Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images

Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kun Fu, Jiamei Fu, Zhirui Wang, Xian Sun
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Context-aware feature selection (CFS) convolutional neural network (CNN) oriented ship detection scattering keypoints synthetic aperture radar (SAR) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/7b60d98163dd47e4b1214bbd1ca6a2f9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7b60d98163dd47e4b1214bbd1ca6a2f9
record_format	dspace
spelling	oai:doaj.org-article:7b60d98163dd47e4b1214bbd1ca6a2f92021-11-18T00:00:32ZScattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images2151-153510.1109/JSTARS.2021.3109469https://doaj.org/article/7b60d98163dd47e4b1214bbd1ca6a2f92021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9528024/https://doaj.org/toc/2151-1535Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this article, a novel ship detection method based on the scattering-keypoint-guided network is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the imaging variability issue. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection dataset. Meanwhile, the public SAR ship detection dataset is introduced to verify the robustness and generalization ability of the detector. Experimental results on these two datasets show that the proposed method achieves the state-of-the-art performance.Kun FuJiamei FuZhirui WangXian SunIEEEarticleContext-aware feature selection (CFS)convolutional neural network (CNN)oriented ship detectionscattering keypointssynthetic aperture radar (SAR)Ocean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11162-11178 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Context-aware feature selection (CFS) convolutional neural network (CNN) oriented ship detection scattering keypoints synthetic aperture radar (SAR) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Context-aware feature selection (CFS) convolutional neural network (CNN) oriented ship detection scattering keypoints synthetic aperture radar (SAR) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Kun Fu Jiamei Fu Zhirui Wang Xian Sun Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images
description	Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this article, a novel ship detection method based on the scattering-keypoint-guided network is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the imaging variability issue. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection dataset. Meanwhile, the public SAR ship detection dataset is introduced to verify the robustness and generalization ability of the detector. Experimental results on these two datasets show that the proposed method achieves the state-of-the-art performance.
format	article
author	Kun Fu Jiamei Fu Zhirui Wang Xian Sun
author_facet	Kun Fu Jiamei Fu Zhirui Wang Xian Sun
author_sort	Kun Fu
title	Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images
title_short	Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images
title_full	Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images
title_fullStr	Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images
title_full_unstemmed	Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images
title_sort	scattering-keypoint-guided network for oriented ship detection in high-resolution and large-scale sar images
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/7b60d98163dd47e4b1214bbd1ca6a2f9
work_keys_str_mv	AT kunfu scatteringkeypointguidednetworkfororientedshipdetectioninhighresolutionandlargescalesarimages AT jiameifu scatteringkeypointguidednetworkfororientedshipdetectioninhighresolutionandlargescalesarimages AT zhiruiwang scatteringkeypointguidednetworkfororientedshipdetectioninhighresolutionandlargescalesarimages AT xiansun scatteringkeypointguidednetworkfororientedshipdetectioninhighresolutionandlargescalesarimages
_version_	1718425232050487296

Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images

Ejemplares similares