A Cloud Detection Method Based on Spectral and Gradient Features for SDGSAT-1 Multispectral Images
Due to the limited penetration of visible bands, optical remote sensing images are inevitably contaminated by clouds. Therefore, cloud detection or cloud mask products for optical image processing is a very important step. Compared with conventional optical remote sensing satellites (such as Landsat...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/1/24 |
| _version_ | 1797431264308887552 |
|---|---|
| author | Kaiqiang Ge Jiayin Liu Feng Wang Bo Chen Yuxin Hu |
| author_facet | Kaiqiang Ge Jiayin Liu Feng Wang Bo Chen Yuxin Hu |
| author_sort | Kaiqiang Ge |
| collection | DOAJ |
| description | Due to the limited penetration of visible bands, optical remote sensing images are inevitably contaminated by clouds. Therefore, cloud detection or cloud mask products for optical image processing is a very important step. Compared with conventional optical remote sensing satellites (such as Landsat series and Sentinel-2), sustainable development science Satellite-1 (SDGSAT-1) multi-spectral imager (MII) lacks a short-wave infrared (SWIR) band that can be used to effectively distinguish cloud and snow. To solve the above problems, a cloud detection method based on spectral and gradient features (SGF) for SDGSAT-1 multispectral images is proposed in this paper. According to the differences in spectral features between cloud and other ground objects, the method combines four features, namely, brightness, normalized difference water index (NDWI), normalized difference vegetation index (NDVI), and haze-optimized transformation (HOT) to distinguish cloud and most ground objects. Meanwhile, in order to adapt to different environments, the dynamic threshold using Otsu’s method is adopted. In addition, it is worth mentioning that gradient features are used to distinguish cloud and snow in this paper. With the test of SDGSAT-1 multispectral images and comparison experiments, the results show that SGF has excellent performance. The overall accuracy of images with snow surface can reach 90.80%, and the overall accuracy of images with other surfaces is above 94%. |
| first_indexed | 2024-03-09T09:42:23Z |
| format | Article |
| id | doaj.art-2243b844756a4212a17d4e2c026db4a7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T09:42:23Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2243b844756a4212a17d4e2c026db4a72023-12-02T00:50:31ZengMDPI AGRemote Sensing2072-42922022-12-011512410.3390/rs15010024A Cloud Detection Method Based on Spectral and Gradient Features for SDGSAT-1 Multispectral ImagesKaiqiang Ge0Jiayin Liu1Feng Wang2Bo Chen3Yuxin Hu4Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaDue to the limited penetration of visible bands, optical remote sensing images are inevitably contaminated by clouds. Therefore, cloud detection or cloud mask products for optical image processing is a very important step. Compared with conventional optical remote sensing satellites (such as Landsat series and Sentinel-2), sustainable development science Satellite-1 (SDGSAT-1) multi-spectral imager (MII) lacks a short-wave infrared (SWIR) band that can be used to effectively distinguish cloud and snow. To solve the above problems, a cloud detection method based on spectral and gradient features (SGF) for SDGSAT-1 multispectral images is proposed in this paper. According to the differences in spectral features between cloud and other ground objects, the method combines four features, namely, brightness, normalized difference water index (NDWI), normalized difference vegetation index (NDVI), and haze-optimized transformation (HOT) to distinguish cloud and most ground objects. Meanwhile, in order to adapt to different environments, the dynamic threshold using Otsu’s method is adopted. In addition, it is worth mentioning that gradient features are used to distinguish cloud and snow in this paper. With the test of SDGSAT-1 multispectral images and comparison experiments, the results show that SGF has excellent performance. The overall accuracy of images with snow surface can reach 90.80%, and the overall accuracy of images with other surfaces is above 94%.https://www.mdpi.com/2072-4292/15/1/24cloud detectionSDGSAT-1spectral featuresgradient features |
| spellingShingle | Kaiqiang Ge Jiayin Liu Feng Wang Bo Chen Yuxin Hu A Cloud Detection Method Based on Spectral and Gradient Features for SDGSAT-1 Multispectral Images Remote Sensing cloud detection SDGSAT-1 spectral features gradient features |
| title | A Cloud Detection Method Based on Spectral and Gradient Features for SDGSAT-1 Multispectral Images |
| title_full | A Cloud Detection Method Based on Spectral and Gradient Features for SDGSAT-1 Multispectral Images |
| title_fullStr | A Cloud Detection Method Based on Spectral and Gradient Features for SDGSAT-1 Multispectral Images |
| title_full_unstemmed | A Cloud Detection Method Based on Spectral and Gradient Features for SDGSAT-1 Multispectral Images |
| title_short | A Cloud Detection Method Based on Spectral and Gradient Features for SDGSAT-1 Multispectral Images |
| title_sort | cloud detection method based on spectral and gradient features for sdgsat 1 multispectral images |
| topic | cloud detection SDGSAT-1 spectral features gradient features |
| url | https://www.mdpi.com/2072-4292/15/1/24 |
| work_keys_str_mv | AT kaiqiangge aclouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT jiayinliu aclouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT fengwang aclouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT bochen aclouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT yuxinhu aclouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT kaiqiangge clouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT jiayinliu clouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT fengwang clouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT bochen clouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages AT yuxinhu clouddetectionmethodbasedonspectralandgradientfeaturesforsdgsat1multispectralimages |