화질복원 딥러닝 모델을 이용한 전투체계 스냅샷 이미지 전송 효율 향상에 관한 연구

최, 병일¹^{, *} ; 이, 재근² ; 손, 이현² ; 유, 성범³

1한화시스템 해양연구소 선임연구원
2한화시스템 해양연구소 전문연구원
3한화시스템 해양연구소 연구원

Improving Snapshot Image Transfer Efficiency in Naval Combat Systems Using Super-Resolution Deep Learning

Byeong-Il Choi¹^{, *} ; Jae-Geun Lee² ; Yi-Hyun Son² ; SeongBeom Yoo³

1Senior engineer, Naval R&D Center, Hanwha Systems
2Principal engineer, Naval R&D Center, Hanwha Systems
3Engineer, Naval R&D Center, Hanwha Systems

Correspondence to: ^*Byeong-Il Choi 264-60, Sanho-daero, Gumi-si, Gyeongsangbuk-do, 39370, Republic of Korea Tel: +82-54-460-8709 Fax: +82-54-460-8519 E-mail: bi.choi@hanwha.com

초록

함정 전투체계는 수상센서 영상과 스냅샷을 통해 표적 탐지 및 식별을 수행한다. 그러나 일부 장비는 고화질 이미지를 전송해 지연과 저장 비효율 문제가 발생한다. 이를 해결하기 위해 본 논문은 저화질 이미지를 송신하고 딥러닝 기반 Real-ESRGAN 모델을 적용해 복원하는 방안을 제안한다. 복원된 이미지 품질은 PSNR과 SSIM 지표로 검증되었으며, 그 결과 전송 지연과 저장 효율이 개선되고 전투체계 운용성과 AI 적용 가능성이 확인되었다.

Abstract

Naval combat systems utilize surface sensor imagery and snapshots as core elements for target detection and identification. However, some equipment transmit high-resolution images, causing delays and inefficiencies in storage management. To address this, this study proposes transmitting low-resolution images and applying the deep learning–based Real-ESRGAN (Real Enhanced Super-Resolution Generative Adversarial Network) model for restoration. The quality of the restored images was evaluated using PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index Measure) metrics, demonstrating reduced transmission delay, improved storage efficiency, enhanced system operability, and the feasibility of AI integration within naval combat systems.

Keywords:

Naval Combat System, Snapshot, Low-Resolution, AI, Real-ESRGAN

키워드:

함정 전투체계, 스냅샷, 저화질, 인공지능

Acknowledgments

This work was supported by the Government of the Republic of Korea in 2024 (912957501).

References

Won-Jin Kim, Young-San Kim, & Hyo-Jo Lee, ‘A Study on Ways to Improve Real-Time Performance of Tactical Data Link Image Transmission by Image Processing in Naval Combat Management System,’ Journal of the Korea Society of Computer and Information, VOL. 29, NO. 11, 2024, pp. 217-227.
Kyung-Min Go, Cheol-Hee Kwon, Jong-Soon Lee, & Young-Taek Kim, ‘Video Image Transmissions over DDS Protocol for Unmanned Air System,’ The Journal of Korean Institute of Communications and Information Sciences, VOL. 35, NO. 11B, 2010, pp. 1732-1737.
Changhan Park, ‘Similarity Comparison of Segmentation Based on Key-Points in Real-ESRGAN Super-Resolution Satellite SAR Images,’ Journal of Institute of Control, Robotics and Systems, VOL. 30, NO. 8, 2024, pp. 853-862. [https://doi.org/10.5302/J.ICROS.2024.24.0133]
Jae-Geun Lee, ‘A Study on the Standard Architecture of Weapon Control Software on Naval Combat System,’ Journal of the Korea Society of Computer and Information, VOL. 26, NO. 11, 2021, pp. 101-110.
Ki-Tae Kwon, Ki-Pyo Kim, & Hwan-Jun Choi, ‘Design of the Scalable Naval Combat System Software Using Abstraction and Design Pattern,’ Journal of the Korea Society of Computer and Information, VOL. 24, NO. 7, 2019, pp. 101-108.
Cheol-Gyu Yi & Young-Gab Kim, ‘A Study on Software Security Test of Naval Ship Combat System,’ Journal of the Korea Institude of Communications and Information Sciences, VOL. 45, NO. 3, 2020, pp. 628-637. [https://doi.org/10.7840/kics.2020.45.3.628]
S. Son, ‘A Study of Submarine Combat Management System Docker-Based Server Virtualization Design and Performance Analysis,’ Journal of the Korea Society of Computer and Information, VOL. 27, NO. 12, 2022, pp. 121-129.
Gyu-Seok Do, Ju-Mi Park, Won-Seok Jang, Young-Sub Yang, & Ji-Seok Yoon, ‘A Study on Deep Learning-Based Automatic Target Recognition System in IR Image for Intelligent Combat Management System,’ Journal of the Korea Society of Computer and Information, VOL. 30, NO. 1, 2025, pp. 33-40. [https://doi.org/10.9708/jksci.2025.30.01.033]
Hong-Jin Park, ‘Trend Analysis of Korea Papers in the Fields of ‘Artificial Intelligence’, ‘Machine Learning’ and ‘Deep Learning’,’ Journal of Korea Institute of Information, Electronics, and Communication Technology, VOL. 13, NO. 4, 2020, pp. 283-292.
Woo-Dam Sim & Jung-Soo Lee, ‘Assessing Techniques for Advancing Land Cover Classification Accuracy Through CNN and Transformer Model Integration,’ Journal of the Korean Association of Geographic Information Studies, VOL. 27, NO. 1, 2024, pp. 115-127. [https://doi.org/10.11108/KAGIS.2024.27.1.115]
Joon-Yong Kim & Koo-Rack Park, ‘Analysis of Accuracy and Loss Performance According to Hyperparameter in RNN Model,’ Journal of Convergence for Information Technology, VOL. 11, NO. 7, 2021, pp. 31-38. [https://doi.org/10.22156/CS4SMB.2021.11.07.031]
Changhan Park, ‘Super-Resolution of SAR Target Images Using Real-ESRGAN,’ Journal of Institute of Control, Robotics and Systems, VOL. 30, NO. 1, 2024, pp. 13-19. [https://doi.org/10.5302/J.ICROS.2024.23.0170]
Xintao Wang, Liangbin Xie, Chao Dong, & Ying Shan, ‘Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data,’ arXiv:2107.10833, 2021. [https://doi.org/10.48550/arXiv.2107.10833]
Xintao Wang, Ke Yu, Shixiang Wu, JinJin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, & Xiaoou Tang, ‘ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks,’ arXiv:1809.00219, 2018. [https://doi.org/10.48550/arXiv.1809.00219]
Namkyoon Kim, ‘Edge Device Implementation of Thermal Imaging Super-Resolution Using Real-ESRGAN,’ Master’s thesis, Korea Polytechnic University, 2023.
Kwangsoo Kang & Jun Haeng Lee, ‘PSNR Appraisal of MRI Image,’ Journal of the Korean Society of Radiology, VOL. 3, NO. 4, 2009, pp. 13-20.
Zhou Wang, A. C. Bovik, H. R. Sheikh, & E. P. Simoncelli, ‘Image Quality Assessment: From Error Visibility to Structural Similarity,’ IEEE Transactions on Image Processing, VOL. 13, NO. 4, 2004, pp. 600-612. [https://doi.org/10.1109/TIP.2003.819861]