Patch-Based Change Detection Method for SAR Images with Label Updating Strategy
Convolutional neural networks (CNNs) have been widely used in change detection of synthetic aperture radar (SAR) images and have been proven to have better precision than traditional methods. A two-stage patch-based deep learning method with a label updating strategy is proposed in this paper. The i...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/7/1236 |
| _version_ | 1797540262081200128 |
|---|---|
| author | Yuanjun Shu Wei Li Menglong Yang Peng Cheng Songchen Han |
| author_facet | Yuanjun Shu Wei Li Menglong Yang Peng Cheng Songchen Han |
| author_sort | Yuanjun Shu |
| collection | DOAJ |
| description | Convolutional neural networks (CNNs) have been widely used in change detection of synthetic aperture radar (SAR) images and have been proven to have better precision than traditional methods. A two-stage patch-based deep learning method with a label updating strategy is proposed in this paper. The initial label and mask are generated at the pre-classification stage. Then a two-stage updating strategy is applied to gradually recover changed areas. At the first stage, diversity of training data is gradually restored. The output of the designed CNN network is further processed to generate a new label and a new mask for the following learning iteration. As the diversity of data is ensured after the first stage, pixels within uncertain areas can be easily classified at the second stage. Experiment results on several representative datasets show the effectiveness of our proposed method compared with several existing competitive methods. |
| first_indexed | 2024-03-10T12:57:35Z |
| format | Article |
| id | doaj.art-ead2540443be424eb8f3de9599167d98 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T12:57:35Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ead2540443be424eb8f3de9599167d982023-11-21T11:48:35ZengMDPI AGRemote Sensing2072-42922021-03-01137123610.3390/rs13071236Patch-Based Change Detection Method for SAR Images with Label Updating StrategyYuanjun Shu0Wei Li1Menglong Yang2Peng Cheng3Songchen Han4School of Aeronautics and Astronautics, Sichuan University, Chengdu 610000, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610000, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610000, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610000, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610000, ChinaConvolutional neural networks (CNNs) have been widely used in change detection of synthetic aperture radar (SAR) images and have been proven to have better precision than traditional methods. A two-stage patch-based deep learning method with a label updating strategy is proposed in this paper. The initial label and mask are generated at the pre-classification stage. Then a two-stage updating strategy is applied to gradually recover changed areas. At the first stage, diversity of training data is gradually restored. The output of the designed CNN network is further processed to generate a new label and a new mask for the following learning iteration. As the diversity of data is ensured after the first stage, pixels within uncertain areas can be easily classified at the second stage. Experiment results on several representative datasets show the effectiveness of our proposed method compared with several existing competitive methods.https://www.mdpi.com/2072-4292/13/7/1236change detectionmultilayer fusion convolutional neural networkend-to-end learningupdating strategysynthetic aperture radar (SAR) |
| spellingShingle | Yuanjun Shu Wei Li Menglong Yang Peng Cheng Songchen Han Patch-Based Change Detection Method for SAR Images with Label Updating Strategy Remote Sensing change detection multilayer fusion convolutional neural network end-to-end learning updating strategy synthetic aperture radar (SAR) |
| title | Patch-Based Change Detection Method for SAR Images with Label Updating Strategy |
| title_full | Patch-Based Change Detection Method for SAR Images with Label Updating Strategy |
| title_fullStr | Patch-Based Change Detection Method for SAR Images with Label Updating Strategy |
| title_full_unstemmed | Patch-Based Change Detection Method for SAR Images with Label Updating Strategy |
| title_short | Patch-Based Change Detection Method for SAR Images with Label Updating Strategy |
| title_sort | patch based change detection method for sar images with label updating strategy |
| topic | change detection multilayer fusion convolutional neural network end-to-end learning updating strategy synthetic aperture radar (SAR) |
| url | https://www.mdpi.com/2072-4292/13/7/1236 |
| work_keys_str_mv | AT yuanjunshu patchbasedchangedetectionmethodforsarimageswithlabelupdatingstrategy AT weili patchbasedchangedetectionmethodforsarimageswithlabelupdatingstrategy AT menglongyang patchbasedchangedetectionmethodforsarimageswithlabelupdatingstrategy AT pengcheng patchbasedchangedetectionmethodforsarimageswithlabelupdatingstrategy AT songchenhan patchbasedchangedetectionmethodforsarimageswithlabelupdatingstrategy |