Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification
Sea ice is one of the most prominent marine disasters in high latitudes. Remote sensing technology provides an effective means for sea ice detection. Remote sensing sea ice images contain rich spectral and spatial information. However, most traditional methods only focus on spectral information or s...
Published in: | Mathematical Problems in Engineering |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Hindawi Limited
2020
|
Subjects: | |
Online Access: | https://doi.org/10.1155/2020/8065396 https://doaj.org/article/700137a4ac734ef4b40aa57fe69df327 |
id |
ftdoajarticles:oai:doaj.org/article:700137a4ac734ef4b40aa57fe69df327 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:700137a4ac734ef4b40aa57fe69df327 2023-05-15T15:35:07+02:00 Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification Yanling Han Cong Wei Ruyan Zhou Zhonghua Hong Yun Zhang Shuhu Yang 2020-01-01T00:00:00Z https://doi.org/10.1155/2020/8065396 https://doaj.org/article/700137a4ac734ef4b40aa57fe69df327 EN eng Hindawi Limited http://dx.doi.org/10.1155/2020/8065396 https://doaj.org/toc/1024-123X https://doaj.org/toc/1563-5147 1024-123X 1563-5147 doi:10.1155/2020/8065396 https://doaj.org/article/700137a4ac734ef4b40aa57fe69df327 Mathematical Problems in Engineering, Vol 2020 (2020) Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 article 2020 ftdoajarticles https://doi.org/10.1155/2020/8065396 2022-12-31T11:25:16Z Sea ice is one of the most prominent marine disasters in high latitudes. Remote sensing technology provides an effective means for sea ice detection. Remote sensing sea ice images contain rich spectral and spatial information. However, most traditional methods only focus on spectral information or spatial information, and do not excavate the feature of spectral and spatial simultaneously in remote sensing sea ice images classification. At the same time, the complex correlation characteristics among spectra and small sample problem in sea ice classification also limit the improvement of sea ice classification accuracy. For this issue, this paper proposes a new remote sensing sea ice image classification method based on squeeze-and-excitation (SE) network, convolutional neural network (CNN), and support vector machines (SVMs). The proposed method designs 3D-CNN deep network so as to fully exploit the spatial-spectrum features of remote sensing sea ice images and integrates SE-Block into 3D-CNN in-depth network in order to distinguish the contributions of different spectra to sea ice classification. According to the different contributions of spectral features, the weight of each spectral feature is optimized by fusing SE-Block in order to further enhance the sample quality. Finally, information-rich and representative samples are chosen by combining the idea of active learning and input into SVM classifier, and this achieves superior classification accuracy of remote sensing sea ice images with small samples. In order to verify the effectiveness of the proposed method, we conducted experiments on three different data from Baffin Bay, Bohai Bay, and Liaodong Bay. The experimental results show that compared with other classical classification methods, the proposed method comprehensively considers the correlation among spectral features and the small samples problems and deeply excavates the spatial-spectrum characteristics of sea ice and achieves better classification performance, which can be effectively applied to ... Article in Journal/Newspaper Baffin Bay Baffin Bay Baffin Sea ice Directory of Open Access Journals: DOAJ Articles Baffin Bay Mathematical Problems in Engineering 2020 1 15 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 |
spellingShingle |
Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 Yanling Han Cong Wei Ruyan Zhou Zhonghua Hong Yun Zhang Shuhu Yang Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification |
topic_facet |
Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 |
description |
Sea ice is one of the most prominent marine disasters in high latitudes. Remote sensing technology provides an effective means for sea ice detection. Remote sensing sea ice images contain rich spectral and spatial information. However, most traditional methods only focus on spectral information or spatial information, and do not excavate the feature of spectral and spatial simultaneously in remote sensing sea ice images classification. At the same time, the complex correlation characteristics among spectra and small sample problem in sea ice classification also limit the improvement of sea ice classification accuracy. For this issue, this paper proposes a new remote sensing sea ice image classification method based on squeeze-and-excitation (SE) network, convolutional neural network (CNN), and support vector machines (SVMs). The proposed method designs 3D-CNN deep network so as to fully exploit the spatial-spectrum features of remote sensing sea ice images and integrates SE-Block into 3D-CNN in-depth network in order to distinguish the contributions of different spectra to sea ice classification. According to the different contributions of spectral features, the weight of each spectral feature is optimized by fusing SE-Block in order to further enhance the sample quality. Finally, information-rich and representative samples are chosen by combining the idea of active learning and input into SVM classifier, and this achieves superior classification accuracy of remote sensing sea ice images with small samples. In order to verify the effectiveness of the proposed method, we conducted experiments on three different data from Baffin Bay, Bohai Bay, and Liaodong Bay. The experimental results show that compared with other classical classification methods, the proposed method comprehensively considers the correlation among spectral features and the small samples problems and deeply excavates the spatial-spectrum characteristics of sea ice and achieves better classification performance, which can be effectively applied to ... |
format |
Article in Journal/Newspaper |
author |
Yanling Han Cong Wei Ruyan Zhou Zhonghua Hong Yun Zhang Shuhu Yang |
author_facet |
Yanling Han Cong Wei Ruyan Zhou Zhonghua Hong Yun Zhang Shuhu Yang |
author_sort |
Yanling Han |
title |
Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification |
title_short |
Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification |
title_full |
Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification |
title_fullStr |
Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification |
title_full_unstemmed |
Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification |
title_sort |
combining 3d-cnn and squeeze-and-excitation networks for remote sensing sea ice image classification |
publisher |
Hindawi Limited |
publishDate |
2020 |
url |
https://doi.org/10.1155/2020/8065396 https://doaj.org/article/700137a4ac734ef4b40aa57fe69df327 |
geographic |
Baffin Bay |
geographic_facet |
Baffin Bay |
genre |
Baffin Bay Baffin Bay Baffin Sea ice |
genre_facet |
Baffin Bay Baffin Bay Baffin Sea ice |
op_source |
Mathematical Problems in Engineering, Vol 2020 (2020) |
op_relation |
http://dx.doi.org/10.1155/2020/8065396 https://doaj.org/toc/1024-123X https://doaj.org/toc/1563-5147 1024-123X 1563-5147 doi:10.1155/2020/8065396 https://doaj.org/article/700137a4ac734ef4b40aa57fe69df327 |
op_doi |
https://doi.org/10.1155/2020/8065396 |
container_title |
Mathematical Problems in Engineering |
container_volume |
2020 |
container_start_page |
1 |
op_container_end_page |
15 |
_version_ |
1766365416000585728 |