DRMNet: Difference Image Reconstruction Enhanced Multiresolution Network for Optical Change Detection
Change detection in satellite images is an important research area as it has a wide range of applications in natural resource monitoring, geo-hazard detections, urban planning, etc. Identifying physical changes on the ground and avoiding spurious changes due to other reasons like co-registration iss...
| 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/9775045/ |
| _version_ | 1818229016899878912 |
|---|---|
| author | Avinash Chouhan Arijit Sur Dibyajyoti Chutia |
| author_facet | Avinash Chouhan Arijit Sur Dibyajyoti Chutia |
| author_sort | Avinash Chouhan |
| collection | DOAJ |
| description | Change detection in satellite images is an important research area as it has a wide range of applications in natural resource monitoring, geo-hazard detections, urban planning, etc. Identifying physical changes on the ground and avoiding spurious changes due to other reasons like co-registration issues, change in illumination conditions, sun angle, and presence of cloud and fog is a challenging task. This work proposes a multitask learning based change detection model where two parallel pipeline architectures predict change map and image difference. The proposed model takes two images and their difference as input and provides them to a backbone network (BN). The output of the BN is fed into the proposed multiscale attention module for the effective identification of changes in multitemporal and very high-resolution aerial images. In another parallel path, the output of the BN is downsampled and passed to the proposed deconvolution with a subpixel convolution module to generate image difference. Two loss functions are utilized in two parallel paths to train the overall model in an end-to-end supervised setting. A comprehensive set of experiments have been carried out, and the results reveal that the proposed DRMNet model has achieved an F1 score improvement of 1.66% in CDD, 1.61% in SYSU, and 0.14% in LEVIR-CD datasets. It achieved an F1 score of 86.11% for the BCDD dataset with the new test image. |
| first_indexed | 2024-12-12T10:11:54Z |
| format | Article |
| id | doaj.art-19e1af8f9c12407d999e80dc2a92df33 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-12T10:11:54Z |
| 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-19e1af8f9c12407d999e80dc2a92df332022-12-22T00:27:46ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01154014402610.1109/JSTARS.2022.31747809775045DRMNet: Difference Image Reconstruction Enhanced Multiresolution Network for Optical Change DetectionAvinash Chouhan0https://orcid.org/0000-0002-8375-5374Arijit Sur1Dibyajyoti Chutia2North Eastern Space Applications Centre, Meghalaya, IndiaDepartment of Computer Science and Engineering, Indian Institute of Technology, Guwahati, IndiaNorth Eastern Space Applications Centre, Meghalaya, IndiaChange detection in satellite images is an important research area as it has a wide range of applications in natural resource monitoring, geo-hazard detections, urban planning, etc. Identifying physical changes on the ground and avoiding spurious changes due to other reasons like co-registration issues, change in illumination conditions, sun angle, and presence of cloud and fog is a challenging task. This work proposes a multitask learning based change detection model where two parallel pipeline architectures predict change map and image difference. The proposed model takes two images and their difference as input and provides them to a backbone network (BN). The output of the BN is fed into the proposed multiscale attention module for the effective identification of changes in multitemporal and very high-resolution aerial images. In another parallel path, the output of the BN is downsampled and passed to the proposed deconvolution with a subpixel convolution module to generate image difference. Two loss functions are utilized in two parallel paths to train the overall model in an end-to-end supervised setting. A comprehensive set of experiments have been carried out, and the results reveal that the proposed DRMNet model has achieved an F1 score improvement of 1.66% in CDD, 1.61% in SYSU, and 0.14% in LEVIR-CD datasets. It achieved an F1 score of 86.11% for the BCDD dataset with the new test image.https://ieeexplore.ieee.org/document/9775045/Change detection (CD)difference image reconstructionmultiscale attentionoptical remote sensing |
| spellingShingle | Avinash Chouhan Arijit Sur Dibyajyoti Chutia DRMNet: Difference Image Reconstruction Enhanced Multiresolution Network for Optical Change Detection IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection (CD) difference image reconstruction multiscale attention optical remote sensing |
| title | DRMNet: Difference Image Reconstruction Enhanced Multiresolution Network for Optical Change Detection |
| title_full | DRMNet: Difference Image Reconstruction Enhanced Multiresolution Network for Optical Change Detection |
| title_fullStr | DRMNet: Difference Image Reconstruction Enhanced Multiresolution Network for Optical Change Detection |
| title_full_unstemmed | DRMNet: Difference Image Reconstruction Enhanced Multiresolution Network for Optical Change Detection |
| title_short | DRMNet: Difference Image Reconstruction Enhanced Multiresolution Network for Optical Change Detection |
| title_sort | drmnet difference image reconstruction enhanced multiresolution network for optical change detection |
| topic | Change detection (CD) difference image reconstruction multiscale attention optical remote sensing |
| url | https://ieeexplore.ieee.org/document/9775045/ |
| work_keys_str_mv | AT avinashchouhan drmnetdifferenceimagereconstructionenhancedmultiresolutionnetworkforopticalchangedetection AT arijitsur drmnetdifferenceimagereconstructionenhancedmultiresolutionnetworkforopticalchangedetection AT dibyajyotichutia drmnetdifferenceimagereconstructionenhancedmultiresolutionnetworkforopticalchangedetection |