Algorithm for Recognition of Small Air Targets by Trajectory Features in Passive Bistatic Radar

   Introduction. In the past few years, the rapid development and widespread use of unmanned aerial vehicles (UAVs) for solving a variety of tasks has created new threats. The problem of ensuring the safety of protected objects, especially in the area of critically important objects or in places with difficult ornithological conditions (airports, wind power facilities), is of particular importance. In this regard, the issue of detecting small air targets and recognizing their type and degree of danger is acquiring greater importance. This paper presents an algorithm for recognizing air targets based on
artificial intelligence technology. The results of a comparative analysis of decision-making methods for recognizing small UAVs and birds based on their trajectory features are presented. The results obtained can be used in the development of systems for recognizing classes of small airborne targets in existing and future radar stations.

   Aim. Development of an algorithm for recognizing small air targets by trajectory features based on machine learning. Implementation and evaluation of the quality of decision-making methods in a given recognition problem.

   Materials and methods. Experimental data on the trajectories of UAVs and birds obtained in a passive bistatic radar system are used. The trajectory parameters of the targets and their statistical characteristics are calculated; a set of features for recognition is formed. Using the MATLAB software package, a program for implementing the recognition algorithm and analyzing the quality of decision-making methods was developed.

   Results. An algorithm for recognizing air targets based on artificial intelligence technology is presented. A comparative analysis of the six most common recognition methods based on machine learning (Naïve Bayes, decision trees, k-nearest neighbors, neural network recognition algorithm, support vector machine, random forests) was carried out, which showed that, under the conditions of this problem, the most effective are k-nearest neighbor method and support vector machine.

   Conclusion. The presented methods can be used to directly determine the class of targets from a set of marks of their trajectories. Further research will be aimed at developing and implementing a real-time recognition algorithm.

1. Zeng H., Zhang H., Chen J., Yang W. UAV Target Detection Algorithm Using GNSS-Based Bistatic Radar. IGARSS 2019 – IEEE Intern. Geoscience and Remote Sensing Symp. Yokohama, Japan, 28 July – 02 Aug. 2019. IEEE, 2019, pp. 2167–2170. doi: 10.1109/IGARSS.2019.8898935

2. Makarenko S. I. Protivodeistvie bespilotnim letatelnim apparatam [Countermeasures Against Unmanned Aerial Vehicles]. SPb, Naukoemkie tekhnologii, 2020, 204 p. (In Russ.)

3. Khristenko A. V., Konovalenko M. O., Rovkin M., Khlusov V., Marchenko A. V., Sutulin A. A., Malyutin N. Magnitude and Spectrum of Electromagnetic Wave Scattered by Small Quadcopter in X-band. IEEE Trans. on Antennas and Propagation. 2018, vol. 66, no. 4, pp. 1977–1984. doi: 10.1109/TAP.2018.2800640

4. How to Counter the Use of Unmanned Aerial Vehicles for Terrorist Purposes. Available at: https://www.tbforum.ru/blog/kak-protivodejstvovat-primeneniyu-bespilotnyh-letatelnyh-apparatov-v-terroristicheskih-celyah (accessed 23. 05. 2023) (In Russ.)

5. Vorobyov E. N. Investigation of Distinctive Features for Recognition of Small UAVs in Passive Radar. Vestnik NovSU. Iss.: Engineering Sciences. 2019, no. 4 (116), pp. 72–77. doi: 10.34680/2076-8052.2019.4(116).72-77 (In Russ.)

6. Petrov I. D., Shkodyrev V. P., Sentsov A. A., Ivanov S. A. Algorithm for Recognition of Small Sized Aerial Objects Based on Analysis of Spectrums Obtained by Radar. T-Comm. 2022, vol. 16, no. 3, pр. 4–10. doi: 10.36724/2072-8735-2022-16-3-4-10 (In Russ.)

7. Dinevich L., Leshem Y. Algorithmic System for Identifying Bird Radio-Echo and Plotting Radar Ornitho-Logical Charts. The Ring. 2007, vol. 29, no. 1–2, pp. 3–39. doi: 10.2478/v10050-008-0040-z

8. Liu J., Xu Q. Y., Chen W. S. Classification of Bird and Drone Targets Based on Motion Characteristics and Random Forest Model Using Surveillance Radar Data. IEEE Access. 2021, vol. 9, pp. 160135–160144. doi: 10.1109/access.2021.3130231

9. Konovalov A. A. Osnovy traektornoy obrabotki ra-diolokatsyonnoy informatsii [Basic of the Radar Target Tracking]. Part 2. SPb, Izd-vo SPbGETU "LETI", 2014, 180 p. (In Russ.)

10. Dao L. V., Konovalov A. A., Le H. M. Analysis of Trajectory Features for Small UAVs Recognition. 2022 Conf. of Russ. Young Researchers in Electrical and Electronic Engineering (ElConRus). IEEE, 2022, pp. 1341–1345. doi: 10.1109/ElConRus54750.2022.9755753

11. Dao V. L. Raspoznavaniye malorazmernukh vozdusnukh RLS po traektornim priznakam s ispolzovanyem metodov masinnovo obuchienya [Recognition of Small Air Radars by Trajectory Features Using Machine Learning Methods]. SPbNTORES: trudi ezegodnoi NTK. 2023, no. 1, pp. 58–61. (In Russ.)

12. Subbotin S. A. Construction of Decision Trees for the Case of Uninformative Features. Radioelectronika, informatika, upravlenia. 2019, no. 1 (48), pp. 122–131. doi: 10.15588/1607-3274-2019-1-12 (In Russ.)

13. Borodinov А. А., Myasnikov V. V. Sravnhenye algoritmov klassifikatsyy radarnukh izobrazenyy pri raslichnikh metodakh predobrabotka na primere baza MSTAR [Comparison of Radar Image Classification Algorithms for Different Preprocessing Methods Using the MSTAR Database as an Example]. Proc. of the IV Intern. Conf. and Youth School "ITNT-2018". Samara: Novaya Tekhnika, 2018, pp. 586–594. (In Russ.)

14. Barbaresco F., Brooks D., Adnet C. Machine and Deep Learning for Drone Radar Recognition by Micro-Doppler and Kinematic criteria. 2020 IEEE Radar Conf. (RadarConf20). Florence, Italy, 21–25 Sept. 2020. IEEE, 2020, pp. 1–6. doi: 10.1109/RadarConf2043947.2020.9266371

15. Donskoy V. I. Algoritmicheskie modeli obucheniya klassifikatsyy [Algorithmic Models for Learning Classification]. Simferopol, DYAIPY, 2014, 228 p. (In Russ.)

16. Chystyakov S. P. Sluchaynie lesa : obzor [ Random Forests : Overview]. Proc. of the Karelian Scientific Center of the Russian Academy of Sciences. 2013, no. 1, pp. 117–136. (In Russ.)

17. Dietterich T. G. An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, And Randomization. Machine learning. 2000, vol. 40, no. 2, pp. 139–157. doi: 10.1023/A:1007607513941

18. Machine Learning Metrics: How to Measure the Performance of a Machine Learning Model. Available at: https://www.altexsoft.com/blog/machine-learning-metrics/ (accessed 23. 05. 2023)