Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal Wetlands
It is significant for restoration and protection of natural resources and ecological services in coastal wetlands to map different land cover types with satellite remote sensing data. Considering difficulties of wetland species classification, hyperspectral images (HSIs) with high spectral resolutio...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9268458/ |
| _version_ | 1819137244037906432 |
|---|---|
| author | Chang Liu Ran Tao Wei Li Mengmeng Zhang Weiwei Sun Qian Du |
| author_facet | Chang Liu Ran Tao Wei Li Mengmeng Zhang Weiwei Sun Qian Du |
| author_sort | Chang Liu |
| collection | DOAJ |
| description | It is significant for restoration and protection of natural resources and ecological services in coastal wetlands to map different land cover types with satellite remote sensing data. Considering difficulties of wetland species classification, hyperspectral images (HSIs) with high spectral resolution and multispectral images (MSI) with high spatial resolution are considered to achieve complementary advantages of multisource data. An effective approach, named as multistream convolutional neural network, is proposed to achieve fine classification of coastal wetlands. First, regression processing is adopted to make chaotically scattered coastal wetland data more compact and different. Second, through appropriate feature extraction and feature fusion strategies, high-level information of multisource data in regression domain is fused to distinguish different land cover. Experiments on GF-5 HSIs and Sentinel-2 MSIs are carried out in order to validate the classification performance of the proposed approach in two coastal wetlands of research value in China, i.e., Yellow River Estuary and Yancheng coastal wetland. Experimental results demonstrate the effectiveness of the proposed method compared with the state-of-the-art methods in the field, especially when the number of sample size is extremely small. |
| first_indexed | 2024-12-22T10:47:47Z |
| format | Article |
| id | doaj.art-06d5be26ee90425ca94d51887d060e7c |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-22T10:47:47Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-06d5be26ee90425ca94d51887d060e7c2022-12-21T18:28:53ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-011498299610.1109/JSTARS.2020.30403059268458Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal WetlandsChang Liu0Ran Tao1https://orcid.org/0000-0002-5243-7189Wei Li2https://orcid.org/0000-0001-7015-7335Mengmeng Zhang3https://orcid.org/0000-0002-5724-9785Weiwei Sun4https://orcid.org/0000-0003-3399-7858Qian Du5https://orcid.org/0000-0001-8354-7500School of Information and Electronics, Beijing Institute of Technology, Beijing, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo, ChinaDepartment of Electrical and Computer Engineering, Mississippi State University, Starkville, MS, USAIt is significant for restoration and protection of natural resources and ecological services in coastal wetlands to map different land cover types with satellite remote sensing data. Considering difficulties of wetland species classification, hyperspectral images (HSIs) with high spectral resolution and multispectral images (MSI) with high spatial resolution are considered to achieve complementary advantages of multisource data. An effective approach, named as multistream convolutional neural network, is proposed to achieve fine classification of coastal wetlands. First, regression processing is adopted to make chaotically scattered coastal wetland data more compact and different. Second, through appropriate feature extraction and feature fusion strategies, high-level information of multisource data in regression domain is fused to distinguish different land cover. Experiments on GF-5 HSIs and Sentinel-2 MSIs are carried out in order to validate the classification performance of the proposed approach in two coastal wetlands of research value in China, i.e., Yellow River Estuary and Yancheng coastal wetland. Experimental results demonstrate the effectiveness of the proposed method compared with the state-of-the-art methods in the field, especially when the number of sample size is extremely small.https://ieeexplore.ieee.org/document/9268458/Coastal wetlandsconvolutional neural network (CNN)data fusionhyperspectral imagery (HSI)least squares regression (LSR)multispectral imagery (MSI) |
| spellingShingle | Chang Liu Ran Tao Wei Li Mengmeng Zhang Weiwei Sun Qian Du Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal Wetlands IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Coastal wetlands convolutional neural network (CNN) data fusion hyperspectral imagery (HSI) least squares regression (LSR) multispectral imagery (MSI) |
| title | Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal Wetlands |
| title_full | Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal Wetlands |
| title_fullStr | Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal Wetlands |
| title_full_unstemmed | Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal Wetlands |
| title_short | Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal Wetlands |
| title_sort | joint classification of hyperspectral and multispectral images for mapping coastal wetlands |
| topic | Coastal wetlands convolutional neural network (CNN) data fusion hyperspectral imagery (HSI) least squares regression (LSR) multispectral imagery (MSI) |
| url | https://ieeexplore.ieee.org/document/9268458/ |
| work_keys_str_mv | AT changliu jointclassificationofhyperspectralandmultispectralimagesformappingcoastalwetlands AT rantao jointclassificationofhyperspectralandmultispectralimagesformappingcoastalwetlands AT weili jointclassificationofhyperspectralandmultispectralimagesformappingcoastalwetlands AT mengmengzhang jointclassificationofhyperspectralandmultispectralimagesformappingcoastalwetlands AT weiweisun jointclassificationofhyperspectralandmultispectralimagesformappingcoastalwetlands AT qiandu jointclassificationofhyperspectralandmultispectralimagesformappingcoastalwetlands |