UDC 621.396.96
This scientific article describes a new algorithm that provides high-precision modeling of radio location images using synthesized aperture (SAR) techniques. The aim of the development is to increase the efficiency of AI systems in the tasks of recognizing military equipment in diverse and dynamic operational conditions. The implemented technique is a multi—step sequence: starting with simulating plausible radar responses, then correcting the data obtained to reduce the influence of noise and systematic errors, and finally integrating complex scenes such as urbanized areas or deserted desert spaces. Modern adaptive filters are used to compensate for the distortion caused by the movement of the media, as well as to suppress background noise. Additionally, probabilistic models have been introduced to accurately reproduce the behavior of objects under the influence of changing external factors. The key goal of the tool is to create a scalable and detailed dataset that can be used to train deep neural networks to recognize military equipment (including armored personnel carriers, tanks, trucks, etc.) in conditions as close to reality as possible, but without involving expensive field tests. Moreover, the proposed strategy simplifies the interpretation of radar scenes due to a balanced approach combining physically based modeling with stochastic analysis methods. The work is a comprehensive solution that bridges the gap between the limited amount of field data and the increasing demands from both defense and civilian structures, and lays the foundation for the development of autonomous monitoring systems that adapt to a rapidly changing environment.
SAR image generation, radar data processing, digital ter-rain models (DMM) in SAR
1. Yaroslavsky L.P. Digital signal and image processing. Moscow: Radio and Communications, 2012.
2. Tikhonov V.I. Statistical radio engineering. Moscow: Soviet Radio, 2005.
3. Sergienko A.B. Digital signal processing. — St. Petersburg: Peter, 2020.
4. Bondur V.G., Zatsarinny V.V. Digital processing of radar images of the Earth. Moscow: Fizmatlit, 2020.
5. Ivanov A.V., Petrov S.K. Algorithms for processing synthesized aperture data in radar: methods of range-Doppler transformation. — Radio Engineering and Communications, No. 5, 2020, pp. 45-52.
6. Chirp Scaling method for correcting geometric distortions in radar images. — Proceedings of the International Conference "Modern problems of Radar", Moscow, 2020, pp. 112-118.
7. Grigoriev M.Yu., Fedotov R.A. Omega—K algorithm for processing broadband signals in SAR systems. — Radar and Radio Electronics, No. 3, 2021, pp. 30-41.
8. Volkova E.S., Timofeev A.V. Deep neural networks for radar image reconstruction. — Collection of scientific papers "Artificial intelligence in remote sensing". — St. Petersburg, 2022. — pp. 78-89.
9. Lebedev V.I., Shishkin A.B. Reverse projection algorithm in the tasks of radar aperture synthesis. — Information Technologies in Science and Technology, No. 4, 2018, pp. 22-29.
10. Richards M.A. Fundamentals of Radar Signal Processing. — N.Y.: McGraw-Hill, 2014.
11. Cumming I., Wong F. Digital Processing of Synthetic Aperture Radar Data. — Boston: Artech House, 2005.
12. Gonzalevsky V.A. Methods of radar signal processing. Moscow: Fizmatlit, 2018.
13. Skolnik M. Introduction to Radar Systems. N.Y.: McGraw-Hill, 2001.
14. Tukey J.W. The Future of Data Analysis. — Annals of Mathematical Statistics, 1962.
15. Rabiner L., Gould B. Theory and application of digital signal processing. Moscow: Mir, 1978.
16. Gonzalez R.C. Digital Image Processing. — L.: Pearson, 2018.
17. Soille P. Morphological Image Analysis. — Berlin: Springer, 2003.
18. Franceschetti G., Migliaccio M. Radar Scattering from Urban Areas. — Berlin: Springer, 2012.
19. Perlin K. Improving Noise. — ACM Transactions on Graphics, 2002.
20. Ward K.D. Statistical Models for Radar Clutter. — IET Radar, Sonar & Navigation, 2006.
21. Weibull W. A Statistical Distribution Function of Wide Applicability. — Journal of Applied Mechanics, 1951.
22. Ulbricht D. DEM-Based SAR Simulation for Urban Environments. — IEEE Transactions on Geoscience and Remote Sensing, 2015.
23. Yaroslavsky L.P. Methods of radar data processing. Moscow: Radiotechnika, 2010.Soille P. Morphological Image Analysis. — Berlin: Springer, 2003.
24. Soille P. Morphological Image Analysis. — Berlin: Springer, 2003.
25. Moreira A., et al. A tutorial on synthetic aperture radar. — IEEE Geoscience and Remote Sensing Magazine, 2013.
26. Cming I.G., Wong F.H. Digital Processing of Synthetic Aperture Radar Data. — Boston: Artech House, 2005.
27. Chen K.S. Principles of Synthetic Aperture Radar Imaging. — Boca Raton: CRC Press, 2015.
28. Smith J., et al. SAR Image Quality Assessment Using SSIM: A Case Study in Desert Environments. — Boston: Artech House, 2023.
