Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery

Oil spill (OS), as one of the main pollutions in the ocean, is a serious threat to the marine environment. Thus, timely and accurate OS detection (OSD) is necessary for ocean management. In this regard, remote sensing (RS) plays a key role due to multiple advantages over large and remote ocean envir...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Seyd Teymoor Seydi, Mahdi Hasanlou, Meisam Amani, Weimin Huang
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/3907b0bbefc643cf8a7a8a855acf33f2
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:3907b0bbefc643cf8a7a8a855acf33f2
record_format dspace
spelling oai:doaj.org-article:3907b0bbefc643cf8a7a8a855acf33f22021-11-18T00:00:19ZOil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery2151-153510.1109/JSTARS.2021.3123163https://doaj.org/article/3907b0bbefc643cf8a7a8a855acf33f22021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9591296/https://doaj.org/toc/2151-1535Oil spill (OS), as one of the main pollutions in the ocean, is a serious threat to the marine environment. Thus, timely and accurate OS detection (OSD) is necessary for ocean management. In this regard, remote sensing (RS) plays a key role due to multiple advantages over large and remote ocean environments. In this study, a new OSD framework based on a deep learning algorithm was developed for optical RS imagery. The proposed method was based on a multiscale multidimensional residual kernel convolution neural network. The proposed method investigated the deep features by the two-dimensional multiscale residual blocks and, then, utilized them at one-dimensional multiscale residual blocks. In this study, Landsat-5 satellite imagery acquired over the Gulf of Mexico was applied to evaluate the performance of the proposed method. The overall accuracy of the proposed method was more than 95%, and the miss detection and false alarm rates were less than 5%, indicating its high potential for OSD. Moreover, it was observed that the proposed method had better performance compared to other OSD algorithms that were investigated in this study.Seyd Teymoor SeydiMahdi HasanlouMeisam AmaniWeimin HuangIEEEarticleConvolution neural network (CNN)deep learningLandsat-5multiscale kernel convolutionocean oil spill detectionremote sensing (RS)Ocean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 10941-10952 (2021)
institution DOAJ
collection DOAJ
language EN
topic Convolution neural network (CNN)
deep learning
Landsat-5
multiscale kernel convolution
ocean oil spill detection
remote sensing (RS)
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
spellingShingle Convolution neural network (CNN)
deep learning
Landsat-5
multiscale kernel convolution
ocean oil spill detection
remote sensing (RS)
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
Seyd Teymoor Seydi
Mahdi Hasanlou
Meisam Amani
Weimin Huang
Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery
description Oil spill (OS), as one of the main pollutions in the ocean, is a serious threat to the marine environment. Thus, timely and accurate OS detection (OSD) is necessary for ocean management. In this regard, remote sensing (RS) plays a key role due to multiple advantages over large and remote ocean environments. In this study, a new OSD framework based on a deep learning algorithm was developed for optical RS imagery. The proposed method was based on a multiscale multidimensional residual kernel convolution neural network. The proposed method investigated the deep features by the two-dimensional multiscale residual blocks and, then, utilized them at one-dimensional multiscale residual blocks. In this study, Landsat-5 satellite imagery acquired over the Gulf of Mexico was applied to evaluate the performance of the proposed method. The overall accuracy of the proposed method was more than 95%, and the miss detection and false alarm rates were less than 5%, indicating its high potential for OSD. Moreover, it was observed that the proposed method had better performance compared to other OSD algorithms that were investigated in this study.
format article
author Seyd Teymoor Seydi
Mahdi Hasanlou
Meisam Amani
Weimin Huang
author_facet Seyd Teymoor Seydi
Mahdi Hasanlou
Meisam Amani
Weimin Huang
author_sort Seyd Teymoor Seydi
title Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery
title_short Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery
title_full Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery
title_fullStr Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery
title_full_unstemmed Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery
title_sort oil spill detection based on multiscale multidimensional residual cnn for optical remote sensing imagery
publisher IEEE
publishDate 2021
url https://doaj.org/article/3907b0bbefc643cf8a7a8a855acf33f2
work_keys_str_mv AT seydteymoorseydi oilspilldetectionbasedonmultiscalemultidimensionalresidualcnnforopticalremotesensingimagery
AT mahdihasanlou oilspilldetectionbasedonmultiscalemultidimensionalresidualcnnforopticalremotesensingimagery
AT meisamamani oilspilldetectionbasedonmultiscalemultidimensionalresidualcnnforopticalremotesensingimagery
AT weiminhuang oilspilldetectionbasedonmultiscalemultidimensionalresidualcnnforopticalremotesensingimagery
_version_ 1718425217862205440