Maritime targets classification based on CNN using Gaofen-3 SAR images

Bibliographic Details
Title: Maritime targets classification based on CNN using Gaofen-3 SAR images
Authors: Mengyuan Ma, Haojie Zhang, Xiaokun Sun, Jie Chen
Source: The Journal of Engineering (2019)
Publisher Information: Wiley, 2019.
Publication Year: 2019
Collection: LCC:Engineering (General). Civil engineering (General)
Subject Terms: support vector machines, image classification, radar imaging, spaceborne radar, synthetic aperture radar, object detection, convolutional neural nets, gaofen-3 sar images, shipping navigation, spaceborne synthetic aperture radar technology, high-resolution sar images, maritime targets recognition, optical images, modified alexnet structure, maritime targets classification, gaofen-3 spaceborne sar images, cargo ships, container ships, convolution neural networks structure, maritime target detection, military fields, maritime targets dataset, windmills, oil tankers, iron towers, supportive vector machine, Engineering (General). Civil engineering (General), TA1-2040
More Details: The classification and detection of maritime targets are widely used in shipping navigation and military fields. With the development of spaceborne synthetic aperture radar (SAR) technology, more and more very high-resolution SAR images can be acquired for maritime targets recognition. However, due to the different imaging mechanisms between SAR images and optical images, it is difficult and laborious to interpret SAR images manually. This study uses a modified Alexnet structure to realise maritime targets classification on the Gaofen-3 spaceborne SAR images. The maritime targets dataset (MTD), including boats, cargo ships, container ships, windmills, oil tankers, and iron towers, is conducted. Moreover, the proposed convolution neural networks (CNNs) structure is trained and tested on the MTD. Experimental results show that the model can get an accuracy of 92.10% in classifying the six kinds of targets, and the performance is superior compared with other CNNs and traditional supportive vector machine algorithms.
Document Type: article
File Description: electronic resource
Language: English
ISSN: 2051-3305
Relation: https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0742; https://doaj.org/toc/2051-3305
DOI: 10.1049/joe.2019.0742
Access URL: https://doaj.org/article/32b5e61c5f8e41659a6102afa8de348c
Accession Number: edsdoj.32b5e61c5f8e41659a6102afa8de348c
Database: Directory of Open Access Journals
More Details
ISSN:20513305
DOI:10.1049/joe.2019.0742
Published in:The Journal of Engineering
Language:English