An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions

This paper focuses on the automatic target recognition (ATR) method based on ship-radiated noise and proposes an underwater acoustic target recognition (UATR) method based on ResNet. In the proposed method, a multi-window spectral analysis (MWSA) method is used to solve the difficulty that the tradi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xinwei Luo, Minghong Zhang, Ting Liu, Ming Huang, Xiaogang Xu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	underwater acoustic target recognition ship-radiated noise time–frequency analysis generative adversarial network ResNet Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581
Acceso en línea:	https://doaj.org/article/22f10f4c3eb24878a4db2c67195d1da9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:22f10f4c3eb24878a4db2c67195d1da9
record_format	dspace
spelling	oai:doaj.org-article:22f10f4c3eb24878a4db2c67195d1da92021-11-25T18:04:41ZAn Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions10.3390/jmse91112462077-1312https://doaj.org/article/22f10f4c3eb24878a4db2c67195d1da92021-11-01T00:00:00Zhttps://www.mdpi.com/2077-1312/9/11/1246https://doaj.org/toc/2077-1312This paper focuses on the automatic target recognition (ATR) method based on ship-radiated noise and proposes an underwater acoustic target recognition (UATR) method based on ResNet. In the proposed method, a multi-window spectral analysis (MWSA) method is used to solve the difficulty that the traditional time–frequency (T–F) analysis method has in extracting multiple signal characteristics simultaneously. MWSA generates spectrograms with different T–F resolutions through multiple window processing to provide input for the classifier. Because of the insufficient number of ship-radiated noise samples, a conditional deep convolutional generative adversarial network (cDCGAN) model was designed for high-quality data augmentation. Experimental results on real ship-radiated noise show that the proposed UATR method has good classification performance.Xinwei LuoMinghong ZhangTing LiuMing HuangXiaogang XuMDPI AGarticleunderwater acoustic target recognitionship-radiated noisetime–frequency analysisgenerative adversarial networkResNetNaval architecture. Shipbuilding. Marine engineeringVM1-989OceanographyGC1-1581ENJournal of Marine Science and Engineering, Vol 9, Iss 1246, p 1246 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	underwater acoustic target recognition ship-radiated noise time–frequency analysis generative adversarial network ResNet Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581
spellingShingle	underwater acoustic target recognition ship-radiated noise time–frequency analysis generative adversarial network ResNet Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 Xinwei Luo Minghong Zhang Ting Liu Ming Huang Xiaogang Xu An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions
description	This paper focuses on the automatic target recognition (ATR) method based on ship-radiated noise and proposes an underwater acoustic target recognition (UATR) method based on ResNet. In the proposed method, a multi-window spectral analysis (MWSA) method is used to solve the difficulty that the traditional time–frequency (T–F) analysis method has in extracting multiple signal characteristics simultaneously. MWSA generates spectrograms with different T–F resolutions through multiple window processing to provide input for the classifier. Because of the insufficient number of ship-radiated noise samples, a conditional deep convolutional generative adversarial network (cDCGAN) model was designed for high-quality data augmentation. Experimental results on real ship-radiated noise show that the proposed UATR method has good classification performance.
format	article
author	Xinwei Luo Minghong Zhang Ting Liu Ming Huang Xiaogang Xu
author_facet	Xinwei Luo Minghong Zhang Ting Liu Ming Huang Xiaogang Xu
author_sort	Xinwei Luo
title	An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions
title_short	An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions
title_full	An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions
title_fullStr	An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions
title_full_unstemmed	An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions
title_sort	underwater acoustic target recognition method based on spectrograms with different resolutions
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/22f10f4c3eb24878a4db2c67195d1da9
work_keys_str_mv	AT xinweiluo anunderwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT minghongzhang anunderwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT tingliu anunderwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT minghuang anunderwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT xiaogangxu anunderwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT xinweiluo underwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT minghongzhang underwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT tingliu underwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT minghuang underwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions AT xiaogangxu underwateracoustictargetrecognitionmethodbasedonspectrogramswithdifferentresolutions
_version_	1718411667720634368

An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions

Ejemplares similares