A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing

For high-resolution side scan sonar images, accurate and fast segmentation of sonar images is crucial for underwater target detection and recognition. However, due to the characteristics of low signal-to-noise ratio (<i>SNR</i>) and complex environmental noise of sonar, the existing meth...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xuyang Wang, Luyu Wang, Guolin Li, Xiang Xie
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	segmentation sonar images fast and accurate region growing Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/9f796be51d1741c9a9de2df8bacc38d1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9f796be51d1741c9a9de2df8bacc38d1
record_format	dspace
spelling	oai:doaj.org-article:9f796be51d1741c9a9de2df8bacc38d12021-11-11T19:00:33ZA Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing10.3390/s212169601424-8220https://doaj.org/article/9f796be51d1741c9a9de2df8bacc38d12021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/6960https://doaj.org/toc/1424-8220For high-resolution side scan sonar images, accurate and fast segmentation of sonar images is crucial for underwater target detection and recognition. However, due to the characteristics of low signal-to-noise ratio (<i>SNR</i>) and complex environmental noise of sonar, the existing methods with high accuracy and good robustness are mostly iterative methods with high complexity and poor real-time performance. For this purpose, a region growing based segmentation using the likelihood ratio testing method (RGLT) is proposed. This method obtains the seed points in the highlight and the shadow regions by likelihood ratio testing based on the statistical probability distribution and then grows them according to the similarity criterion. The growth avoids the processing of the seabed reverberation regions, which account for the largest proportion of sonar images, thus greatly reducing segmentation time and improving segmentation accuracy. In addition, a pre-processing filtering method called standard deviation filtering (<i>STDF</i>) is proposed to improve the <i>SNR</i> and remove the speckle noise. Experiments were conducted on three sonar databases, which showed that RGLT has significantly improved quantitative metrics such as accuracy, speed, and segmentation visual effects. The average accuracy and running times of the proposed segmentation method for 100 × 400 images are separately 95.90% and 0.44 s.Xuyang WangLuyu WangGuolin LiXiang XieMDPI AGarticlesegmentationsonar imagesfast and accurateregion growingChemical technologyTP1-1185ENSensors, Vol 21, Iss 6960, p 6960 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	segmentation sonar images fast and accurate region growing Chemical technology TP1-1185
spellingShingle	segmentation sonar images fast and accurate region growing Chemical technology TP1-1185 Xuyang Wang Luyu Wang Guolin Li Xiang Xie A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing
description	For high-resolution side scan sonar images, accurate and fast segmentation of sonar images is crucial for underwater target detection and recognition. However, due to the characteristics of low signal-to-noise ratio (<i>SNR</i>) and complex environmental noise of sonar, the existing methods with high accuracy and good robustness are mostly iterative methods with high complexity and poor real-time performance. For this purpose, a region growing based segmentation using the likelihood ratio testing method (RGLT) is proposed. This method obtains the seed points in the highlight and the shadow regions by likelihood ratio testing based on the statistical probability distribution and then grows them according to the similarity criterion. The growth avoids the processing of the seabed reverberation regions, which account for the largest proportion of sonar images, thus greatly reducing segmentation time and improving segmentation accuracy. In addition, a pre-processing filtering method called standard deviation filtering (<i>STDF</i>) is proposed to improve the <i>SNR</i> and remove the speckle noise. Experiments were conducted on three sonar databases, which showed that RGLT has significantly improved quantitative metrics such as accuracy, speed, and segmentation visual effects. The average accuracy and running times of the proposed segmentation method for 100 × 400 images are separately 95.90% and 0.44 s.
format	article
author	Xuyang Wang Luyu Wang Guolin Li Xiang Xie
author_facet	Xuyang Wang Luyu Wang Guolin Li Xiang Xie
author_sort	Xuyang Wang
title	A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing
title_short	A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing
title_full	A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing
title_fullStr	A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing
title_full_unstemmed	A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing
title_sort	robust and fast method for sidescan sonar image segmentation based on region growing
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9f796be51d1741c9a9de2df8bacc38d1
work_keys_str_mv	AT xuyangwang arobustandfastmethodforsidescansonarimagesegmentationbasedonregiongrowing AT luyuwang arobustandfastmethodforsidescansonarimagesegmentationbasedonregiongrowing AT guolinli arobustandfastmethodforsidescansonarimagesegmentationbasedonregiongrowing AT xiangxie arobustandfastmethodforsidescansonarimagesegmentationbasedonregiongrowing AT xuyangwang robustandfastmethodforsidescansonarimagesegmentationbasedonregiongrowing AT luyuwang robustandfastmethodforsidescansonarimagesegmentationbasedonregiongrowing AT guolinli robustandfastmethodforsidescansonarimagesegmentationbasedonregiongrowing AT xiangxie robustandfastmethodforsidescansonarimagesegmentationbasedonregiongrowing
_version_	1718431662082097152

A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing

Ejemplares similares