Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttion

To identify and classify objects on images obtained using UAV imaging and orbital-based imaging, a neural network classification model based on the use of an autoencoder and built on the architecture of an ensemble of multilayer perceptrons is proposed. Additionally, at the stage of highlighting inf...

Full description

Saved in:
Bibliographic Details
Main Authors: A. A. Doudkin, V. V. Ganchenko, A. V. Inyutin, E. E. Marushko
Format: Article
Language:English
Published: Belarusian National Technical University 2023-02-01
Series:Системный анализ и прикладная информатика
Subjects:
Online Access:https://sapi.bntu.by/jour/article/view/591
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849403936712163328
author A. A. Doudkin
V. V. Ganchenko
A. V. Inyutin
E. E. Marushko
author_facet A. A. Doudkin
V. V. Ganchenko
A. V. Inyutin
E. E. Marushko
author_sort A. A. Doudkin
collection DOAJ
description To identify and classify objects on images obtained using UAV imaging and orbital-based imaging, a neural network classification model based on the use of an autoencoder and built on the architecture of an ensemble of multilayer perceptrons is proposed. Additionally, at the stage of highlighting informative features, is added a color information, which is based on the per-channel histograms and is invariant to the scale and rotations of the image. The model is implemented using the Keras library. The use of the proposed model for classification into four classes: “Fire”, “Smoke”, “Vegetation” and “Buildings”, allows to achieve a classification accuracy above 99%.
format Article
id doaj-art-cc58bac5418240b28ade47e81e4b1fae
institution Kabale University
issn 2309-4923
2414-0481
language English
publishDate 2023-02-01
publisher Belarusian National Technical University
record_format Article
series Системный анализ и прикладная информатика
spelling doaj-art-cc58bac5418240b28ade47e81e4b1fae2025-08-20T03:37:08ZengBelarusian National Technical UniversityСистемный анализ и прикладная информатика2309-49232414-04812023-02-0104303710.21122/2309-4923-2022-4-30-37440Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttionA. A. Doudkin0V. V. Ganchenko1A. V. Inyutin2E. E. Marushko3United Institute of Informatics Problems of the National Academy of Sciences of BelarusUnited Institute of Informatics Problems of the National Academy of Sciences of BelarusUnited Institute of Informatics Problems of the National Academy of Sciences of BelarusUnited Institute of Informatics Problems of the National Academy of Sciences of BelarusTo identify and classify objects on images obtained using UAV imaging and orbital-based imaging, a neural network classification model based on the use of an autoencoder and built on the architecture of an ensemble of multilayer perceptrons is proposed. Additionally, at the stage of highlighting informative features, is added a color information, which is based on the per-channel histograms and is invariant to the scale and rotations of the image. The model is implemented using the Keras library. The use of the proposed model for classification into four classes: “Fire”, “Smoke”, “Vegetation” and “Buildings”, allows to achieve a classification accuracy above 99%.https://sapi.bntu.by/jour/article/view/591metal fracturetexture featuresmacrogeometric descriptors
spellingShingle A. A. Doudkin
V. V. Ganchenko
A. V. Inyutin
E. E. Marushko
Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttion
Системный анализ и прикладная информатика
metal fracture
texture features
macrogeometric descriptors
title Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttion
title_full Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttion
title_fullStr Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttion
title_full_unstemmed Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttion
title_short Identification and classification of objects in images obtained by UAV and orbital base imaging equipmenttion
title_sort identification and classification of objects in images obtained by uav and orbital base imaging equipmenttion
topic metal fracture
texture features
macrogeometric descriptors
url https://sapi.bntu.by/jour/article/view/591
work_keys_str_mv AT aadoudkin identificationandclassificationofobjectsinimagesobtainedbyuavandorbitalbaseimagingequipmenttion
AT vvganchenko identificationandclassificationofobjectsinimagesobtainedbyuavandorbitalbaseimagingequipmenttion
AT avinyutin identificationandclassificationofobjectsinimagesobtainedbyuavandorbitalbaseimagingequipmenttion
AT eemarushko identificationandclassificationofobjectsinimagesobtainedbyuavandorbitalbaseimagingequipmenttion