MDESNet: Multitask Difference-Enhanced Siamese Network for Building Change Detection in High-Resolution Remote Sensing Images
Building change detection is a prominent topic in remote sensing applications. Scholars have proposed a variety of fully-convolutional-network-based change detection methods for high-resolution remote sensing images, achieving impressive results on several building datasets. However, existing method...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3775 |
| _version_ | 1827601728152797184 |
|---|---|
| author | Jiaxiang Zheng Yichen Tian Chao Yuan Kai Yin Feifei Zhang Fangmiao Chen Qiang Chen |
| author_facet | Jiaxiang Zheng Yichen Tian Chao Yuan Kai Yin Feifei Zhang Fangmiao Chen Qiang Chen |
| author_sort | Jiaxiang Zheng |
| collection | DOAJ |
| description | Building change detection is a prominent topic in remote sensing applications. Scholars have proposed a variety of fully-convolutional-network-based change detection methods for high-resolution remote sensing images, achieving impressive results on several building datasets. However, existing methods cannot solve the problem of pseudo-changes caused by factors such as “same object with different spectrums” and “different objects with same spectrums” in high-resolution remote sensing images because their networks are constructed using simple similarity measures. To increase the ability of the model to resist pseudo-changes and improve detection accuracy, we propose an improved method based on fully convolutional network, called multitask difference-enhanced Siamese network (MDESNet) for building change detection in high-resolution remote sensing images. We improved its feature extraction ability by adding semantic constraints and effectively utilized features while improving its recognition performance. Furthermore, we proposed a similarity measure combining concatenation and difference, called the feature difference enhancement (FDE) module, and designed comparative experiments to demonstrate its effectiveness in resisting pseudo-changes. Using the building change detection dataset (BCDD), we demonstrate that our method outperforms other state-of-the-art change detection methods, achieving the highest F1-score (0.9124) and OA (0.9874), indicating its advantages for high-resolution remote sensing image building change detection tasks. |
| first_indexed | 2024-03-09T05:02:35Z |
| format | Article |
| id | doaj.art-ecc487500ab74f5cb3dede6e4ad6d1c5 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:02:35Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ecc487500ab74f5cb3dede6e4ad6d1c52023-12-03T12:58:55ZengMDPI AGRemote Sensing2072-42922022-08-011415377510.3390/rs14153775MDESNet: Multitask Difference-Enhanced Siamese Network for Building Change Detection in High-Resolution Remote Sensing ImagesJiaxiang Zheng0Yichen Tian1Chao Yuan2Kai Yin3Feifei Zhang4Fangmiao Chen5Qiang Chen6Aerospace 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, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaBuilding change detection is a prominent topic in remote sensing applications. Scholars have proposed a variety of fully-convolutional-network-based change detection methods for high-resolution remote sensing images, achieving impressive results on several building datasets. However, existing methods cannot solve the problem of pseudo-changes caused by factors such as “same object with different spectrums” and “different objects with same spectrums” in high-resolution remote sensing images because their networks are constructed using simple similarity measures. To increase the ability of the model to resist pseudo-changes and improve detection accuracy, we propose an improved method based on fully convolutional network, called multitask difference-enhanced Siamese network (MDESNet) for building change detection in high-resolution remote sensing images. We improved its feature extraction ability by adding semantic constraints and effectively utilized features while improving its recognition performance. Furthermore, we proposed a similarity measure combining concatenation and difference, called the feature difference enhancement (FDE) module, and designed comparative experiments to demonstrate its effectiveness in resisting pseudo-changes. Using the building change detection dataset (BCDD), we demonstrate that our method outperforms other state-of-the-art change detection methods, achieving the highest F1-score (0.9124) and OA (0.9874), indicating its advantages for high-resolution remote sensing image building change detection tasks.https://www.mdpi.com/2072-4292/14/15/3775remote sensingbuilding change detectionSiamese networkdifference-enhancedmultitask |
| spellingShingle | Jiaxiang Zheng Yichen Tian Chao Yuan Kai Yin Feifei Zhang Fangmiao Chen Qiang Chen MDESNet: Multitask Difference-Enhanced Siamese Network for Building Change Detection in High-Resolution Remote Sensing Images Remote Sensing remote sensing building change detection Siamese network difference-enhanced multitask |
| title | MDESNet: Multitask Difference-Enhanced Siamese Network for Building Change Detection in High-Resolution Remote Sensing Images |
| title_full | MDESNet: Multitask Difference-Enhanced Siamese Network for Building Change Detection in High-Resolution Remote Sensing Images |
| title_fullStr | MDESNet: Multitask Difference-Enhanced Siamese Network for Building Change Detection in High-Resolution Remote Sensing Images |
| title_full_unstemmed | MDESNet: Multitask Difference-Enhanced Siamese Network for Building Change Detection in High-Resolution Remote Sensing Images |
| title_short | MDESNet: Multitask Difference-Enhanced Siamese Network for Building Change Detection in High-Resolution Remote Sensing Images |
| title_sort | mdesnet multitask difference enhanced siamese network for building change detection in high resolution remote sensing images |
| topic | remote sensing building change detection Siamese network difference-enhanced multitask |
| url | https://www.mdpi.com/2072-4292/14/15/3775 |
| work_keys_str_mv | AT jiaxiangzheng mdesnetmultitaskdifferenceenhancedsiamesenetworkforbuildingchangedetectioninhighresolutionremotesensingimages AT yichentian mdesnetmultitaskdifferenceenhancedsiamesenetworkforbuildingchangedetectioninhighresolutionremotesensingimages AT chaoyuan mdesnetmultitaskdifferenceenhancedsiamesenetworkforbuildingchangedetectioninhighresolutionremotesensingimages AT kaiyin mdesnetmultitaskdifferenceenhancedsiamesenetworkforbuildingchangedetectioninhighresolutionremotesensingimages AT feifeizhang mdesnetmultitaskdifferenceenhancedsiamesenetworkforbuildingchangedetectioninhighresolutionremotesensingimages AT fangmiaochen mdesnetmultitaskdifferenceenhancedsiamesenetworkforbuildingchangedetectioninhighresolutionremotesensingimages AT qiangchen mdesnetmultitaskdifferenceenhancedsiamesenetworkforbuildingchangedetectioninhighresolutionremotesensingimages |