ISAR 영상 기반 해상표적 식별을 위한 인공지능 연구
An Artificial Intelligence Research for Maritime Targets Identification based on ISAR Images
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Artificial intelligence is driving the Fourth Industrial Revolution and is in the spotlight as a general-purpose technology. As the data collection from the battlefield increases rapidly, the need to us artificial intelligence is increasing in the military, but it is still in its early stages. In order to identify maritime targets, Republic of Korea navy acquires images by ISAR(Inverse Synthetic Aperture Radar) of maritime patrol aircraft, and humans make out them. The radar image is displayed by synthesizing signals reflected from the target after radiating radar waves. In addition, day/night and all-weather observations are possible. In this study, an artificial intelligence is used to identify maritime targets based on radar images. Data of radar images of 24 maritime targets in Republic of Korea and North Korea acquired by ISAR were pre-processed, and an artificial intelligence algo- rithm(ResNet-50) was applied. The accuracy of maritime targets identification showed about 99%. Out of the 81 warship types, 75 types took less than 5 seconds, and 6 types took 15 to 163 seconds.
Abstract
Artificial intelligence is driving the Fourth Industrial Revolution and is in the spotlight as a general-purpose technology. As the data collection from the battlefield increases rapidly, the need to us artificial intelligence is increasing in the military, but it is still in its early stages. In order to identify maritime targets, Republic of Korea navy acquires images by ISAR(Inverse Synthetic Aperture Radar) of maritime patrol aircraft, and humans make out them. The radar image is displayed by synthesizing signals reflected from the target after radiating radar waves. In addition, day/night and all-weather observations are possible. In this study, an artificial intelligence is used to identify maritime targets based on radar images. Data of radar images of 24 maritime targets in Republic of Korea and North Korea acquired by ISAR were pre-processed, and an artificial intelligence algo- rithm(ResNet-50) was applied. The accuracy of maritime targets identification showed about 99%. Out of the 81 warship types, 75 types took less than 5 seconds, and 6 types took 15 to 163 seconds.
참고문헌 (17)
- Alex, K, "ImageNet Classification with Deep Convolutional Neural Networks", Advances in Neural Information Processing Systems, 25, pp.1097~1105 (2012)
- Barragan-Montero, A, "Artificial intelligence and machine learning for medical imaging: A technology review", Physica Medica, 83, pp.242~256 (2021)
- Chen, X, "Range image-based LiDAR localization for autonomous vehicles", Proceedings of the IEEE International Conference on Robotics & Automation (2021)
- 최대욱, "야간 및 저시정 해양환경을 고려한 인공신경망 기반의 선박 분류 향상에 관한 연구", 한국CDE학회 논문집, 24(3), pp.320~328 (2019), 한국CDE학회[DOI]
- Han, S.H, "Results of the Demonstration of Warship Tactical Recommendation System", Defense Technology, 492, pp.110~123
- He, K, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)
- Jia, C, "Application of simultaneous location and map construction algorithms based on lidar in the intelligent robot food runner", Journal of Physics: Conference Series, 1972(1), pp.10~12 (2021)
- 김종환, "영상정보에 기초한 전차 자율탐지 및 조준점탐색 연구", 한국시뮬레이션학회 논문지, 27(2), pp.1~10 (2018), 한국시뮬레이션학회[DOI]
- 김정환, "딥러닝을 활용한 다국적 군함 탐지 및 분류모형 연구", 한국국방경영분석학회지, 46(2), pp.73~83 (2020), 한국국방경영분석학회
- Kim, K.H, "Improvement of anti submarine identification ability using deep learning based on artificial intelligence", Journal of the Maritime Strategy, 188, pp.44~87 (2020)
- A study on the establishment of defense decision support system using artificial intelligence, "Kim, Y.D", Korea Institute for Defense Analyses, ~ (2017)
- Kwon, P.G, "Implementation and development of warship combat system using artificial intelligence technology", Seminar on Combat System and Educational Development (2016)
- Moon, J.M, "Development of warship combat system using artificial intelligence technology", Journal of the Maritime Strategy, 188, pp.88~115 (2020)
- Newman, J, "Automatic annotation of american football video footage for game strategy analysis", Proceedings of the International Symposium on Intelligent Robotics and Industrial Applications using Computer Vision (2021)
- ROK Navy Six-One Air Group, "Understanding the Maritime Patrol Aircraft" (2015)
- Skolnik Merrill, "Radar Handbook" (1990), McGraw Hill