Single-Polarized SAR Image Preprocessing in Scope of Transfer Learning for Oil Spill Detection

Скорочена інформація про документ
dc.contributor.authorKussul, Nataliia
dc.contributor.authorKuzin, Volodymyr
dc.contributor.authorSalii, Yevhenii
dc.contributor.authorYailymov, Bohdan
dc.contributor.authorShelestov, Andrii
dc.date.accessioned2025-01-02T13:56:19Z
dc.date.available2025-01-02T13:56:19Z
dc.date.issued2024
dc.description.abstractThis study proposes a novel preprocessing approach for improving oil spill detection from Synthetic Aperture Radar (SAR) satellite imagery using deep learning models. A transfer learning approach with the LinkNet segmentation architecture pre-trained on ImageNet is employed. The model is trained on Sentinel-1 SAR data from 2018–2023 using a designed preprocessing pipeline that converts the single-channel SAR input to a 3-channel RGB image. The proposed preprocessing involves transforming the original SAR intensity values to a normal distribution, extracting nonlinear features, and encoding them into the RGB channels. Quantitative results on a test set show the preprocessed model achieves an improvement of 0.038 in F1-score and 0.054 in Intersection over Union compared to the original dB-scale preprocessing approach. Qualitative evaluation on independent SAR scenes from the Mediterranean Sea also demonstrates the model's ability to generalize to new geographic areas after training on data from other regions. The proposed preprocessing technique shows promising performance gains for automatic oil spill segmentation from SAR imagery and potential for integration with other preprocessing methods and task-specific neural network architectures.
dc.format.extent6 p.
dc.identifier.citationSingle-Polarized SAR Image Preprocessing in Scope of Transfer Learning for Oil Spill Detection / Nataliia Kussul, Volodymyr Kuzin, Yevhenii Salii, Bohdan Yailymov, Andrii Shelestov // IEEE Intelligent Systems IS’24 : 12th International Conference, Varna, Bulgaria, August 29-31, 2024. - Varna, 2024. - 6 p.
dc.identifier.doihttps://doi.org/10.1109/IS61756.2024.10705228
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/71519
dc.language.isoen
dc.publisherIEEE IM/CS/SMC
dc.publisher.placeVarna
dc.relation.ispartofIEEE Intelligent Systems IS’24 : 12th International Conference, Varna, Bulgaria, August 29-31, 2024
dc.subjectoil spill detection
dc.subjectremote sensing
dc.subjectsatellite imagery
dc.subjectsynthetic aperture radar (SAR)
dc.subjectdeep learning
dc.subjectimage preprocessing
dc.subjectconvolutional neural networks
dc.subjecttransfer learning
dc.titleSingle-Polarized SAR Image Preprocessing in Scope of Transfer Learning for Oil Spill Detection
dc.typeArticle

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
Single-polarized_SAR_Image.pdf
Розмір:
1.45 MB
Формат:
Adobe Portable Document Format
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
8.98 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Матеріали конференцій, семінарів і т.п. (ММАД)