SFSCDNet: A Deep Learning Model With Spatial Flow-Based Semantic Change Detection From Bi-Temporal Satellite Images
Semantic change detection in remote sensing imagery plays a pivotal role in urban planning, environmental monitoring, and disaster assessment applications. Existing deep learning-based methods, particularly those relying on triple-branch architectures, often struggle to accurately localize and predi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10807279/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540553460318208 |
|---|---|
| author | K. S. Basavaraju N. Sravya Vibha Damodara Kevala Shilpa Suresh Shyam Lal |
| author_facet | K. S. Basavaraju N. Sravya Vibha Damodara Kevala Shilpa Suresh Shyam Lal |
| author_sort | K. S. Basavaraju |
| collection | DOAJ |
| description | Semantic change detection in remote sensing imagery plays a pivotal role in urban planning, environmental monitoring, and disaster assessment applications. Existing deep learning-based methods, particularly those relying on triple-branch architectures, often struggle to accurately localize and predict changes in complex spatial environments characterized by diverse land-cover types. To overcome these limitations, this paper proposes a novel network called the Spatial Flow-based Semantic Change Detection Network. This network processes bi-temporal satellite images using a dual-encoder, triple-decoder architecture that progressively refines spatial features at each network stage, improving semantic change detection results. The Attention-Based Siamese Encoder, Cascaded Convolutional Attention Fusion Block, Cascaded Convolutional Attention Refinement Block and Differentiable Binarization layer helps in improving semantic change detection performance. Experimental results of proposed network on the SECOND dataset demonstrate that the proposed model significantly improves the ability to localize critical changes and distinguish between change and no-change regions. The proposed network achieves an overall accuracy of 86.32%, a mean Intersection over Union of 70.33%, a Separated Kappa of 21.21%, and an F1-score for semantic change detection of 66.01%, with a score of 35.94%. These results represent substantial improvements over previous state-of-the-art models, including a 0.26% increase in overall accuracy, a 2.21% increase in mean Intersection over Union, a 2.62% enhancement in Separated Kappa, and a 3.6% improvement in F1-score for semantic change detection compared to the best-performing models. Notably, the proposed network achieves these results with only 14.56 million parameters, making it more effective and efficient than its competitors, which utilize over 22 million parameters. |
| format | Article |
| id | doaj-art-b806600ed665468fbff06981b8539173 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b806600ed665468fbff06981b85391732025-02-05T00:00:46ZengIEEEIEEE Access2169-35362024-01-011219503219505310.1109/ACCESS.2024.352042810807279SFSCDNet: A Deep Learning Model With Spatial Flow-Based Semantic Change Detection From Bi-Temporal Satellite ImagesK. S. Basavaraju0https://orcid.org/0000-0002-2755-595XN. Sravya1https://orcid.org/0009-0009-3823-1908Vibha Damodara Kevala2Shilpa Suresh3https://orcid.org/0000-0003-1796-5995Shyam Lal4https://orcid.org/0000-0002-4355-6354Department of Electronics and Communication Engineering, National Institute of Technology Karnataka, Surathkal, Mangaluru, IndiaDepartment of Electronics and Communication Engineering, National Institute of Technology Karnataka, Surathkal, Mangaluru, IndiaDepartment of Electronics and Communication Engineering, National Institute of Technology Karnataka, Surathkal, Mangaluru, IndiaDepartment of Mechatronics, Manipal Institute of Technology, Manipal Academy of Higher Education, Udupi, Karnataka, IndiaDepartment of Electronics and Communication Engineering, National Institute of Technology Karnataka, Surathkal, Mangaluru, IndiaSemantic change detection in remote sensing imagery plays a pivotal role in urban planning, environmental monitoring, and disaster assessment applications. Existing deep learning-based methods, particularly those relying on triple-branch architectures, often struggle to accurately localize and predict changes in complex spatial environments characterized by diverse land-cover types. To overcome these limitations, this paper proposes a novel network called the Spatial Flow-based Semantic Change Detection Network. This network processes bi-temporal satellite images using a dual-encoder, triple-decoder architecture that progressively refines spatial features at each network stage, improving semantic change detection results. The Attention-Based Siamese Encoder, Cascaded Convolutional Attention Fusion Block, Cascaded Convolutional Attention Refinement Block and Differentiable Binarization layer helps in improving semantic change detection performance. Experimental results of proposed network on the SECOND dataset demonstrate that the proposed model significantly improves the ability to localize critical changes and distinguish between change and no-change regions. The proposed network achieves an overall accuracy of 86.32%, a mean Intersection over Union of 70.33%, a Separated Kappa of 21.21%, and an F1-score for semantic change detection of 66.01%, with a score of 35.94%. These results represent substantial improvements over previous state-of-the-art models, including a 0.26% increase in overall accuracy, a 2.21% increase in mean Intersection over Union, a 2.62% enhancement in Separated Kappa, and a 3.6% improvement in F1-score for semantic change detection compared to the best-performing models. Notably, the proposed network achieves these results with only 14.56 million parameters, making it more effective and efficient than its competitors, which utilize over 22 million parameters.https://ieeexplore.ieee.org/document/10807279/Deep learningchange detectionbinary change detectionsemantic change detectionremote sensingsatellite images |
| spellingShingle | K. S. Basavaraju N. Sravya Vibha Damodara Kevala Shilpa Suresh Shyam Lal SFSCDNet: A Deep Learning Model With Spatial Flow-Based Semantic Change Detection From Bi-Temporal Satellite Images IEEE Access Deep learning change detection binary change detection semantic change detection remote sensing satellite images |
| title | SFSCDNet: A Deep Learning Model With Spatial Flow-Based Semantic Change Detection From Bi-Temporal Satellite Images |
| title_full | SFSCDNet: A Deep Learning Model With Spatial Flow-Based Semantic Change Detection From Bi-Temporal Satellite Images |
| title_fullStr | SFSCDNet: A Deep Learning Model With Spatial Flow-Based Semantic Change Detection From Bi-Temporal Satellite Images |
| title_full_unstemmed | SFSCDNet: A Deep Learning Model With Spatial Flow-Based Semantic Change Detection From Bi-Temporal Satellite Images |
| title_short | SFSCDNet: A Deep Learning Model With Spatial Flow-Based Semantic Change Detection From Bi-Temporal Satellite Images |
| title_sort | sfscdnet a deep learning model with spatial flow based semantic change detection from bi temporal satellite images |
| topic | Deep learning change detection binary change detection semantic change detection remote sensing satellite images |
| url | https://ieeexplore.ieee.org/document/10807279/ |
| work_keys_str_mv | AT ksbasavaraju sfscdnetadeeplearningmodelwithspatialflowbasedsemanticchangedetectionfrombitemporalsatelliteimages AT nsravya sfscdnetadeeplearningmodelwithspatialflowbasedsemanticchangedetectionfrombitemporalsatelliteimages AT vibhadamodarakevala sfscdnetadeeplearningmodelwithspatialflowbasedsemanticchangedetectionfrombitemporalsatelliteimages AT shilpasuresh sfscdnetadeeplearningmodelwithspatialflowbasedsemanticchangedetectionfrombitemporalsatelliteimages AT shyamlal sfscdnetadeeplearningmodelwithspatialflowbasedsemanticchangedetectionfrombitemporalsatelliteimages |