Full article - Open Access.

Idioma principal | Segundo idioma

OIL SPILL DETECTION UTILIZING UNET-R IMAGE SEGMENTATION AND SENTINEL I DATA

OIL SPILL DETECTION UTILIZING UNET-R IMAGE SEGMENTATION AND SENTINEL I DATA

Goes, Pedro Henrique Meirelles e ; Sena, Andressa Reis Barretto da Silva ; Mendonça, Luis Felipe Ferreira de ; Queiroz, Rafael Santana ;

Full article:

Marine ecosystems are significantly threatened by pollution, with the offshore oil and gas industry as a major contributor. Daily occurrences of oil spills exacerbate the issue, making the detection and monitoring of these petroleum spills crucial to mitigating their detrimental impact on the environment. This paper proposes using a UNET-R architecture that combines the strengths of both the transformer and the encoder-decoder structure characteristic of "U-shaped" network design and the Sentinel I image dataset to accurately segment oil scattered in the ocean. The model achieved promising results, obtaining an F1 score of 86%. These findings demonstrate the potential of the proposed approach in effectively detecting and monitoring oil spills in marine environments.

Full article:

Marine ecosystems are significantly threatened by pollution, with the offshore oil and gas industry as a major contributor. Daily occurrences of oil spills exacerbate the issue, making the detection and monitoring of these petroleum spills crucial to mitigating their detrimental impact on the environment. This paper proposes using a UNET-R architecture that combines the strengths of both the transformer and the encoder-decoder structure characteristic of "U-shaped" network design and the Sentinel I image dataset to accurately segment oil scattered in the ocean. The model achieved promising results, obtaining an F1 score of 86%. These findings demonstrate the potential of the proposed approach in effectively detecting and monitoring oil spills in marine environments.

Palavras-chave: Deep learning; UNET-R; Segmentation; Oil Spill,

Palavras-chave: Deep learning; UNET-R; Segmentation; Oil Spill,

DOI: 10.5151/siintec2023-306325

Referências bibliográficas
  • [1] HATAMIZADEH, Ali et al. Transformers for 3D Medical Image Segmentation; Vanderbilt University. 202 HASIMOTO-BELTRAN, Rogelio et al. Ocean oil spill detection from SAR images based on multi-channel deep learning semantic segmentation. 14 December 2022. ZHANG, Yanan; ZHU, Qiqi; GUAN, Qingfeng. Oil Spill Detection Based on CBD-NET Using Marine SAR Image. In: Sensing Symposium. China University of Geosciences, Wuhan, China. IEEE, 202 SHABAN, Mohamed et al. A Deep-Learning Framework for the Detection of Oil Spills from SAR Data. MDPI. 28 March 202 MOURA, Najla Vilar Aires de et al. Deep-water oil-spill monitoring and recurrence analysis in the Brazilian territory using Sentinel-1 time series and deep learning. 20 January 2022. CHEHRESA, Saeed et al. Optimum Features Selection for oil Spill Detection in SAR Image. Published: 19 February 2016 LIU, Xiaojian et al. Multi-source knowledge graph reasoning for ocean oil spill detection from satellite SAR images. 10 December 2022.
Como citar:

Goes, Pedro Henrique Meirelles e ; Sena, Andressa Reis Barretto da Silva; Mendonça, Luis Felipe Ferreira de ; Queiroz, Rafael Santana ; "OIL SPILL DETECTION UTILIZING UNET-R IMAGE SEGMENTATION AND SENTINEL I DATA", p. 485-492 . In: . São Paulo: Blucher, 2023.
ISSN 2357-7592, DOI 10.5151/siintec2023-306325

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações