FUSING SENTINEL-1 AND SENTINEL-2 IMAGES WITH TRANSFORMER-BASED NETWORK FOR DEFORESTATION DETECTION IN THE BRAZILIAN AMAZON UNDER DIVERSE CLOUD CONDITIONS
Deforestation is an environmental problem that significantly impacts biodiversity and climate change. Deforestation detection is usually performed using optical remote sensing images, limiting the detection capability to the dry season in which images are not comprised of clouds. In this work, we pr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-12-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-annals.copernicus.org/articles/X-1-W1-2023/999/2023/isprs-annals-X-1-W1-2023-999-2023.pdf |
| _version_ | 1797403386304266240 |
|---|---|
| author | F. Ferrari M. P. Ferreira R. Q. Feitosa |
| author_facet | F. Ferrari M. P. Ferreira R. Q. Feitosa |
| author_sort | F. Ferrari |
| collection | DOAJ |
| description | Deforestation is an environmental problem that significantly impacts biodiversity and climate change. Deforestation detection is usually performed using optical remote sensing images, limiting the detection capability to the dry season in which images are not comprised of clouds. In this work, we proposed Transformer-based models to fuse bitemporal Sentinel-1 and Sentinel-2 images to identify new deforestation areas in the Brazilian Amazon area under diverse cloud conditions. The models were evaluated considering clear and cloud-covered pixel conditions. The results confirmed previous works in which the fusion of optical and SAR images improved deforestation detection capabilities. We also concluded that the better Transformer-based network reached the F1-Score of 0.92, considering all pixels, outperforming the better Convolution-based which reached the F1-Score of 0.86, without increasing the training and prediction times. |
| first_indexed | 2024-03-09T02:38:36Z |
| format | Article |
| id | doaj.art-a59b9ee4e1094e93b836563100972348 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-03-09T02:38:36Z |
| publishDate | 2023-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-a59b9ee4e1094e93b8365631009723482023-12-06T07:54:20ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502023-12-01X-1-W1-2023999100610.5194/isprs-annals-X-1-W1-2023-999-2023FUSING SENTINEL-1 AND SENTINEL-2 IMAGES WITH TRANSFORMER-BASED NETWORK FOR DEFORESTATION DETECTION IN THE BRAZILIAN AMAZON UNDER DIVERSE CLOUD CONDITIONSF. Ferrari0M. P. Ferreira1R. Q. Feitosa2Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Rio de Janeiro, RJ, BrazilMilitary Institute of Engineering, Rio de Janeiro, RJ, BrazilPontifical Catholic University of Rio de Janeiro (PUC-Rio), Rio de Janeiro, RJ, BrazilDeforestation is an environmental problem that significantly impacts biodiversity and climate change. Deforestation detection is usually performed using optical remote sensing images, limiting the detection capability to the dry season in which images are not comprised of clouds. In this work, we proposed Transformer-based models to fuse bitemporal Sentinel-1 and Sentinel-2 images to identify new deforestation areas in the Brazilian Amazon area under diverse cloud conditions. The models were evaluated considering clear and cloud-covered pixel conditions. The results confirmed previous works in which the fusion of optical and SAR images improved deforestation detection capabilities. We also concluded that the better Transformer-based network reached the F1-Score of 0.92, considering all pixels, outperforming the better Convolution-based which reached the F1-Score of 0.86, without increasing the training and prediction times.https://isprs-annals.copernicus.org/articles/X-1-W1-2023/999/2023/isprs-annals-X-1-W1-2023-999-2023.pdf |
| spellingShingle | F. Ferrari M. P. Ferreira R. Q. Feitosa FUSING SENTINEL-1 AND SENTINEL-2 IMAGES WITH TRANSFORMER-BASED NETWORK FOR DEFORESTATION DETECTION IN THE BRAZILIAN AMAZON UNDER DIVERSE CLOUD CONDITIONS ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | FUSING SENTINEL-1 AND SENTINEL-2 IMAGES WITH TRANSFORMER-BASED NETWORK FOR DEFORESTATION DETECTION IN THE BRAZILIAN AMAZON UNDER DIVERSE CLOUD CONDITIONS |
| title_full | FUSING SENTINEL-1 AND SENTINEL-2 IMAGES WITH TRANSFORMER-BASED NETWORK FOR DEFORESTATION DETECTION IN THE BRAZILIAN AMAZON UNDER DIVERSE CLOUD CONDITIONS |
| title_fullStr | FUSING SENTINEL-1 AND SENTINEL-2 IMAGES WITH TRANSFORMER-BASED NETWORK FOR DEFORESTATION DETECTION IN THE BRAZILIAN AMAZON UNDER DIVERSE CLOUD CONDITIONS |
| title_full_unstemmed | FUSING SENTINEL-1 AND SENTINEL-2 IMAGES WITH TRANSFORMER-BASED NETWORK FOR DEFORESTATION DETECTION IN THE BRAZILIAN AMAZON UNDER DIVERSE CLOUD CONDITIONS |
| title_short | FUSING SENTINEL-1 AND SENTINEL-2 IMAGES WITH TRANSFORMER-BASED NETWORK FOR DEFORESTATION DETECTION IN THE BRAZILIAN AMAZON UNDER DIVERSE CLOUD CONDITIONS |
| title_sort | fusing sentinel 1 and sentinel 2 images with transformer based network for deforestation detection in the brazilian amazon under diverse cloud conditions |
| url | https://isprs-annals.copernicus.org/articles/X-1-W1-2023/999/2023/isprs-annals-X-1-W1-2023-999-2023.pdf |
| work_keys_str_mv | AT fferrari fusingsentinel1andsentinel2imageswithtransformerbasednetworkfordeforestationdetectioninthebrazilianamazonunderdiversecloudconditions AT mpferreira fusingsentinel1andsentinel2imageswithtransformerbasednetworkfordeforestationdetectioninthebrazilianamazonunderdiversecloudconditions AT rqfeitosa fusingsentinel1andsentinel2imageswithtransformerbasednetworkfordeforestationdetectioninthebrazilianamazonunderdiversecloudconditions |