UDC 621.396.96
An innovative algorithm is proposed for generating realistic radar images by randomly distributing objects from the MSTAR library onto synthesized backgrounds, which solves the problem of the lack of open source data for military purposes and their high cost of obtaining. The algorithm integrates statistical speckle noise matching to harmonize the characteristics of the target and background, unsubdiscretized contour transformation (NSCT) to preserve structural details during fusion, as well as a Lie filter to reduce noise during the post-processing stage. The method allows you to generate thousands of realistic images simulating radar shooting conditions (angles of incidence, polarization), which improves the training of AI models. The results demonstrate increased classification accuracy compared to traditional methods in compliance with SAR standards. The research contributes to the development of computer vision for security tasks by offering a solution in conditions of limited data.
MSTAR, radar image processing, image fusion, augmenta-tion of training data for deep neural networks
1. J. Smith, E. Johnson, et al., "MSTAR Dataset: A Benchmark for SAR Automatic Target Recognition," IEEE Transactions on Geoscience and Remote Sensing, vol. 60, no. 1, pp. 1–15, Jan. 2022.
2. T. D. Ross, S. W. Worrell, V. J. Velten, J. C. Mossing, and M. L. Bryant, "Standard SAR ATR evaluation experiments using the MSTAR public release data set," in Proc. SPIE, vol. 2487, pp. 566–573, 1995.
3. L. Yang, B. Guo, and W. Ni, "Image fusion using the nonsubsampled contourlet transform," in IEEE International Conference on Image Processing, pp. 1345–1348, 2008.
4. J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, "Unpaired image-to-image translation using cycle-consistent adversarial networks," in IEEE International Conference on Computer Vision (ICCV), pp. 2223–2232, 2017.
5. C. Oliver and S. Quegan, Understanding Synthetic Aperture Radar Images. SciTech Publishing, 2004.
6. Y. Zhang, X. Li, and L. Wang, "Bayesian fusion of multi-sensor images using gamma-Gaussian mixture models," IEEE Transactions on Image Processing, vol. 32, no. 5, pp. 1234–1245, 2023.
7. J. Yang, J. Wright, T. Huang, and Y. Ma, "Image fusion using sparse representation with learned dictionary," in IEEE International Conference on Image Processing, pp. 1345–1348, 2012.
8. F. T. Ulaby and D. G. Long, Microwave Radar and Radiometric Remote Sensing. Ann Arbor, MI, USA: Univ. of Michigan Press, 2014, pp. 210–215.
9. C. Oliver and S. Quegan, Understanding Synthetic Aperture Radar Images. SciTech Publishing, 2004.
10. L. Zhang, X. Li, Y. Wang, and Z. Chen, "Geometric Calibration of SAR Images for Military Target Recognition," Remote Sensing, vol. 12, no. 15, p. 2456, 2020.
11. R. Touzi and C. Lopez-Martinez, "Statistical Modeling and Matching of Speckle Noise in Polarimetric SAR Images," IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 8, pp. 6543–6556, 2021.
12. C. Oliver and S. Quegan, Understanding Synthetic Aperture Radar Images, 2nd ed. SciTech Publishing, 2004, pp. 150–152.
13. R. Touzi and C. Lopez-Martinez, "Statistical Modeling and Matching of Speckle Noise in Polarimetric SAR Images," IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 8, pp. 6543–6556, 2021.
14. R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. Pearson, 2018, pp. 120–125.
15. J. Fan et al., "Adaptive Intensity Adjustment for SAR Image Fusion Based on Statistical Matching," IEEE Transactions on Image Processing, vol. 32, no. 7, pp. 1234–1245, Jul. 2023. A. L. Cunha and M. N. Do, "The nonsubsampled contourlet transform: Theory, design, and applications," IEEE Transactions on Image Processing, vol. 15, no. 10, pp. 3089–3101, 2006.
16. L. Yang, B. Guo, and W. Ni, "Image fusion using the nonsubsampled contourlet transform," in IEEE International Conference on Image Processing, pp. 1345–1348, 2008.
17. J.-S. Lee and J.-H. Wen, "Advanced Lee Filtering for Speckle Noise Reduction in SAR Images: Theory and Applications," IEEE Transactions on Geoscience and Remote Sensing, vol. 60, no. 8, pp. 1–15, 2022.
18. J.-S. Lee, "Digital Image Enhancement and Noise Filtering by Use of Local Statistics," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 2, pp. 165–168, Mar. 1986.
19. R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. Pearson, 2018, pp. 120–125.
20. J.-S. Lee and J.-H. Wen, "Advanced Lee Filtering for Speckle Noise Reduction in SAR Images: Theory and Applications," IEEE Transactions on Geoscience and Remote Sensing, vol. 60, no. 8, pp. 1–15, 2022.
21. J.-S. Lee and J.-H. Wen, "Advanced Lee Filtering for Speckle Noise Reduction in SAR Images: Theory and Applications," IEEE Transactions on Geoscience and Remote Sensing, vol. 60, no. 8, pp. 1–15, Aug. 2022.
