Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN

Object localization is an important application of remote sensing images and the basis of information extraction. The acquired accuracy is the key factor to improve the accuracy of object structure information inversion. The floating roof oil tank is a typical cylindrical artificial object, and its...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Han Jiang, Yueting Zhang, Jiayi Guo, Fangfang Li, Yuxin Hu, Bin Lei, Chibiao Ding
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	remote sensing image oil tank localization CNN FRST Science Q
Acceso en línea:	https://doaj.org/article/2a870c11a1a648f185839a8af027138b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2a870c11a1a648f185839a8af027138b
record_format	dspace
spelling	oai:doaj.org-article:2a870c11a1a648f185839a8af027138b2021-11-25T18:55:07ZAccurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN10.3390/rs132246462072-4292https://doaj.org/article/2a870c11a1a648f185839a8af027138b2021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4646https://doaj.org/toc/2072-4292Object localization is an important application of remote sensing images and the basis of information extraction. The acquired accuracy is the key factor to improve the accuracy of object structure information inversion. The floating roof oil tank is a typical cylindrical artificial object, and its top cover fluctuates up and down with the change in oil storage. Taking the oil tank as an example, this study explores the localization by combining the traditional feature parameter method and convolutional neural networks (CNNs). In this study, an improved fast radial symmetry transform (FRST) algorithm called fast gradient modulus radial symmetry transform (FGMRST) is proposed and an approach based on FGMRST combined with CNN is proposed. It effectively adds the priori of circle features to the calculation process. Compared with only using CNN, it achieves higher precision localization with fewer network layers. The experimental results based on SkySat data show that the method can effectively improve the calculation accuracy and efficiency of the same order of magnitude network, and by increasing the network depth, the accuracy still has a significant improvement.Han JiangYueting ZhangJiayi GuoFangfang LiYuxin HuBin LeiChibiao DingMDPI AGarticleremote sensing imageoil tanklocalizationCNNFRSTScienceQENRemote Sensing, Vol 13, Iss 4646, p 4646 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	remote sensing image oil tank localization CNN FRST Science Q
spellingShingle	remote sensing image oil tank localization CNN FRST Science Q Han Jiang Yueting Zhang Jiayi Guo Fangfang Li Yuxin Hu Bin Lei Chibiao Ding Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN
description	Object localization is an important application of remote sensing images and the basis of information extraction. The acquired accuracy is the key factor to improve the accuracy of object structure information inversion. The floating roof oil tank is a typical cylindrical artificial object, and its top cover fluctuates up and down with the change in oil storage. Taking the oil tank as an example, this study explores the localization by combining the traditional feature parameter method and convolutional neural networks (CNNs). In this study, an improved fast radial symmetry transform (FRST) algorithm called fast gradient modulus radial symmetry transform (FGMRST) is proposed and an approach based on FGMRST combined with CNN is proposed. It effectively adds the priori of circle features to the calculation process. Compared with only using CNN, it achieves higher precision localization with fewer network layers. The experimental results based on SkySat data show that the method can effectively improve the calculation accuracy and efficiency of the same order of magnitude network, and by increasing the network depth, the accuracy still has a significant improvement.
format	article
author	Han Jiang Yueting Zhang Jiayi Guo Fangfang Li Yuxin Hu Bin Lei Chibiao Ding
author_facet	Han Jiang Yueting Zhang Jiayi Guo Fangfang Li Yuxin Hu Bin Lei Chibiao Ding
author_sort	Han Jiang
title	Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN
title_short	Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN
title_full	Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN
title_fullStr	Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN
title_full_unstemmed	Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN
title_sort	accurate localization of oil tanks in remote sensing images via fgmrst-based cnn
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/2a870c11a1a648f185839a8af027138b
work_keys_str_mv	AT hanjiang accuratelocalizationofoiltanksinremotesensingimagesviafgmrstbasedcnn AT yuetingzhang accuratelocalizationofoiltanksinremotesensingimagesviafgmrstbasedcnn AT jiayiguo accuratelocalizationofoiltanksinremotesensingimagesviafgmrstbasedcnn AT fangfangli accuratelocalizationofoiltanksinremotesensingimagesviafgmrstbasedcnn AT yuxinhu accuratelocalizationofoiltanksinremotesensingimagesviafgmrstbasedcnn AT binlei accuratelocalizationofoiltanksinremotesensingimagesviafgmrstbasedcnn AT chibiaoding accuratelocalizationofoiltanksinremotesensingimagesviafgmrstbasedcnn
_version_	1718410512547446784

Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN

Ejemplares similares