DSNUNet: An Improved Forest Change Detection Network by Combining Sentinel-1 and Sentinel-2 Images
The use of remote sensing images to detect forest changes is of great significance for forest resource management. With the development and implementation of deep learning algorithms in change detection, a large number of models have been designed to detect changes in multi-phase remote sensing imag...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/19/5046 |
| _version_ | 1797477023036211200 |
|---|---|
| author | Jiawei Jiang Yuanjun Xing Wei Wei Enping Yan Jun Xiang Dengkui Mo |
| author_facet | Jiawei Jiang Yuanjun Xing Wei Wei Enping Yan Jun Xiang Dengkui Mo |
| author_sort | Jiawei Jiang |
| collection | DOAJ |
| description | The use of remote sensing images to detect forest changes is of great significance for forest resource management. With the development and implementation of deep learning algorithms in change detection, a large number of models have been designed to detect changes in multi-phase remote sensing images. Although synthetic aperture radar (SAR) data have strong potential for application in forest change detection tasks, most existing deep learning-based models have been designed for optical imagery. Therefore, to effectively combine optical and SAR data in forest change detection, this paper proposes a double Siamese branch-based change detection network called DSNUNet. DSNUNet uses two sets of feature branches to extract features from dual-phase optical and SAR images and employs shared weights to combine features into groups. In the proposed DSNUNet, different feature extraction branch widths were used to compensate for a difference in the amount of information between optical and SAR images. The proposed DSNUNet was validated by experiments on the manually annotated forest change detection dataset. According to the obtained results, the proposed method outperformed other change detection methods, achieving an F1-score of 76.40%. In addition, different combinations of width between feature extraction branches were analyzed in this study. The results revealed an optimal performance of the model at initial channel numbers of the optical imaging branch and SAR image branch of 32 and 8, respectively. The prediction results demonstrated the effectiveness of the proposed method in accurately predicting forest changes and suppressing cloud interferences to some extent. |
| first_indexed | 2024-03-09T21:12:04Z |
| format | Article |
| id | doaj.art-6425a895f06649c28f3bb793ee619825 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:12:04Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6425a895f06649c28f3bb793ee6198252023-11-23T21:43:04ZengMDPI AGRemote Sensing2072-42922022-10-011419504610.3390/rs14195046DSNUNet: An Improved Forest Change Detection Network by Combining Sentinel-1 and Sentinel-2 ImagesJiawei Jiang0Yuanjun Xing1Wei Wei2Enping Yan3Jun Xiang4Dengkui Mo5Key Laboratory of State Forestry and Grassland Administration on Forest Resources Management and Monitoring in Southern Area, Changsha 410004, ChinaCentral South Forest Inventory and Planning Institute of State Forestry Administration, Changsha 410004, ChinaForestry Research Institute of Guangxi Zhuang Autonomous Region, Nanning 530002, ChinaKey Laboratory of State Forestry and Grassland Administration on Forest Resources Management and Monitoring in Southern Area, Changsha 410004, ChinaKey Laboratory of State Forestry and Grassland Administration on Forest Resources Management and Monitoring in Southern Area, Changsha 410004, ChinaKey Laboratory of State Forestry and Grassland Administration on Forest Resources Management and Monitoring in Southern Area, Changsha 410004, ChinaThe use of remote sensing images to detect forest changes is of great significance for forest resource management. With the development and implementation of deep learning algorithms in change detection, a large number of models have been designed to detect changes in multi-phase remote sensing images. Although synthetic aperture radar (SAR) data have strong potential for application in forest change detection tasks, most existing deep learning-based models have been designed for optical imagery. Therefore, to effectively combine optical and SAR data in forest change detection, this paper proposes a double Siamese branch-based change detection network called DSNUNet. DSNUNet uses two sets of feature branches to extract features from dual-phase optical and SAR images and employs shared weights to combine features into groups. In the proposed DSNUNet, different feature extraction branch widths were used to compensate for a difference in the amount of information between optical and SAR images. The proposed DSNUNet was validated by experiments on the manually annotated forest change detection dataset. According to the obtained results, the proposed method outperformed other change detection methods, achieving an F1-score of 76.40%. In addition, different combinations of width between feature extraction branches were analyzed in this study. The results revealed an optimal performance of the model at initial channel numbers of the optical imaging branch and SAR image branch of 32 and 8, respectively. The prediction results demonstrated the effectiveness of the proposed method in accurately predicting forest changes and suppressing cloud interferences to some extent.https://www.mdpi.com/2072-4292/14/19/5046Sentinel-1Sentinel-2forestchange detectiondeep learning |
| spellingShingle | Jiawei Jiang Yuanjun Xing Wei Wei Enping Yan Jun Xiang Dengkui Mo DSNUNet: An Improved Forest Change Detection Network by Combining Sentinel-1 and Sentinel-2 Images Remote Sensing Sentinel-1 Sentinel-2 forest change detection deep learning |
| title | DSNUNet: An Improved Forest Change Detection Network by Combining Sentinel-1 and Sentinel-2 Images |
| title_full | DSNUNet: An Improved Forest Change Detection Network by Combining Sentinel-1 and Sentinel-2 Images |
| title_fullStr | DSNUNet: An Improved Forest Change Detection Network by Combining Sentinel-1 and Sentinel-2 Images |
| title_full_unstemmed | DSNUNet: An Improved Forest Change Detection Network by Combining Sentinel-1 and Sentinel-2 Images |
| title_short | DSNUNet: An Improved Forest Change Detection Network by Combining Sentinel-1 and Sentinel-2 Images |
| title_sort | dsnunet an improved forest change detection network by combining sentinel 1 and sentinel 2 images |
| topic | Sentinel-1 Sentinel-2 forest change detection deep learning |
| url | https://www.mdpi.com/2072-4292/14/19/5046 |
| work_keys_str_mv | AT jiaweijiang dsnunetanimprovedforestchangedetectionnetworkbycombiningsentinel1andsentinel2images AT yuanjunxing dsnunetanimprovedforestchangedetectionnetworkbycombiningsentinel1andsentinel2images AT weiwei dsnunetanimprovedforestchangedetectionnetworkbycombiningsentinel1andsentinel2images AT enpingyan dsnunetanimprovedforestchangedetectionnetworkbycombiningsentinel1andsentinel2images AT junxiang dsnunetanimprovedforestchangedetectionnetworkbycombiningsentinel1andsentinel2images AT dengkuimo dsnunetanimprovedforestchangedetectionnetworkbycombiningsentinel1andsentinel2images |