Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing Technology
Marine oil spills seriously impact the marine environment and transportation. When oil spill accidents occur, oil spill distribution information, in particular, the relative thickness of the oil film, is vital for emergency decision-making and cleaning. Hyperspectral remote sensing technology is an...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | ISPRS International Journal of Geo-Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2220-9964/8/4/181 |
id |
doaj-da4e969e773d42dd86d93c160ffa64b2 |
---|---|
record_format |
Article |
spelling |
doaj-da4e969e773d42dd86d93c160ffa64b22020-11-24T21:44:27ZengMDPI AGISPRS International Journal of Geo-Information2220-99642019-04-018418110.3390/ijgi8040181ijgi8040181Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing TechnologyXueyuan Zhu0Ying Li1Qiang Zhang2Bingxin Liu3Navigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaMarine oil spills seriously impact the marine environment and transportation. When oil spill accidents occur, oil spill distribution information, in particular, the relative thickness of the oil film, is vital for emergency decision-making and cleaning. Hyperspectral remote sensing technology is an effective means to extract oil spill information. In this study, the concept of deep learning is introduced to the classification of oil film thickness based on hyperspectral remote sensing technology. According to the spatial and spectral characteristics, the stacked autoencoder network model based on the support vector machine is improved, enhancing the algorithm’s classification accuracy in validating data sets. A method for classifying oil film thickness using the convolutional neural network is designed and implemented to solve the problem of space homogeneity and heterogeneity. Through numerous experiments and analyses, the potential of the two proposed deep learning methods for accurately classifying hyperspectral oil spill data is verified.https://www.mdpi.com/2220-9964/8/4/181spectral information extractiondeep learningoil film classification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xueyuan Zhu Ying Li Qiang Zhang Bingxin Liu |
spellingShingle |
Xueyuan Zhu Ying Li Qiang Zhang Bingxin Liu Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing Technology ISPRS International Journal of Geo-Information spectral information extraction deep learning oil film classification |
author_facet |
Xueyuan Zhu Ying Li Qiang Zhang Bingxin Liu |
author_sort |
Xueyuan Zhu |
title |
Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing Technology |
title_short |
Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing Technology |
title_full |
Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing Technology |
title_fullStr |
Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing Technology |
title_full_unstemmed |
Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing Technology |
title_sort |
oil film classification using deep learning-based hyperspectral remote sensing technology |
publisher |
MDPI AG |
series |
ISPRS International Journal of Geo-Information |
issn |
2220-9964 |
publishDate |
2019-04-01 |
description |
Marine oil spills seriously impact the marine environment and transportation. When oil spill accidents occur, oil spill distribution information, in particular, the relative thickness of the oil film, is vital for emergency decision-making and cleaning. Hyperspectral remote sensing technology is an effective means to extract oil spill information. In this study, the concept of deep learning is introduced to the classification of oil film thickness based on hyperspectral remote sensing technology. According to the spatial and spectral characteristics, the stacked autoencoder network model based on the support vector machine is improved, enhancing the algorithm’s classification accuracy in validating data sets. A method for classifying oil film thickness using the convolutional neural network is designed and implemented to solve the problem of space homogeneity and heterogeneity. Through numerous experiments and analyses, the potential of the two proposed deep learning methods for accurately classifying hyperspectral oil spill data is verified. |
topic |
spectral information extraction deep learning oil film classification |
url |
https://www.mdpi.com/2220-9964/8/4/181 |
work_keys_str_mv |
AT xueyuanzhu oilfilmclassificationusingdeeplearningbasedhyperspectralremotesensingtechnology AT yingli oilfilmclassificationusingdeeplearningbasedhyperspectralremotesensingtechnology AT qiangzhang oilfilmclassificationusingdeeplearningbasedhyperspectralremotesensingtechnology AT bingxinliu oilfilmclassificationusingdeeplearningbasedhyperspectralremotesensingtechnology |
_version_ |
1725910206108401664 |