Multi-Featured Sea Ice Classification with SAR Image Based on Convolutional Neural Network
Sea ice is a significant factor in influencing environmental change on Earth. Monitoring sea ice is of major importance, and one of the main objectives of this monitoring is sea ice classification. Currently, synthetic aperture radar (SAR) data are primarily used for sea ice classification, with a s...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs15164014 https://doaj.org/article/161cfdf79eee4d648379ad443f25b2f0 |
id |
ftdoajarticles:oai:doaj.org/article:161cfdf79eee4d648379ad443f25b2f0 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:161cfdf79eee4d648379ad443f25b2f0 2023-09-26T15:22:54+02:00 Multi-Featured Sea Ice Classification with SAR Image Based on Convolutional Neural Network Hongyang Wan Xiaowen Luo Ziyin Wu Xiaoming Qin Xiaolun Chen Bin Li Jihong Shang Dineng Zhao 2023-08-01T00:00:00Z https://doi.org/10.3390/rs15164014 https://doaj.org/article/161cfdf79eee4d648379ad443f25b2f0 EN eng MDPI AG https://www.mdpi.com/2072-4292/15/16/4014 https://doaj.org/toc/2072-4292 doi:10.3390/rs15164014 2072-4292 https://doaj.org/article/161cfdf79eee4d648379ad443f25b2f0 Remote Sensing, Vol 15, Iss 4014, p 4014 (2023) sea ice classification SAR polarization decomposition JTFA multi-feature Science Q article 2023 ftdoajarticles https://doi.org/10.3390/rs15164014 2023-08-27T00:34:52Z Sea ice is a significant factor in influencing environmental change on Earth. Monitoring sea ice is of major importance, and one of the main objectives of this monitoring is sea ice classification. Currently, synthetic aperture radar (SAR) data are primarily used for sea ice classification, with a single polarization band or simple combinations of polarization bands being common choices. While much of the current research has focused on optimizing network structures to achieve high classification accuracy, which requires substantial training resources, we aim to extract more information from the SAR data for classification. Therefore we propose a multi-featured SAR sea ice classification method that combines polarization features calculated by polarization decomposition and spectrogram features calculated by joint time-frequency analysis (JTFA). We built a convolutional neural network (CNN) structure for learning the multi-features of sea ice, which combines spatial features and physical properties, including polarization and spectrogram features of sea ice. In this paper, we utilized ALOS PALSAR SLC data with HH, HV, VH, and VV, four types of polarization for the multi-featured sea ice classification method. We divided the sea ice into new ice (NI), first-year ice (FI), old ice (OI), deformed ice (DI), and open water (OW). Then, the accuracy calculation by confusion matrix and comparative analysis were carried out. Our experimental results demonstrate that the multi-feature method proposed in this paper can achieve high accuracy with a smaller data volume and computational effort. In the four scenes selected for validation, the overall accuracy could reach 95%, 91%, 96%, and 95%, respectively, which represents a significant improvement compared to the single-feature sea ice classification method. Article in Journal/Newspaper Sea ice Directory of Open Access Journals: DOAJ Articles Remote Sensing 15 16 4014 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
sea ice classification SAR polarization decomposition JTFA multi-feature Science Q |
spellingShingle |
sea ice classification SAR polarization decomposition JTFA multi-feature Science Q Hongyang Wan Xiaowen Luo Ziyin Wu Xiaoming Qin Xiaolun Chen Bin Li Jihong Shang Dineng Zhao Multi-Featured Sea Ice Classification with SAR Image Based on Convolutional Neural Network |
topic_facet |
sea ice classification SAR polarization decomposition JTFA multi-feature Science Q |
description |
Sea ice is a significant factor in influencing environmental change on Earth. Monitoring sea ice is of major importance, and one of the main objectives of this monitoring is sea ice classification. Currently, synthetic aperture radar (SAR) data are primarily used for sea ice classification, with a single polarization band or simple combinations of polarization bands being common choices. While much of the current research has focused on optimizing network structures to achieve high classification accuracy, which requires substantial training resources, we aim to extract more information from the SAR data for classification. Therefore we propose a multi-featured SAR sea ice classification method that combines polarization features calculated by polarization decomposition and spectrogram features calculated by joint time-frequency analysis (JTFA). We built a convolutional neural network (CNN) structure for learning the multi-features of sea ice, which combines spatial features and physical properties, including polarization and spectrogram features of sea ice. In this paper, we utilized ALOS PALSAR SLC data with HH, HV, VH, and VV, four types of polarization for the multi-featured sea ice classification method. We divided the sea ice into new ice (NI), first-year ice (FI), old ice (OI), deformed ice (DI), and open water (OW). Then, the accuracy calculation by confusion matrix and comparative analysis were carried out. Our experimental results demonstrate that the multi-feature method proposed in this paper can achieve high accuracy with a smaller data volume and computational effort. In the four scenes selected for validation, the overall accuracy could reach 95%, 91%, 96%, and 95%, respectively, which represents a significant improvement compared to the single-feature sea ice classification method. |
format |
Article in Journal/Newspaper |
author |
Hongyang Wan Xiaowen Luo Ziyin Wu Xiaoming Qin Xiaolun Chen Bin Li Jihong Shang Dineng Zhao |
author_facet |
Hongyang Wan Xiaowen Luo Ziyin Wu Xiaoming Qin Xiaolun Chen Bin Li Jihong Shang Dineng Zhao |
author_sort |
Hongyang Wan |
title |
Multi-Featured Sea Ice Classification with SAR Image Based on Convolutional Neural Network |
title_short |
Multi-Featured Sea Ice Classification with SAR Image Based on Convolutional Neural Network |
title_full |
Multi-Featured Sea Ice Classification with SAR Image Based on Convolutional Neural Network |
title_fullStr |
Multi-Featured Sea Ice Classification with SAR Image Based on Convolutional Neural Network |
title_full_unstemmed |
Multi-Featured Sea Ice Classification with SAR Image Based on Convolutional Neural Network |
title_sort |
multi-featured sea ice classification with sar image based on convolutional neural network |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/rs15164014 https://doaj.org/article/161cfdf79eee4d648379ad443f25b2f0 |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
Remote Sensing, Vol 15, Iss 4014, p 4014 (2023) |
op_relation |
https://www.mdpi.com/2072-4292/15/16/4014 https://doaj.org/toc/2072-4292 doi:10.3390/rs15164014 2072-4292 https://doaj.org/article/161cfdf79eee4d648379ad443f25b2f0 |
op_doi |
https://doi.org/10.3390/rs15164014 |
container_title |
Remote Sensing |
container_volume |
15 |
container_issue |
16 |
container_start_page |
4014 |
_version_ |
1778148822368649216 |