Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/74529
Información del item - Informació de l'item - Item information
Title: Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks
Authors: Gallego, Antonio-Javier | Pertusa, Antonio | Gil, Pablo
Research Group/s: Reconocimiento de Formas e Inteligencia Artificial | Automática, Robótica y Visión Artificial
Center, Department or Service: Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos | Universidad de Alicante. Departamento de Física, Ingeniería de Sistemas y Teoría de la Señal
Keywords: Deep learning | Aerial image classification | Ships classification | Maritime surveillance | Optical remote sensing | Convolutional neural networks
Knowledge Area: Lenguajes y Sistemas Informáticos | Ingeniería de Sistemas y Automática
Issue Date: 24-Mar-2018
Publisher: MDPI
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
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.
Sponsor: 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).
URI: http://hdl.handle.net/10045/74529
ISSN: 2072-4292
DOI: 10.3390/rs10040511
Language: eng
Type: info:eu-repo/semantics/article
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/).
Peer Review: si
Publisher version: https://doi.org/10.3390/rs10040511
Appears in Collections:INV - GRFIA - Artículos de Revistas
INV - AUROVA - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2018_Gallego_etal_RemoteSensing.pdf2,73 MBAdobe PDFOpen Preview


This item is licensed under a Creative Commons License Creative Commons