한국시뮬레이션학회논문지 (Journal of the Korea Society for Simulation)

한국시뮬레이션학회 (The Korea Society for Simulation)
권호 표지
DOI QR코드

DOI QR Code

CNN 모델을 활용한 항공기 ISAR 영상 데이터베이스 구축에 관한 연구

A Study on the Establishment of ISAR Image Database Using Convolution Neural Networks Model

  • 투고 : 2020.09.21
  • 심사 : 2020.10.24
  • 발행 : 2020.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

비협조적 표적식별(NCTR, Non-Cooperative Target Recognition)은 전자정보 등 다른 체계의 지원 없이 레이다 자체적으로 표적을 식별하는 기능을 말한다. 이를 구현하기 위한 대표적인 방법 중 하나인 역합성개구레이다(ISAR) 영상은 표적의 기동 및 위치에 따라 크게 변하기 때문에 기종을 판단할 수 있는 데이터베이스 없이 이를 자동으로 식별하기란 매우 어렵다. 본 연구에서는 실측 영상이 부족한 상황에서도 ISAR 영상 시뮬레이션 및 딥러닝 기법을 활용한 식별 데이터베이스 구축방안에 대해 논한다. 다양한 레이다 운용 환경에 따라 변화하는 ISAR 영상을 모사하기 위해 '완전 산란체', '결손 산란체', 'JEM 잡음'으로 명명한 영상 형성 과정을 거쳐 이를 학습하는 모델을 제안한다. 이 모델의 학습 결과를 통해 유사한 형상의 시뮬레이션 영상은 물론 처음 입력된 실측 ISAR 영상도 식별할 수 있음을 확인하였다.

NCTR(Non-Cooperative Target Recognition) refers to the function of radar to identify target on its own without support from other systems such as ELINT(ELectronic INTelligence). ISAR(Inverse Synthetic Aperture Radar) image is one of the representative methods of NCTR, but it is difficult to automatically classify the target without an identification database due to the significant changes in the image depending on the target's maneuver and location. In this study, we discuss how to build an identification database using simulation and deep-learning technique even when actual images are insufficient. To simulate ISAR images changing with various radar operating environment, A model that generates and learns images through the process named 'Perfect scattering image,' 'Lost scattering image' and 'JEM noise added image' is proposed. And the learning outcomes of this model show that not only simulation images of similar shapes but also actual ISAR images that were first entered can be classified.

키워드

참고문헌

  1. Tait, P., Introduction to radar target recognition, IET Radar, Sonar and Navigation Series 18, London, 2005.
  2. Blacknell, D. and Griffiths, H., Radar automatic target recognition and non-cooperative target recognition, IET Radar, Sonar and Navigation Series 33, London, pp. 48-74, 2013.
  3. Lee, D. J., "A Study on the Requirements of KF-X Mounted Equipment", Air Review, ROK Joint Forces Military University, 2016.
  4. Lee, C. J. and Lee, M. G., "A Study on performance verification Case and application method of AESA radar", Korea National Defense University, 2016.
  5. Kim, K. T., Seo, D. K. and Kim, H. T., "Efficient classification of ISAR images", IEEE Transactions on Antennas and Propagation, Vol. 53, No. 5, pp. 1611-1621, 2005. https://doi.org/10.1109/TAP.2005.846780
  6. Park, S. H., Joo, M. G. and Kim, K. T., "Construction of ISAR training database for automatic target recognition", Journal of Electromagnetic Waves and Applications, Vol. 25, pp. 1493-1503, 2011. https://doi.org/10.1163/156939311797164909
  7. Choi, I. O., Kim, K. T., Jung, J. H. and Park, S. H., "Efficient recognition of ISAR Images usings 1D central moments", Journal of KIIT, Vol. 14, No. 1, pp. 61-68, 2016.
  8. Bai, X., Zhou, X., Zhang, F., Wang, L. Xue, R. and Zhou, F., "Robust Pol-ISAR Target Recognition Based on ST-MC-DCNN", IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, No. 12, pp. 9912-9927, 2019. https://doi.org/10.1109/tgrs.2019.2930112
  9. Wei, S., Liang, J., Wang, M., Zeng X., Shi, J. and Zhang, X., "CIST: An Improved ISAR Imaging Method Using Convolution Neural Network", Remote Sens. 2020, 12(16), 2641, 2020. https://doi.org/10.3390/rs12162641
  10. Ozdrmir C., Inverse synthetic aperture radar imaging with matlab algorithm, John Wiley & Sons, Inc., New York, 2012.
  11. Kim, K. T. and Jeong, H. R., "ISAR imaging of a real aircraft using KOMSAR", The Journal of Korean Institute of Electromagnetic Engineering and Science, vol. 18, pp. 717-722, Jul. 2007. https://doi.org/10.5515/KJKIEES.2007.18.7.717
  12. Peng, M., Wang, C., Chen, T. and Liu, G., "NIRFaceNet: A convolutional neural network for near-infrared Face Identification", Information, Vol. 7(4), 61, 2016. https://doi.org/10.3390/info7040061
  13. Simonyan, K. and Zisserman, A., "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556, 2014
  14. Zhang, X., Zou, J., He, K. and Sun, J. "Accelerating very deep convolutional networks for classification and detection." arXiv preprint arXiv:1505.06798, 2015.
  15. He, K., Zhang, X., Ren, S. and Sun, J., "Deep residual learning for image recognition", arXiv preprint arXiv:1512.03385, 2015
  16. French, A., "Target recognition techniques for multifunction phased array radar", Ph.D Thesis, University College London, pp. 29-52, 2010.
  17. Martin, J. and Mulgrew, B., "Analysis of the effect of blade pitch on the return signal from rotating aircraft blades", IEEE International Radar Conference 1992, pp. 446, 1992.