Improved PSP and U-Net architectures for forest segmentation in remote sensing pictures

dc.contributor.author	Slyusar, V. I.
dc.contributor.author	Sliusar, I. I.
dc.contributor.author	Pavlenko, A.
dc.date.issued	2022-11-14
dc.description	Slyusar V., Sliusar I., Pavlenko A. Improved PSP and U-Net architectures for forest segmentation in remote sensing pictures.// IEEE 2nd Ukrainian Microwave Week (Virtual Event) IEEE UkrMW-2022, 14 – 18 November, 2022. - V. N. Karazin Kharkiv National University, Kharkiv, Ukraine. – 4 p. DOI: 10.1109/UkrMW58013.2022.10037105.
dc.description.abstract	Various PSP and U-Net architectures for forest segmentation in remote sensing pictures have been proposed and investigated. The main improvements of the proposed architectures are based on using the BathNormalization layers, replacing MaxPool2D layers with AveragePooling2D, changing Conv2DTranspose to UpSampling2D blocks, etc. For the training of neural networks was used modified dataset of 128x128 pictures based on the dataset from Kaggle. As a result of improving architecture was given the maximum segmentation accuracy of 80.8 % on the validation set of pictures.
dc.identifier.other	https://doi.org/10.1109/UkrMW58013.2022.10037105
dc.identifier.uri	https://dspace.pdau.edu.ua/handle/123456789/15236
dc.language.iso	en
dc.publisher	IEEE
dc.title	Improved PSP and U-Net architectures for forest segmentation in remote sensing pictures
dc.type	Thesis

Зараз показуємо 1 - 1 з 1

Зараз показуємо 1 - 1 з 1