Cargando…

A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background

Convolution neural network (CNN)-based detectors have shown great performance on ship detections of synthetic aperture radar (SAR) images. However, the performance of current models has not been satisfactory enough for detecting multiscale ships and small-size ones in front of complex backgrounds. T...

Descripción completa

Detalles Bibliográficos
Autores principales: Dai, Wenxin, Mao, Yuqing, Yuan, Rongao, Liu, Yijing, Pu, Xuemei, Li, Chuan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7273208/
https://www.ncbi.nlm.nih.gov/pubmed/32365747
http://dx.doi.org/10.3390/s20092547
_version_ 1783542354113724416
author Dai, Wenxin
Mao, Yuqing
Yuan, Rongao
Liu, Yijing
Pu, Xuemei
Li, Chuan
author_facet Dai, Wenxin
Mao, Yuqing
Yuan, Rongao
Liu, Yijing
Pu, Xuemei
Li, Chuan
author_sort Dai, Wenxin
collection PubMed
description Convolution neural network (CNN)-based detectors have shown great performance on ship detections of synthetic aperture radar (SAR) images. However, the performance of current models has not been satisfactory enough for detecting multiscale ships and small-size ones in front of complex backgrounds. To address the problem, we propose a novel SAR ship detector based on CNN, which consist of three subnetworks: the Fusion Feature Extractor Network (FFEN), Region Proposal Network (RPN), and Refine Detection Network (RDN). Instead of using a single feature map, we fuse feature maps in bottom–up and top–down ways and generate proposals from each fused feature map in FFEN. Furthermore, we further merge features generated by the region-of-interest (RoI) pooling layer in RDN. Based on the feature representation strategy, the CNN framework constructed can significantly enhance the location and semantics information for the multiscale ships, in particular for the small ships. On the other hand, the residual block is introduced to increase the network depth, through which the detection precision could be further improved. The public SAR ship dataset (SSDD) and China Gaofen-3 satellite SAR image are used to validate the proposed method. Our method shows excellent performance for detecting the multiscale and small-size ships with respect to some competitive models and exhibits high potential in practical application.
format Online
Article
Text
id pubmed-7273208
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-72732082020-06-19 A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background Dai, Wenxin Mao, Yuqing Yuan, Rongao Liu, Yijing Pu, Xuemei Li, Chuan Sensors (Basel) Article Convolution neural network (CNN)-based detectors have shown great performance on ship detections of synthetic aperture radar (SAR) images. However, the performance of current models has not been satisfactory enough for detecting multiscale ships and small-size ones in front of complex backgrounds. To address the problem, we propose a novel SAR ship detector based on CNN, which consist of three subnetworks: the Fusion Feature Extractor Network (FFEN), Region Proposal Network (RPN), and Refine Detection Network (RDN). Instead of using a single feature map, we fuse feature maps in bottom–up and top–down ways and generate proposals from each fused feature map in FFEN. Furthermore, we further merge features generated by the region-of-interest (RoI) pooling layer in RDN. Based on the feature representation strategy, the CNN framework constructed can significantly enhance the location and semantics information for the multiscale ships, in particular for the small ships. On the other hand, the residual block is introduced to increase the network depth, through which the detection precision could be further improved. The public SAR ship dataset (SSDD) and China Gaofen-3 satellite SAR image are used to validate the proposed method. Our method shows excellent performance for detecting the multiscale and small-size ships with respect to some competitive models and exhibits high potential in practical application. MDPI 2020-04-30 /pmc/articles/PMC7273208/ /pubmed/32365747 http://dx.doi.org/10.3390/s20092547 Text en © 2020 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
Dai, Wenxin
Mao, Yuqing
Yuan, Rongao
Liu, Yijing
Pu, Xuemei
Li, Chuan
A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background
title A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background
title_full A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background
title_fullStr A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background
title_full_unstemmed A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background
title_short A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background
title_sort novel detector based on convolution neural networks for multiscale sar ship detection in complex background
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7273208/
https://www.ncbi.nlm.nih.gov/pubmed/32365747
http://dx.doi.org/10.3390/s20092547
work_keys_str_mv AT daiwenxin anoveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT maoyuqing anoveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT yuanrongao anoveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT liuyijing anoveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT puxuemei anoveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT lichuan anoveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT daiwenxin noveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT maoyuqing noveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT yuanrongao noveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT liuyijing noveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT puxuemei noveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground
AT lichuan noveldetectorbasedonconvolutionneuralnetworksformultiscalesarshipdetectionincomplexbackground