Deep-Learning-Based Method for the Identification of Typical Crops Using Dual-Polarimetric Synthetic Aperture Radar and High-Resolution Optical Images
Timely monitoring of distribution and growth state of crops is crucial for agricultural management. Remote sensing (RS) techniques provide an effective tool to monitor crops. This study proposes a novel approach for the identification of typical crops, including rapeseed and wheat, using multisource...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/148 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549006624260096 |
|---|---|
| author | Xiaoshuang Ma Le Li Yinglei Wu |
| author_facet | Xiaoshuang Ma Le Li Yinglei Wu |
| author_sort | Xiaoshuang Ma |
| collection | DOAJ |
| description | Timely monitoring of distribution and growth state of crops is crucial for agricultural management. Remote sensing (RS) techniques provide an effective tool to monitor crops. This study proposes a novel approach for the identification of typical crops, including rapeseed and wheat, using multisource remote sensing data and deep learning technology. By adopting an improved DeepLabV3+ network architecture that integrates a feature-enhanced module and an attention module, multiple features from both optical data and synthetic aperture radar (SAR) data are fully mined to take into account the spectral reflectance traits and polarimetric scattering straits of crops. The proposal can effectively address the limitations of using a single data source, alleviating the misclassification problem brought by the spectral similarity of crops in certain bands. Experimental results demonstrate that the proposed crop identification DeepLabV3+ (CI-DeepLabV3+) method outperforms traditional classification methods and the original DeepLabV3+ network, with an overall accuracy and F1 score of 94.54% and 94.55%, respectively. Experimental results also support the conclusion that using multiple features from multi-source data can indeed improve the performance of the network. |
| format | Article |
| id | doaj-art-9224fa35688f4d7ab6a44f3f2f7fc6a1 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-9224fa35688f4d7ab6a44f3f2f7fc6a12025-01-10T13:20:23ZengMDPI AGRemote Sensing2072-42922025-01-0117114810.3390/rs17010148Deep-Learning-Based Method for the Identification of Typical Crops Using Dual-Polarimetric Synthetic Aperture Radar and High-Resolution Optical ImagesXiaoshuang Ma0Le Li1Yinglei Wu2School of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaSchool of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaChina JIKAN Research Institute of Engineering Investigations and Design, Co., Ltd., Xi’an 710021, ChinaTimely monitoring of distribution and growth state of crops is crucial for agricultural management. Remote sensing (RS) techniques provide an effective tool to monitor crops. This study proposes a novel approach for the identification of typical crops, including rapeseed and wheat, using multisource remote sensing data and deep learning technology. By adopting an improved DeepLabV3+ network architecture that integrates a feature-enhanced module and an attention module, multiple features from both optical data and synthetic aperture radar (SAR) data are fully mined to take into account the spectral reflectance traits and polarimetric scattering straits of crops. The proposal can effectively address the limitations of using a single data source, alleviating the misclassification problem brought by the spectral similarity of crops in certain bands. Experimental results demonstrate that the proposed crop identification DeepLabV3+ (CI-DeepLabV3+) method outperforms traditional classification methods and the original DeepLabV3+ network, with an overall accuracy and F1 score of 94.54% and 94.55%, respectively. Experimental results also support the conclusion that using multiple features from multi-source data can indeed improve the performance of the network.https://www.mdpi.com/2072-4292/17/1/148crop classificationmulti-source remote sensingpolarimetric synthetic aperture radardeep learning |
| spellingShingle | Xiaoshuang Ma Le Li Yinglei Wu Deep-Learning-Based Method for the Identification of Typical Crops Using Dual-Polarimetric Synthetic Aperture Radar and High-Resolution Optical Images Remote Sensing crop classification multi-source remote sensing polarimetric synthetic aperture radar deep learning |
| title | Deep-Learning-Based Method for the Identification of Typical Crops Using Dual-Polarimetric Synthetic Aperture Radar and High-Resolution Optical Images |
| title_full | Deep-Learning-Based Method for the Identification of Typical Crops Using Dual-Polarimetric Synthetic Aperture Radar and High-Resolution Optical Images |
| title_fullStr | Deep-Learning-Based Method for the Identification of Typical Crops Using Dual-Polarimetric Synthetic Aperture Radar and High-Resolution Optical Images |
| title_full_unstemmed | Deep-Learning-Based Method for the Identification of Typical Crops Using Dual-Polarimetric Synthetic Aperture Radar and High-Resolution Optical Images |
| title_short | Deep-Learning-Based Method for the Identification of Typical Crops Using Dual-Polarimetric Synthetic Aperture Radar and High-Resolution Optical Images |
| title_sort | deep learning based method for the identification of typical crops using dual polarimetric synthetic aperture radar and high resolution optical images |
| topic | crop classification multi-source remote sensing polarimetric synthetic aperture radar deep learning |
| url | https://www.mdpi.com/2072-4292/17/1/148 |
| work_keys_str_mv | AT xiaoshuangma deeplearningbasedmethodfortheidentificationoftypicalcropsusingdualpolarimetricsyntheticapertureradarandhighresolutionopticalimages AT leli deeplearningbasedmethodfortheidentificationoftypicalcropsusingdualpolarimetricsyntheticapertureradarandhighresolutionopticalimages AT yingleiwu deeplearningbasedmethodfortheidentificationoftypicalcropsusingdualpolarimetricsyntheticapertureradarandhighresolutionopticalimages |