Automatic Deforestation Detection based on the Deep Learning in Ukraine

Скорочена інформація про документ
dc.contributor.authorShumilo, Leonid
dc.contributor.authorLavreniuk, Mykola
dc.contributor.authorKussul, Nataliia
dc.contributor.authorShevchuk, Bella
dc.date.accessioned2022-02-03T14:03:17Z
dc.date.available2022-02-03T14:03:17Z
dc.date.issued2021
dc.description.abstractenUkraine's big problem is the disappearance of forest cover. According to the international forest monitoring project Global Forest Watch, Ukraine lost 1.08Mha of forests from 2000 to 2020. Such sad statistics are possible only due to the lack of monitoring tools for the forest industry in Ukraine. Such a tool can be created by combining Remote Sensing and Deep Learning approaches. To implement such approach for the automatic use, we combine Optical and Synthetic Aperture Radar images of the Sentinel-2 and Sentinel-1 satellite missions on which object-detection is performed using a U-Net-based neural network trained with use of the semi-supervised learning technique. This approach is being tested and shows its effectiveness in Kyiv region and going to be implemented in the same way for the Lviv, Odessa and Zakarpatya oblasts.uk
dc.format.pagerangeP. 337– 42uk
dc.identifier.citationAutomatic Deforestation Detection based on the Deep Learning in Ukraine / L. Shumilo, M. Lavreniuk, N. Kussul, B. Shevchuk // In 2021 11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS). – 2021, September. – Vol. 1. – P. 337-342.uk
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/46162
dc.language.isoenuk
dc.publisherIEEEuk
dc.subjectDeep Learninguk
dc.subjectU-Netuk
dc.subjectRemote Sensinguk
dc.subjectdeforestationuk
dc.subjectobject detectionuk
dc.titleAutomatic Deforestation Detection based on the Deep Learning in Ukraineuk
dc.typeArticleuk

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
Automatic Deforestation Detection based.pdf
Розмір:
1.18 MB
Формат:
Adobe Portable Document Format
Опис:
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
9.01 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

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