한국군사과학기술학회지 (Journal of the Korea Institute of Military Science and Technology)

  • 제23권2호
  • /
  • Pages.115-124
  • /
  • 2020
  • /
  • 1598-9127(pISSN)
  • /
  • 2636-0640(eISSN)
한국군사과학기술학회 (The Korea Institute of Military Science and Technology)
권호 표지
DOI QR코드

DOI QR Code

컨볼루션 신경망의 앙상블 모델을 활용한 마스트 영상 기반 잠수함 탐지율 향상에 관한 연구

A Study on the Improvement of Submarine Detection Based on Mast Images Using An Ensemble Model of Convolutional Neural Networks

  • 정미애 (국방대학교 국방과학학과) ;
  • 마정목 (국방대학교 국방과학학과)
  • Jeong, Miae (Department of Defense Science, National Defense University) ;
  • Ma, Jungmok (Department of Defense Science, National Defense University)
  • 투고 : 2020.02.17
  • 심사 : 2020.03.30
  • 발행 : 2020.04.05
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Due to the increasing threats of submarines from North Korea and other countries, ROK Navy should improve the detection capability of submarines. There are two ways to detect submarines : acoustic detection and non-acoustic detection. Since the acoustic-detection way has limitations in spite of its usefulness, it should have the complementary way. The non-acoustic detection is the way to detect submarines which are operating mast sets such as periscopes and snorkels by non-acoustic sensors. So, this paper proposes a new submarine non-acoustic detection model using an ensemble of Convolutional Neural Network models in order to automate the non-acoustic detection. The proposed model is trained to classify targets as 4 classes which are submarines, flag buoys, lighted buoys, small boats. Based on the numerical study with 10,287 images, we confirm the proposed model can achieve 91.5 % test accuracy for the non-acoustic detection of submarines.

키워드

참고문헌

  1. S. H. Lee, "The Value and Implications of Submarine in the Battle of the Sea," Lighthouse of Officer, Vol. 26, pp. 79-94, 2012.
  2. S. G. Lee, et al., "Understanding Submarines 100 Questions 100 Answers," ROKN Submarine Fleet Command, 2014.
  3. S. S. Byun, "A Study on the Non-acoustic Antisubmarine Detection Against Submarine Threats," Maritime Strategy, Vol. 153, pp. 49-91, 2012.
  4. J. W. Park, "Comprehensive Analysis of Enemy Penetration Forces," Commander Republic of Korea Fleet, 2018.
  5. I. K. Lee, "Development of Anti-submarine Warfare against North Korean Submarine Threats," Maritime Strategy, Vol. 161, pp. 157-195, 2014.
  6. Saberwyn, "Onslow Masts," April 19, 2010, https://commons.wikimedia.org/wiki/File:Onslow_masts.jpg. (accessed Jan. 2, 2020.)
  7. Y. W. Yoo, "Representative of Maritime Patrol Aircraft, P-3C," August 10, 2011, http://bemil.chosun.com/site/data/html_dir/2011/08/10/2011081001045.html?related_all. (accessed Jan. 10, 2020.)
  8. Solaris, "Deep Learning to Learn by Tensorflow," Youngjin.com, Seoul, 2018.
  9. J. H. Kim, D. S. Choi, H. S. Lee, J. W. Lee, “Target Classification of Active Sonar Returns based on Convolutional Neural Network,” Journal of the Korea Institute of Information and Communication Engineering, Vol. 21, No. 10, pp. 1909-1916, 2017. https://doi.org/10.6109/jkiice.2017.21.10.1909
  10. D. W. Kim, J. W. Seok, K. S. Bae, “Target/nontarget Classification Using Active Sonar Spectrogram Image and CNN,” Institute of Korean Electrical and Electronics Engineers, Vol. 22, No. 4, pp. 1044-1049, 2018.
  11. K. H. Kim, S. J. Hong, B. H. Choi, L. H. Kim, E. T. Kim, "Ship Detection Using Faster R-CNN in Maritime Scenarios," Information and Control Symposium, pp. 158-159, 2017.
  12. S. W. Park, J. C. Kim, D. Y. Kim, “A Study on Classification Performance Analysis of Convolutional Neural Network Using Ensemble Learning Algorithm,” Journal of Korea Multimedia Society, Vol. 22, No. 6, pp. 665-675, 2019. https://doi.org/10.9717/KMMS.2019.22.6.665
  13. B. S. Kim, "A Study on Trash Classification using Convolution Neural Network," M. E. Thesis, University of Ulsan, 2018.
  14. C. Francois, "Deep Learning with Python," Gilbut Publishing, Seoul, 2018.
  15. K. Simonyan, A. Zisserman, "Very Deep Convolutional Networks for Large-scale Image Recognition," International Conference on Learning Representations, pp. 1-14, 2015.
  16. K. He, X. Zhang, S. Res, J. Sun, "Deep Residual Learning for iMage Recognition in Computer Vision and Pattern Recognition," The IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
  17. C. W. Kim, "Daeson's Deep Learning Foundation," Digital Books, Seoul, 2018.