Spatially and Semantically Enhanced Siamese Network for Semantic Change Detection in High-Resolution Remote Sensing Images
Given a pair of bitemporal very high resolution (VHR) remote sensing images, the semantic change detection task aims to locate land surface changes and identify their semantic classes. The existing algorithms use independent branches to locate and identify separately without considering the associat...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9736642/ |
| _version_ | 1819047400463925248 |
|---|---|
| author | Manqi Zhao Zifei Zhao Shuai Gong Yunfei Liu Jian Yang Xiong Xiong Shengyang Li |
| author_facet | Manqi Zhao Zifei Zhao Shuai Gong Yunfei Liu Jian Yang Xiong Xiong Shengyang Li |
| author_sort | Manqi Zhao |
| collection | DOAJ |
| description | Given a pair of bitemporal very high resolution (VHR) remote sensing images, the semantic change detection task aims to locate land surface changes and identify their semantic classes. The existing algorithms use independent branches to locate and identify separately without considering the association between branches. In this article, we propose an end-to-end spatially and semantically enhanced Siamese network (SSESN) for semantic change detection. The SSESN aggregates the rich spatial and semantic information in the VHR image through a designed spatial and semantic feature aggregation module. Additionally, a change-aware module is proposed to decouple the aggregated features. Features in the binary branch are fused to the semantic branches as prior location information. This allows the spatially enhanced features to predict changed regions and the semantically enhanced features to refine the region categorizations. Experimental results show that our method provides comparable results with the state-of-the-art binary change detection and semantic change detection algorithms. |
| first_indexed | 2024-12-21T10:59:46Z |
| format | Article |
| id | doaj.art-17d4dd30b6f8473884aa0363dbc928f2 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-21T10:59:46Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-17d4dd30b6f8473884aa0363dbc928f22022-12-21T19:06:22ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01152563257310.1109/JSTARS.2022.31595289736642Spatially and Semantically Enhanced Siamese Network for Semantic Change Detection in High-Resolution Remote Sensing ImagesManqi Zhao0https://orcid.org/0000-0002-5953-0079Zifei Zhao1Shuai Gong2https://orcid.org/0000-0002-0657-9370Yunfei Liu3Jian Yang4Xiong Xiong5https://orcid.org/0000-0002-7178-5752Shengyang Li6https://orcid.org/0000-0002-9888-9869Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, ChinaGiven a pair of bitemporal very high resolution (VHR) remote sensing images, the semantic change detection task aims to locate land surface changes and identify their semantic classes. The existing algorithms use independent branches to locate and identify separately without considering the association between branches. In this article, we propose an end-to-end spatially and semantically enhanced Siamese network (SSESN) for semantic change detection. The SSESN aggregates the rich spatial and semantic information in the VHR image through a designed spatial and semantic feature aggregation module. Additionally, a change-aware module is proposed to decouple the aggregated features. Features in the binary branch are fused to the semantic branches as prior location information. This allows the spatially enhanced features to predict changed regions and the semantically enhanced features to refine the region categorizations. Experimental results show that our method provides comparable results with the state-of-the-art binary change detection and semantic change detection algorithms.https://ieeexplore.ieee.org/document/9736642/Change aware (CA)change detectionremote sensing imagesiamese networkspatial and semantic aggregation |
| spellingShingle | Manqi Zhao Zifei Zhao Shuai Gong Yunfei Liu Jian Yang Xiong Xiong Shengyang Li Spatially and Semantically Enhanced Siamese Network for Semantic Change Detection in High-Resolution Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change aware (CA) change detection remote sensing image siamese network spatial and semantic aggregation |
| title | Spatially and Semantically Enhanced Siamese Network for Semantic Change Detection in High-Resolution Remote Sensing Images |
| title_full | Spatially and Semantically Enhanced Siamese Network for Semantic Change Detection in High-Resolution Remote Sensing Images |
| title_fullStr | Spatially and Semantically Enhanced Siamese Network for Semantic Change Detection in High-Resolution Remote Sensing Images |
| title_full_unstemmed | Spatially and Semantically Enhanced Siamese Network for Semantic Change Detection in High-Resolution Remote Sensing Images |
| title_short | Spatially and Semantically Enhanced Siamese Network for Semantic Change Detection in High-Resolution Remote Sensing Images |
| title_sort | spatially and semantically enhanced siamese network for semantic change detection in high resolution remote sensing images |
| topic | Change aware (CA) change detection remote sensing image siamese network spatial and semantic aggregation |
| url | https://ieeexplore.ieee.org/document/9736642/ |
| work_keys_str_mv | AT manqizhao spatiallyandsemanticallyenhancedsiamesenetworkforsemanticchangedetectioninhighresolutionremotesensingimages AT zifeizhao spatiallyandsemanticallyenhancedsiamesenetworkforsemanticchangedetectioninhighresolutionremotesensingimages AT shuaigong spatiallyandsemanticallyenhancedsiamesenetworkforsemanticchangedetectioninhighresolutionremotesensingimages AT yunfeiliu spatiallyandsemanticallyenhancedsiamesenetworkforsemanticchangedetectioninhighresolutionremotesensingimages AT jianyang spatiallyandsemanticallyenhancedsiamesenetworkforsemanticchangedetectioninhighresolutionremotesensingimages AT xiongxiong spatiallyandsemanticallyenhancedsiamesenetworkforsemanticchangedetectioninhighresolutionremotesensingimages AT shengyangli spatiallyandsemanticallyenhancedsiamesenetworkforsemanticchangedetectioninhighresolutionremotesensingimages |