레이더-광학장비 연계 객체 식별 AI 시스템의 개발 방안에 대한 연구

이헌기¹ ; 김도영² ; 최영두³ ; 장원석⁴ ; 전민규¹ ; 한민석⁵ ; 김세라⁶ ; 홍순국⁷^{, *}

1해군사관학교 기계시스템공학과 조교수
2국방기술품질원 지휘정찰센터 선임연구원
3해군 소령/해군사관학교 전기전자공학과 조교수
4한화시스템 해양시스템1팀 수석연구원
5해군사관학교 전기전자공학과 부교수
6해군사관학교 기초과학과 부교수
7해군 대령/해군사관학교 기계시스템공학과 교수

A Study on the Development of AI System for Target Identification through Combination of RADAR and Optical Equipment

Hun-Kee Lee¹ ; Do-Young Kim² ; Youngdoo Choi³ ; Wonseok Jang⁴ ; Min-Gyu Jeon¹ ; Min-Seok Han⁵ ; Sera Kim⁶ ; Soon-Kook Hong⁷^{, *}

1Assistant professor, Dept. of Mechanical System Engineering, Republic of Korea Naval Academy
2Senior researcher, C4ISR System Center, Defense Agency for Technology and Quality
3LCDR, ROK Navy/Assistant Professor, Dept. of Electrical Engineering, Republic of Korea Naval Academy
4Chief engineer, Naval System Team 1, Hanhwa Systems
5Associate professor, Dept. of Electrical Engineering, Republic of Korea Naval Academy
6Associate professor, Dept. of Natural Science, Republic of Korea Naval Academy
7CAPT, ROK Navy/Professor, Dept. of Mechanical System Engineering, Republic of Korea Naval Academy

Correspondence to: ^*Soon-Kook Hong Dept. of Mechanical System Engineering, Republic of Korea Naval Academy 1 Jungwon-ro, Jinhae-gu, Changwon-si, Gyungsangnam-do, 51704, Republic of Korea Tel: +82-55-907-5314 E-mail: hks753@gmail.com

초록

본 연구에서는 장거리 객체 탐지 능력은 탁월하나 객체의 식별 및 분류에 있어서 취약한 레이더 시스템을 보완하고자 레이더를 통해 획득한 객체의 표적 제원을 바탕으로 광학장비-YOLO-ESPCN 연계를 통한 AI 객체 식별 시스템을 제안하였다. 제안된 시스템은 광학장비를 통한 객체의 직접 관측을 바탕으로 근거리에서의 정확한 객체 식별 및 분류가 이루어졌으며, 해상 유·무인 복합체계에 적용 가능성을 나타냈다.

Abstract

In this study, we proposed AI object classification system through optical equipment-YOLO-ESPCN linkage based on target data of objects acquired through radar, where it has excellent long-range object detection capabilities but is vulnerable in classification of objects. The proposed model was accurately identified and classified at a short-distance based on direct observation through optical equipment, and showed that it could be applied to a maritime manned/unmanned complex system.

Keywords:

Target Classification, Transfer Learning, AI System, Surveillance and Reconnaissance

키워드:

표적 식별, 전이학습, 인공지능 시스템, 감시·정찰

Acknowledgments

이 논문은 2023년 정부(방위사업청)의 재원으로 국방기술진흥연구소의 지원을 받아 수행된 연구임 (KRIT-CT-23-030)

References

Ic-Pyo Hong, “Analysis of Radar Cross Section Characteristics for Camouflage Net with Stealth,” Journal of Korean Institute of Information Technology, Vol. 13, pp. 53-60, 2015. [https://doi.org/10.14801/jkiit.2015.13.4.53]
Dong-Geon Song, Byeong-Ju Yan and Rho-Shin Myong, “Effects of IR Reduction Design on RCS of UCAV,” Journal of the Korean Society for Aeronautical and Space and Science, Vol. 46, pp. 297-305, 2017. [https://doi.org/10.5139/JKSAS.2018.46.4.297]
Seungnam Kang, Soonbok Lee, Hoseok Jang, Jihong Kim and Hongjae Kim, “Considerations for the Construction of 360° Surrounding Video and the Establishment of Intelligent Marine Object Image Identification System,” Proceedings of 2019 Smart Navy Conference, 2019.
Joseph Redmon, Santosh Divvala, Ross Girshick and Ali Fafhadi, “You Only Look Once: Unified, Real-time Object Detection" Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. [https://doi.org/10.1109/CVPR.2016.91]
Peiyuan Jiang, Daji Ergu, Fangyao Liu, Ying Cai and Bo Ma, “A Review of Yolo Algorithm Developments,” Procedia Computer Science, Vol. 199, pp. 1066-1073, 2022. [https://doi.org/10.1016/j.procs.2022.01.135]
Alex Bewley, Zongyuan Ge, Lionel Ott, Fabio Ramos and Ben Upcroft, “Simple Online and Realtime Tracking,” 2016 IEEE International Conference on Image Processing. 2016. [https://doi.org/10.1109/ICIP.2016.7533003]
Wenzhe Shi, Jose Caballero, Ferenc Juszar, Johannes Totz, Andrew P. Aitken, Rob Bishop, Daniel Ruekert and Zehan Wang, “Real-time Single Image and Video Super-resolution Using an Efficient Sub-pixel Convolutional Neural Network,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874-1883, 2016. [https://doi.org/10.1109/CVPR.2016.207]