Abstract

The article considers aerospace technologies in terms of the details of the space survey of distributed objects. With discrete shooting of areas of interest, a set of images is formed, which are processed by segmentation tools. A set of overlapping or overlapping segments forms objects belonging to the register (areas of interest). The theoretical features of creating mathematical support for the process of forming areas of interest in which objects are present, based on a set of image segments obtained as a result of image processing by segmentation tools, are described. In particular, a mathematical model is presented for creating initial zones from multiple segments of sequential images. The process consists of determining the dynamic neighbourhood, determining the interaction weights and the rules for updating them, updating the spatial vectors of the segments of the processed images. The obtained results provide the creation of mathematical support for the process of forming areas of interest in which objects are present, based on a set of image segments obtained as a result of image processing by segmentation tools.

Details

Title
Formation of a register of special technology objects based on integrating segmented images
Author
Atlasov, I V 1 ; Bozhko, L M 2 ; Kravets, O Ja 3 ; Mutin, D I 4 ; Popov, D V 5 

 Moscow University of Ministry of Internal Affairs of Russian Federation named by V.Ja. Kikot’ , 12, Academician Volgin str., Moscow, 117997 , Russian Federation 
 Emperor Alexander I St. Petersburg State Transport University , 9, Moscow ave., Saint Petersburg, 190031 , Russian Federation 
 Voronezh State Technical University , 84, 20-letiya Oktyabrya str., Voronezh, 394006 , Russian Federation 
 Moscow State University of Technology “STANKIN” , 1, Vadkovsky Lane, Moscow, 127055 , Russian Federation 
 Ufa State Petroleum Technological University , 1, Kosmonavtov str., Ufa, 450064 , Russian Federation 
First page
022063
Publication year
2022
Publication date
Dec 2022
Publisher
IOP Publishing
ISSN
17426588
e-ISSN
17426596
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2755152306
Copyright
Published under licence by IOP Publishing Ltd. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.