Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data
Synthetic aperture radar (SAR) image is an effective remote sensing data source for geographic surveys. However, accurate land cover mapping based on SAR image in areas of complex terrain has become a challenge due to serious geometric distortions and the inadequate separation ability of dual-polari...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/8/2177 |
| _version_ | 1797603580571549696 |
|---|---|
| author | Hongxia Wang Haoran Yang Yabo Huang Lin Wu Zhengwei Guo Ning Li |
| author_facet | Hongxia Wang Haoran Yang Yabo Huang Lin Wu Zhengwei Guo Ning Li |
| author_sort | Hongxia Wang |
| collection | DOAJ |
| description | Synthetic aperture radar (SAR) image is an effective remote sensing data source for geographic surveys. However, accurate land cover mapping based on SAR image in areas of complex terrain has become a challenge due to serious geometric distortions and the inadequate separation ability of dual-polarization data. To address these issues, a new land cover mapping framework which is suitable for complex terrain is proposed based on Gaofen-3 data of ascending and descending orbits. Firstly, the geometric distortion area is determined according to the local incident angle, based on analysis of the SAR imaging mechanism, and the correct polarization information of the opposite track is used to compensate for the geometric distortion area, including layovers and shadows. Then, the dual orbital polarization characteristics (DOPC) and dual polarization radar vegetation index (DpRVI) of dual-pol SAR data are extracted, and the optimal feature combination is found by means of Jeffries–Matusita (J-M) distance analysis. Finally, the deep learning method 2D convolutional neural network (2D-CNN) is applied to classify the compensated images. The proposed method was applied to a mountainous region of the Danjiangkou ecological protection area in China. The accuracy and reliability of the method were experimentally compared using the uncompensated images and the images without DpRVI. Quantitative evaluation revealed that the proposed method achieved better performance in complex terrain areas, with an overall accuracy (OA) score of 0.93, and a Kappa coefficient score of 0.92. Compared with the uncompensated image, OA increased by 5% and Kappa increased by 6%. Compared with the images without DpRVI, OA increased by 4% and Kappa increased by 5%. In summary, the results demonstrate the importance of ascending and descending orbit data to compensate geometric distortion and reveal the effectiveness of optimal feature combination including DpRVI. Its simple and effective polarization information compensation capability can broaden the promising application prospects of SAR images. |
| first_indexed | 2024-03-11T04:34:05Z |
| format | Article |
| id | doaj.art-7d05917e2b7d456fa2770054628827d3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:34:05Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7d05917e2b7d456fa2770054628827d32023-11-17T21:13:08ZengMDPI AGRemote Sensing2072-42922023-04-01158217710.3390/rs15082177Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit DataHongxia Wang0Haoran Yang1Yabo Huang2Lin Wu3Zhengwei Guo4Ning Li5College of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaSchool of Artificial Intelligence, Henan University, Kaifeng 475004, ChinaCollege of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaCollege of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaCollege of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaCollege of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaSynthetic aperture radar (SAR) image is an effective remote sensing data source for geographic surveys. However, accurate land cover mapping based on SAR image in areas of complex terrain has become a challenge due to serious geometric distortions and the inadequate separation ability of dual-polarization data. To address these issues, a new land cover mapping framework which is suitable for complex terrain is proposed based on Gaofen-3 data of ascending and descending orbits. Firstly, the geometric distortion area is determined according to the local incident angle, based on analysis of the SAR imaging mechanism, and the correct polarization information of the opposite track is used to compensate for the geometric distortion area, including layovers and shadows. Then, the dual orbital polarization characteristics (DOPC) and dual polarization radar vegetation index (DpRVI) of dual-pol SAR data are extracted, and the optimal feature combination is found by means of Jeffries–Matusita (J-M) distance analysis. Finally, the deep learning method 2D convolutional neural network (2D-CNN) is applied to classify the compensated images. The proposed method was applied to a mountainous region of the Danjiangkou ecological protection area in China. The accuracy and reliability of the method were experimentally compared using the uncompensated images and the images without DpRVI. Quantitative evaluation revealed that the proposed method achieved better performance in complex terrain areas, with an overall accuracy (OA) score of 0.93, and a Kappa coefficient score of 0.92. Compared with the uncompensated image, OA increased by 5% and Kappa increased by 6%. Compared with the images without DpRVI, OA increased by 4% and Kappa increased by 5%. In summary, the results demonstrate the importance of ascending and descending orbit data to compensate geometric distortion and reveal the effectiveness of optimal feature combination including DpRVI. Its simple and effective polarization information compensation capability can broaden the promising application prospects of SAR images.https://www.mdpi.com/2072-4292/15/8/2177complex terrainland cover classificationsynthetic aperture radar (SAR)ascending and descending orbitDpRVIGaofen-3 |
| spellingShingle | Hongxia Wang Haoran Yang Yabo Huang Lin Wu Zhengwei Guo Ning Li Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data Remote Sensing complex terrain land cover classification synthetic aperture radar (SAR) ascending and descending orbit DpRVI Gaofen-3 |
| title | Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data |
| title_full | Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data |
| title_fullStr | Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data |
| title_full_unstemmed | Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data |
| title_short | Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data |
| title_sort | classification of land cover in complex terrain using gaofen 3 sar ascending and descending orbit data |
| topic | complex terrain land cover classification synthetic aperture radar (SAR) ascending and descending orbit DpRVI Gaofen-3 |
| url | https://www.mdpi.com/2072-4292/15/8/2177 |
| work_keys_str_mv | AT hongxiawang classificationoflandcoverincomplexterrainusinggaofen3sarascendinganddescendingorbitdata AT haoranyang classificationoflandcoverincomplexterrainusinggaofen3sarascendinganddescendingorbitdata AT yabohuang classificationoflandcoverincomplexterrainusinggaofen3sarascendinganddescendingorbitdata AT linwu classificationoflandcoverincomplexterrainusinggaofen3sarascendinganddescendingorbitdata AT zhengweiguo classificationoflandcoverincomplexterrainusinggaofen3sarascendinganddescendingorbitdata AT ningli classificationoflandcoverincomplexterrainusinggaofen3sarascendinganddescendingorbitdata |