve performance. The kNN results are compared to those obtained with the CNN Softmax output. Several CNN models have been configured and evaluated in order to seek the best hyperparameters, and the most suitable setting for this task was found by using transfer learning at different levels. A new dataset (named MASATI) composed of aerial imagery with more than 6000 samples has also been created to train and evaluate our architecture. The experimentation shows a success rate of over 99% for our approach, in contrast with the 79% obtained with traditional methods in classification of ship images, also outperforming other methods based on CNNs. A dataset of images (MWPU VHR-10) used in previous works was additionally used to evaluate the proposed approach. Our best setup achieves a success ratio of 86% with these data, significantly outperforming previous state-of-the-art ship classification methods. | es_ES |
dc.description.sponsorship | This work was funded by both the Spanish Government’s Ministry of Economy, Industry and Competitiveness and Babcock MCS Spain through the projects RTC-2014-1863-8 and INAER4-14Y(IDI-20141234). | es_ES |
dc.language | eng | es_ES |
dc.publisher | MDPI | es_ES |
dc.rights | © 2018 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/). | es_ES |
dc.subject | Deep learning | es_ES |
dc.subject | Aerial image classification | es_ES |
dc.subject | Ships classification | es_ES |
dc.subject | Maritime surveillance | es_ES |
dc.subject | Optical remote sensing | es_ES |
dc.subject | Convolutional neural networks | es_ES |
dc.subject.other | Lenguajes y Sistemas Informáticos | es_ES |
dc.subject.other | Ingeniería de Sistemas y Automática | es_ES |
dc.title | Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.peerreviewed | si | es_ES |
dc.identifier.doi | 10.3390/rs10040511 | - |
dc.relation.publisherversion | https://doi.org/10.3390/rs10040511 | es_ES |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es_ES |
Aparece en las colecciones: | INV - GRFIA - Artículos de Revistas INV - AUROVA - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
2018_Gallego_etal_RemoteSensing.pdf | 2,73 MB | Adobe PDF | Abrir Vista previa | |
Este ítem está licenciado bajo Licencia Creative Commons