Object-Level Contrastive-Learning-Based Multi-Branch Network for Building Change Detection from Bi-Temporal Remote Sensing Images
Buildings are fundamental elements of human environments, and detecting changes in them is crucial for land cover studies, urban expansion monitoring, and the detection of illegal construction activities. Existing methods primarily focus on pixel-level differences in bi-temporal remote sensing image...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/217 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587603771129856 |
|---|---|
| author | Shiming Li Fengtao Yan Cheng Liao Qingfeng Hu Kaifeng Ma Wei Wang Hui Zhang |
| author_facet | Shiming Li Fengtao Yan Cheng Liao Qingfeng Hu Kaifeng Ma Wei Wang Hui Zhang |
| author_sort | Shiming Li |
| collection | DOAJ |
| description | Buildings are fundamental elements of human environments, and detecting changes in them is crucial for land cover studies, urban expansion monitoring, and the detection of illegal construction activities. Existing methods primarily focus on pixel-level differences in bi-temporal remote sensing imagery. However, pseudo-changes, such as variations in non-building areas caused by differences in illumination, seasonal changes, and other factors, pose significant challenges for reliable building change detection. To address these issues, we propose a novel object-level contrastive-learning-based multi-branch network (OCL-Net) for detecting building changes by integrating bi-temporal remote sensing images. First, we design a multi-head decoder to separately extract more distinguishable building change features and auxiliary semantic features from bi-temporal images, effectively leveraging building-specific priors. Second, an object-level contrastive learning loss is designed and jointly optimized with a pixel-level similarity loss to ensure the global consistency of buildings. Finally, an attention-based discriminative feature generation and fusion block is designed to enhance the representation of multi-scale change features. We validate the effectiveness of the proposed method through comparative experiments on the publicly available WHU-CD and S2Looking datasets. Our approach achieves IoU values of 88.54% and 51.94%, respectively, surpassing state-of-the-art methods for building change detection. |
| format | Article |
| id | doaj-art-de78e03995b0413aa47e8cbe2745c84d |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-de78e03995b0413aa47e8cbe2745c84d2025-01-24T13:47:45ZengMDPI AGRemote Sensing2072-42922025-01-0117221710.3390/rs17020217Object-Level Contrastive-Learning-Based Multi-Branch Network for Building Change Detection from Bi-Temporal Remote Sensing ImagesShiming Li0Fengtao Yan1Cheng Liao2Qingfeng Hu3Kaifeng Ma4Wei Wang5Hui Zhang6Faculty of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaFaculty of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaState Key Laboratory of Intelligent Geotechnics and Tunnelling (FSDI), Xi’an 710043, ChinaFaculty of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaFaculty of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaState Key Laboratory of Intelligent Geotechnics and Tunnelling (FSDI), Xi’an 710043, ChinaFaculty of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaBuildings are fundamental elements of human environments, and detecting changes in them is crucial for land cover studies, urban expansion monitoring, and the detection of illegal construction activities. Existing methods primarily focus on pixel-level differences in bi-temporal remote sensing imagery. However, pseudo-changes, such as variations in non-building areas caused by differences in illumination, seasonal changes, and other factors, pose significant challenges for reliable building change detection. To address these issues, we propose a novel object-level contrastive-learning-based multi-branch network (OCL-Net) for detecting building changes by integrating bi-temporal remote sensing images. First, we design a multi-head decoder to separately extract more distinguishable building change features and auxiliary semantic features from bi-temporal images, effectively leveraging building-specific priors. Second, an object-level contrastive learning loss is designed and jointly optimized with a pixel-level similarity loss to ensure the global consistency of buildings. Finally, an attention-based discriminative feature generation and fusion block is designed to enhance the representation of multi-scale change features. We validate the effectiveness of the proposed method through comparative experiments on the publicly available WHU-CD and S2Looking datasets. Our approach achieves IoU values of 88.54% and 51.94%, respectively, surpassing state-of-the-art methods for building change detection.https://www.mdpi.com/2072-4292/17/2/217building change detectioncontrastive learningremote sensingbi-temporal image |
| spellingShingle | Shiming Li Fengtao Yan Cheng Liao Qingfeng Hu Kaifeng Ma Wei Wang Hui Zhang Object-Level Contrastive-Learning-Based Multi-Branch Network for Building Change Detection from Bi-Temporal Remote Sensing Images Remote Sensing building change detection contrastive learning remote sensing bi-temporal image |
| title | Object-Level Contrastive-Learning-Based Multi-Branch Network for Building Change Detection from Bi-Temporal Remote Sensing Images |
| title_full | Object-Level Contrastive-Learning-Based Multi-Branch Network for Building Change Detection from Bi-Temporal Remote Sensing Images |
| title_fullStr | Object-Level Contrastive-Learning-Based Multi-Branch Network for Building Change Detection from Bi-Temporal Remote Sensing Images |
| title_full_unstemmed | Object-Level Contrastive-Learning-Based Multi-Branch Network for Building Change Detection from Bi-Temporal Remote Sensing Images |
| title_short | Object-Level Contrastive-Learning-Based Multi-Branch Network for Building Change Detection from Bi-Temporal Remote Sensing Images |
| title_sort | object level contrastive learning based multi branch network for building change detection from bi temporal remote sensing images |
| topic | building change detection contrastive learning remote sensing bi-temporal image |
| url | https://www.mdpi.com/2072-4292/17/2/217 |
| work_keys_str_mv | AT shimingli objectlevelcontrastivelearningbasedmultibranchnetworkforbuildingchangedetectionfrombitemporalremotesensingimages AT fengtaoyan objectlevelcontrastivelearningbasedmultibranchnetworkforbuildingchangedetectionfrombitemporalremotesensingimages AT chengliao objectlevelcontrastivelearningbasedmultibranchnetworkforbuildingchangedetectionfrombitemporalremotesensingimages AT qingfenghu objectlevelcontrastivelearningbasedmultibranchnetworkforbuildingchangedetectionfrombitemporalremotesensingimages AT kaifengma objectlevelcontrastivelearningbasedmultibranchnetworkforbuildingchangedetectionfrombitemporalremotesensingimages AT weiwang objectlevelcontrastivelearningbasedmultibranchnetworkforbuildingchangedetectionfrombitemporalremotesensingimages AT huizhang objectlevelcontrastivelearningbasedmultibranchnetworkforbuildingchangedetectionfrombitemporalremotesensingimages |