Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing Images
High-resolution remote sensing images with rich land surface structure can provide data support for accurately understanding more detailed change information of land cover and land use (LCLU) at different times. In this study, we present a novel scene change understanding framework for remote sensin...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3709 |
| _version_ | 1797440758489284608 |
|---|---|
| author | Sihan Yang Fei Song Gwanggil Jeon Rui Sun |
| author_facet | Sihan Yang Fei Song Gwanggil Jeon Rui Sun |
| author_sort | Sihan Yang |
| collection | DOAJ |
| description | High-resolution remote sensing images with rich land surface structure can provide data support for accurately understanding more detailed change information of land cover and land use (LCLU) at different times. In this study, we present a novel scene change understanding framework for remote sensing which includes scene classification and change detection. To enhance the feature representation of images in scene classification, a robust label semantic relation learning (LSRL) network based on EfficientNet is presented for scene classification. It consists of a semantic relation learning module based on graph convolutional networks and a joint expression learning framework based on similarity. Since the bi-temporal remote sensing image pairs include spectral information in both temporal and spatial dimensions, land cover and land use change monitoring can be improved by using the relationship between different spatial and temporal locations. Therefore, a change detection method based on swin transformer blocks (STB-CD) is presented to obtain contextual relationships between targets. The experimental results on the LEVIR-CD, NWPU-RESISC45, and AID datasets demonstrate the superiority of LSRL and STB-CD over other state-of-the-art methods. |
| first_indexed | 2024-03-09T12:13:58Z |
| format | Article |
| id | doaj.art-843c3ce735774a4087b15cc5fdaf4243 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T12:13:58Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-843c3ce735774a4087b15cc5fdaf42432023-11-30T22:49:15ZengMDPI AGRemote Sensing2072-42922022-08-011415370910.3390/rs14153709Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing ImagesSihan Yang0Fei Song1Gwanggil Jeon2Rui Sun3School of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611700, ChinaDepartment of Embedded Systems Engineering, Incheon National University, Incheon 22012, KoreaUnit 63636 of the Chinese People’s Liberation Army, Lanzhou 735000, ChinaHigh-resolution remote sensing images with rich land surface structure can provide data support for accurately understanding more detailed change information of land cover and land use (LCLU) at different times. In this study, we present a novel scene change understanding framework for remote sensing which includes scene classification and change detection. To enhance the feature representation of images in scene classification, a robust label semantic relation learning (LSRL) network based on EfficientNet is presented for scene classification. It consists of a semantic relation learning module based on graph convolutional networks and a joint expression learning framework based on similarity. Since the bi-temporal remote sensing image pairs include spectral information in both temporal and spatial dimensions, land cover and land use change monitoring can be improved by using the relationship between different spatial and temporal locations. Therefore, a change detection method based on swin transformer blocks (STB-CD) is presented to obtain contextual relationships between targets. The experimental results on the LEVIR-CD, NWPU-RESISC45, and AID datasets demonstrate the superiority of LSRL and STB-CD over other state-of-the-art methods.https://www.mdpi.com/2072-4292/14/15/3709high-resolution remote sensing imagesLCLUscene change understandinglabel semantic relationchange detectiontransformer |
| spellingShingle | Sihan Yang Fei Song Gwanggil Jeon Rui Sun Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing Images Remote Sensing high-resolution remote sensing images LCLU scene change understanding label semantic relation change detection transformer |
| title | Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing Images |
| title_full | Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing Images |
| title_fullStr | Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing Images |
| title_full_unstemmed | Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing Images |
| title_short | Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing Images |
| title_sort | scene changes understanding framework based on graph convolutional networks and swin transformer blocks for monitoring lclu using high resolution remote sensing images |
| topic | high-resolution remote sensing images LCLU scene change understanding label semantic relation change detection transformer |
| url | https://www.mdpi.com/2072-4292/14/15/3709 |
| work_keys_str_mv | AT sihanyang scenechangesunderstandingframeworkbasedongraphconvolutionalnetworksandswintransformerblocksformonitoringlcluusinghighresolutionremotesensingimages AT feisong scenechangesunderstandingframeworkbasedongraphconvolutionalnetworksandswintransformerblocksformonitoringlcluusinghighresolutionremotesensingimages AT gwanggiljeon scenechangesunderstandingframeworkbasedongraphconvolutionalnetworksandswintransformerblocksformonitoringlcluusinghighresolutionremotesensingimages AT ruisun scenechangesunderstandingframeworkbasedongraphconvolutionalnetworksandswintransformerblocksformonitoringlcluusinghighresolutionremotesensingimages |