Journal of Siberian Federal University. Engineering & Technologies / Probabilistic Assessment of Objects Belonging to a Given Class Based on the Combination of Multispectral Images of Different Times

Full text (.pdf)
Issue
Journal of Siberian Federal University. Engineering & Technologies. 2022 15 (3)
Authors
Svishcho, Vitalii S.; Uvarov, Andrey I.; Kryukov, Oleg V.
Contact information
Svishcho, Vitalii S.: Military Training and Research Center of the Air Force «Air Force Academy ft. Professor N. E. Zhukovsky and Y. A. Gagarin» Voronezh, Russian Federation; Uvarov, Andrey I.: Military Training and Research Center of the Air Force «Air Force Academy ft. Professor N. E. Zhukovsky and Y. A. Gagarin» Voronezh, Russian Federation; ; Kryukov, Oleg V.: Voronezh State Agrarian University named after Peter I Voronezh, Russian Federation
Keywords
object detection and recognition; combining; deep learning; probability estimation
Abstract

Object detection is the task of classifying and localization of objects in an image. This article discusses methods of image aggregation. Probabilistic indicators of the quality of optoelectronic means when detecting images of observed objects are determined. The technique of image aggregation in a multispectral optoelectronic system based on the probabilistic belonging of an object to a given class is presented. Probabilistic data on the object belonging to a given class using the machine learning method were obtained. The results of image aggregation with different parameters of the classification criterion are presented

Pages
370–380
DOI
10.17516/1999-494X‑0396
Paper at repository of SibFU
https://elib.sfu-kras.ru/handle/2311/145699

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).