Evaluation of radar image processing efficiency based on intelligent analysis of processes
DOI:
https://doi.org/10.30837/rt.2021.4.207.09Keywords:
semantic analysis, radar signal, identification, extended atmospheric formations, aerial objectAbstract
The paper presents results of development of the method and experimental studies of the system for automatic detection of radar signals of aerial objects and their recognition with the processing of real records in surveillance radars. The relevance of this work consists in creation of algorithms for automatic information processing to ensure effective detection of useful signals due to accumulation of signal (energy) and semantic information. The method is based on the definition of semantic components at the stage of formation and analysis of the symbolic model of signals from point and extended air objects. Signal information is described by the predicate function of process knowledge of the formation and analysis of a symbolic model of a burst of impulse signals from point-like mobile aircraft such as an airplane, a helicopter, a UAV, and from extended atmospheric formations such as angel-echoes, clouds. As a result of semantic analysis of symbolic images of signal marks, classification distinctive features of air objects were obtained. The semantic components of the decision-making algorithm, similar to the decision-making algorithms used by the operator, have been investigated. In the developed algorithm, signal information is described by a predicate function on the set of signal mark pulse amplitudes that have exceeded a certain threshold value. Recognizing of aerial objects is carried out by solving the developed equations of predicate operations. The verification of the developed method was carried out on real data obtained on a survey radar of the centimeter range (pulse duration was 1 μs, probing frequency wass 365 Hz, survey period was 10 s). Based on these data, the types of characteristic marks of radar signals are modeled. According to the results of the experiments, they were all correctly identified.
References
Jianping Ou, Jun Zhang, and Ronghui Zhan. Processing Technology Based on Radar Signal Design and Classification // International Journal of Aerospace Engineering. Vol. 2020, рр. 1-19. Article ID 4673763. https://doi.org/10.1155/2020/4673763.
Skolnik M. I. (eds) (2021) Radar Handbook, McGraw-Hill, New York.
Berkler Katrin. Trends in artificial intelligence / Editorial team Janis Eitner (V.i.S.d.P.), Katrin Berkler, Henning Köhler, Roman Möhlmann. Fraunhofer-Gesellschaft e.V., 2018. p.p. 1-32.
Левыкин В.М., Чалая О.В. Модель жизненного цикла знаний – емкого бизнес-процесса // УСыМ. 2017. №1. С. 68-85.
Журавлев, Ю. И. Об алгебраическом подходе к решению задач распознавания или классификации / Ю. И. Журавлев // Проблемы кибернетики. 2005. Вып. 33. С. 5–68.
Russell S. (2019) Human compatible: Artificial intelligence and the problem of control, Penguin.
Solonskaya S., Zhirnov V. (2018). Intelligent analysis of radar data based on fuzzy transforms // Telecommunications and Radio Engineering, 77(15), pp.1321-1329.
You He; Jianjuan Xiu; Xin Guan. Radar Data Processing with Applications // Publisher John Wiley & Sons. 2017. https://app.knovel.com/web/toc.v/cid:kpRDPA0001/viewerType:toc/. ISBN978-1-118-95686.
Kozulia Tatiana, Sharonova Natalia, Kozulia Mariia. Knowledge-based information support formation for complex systems research // Системні дослідження та інформаційні технології. 2017. No 3. P. 63-72.
Солонская, С.В., Жирнов, В.В. Предикатная модель процессных знаний при обнаружении и распознавании протяженных объектов типа облака, тучи, «ангел-эхо» в обзорных РЛС // Радиотехника. 2020. № 202. С 164-172.
Bendich P., Bubenik P., Wagner A. Аlgorithms and complexity for Turaev–Viro invariants // Journal of Applied and Computational Topology, vol. 2.1, pp.33-53, 2018.
Zhyrnov V., Solonska S. (2020). Intelligent system for detection of low-visible air objects in surveillance radars // Telecommunications and Radio Engineering. 2020. Vol. 79, Issue 17. pp. 1513-1519.
Advanced Methods and Deep Learning in Computer Vision.1st Edition / Editors: E. R. Davies, Matthew Turk. Academic Press. 2021. Page Count: 586. ISBN: 9780128221099.
Zubkov O., Sheiko S.. Oleynikov M., Kartashov V., Babkin S. INVESTIGATION OF EFFICIENCY OF DETECTION AND RECOGNITION OF DRONE IMAGES FROM VIDEO STREAM OF STATIONARY VIDEO CAMERA // Telecommunications and Radio Engineering. 2021. Vol. 80, Issue 3. pp. 23-37.
Sytnik, Igor Vyzmitinov. ADAPTIVE APPROACH TO FILTERING OF STOCHASTIC PROCESSES IN RESCUER RADAR // Telecommunications and Radio Engineering. 2021. Vol. 80, Issue 3. pp. 1513-1519.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).