https://libeldoc.bsuir.by/handle/123456789/45943
Title: | Augmentation Tools for Object Detection in Satellite Images by Using U-Net Neural Network |
Authors: | Zhuk, A. Ablameyko, S. Абламейко, С. В. |
Keywords: | материалы конференций;conference proceedings;object detection;satellite images;neural network;U-Net;data set;data augmentations |
Issue Date: | 2021 |
Publisher: | UIIP NASB |
Citation: | Zhuk, A. Augmentation Tools for Object Detection in Satellite Images by Using U-Net Neural Network / Zhuk A., Ablameyko S. // Pattern Recognition and Information Processing (PRIP'2021) = Распознавание образов и обработка информации (2021) : Proceedings of the 15th International Conference, 21–24 Sept. 2021, Minsk, Belarus / United Institute of Informatics Problems of the National Academy of Sciences of Belarus. – Minsk, 2021. – P. 119–122. |
Abstract: | The paper proposes an approach to detect discrete objects on images, namely buildings using the U-NET neural network. The main idea of our approach is to use additional augmentations during model learning. The experiments carried out have shown good results. |
URI: | https://libeldoc.bsuir.by/handle/123456789/45943 |
Appears in Collections: | Pattern Recognition and Information Processing (PRIP'2021) = Распознавание образов и обработка информации (2021) |
File | Description | Size | Format | |
---|---|---|---|---|
Zhuk_Augmentation.pdf | 1.23 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.