SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size

It is expensive and time-consuming to obtain a large number of labeled synthetic aperture radar (SAR) images. In the task of small training data size, the results of target detection on SAR images using deep network approaches are usually not ideal. In this study, considering that optical remote sen...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuchen Guo, Lan Du, Guoxin Lyu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	synthetic aperture radar target detection domain adaptation generative adversarial network Science Q
Acceso en línea:	https://doaj.org/article/a2d43a04c2464102b59bff6fd4256444
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a2d43a04c2464102b59bff6fd4256444
record_format	dspace
spelling	oai:doaj.org-article:a2d43a04c2464102b59bff6fd42564442021-11-11T18:49:51ZSAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size10.3390/rs132142022072-4292https://doaj.org/article/a2d43a04c2464102b59bff6fd42564442021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4202https://doaj.org/toc/2072-4292It is expensive and time-consuming to obtain a large number of labeled synthetic aperture radar (SAR) images. In the task of small training data size, the results of target detection on SAR images using deep network approaches are usually not ideal. In this study, considering that optical remote sensing images are much easier to be labeled than SAR images, we assume to have a large number of labeled optical remote sensing images and a small number of labeled SAR images with the similar scenes, propose to transfer knowledge from optical remote sensing images to SAR images, and develop a domain adaptive Faster R-CNN for SAR target detection with small training data size. In the proposed method, in order to make full use of the label information and realize more accurate domain adaptation knowledge transfer, an instance level domain adaptation constraint is used rather than feature level domain adaptation constraint. Specifically, generative adversarial network (GAN) constraint is applied as the domain adaptation constraint in the adaptation module after the proposals of Faster R-CNN to achieve instance level domain adaptation and learn the transferable features. The experimental results on the measured SAR image dataset show that the proposed method has higher detection accuracy in the task of SAR target detection with small training data size than the traditional Faster R-CNN.Yuchen GuoLan DuGuoxin LyuMDPI AGarticlesynthetic aperture radartarget detectiondomain adaptationgenerative adversarial networkScienceQENRemote Sensing, Vol 13, Iss 4202, p 4202 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	synthetic aperture radar target detection domain adaptation generative adversarial network Science Q
spellingShingle	synthetic aperture radar target detection domain adaptation generative adversarial network Science Q Yuchen Guo Lan Du Guoxin Lyu SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size
description	It is expensive and time-consuming to obtain a large number of labeled synthetic aperture radar (SAR) images. In the task of small training data size, the results of target detection on SAR images using deep network approaches are usually not ideal. In this study, considering that optical remote sensing images are much easier to be labeled than SAR images, we assume to have a large number of labeled optical remote sensing images and a small number of labeled SAR images with the similar scenes, propose to transfer knowledge from optical remote sensing images to SAR images, and develop a domain adaptive Faster R-CNN for SAR target detection with small training data size. In the proposed method, in order to make full use of the label information and realize more accurate domain adaptation knowledge transfer, an instance level domain adaptation constraint is used rather than feature level domain adaptation constraint. Specifically, generative adversarial network (GAN) constraint is applied as the domain adaptation constraint in the adaptation module after the proposals of Faster R-CNN to achieve instance level domain adaptation and learn the transferable features. The experimental results on the measured SAR image dataset show that the proposed method has higher detection accuracy in the task of SAR target detection with small training data size than the traditional Faster R-CNN.
format	article
author	Yuchen Guo Lan Du Guoxin Lyu
author_facet	Yuchen Guo Lan Du Guoxin Lyu
author_sort	Yuchen Guo
title	SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size
title_short	SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size
title_full	SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size
title_fullStr	SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size
title_full_unstemmed	SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size
title_sort	sar target detection based on domain adaptive faster r-cnn with small training data size
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/a2d43a04c2464102b59bff6fd4256444
work_keys_str_mv	AT yuchenguo sartargetdetectionbasedondomainadaptivefasterrcnnwithsmalltrainingdatasize AT landu sartargetdetectionbasedondomainadaptivefasterrcnnwithsmalltrainingdatasize AT guoxinlyu sartargetdetectionbasedondomainadaptivefasterrcnnwithsmalltrainingdatasize
_version_	1718431716349050880

SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size

Ejemplares similares