Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed Imagery
Super-resolution mapping (SRM) can effectively predict the spatial distribution of land cover classes within mixed pixels at a higher spatial resolution than the original remotely sensed imagery. The uncertainty of land cover fraction errors within mixed pixels is one of the most important factors a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9982425/ |
| _version_ | 1797330388490649600 |
|---|---|
| author | Cheng Shang Shan Jiang Feng Ling Xiaodong Li Yadong Zhou Yun Du |
| author_facet | Cheng Shang Shan Jiang Feng Ling Xiaodong Li Yadong Zhou Yun Du |
| author_sort | Cheng Shang |
| collection | DOAJ |
| description | Super-resolution mapping (SRM) can effectively predict the spatial distribution of land cover classes within mixed pixels at a higher spatial resolution than the original remotely sensed imagery. The uncertainty of land cover fraction errors within mixed pixels is one of the most important factors affecting SRM accuracy. Studies have shown that SRM methods using deep learning techniques have significantly improved land cover mapping accuracy but have not coped well with spectral–spatial errors. This study proposes an end-to-end SRM model using a spectral–spatial generative adversarial network (SGS) with the direct input of multispectral remotely sensed imagery, which deals with spectral–spatial error. The proposed SGS comprises the following three parts: first, cube-based convolution for spectral unmixing is adopted to generate land cover fraction images. Second, a residual-in-residual dense block fully and jointly considers spectral and spatial information and reduces spectral errors. Third, a relativistic average GAN is designed as a backbone to further improve the super-resolution performance and reduce spectral–spatial errors. SGS was tested in one synthetic and two realistic experiments with multi/hyperspectral remotely sensed imagery as the input, comparing the results with those of hard classification and several classic SRM methods. The results showed that SGS performed well at reducing land cover fraction errors, reconstructing spatial details, removing unpleasant and unrealistic land cover artifacts, and eliminating false recognition. |
| first_indexed | 2024-03-08T07:19:08Z |
| format | Article |
| id | doaj.art-2ac91841aa1a4a3aa8a17aa5fcf36a08 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-08T07:19:08Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-2ac91841aa1a4a3aa8a17aa5fcf36a082024-02-03T00:01:46ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-011652253710.1109/JSTARS.2022.32287419982425Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed ImageryCheng Shang0https://orcid.org/0000-0002-6175-1268Shan Jiang1Feng Ling2https://orcid.org/0000-0002-0685-4897Xiaodong Li3https://orcid.org/0000-0001-8285-8446Yadong Zhou4Yun Du5School of Geosciences, Yangtze University, Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaKey laboratory of Monitoring and Estimate for Environment and Disaster of Hubei province, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuhan, ChinaKey laboratory of Monitoring and Estimate for Environment and Disaster of Hubei province, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuhan, ChinaKey laboratory of Monitoring and Estimate for Environment and Disaster of Hubei province, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuhan, ChinaKey laboratory of Monitoring and Estimate for Environment and Disaster of Hubei province, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuhan, ChinaSuper-resolution mapping (SRM) can effectively predict the spatial distribution of land cover classes within mixed pixels at a higher spatial resolution than the original remotely sensed imagery. The uncertainty of land cover fraction errors within mixed pixels is one of the most important factors affecting SRM accuracy. Studies have shown that SRM methods using deep learning techniques have significantly improved land cover mapping accuracy but have not coped well with spectral–spatial errors. This study proposes an end-to-end SRM model using a spectral–spatial generative adversarial network (SGS) with the direct input of multispectral remotely sensed imagery, which deals with spectral–spatial error. The proposed SGS comprises the following three parts: first, cube-based convolution for spectral unmixing is adopted to generate land cover fraction images. Second, a residual-in-residual dense block fully and jointly considers spectral and spatial information and reduces spectral errors. Third, a relativistic average GAN is designed as a backbone to further improve the super-resolution performance and reduce spectral–spatial errors. SGS was tested in one synthetic and two realistic experiments with multi/hyperspectral remotely sensed imagery as the input, comparing the results with those of hard classification and several classic SRM methods. The results showed that SGS performed well at reducing land cover fraction errors, reconstructing spatial details, removing unpleasant and unrealistic land cover artifacts, and eliminating false recognition.https://ieeexplore.ieee.org/document/9982425/Deep learning (DL)generative adversarial network (GAN)land cover fractionsspectral–spatial errorssuper-resolution mapping (SRM) |
| spellingShingle | Cheng Shang Shan Jiang Feng Ling Xiaodong Li Yadong Zhou Yun Du Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed Imagery IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning (DL) generative adversarial network (GAN) land cover fractions spectral–spatial errors super-resolution mapping (SRM) |
| title | Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed Imagery |
| title_full | Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed Imagery |
| title_fullStr | Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed Imagery |
| title_full_unstemmed | Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed Imagery |
| title_short | Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed Imagery |
| title_sort | spectral spatial generative adversarial network for super resolution land cover mapping with multispectral remotely sensed imagery |
| topic | Deep learning (DL) generative adversarial network (GAN) land cover fractions spectral–spatial errors super-resolution mapping (SRM) |
| url | https://ieeexplore.ieee.org/document/9982425/ |
| work_keys_str_mv | AT chengshang spectralspatialgenerativeadversarialnetworkforsuperresolutionlandcovermappingwithmultispectralremotelysensedimagery AT shanjiang spectralspatialgenerativeadversarialnetworkforsuperresolutionlandcovermappingwithmultispectralremotelysensedimagery AT fengling spectralspatialgenerativeadversarialnetworkforsuperresolutionlandcovermappingwithmultispectralremotelysensedimagery AT xiaodongli spectralspatialgenerativeadversarialnetworkforsuperresolutionlandcovermappingwithmultispectralremotelysensedimagery AT yadongzhou spectralspatialgenerativeadversarialnetworkforsuperresolutionlandcovermappingwithmultispectralremotelysensedimagery AT yundu spectralspatialgenerativeadversarialnetworkforsuperresolutionlandcovermappingwithmultispectralremotelysensedimagery |