A Spectral-Spatial Features Integrated Network for Hyperspectral Detection of Marine Oil Spill
Marine oil spills are one of the most serious problems of marine environmental pollution. Hyperspectral remote sensing has been proven to be an effective tool for monitoring marine oil spills. To make full use of spectral and spatial features, this study proposes a spectral-spatial features integrat...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/8/1568 |
id |
doaj-5cfe4f21d40e4a6891522a1d631bed13 |
---|---|
record_format |
Article |
spelling |
doaj-5cfe4f21d40e4a6891522a1d631bed132021-04-18T23:00:17ZengMDPI AGRemote Sensing2072-42922021-04-01131568156810.3390/rs13081568A Spectral-Spatial Features Integrated Network for Hyperspectral Detection of Marine Oil SpillBin Wang0Qifan Shao1Dongmei Song2Zhongwei Li3Yunhe Tang4Changlong Yang5Mingyue Wang6College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaMarine oil spills are one of the most serious problems of marine environmental pollution. Hyperspectral remote sensing has been proven to be an effective tool for monitoring marine oil spills. To make full use of spectral and spatial features, this study proposes a spectral-spatial features integrated network (SSFIN) and applies it for hyperspectral detection of a marine oil spill. Specifically, 1-D and 2-D convolutional neural network (CNN) models have been employed for the extraction of the spectral and spatial features, respectively. During the stage of spatial feature extraction, three consecutive convolution layers are concatenated to achieve the fusion of multilevel spatial features. Next, the extracted spectral and spatial features are concatenated and fed to the fully connected layer so as to obtain the joint spectral-spatial features. In addition, L2 regularization is applied to the convolution layer to prevent overfitting, and dropout operation is employed to the full connection layer to improve the network performance. The effectiveness of the method proposed here has firstly been verified on the Pavia University dataset with competitive classification experimental results. Eventually, the experimental results upon oil spill datasets demonstrate the strong capacity of oil spill detection by this method, which can effectively distinguish thick oil film, thin oil film, and seawater.https://www.mdpi.com/2072-4292/13/8/1568marine oil spill detectionhyperspectral imageconvolutional neural networkspectral-spatial feature extraction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bin Wang Qifan Shao Dongmei Song Zhongwei Li Yunhe Tang Changlong Yang Mingyue Wang |
spellingShingle |
Bin Wang Qifan Shao Dongmei Song Zhongwei Li Yunhe Tang Changlong Yang Mingyue Wang A Spectral-Spatial Features Integrated Network for Hyperspectral Detection of Marine Oil Spill Remote Sensing marine oil spill detection hyperspectral image convolutional neural network spectral-spatial feature extraction |
author_facet |
Bin Wang Qifan Shao Dongmei Song Zhongwei Li Yunhe Tang Changlong Yang Mingyue Wang |
author_sort |
Bin Wang |
title |
A Spectral-Spatial Features Integrated Network for Hyperspectral Detection of Marine Oil Spill |
title_short |
A Spectral-Spatial Features Integrated Network for Hyperspectral Detection of Marine Oil Spill |
title_full |
A Spectral-Spatial Features Integrated Network for Hyperspectral Detection of Marine Oil Spill |
title_fullStr |
A Spectral-Spatial Features Integrated Network for Hyperspectral Detection of Marine Oil Spill |
title_full_unstemmed |
A Spectral-Spatial Features Integrated Network for Hyperspectral Detection of Marine Oil Spill |
title_sort |
spectral-spatial features integrated network for hyperspectral detection of marine oil spill |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-04-01 |
description |
Marine oil spills are one of the most serious problems of marine environmental pollution. Hyperspectral remote sensing has been proven to be an effective tool for monitoring marine oil spills. To make full use of spectral and spatial features, this study proposes a spectral-spatial features integrated network (SSFIN) and applies it for hyperspectral detection of a marine oil spill. Specifically, 1-D and 2-D convolutional neural network (CNN) models have been employed for the extraction of the spectral and spatial features, respectively. During the stage of spatial feature extraction, three consecutive convolution layers are concatenated to achieve the fusion of multilevel spatial features. Next, the extracted spectral and spatial features are concatenated and fed to the fully connected layer so as to obtain the joint spectral-spatial features. In addition, L2 regularization is applied to the convolution layer to prevent overfitting, and dropout operation is employed to the full connection layer to improve the network performance. The effectiveness of the method proposed here has firstly been verified on the Pavia University dataset with competitive classification experimental results. Eventually, the experimental results upon oil spill datasets demonstrate the strong capacity of oil spill detection by this method, which can effectively distinguish thick oil film, thin oil film, and seawater. |
topic |
marine oil spill detection hyperspectral image convolutional neural network spectral-spatial feature extraction |
url |
https://www.mdpi.com/2072-4292/13/8/1568 |
work_keys_str_mv |
AT binwang aspectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT qifanshao aspectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT dongmeisong aspectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT zhongweili aspectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT yunhetang aspectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT changlongyang aspectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT mingyuewang aspectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT binwang spectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT qifanshao spectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT dongmeisong spectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT zhongweili spectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT yunhetang spectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT changlongyang spectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill AT mingyuewang spectralspatialfeaturesintegratednetworkforhyperspectraldetectionofmarineoilspill |
_version_ |
1721521683030867968 |