Zhurnal Radioelektroniki - Journal of Radio Electronics. eISSN 1684-1719. 2022. №4
ContentsFull text in Russian (pdf)
DOI: https://doi.org/10.30898/1684-1719.2022.4.2
MONITORING OF MARITIME NAVIGATION FACILITIES
BASED ON AEROSPACE REMOTE SENSING DATA IN THE MICROWAVE RANGE
USING NEURAL NETWORK TECHNOLOGIES
M.L. Belokopytov, D.A. Shlyonskikh, S.V. Morozov, S.V. Sirota
Military space academy by A. Mozhaysky name
197198, St. Petersburg, Zhdanovskaya st., 13
The paper was received April 22, 2022.
Abstract. The article is devoted to the issues of automated search for objects of maritime navigation on radar images. A comparative analysis of the Yolov5 neural network family has been carried out. To detect objects, a one-stage automatic detector was used, built on the basis of a convolutional neural network of the Yolov5x type and trained on the SAR Ship Dataset. Digital modeling of the proposed recognition system has been performed. Verification of the trained model was carried out, as well as evaluation of the quality of the convolutional neural network algorithm. The main difficulties encountered in the preparation of a training sample are considered. The ways of their solution are proposed. Conclusions are drawn regarding the possibility of using the developed detector in order to automate the process of recognition of marine objects.
Key words: objects of maritime navigation, recognition, neural network, radar image.
Corresponding author: Mark Lvovich Belokopytov, hommer1990@mail.ru
1. Dorosinsky L.G., Trukhin M.P. Teoriya i praktika obrabotki signalov ot prostranstvenno-raspredelennykh tselei [Theory and practice of signal processing from spatially distributed targets]. Ulyanovsk, Zebra Publ. 2015. 243 p. (In Russian)
2. Nasyrov I.A. Vvedenie v sovremennye sputnikovye radionavigatsionnye sistemy. Chast' 1: obshchie printsipy, sovremennoe sostoyanie, perspektivy razvitiya [Introduction to modern satellite radio navigation systems. Part 1: general principles, current state, development prospects. Study guide]. Kazan State University Publ. 2005. 43 p. (In Russian)
3. Zhao Z., Zheng P., Xu S., Wu X. Object Detection with Deep Learning: A Review IEEE Transactions on Neural Networks and Learning Systems. 2018. P.1-21.
4. Vakulenko S.A., Zhikhareva A.A. Prakticheskii kurs po neironnym setyam [Practical course on neural networks]. St. Petersburg, ITMO University Publ. 2018. 71 p. (In Russian)
5. T. Zhang, X. Zhang, Jianwei Li. SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis Remote Sensing MDPI. 2021. V.13. P.3690.
6. Trask A. Glubokoe obuchenie [Deep learning]. St. Petersburg, St. Petersburg Publ. 2019. 352 p. (In Russian)
7. Ananyin E.V., Andryushchenko M.S. Methods of radar signature research in the development of inconspicuous samples of military equipment. Voprosy oboronnoi tekhniki. Seriya 16: tekhnicheskie sredstva protivodeistviya terrorizmu [Issues of defense technology. Series 16: Technical means of countering terrorism]. St. Petersburg. 2015. V.87-88. P.102-108. (In Russian)
8. Tertyshnik V.V., Zinoviev A.V. Methodology for calculating radar portraits of aerodynamic objects Radiotekhnika i svyaz': materialy Mezhdunar. nauch.-tekhn. konf., posvyashch. 15-letiyu kaf. Radiotekhniki [Radio engineering and communications: materials of International Scientific and Technical conf., dedicated]. Saratov, Sarat. gos. tech. un-t Publ. 2004. P.11-24. (In Russian)
9. Filippskikh E.E., Popov A.V., Galkin F.A. Model-oriented methodology for calculating radar portraits (signatures) of metal objects. Trudy VKA im. A.F.Mozhaiskogo: materialy XXXII Vserossiiskogo simpoziuma «Radiolokatsionnoe issledovanie prirodnykh sred» [Proceedings of the Mozhaisky VKA: proceedings of the XXXII All-Russian Symposium "Radar research of natural environments"]. St. Petersburg, VKA A.F. Mozhaisky Publ. 2021. P. 87-99. (In Russian)
10. Ivanov V.G., Gavrilin I.V., Nasypov D.N. Integrated electronic map as a unified information system of the combat situation. SAPR i grafika [CAD and graphics]. St. Petersburg. 2017. V.8. P.67-72. (In Russian)
For citation:
Belokopytov M.L., Shlenskikh D.A., Morozov S.V., Sirota S.V. Monitoring of maritime navigation facilities based on aerospace remote sensing data in the microwave range using neural network technologies. Zhurnal radioelektroniki [Journal of Radio Electronics] [online]. 2022. №4. https://doi.org/10.30898/1684-1719.2022.4.2 (In Russian)