Current Issues

Korea Society for Naval Science and Technology - Vol. 8 , No. 1

[Paper List]


[ Article ]
Journal of the KNST - Vol. 8, No. 1, pp. 30-35
Abbreviation: KNST
ISSN: 2635-4926 (Print)
Print publication date 31 Mar 2025
Received 21 Feb 2025 Revised 04 Mar 2025 Accepted 22 Mar 2025
DOI: https://doi.org/10.31818/JKNST.2025.3.8.1.30
CNN 기법을 활용한 해저지형 영상 내에서의 해저산 중심 위치 산출 연구
김현승¹^{, *} ; 현철² ; 이성균² ; 고진용²

1LIG넥스원 해양연구소 선임연구원

2LIG넥스원 해양연구소 수석연구원
Research on Estimating the Central Position of Seamount in Seafloor Topography Images Using CNN Techniques
Hyunseung Kim¹^{, *} ; Chul Hyun² ; Sungkyun Lee² ; Jinyong Go²
1Senior researcher, Marine R&D Center, LIG Nex1

2Chief researcher, Marine R&D Center, LIG Nex1

Correspondence to : ^*Hyunseung Kim Marine R&D Center, LIG Nex1 333 Pangyo-ro, Bundang-gu, Seongnam-si, Gyeonggi-do, 13488, Republic of Korea Tel: +82-31-5179-7272 Fax: +82-31-5179-7086 E-mail: hyunseung.kim2@lignex1.com
Ⓒ 2025 Korea Society for Naval Science & Technology

초록

본 논문은 해저지형 영상으로부터 해저산의 중심 위치를 산출할 수 있도록 CNN(convolutional neural network) 기법을 활용한 딥러닝 학습 알고리즘을 제안하였다. 실제 한반도 인근 해역 수심 데이터로부터 약 150장의 해저지형 영상을 생성하여 학습시키고, 해저산 중심 위치 산출 정확도를 분석함으로써 최적의 특징점 추출기를 모델링하는 연구를 수행하였다. 본 논문에서 제안하는 알고리즘을 기반으로 수중 운동체의 주행 경로상의 해저지형을 사전에 분석함으로써 자율 주행에 기여할 수 있다.

Abstract

This paper proposed a deep learning training algorithm utilizing CNN(convolutional neural network) techniques to estimate the central position of seamount from seafloor topography images. Approximately 150 seafloor topography images were generated from bathymetric data near the Korean Peninsula for training, and the accuracy of sea mount center estimation was analyzed to model an optimal feature extractor. Based on the proposed algorithm, pre-analysis of seafloor topography along the trajectory of underwater vehicles can contribute to autonomous navigation.


Keywords: Seafloor Topography, Convolutional Neural Network, Feature Extraction, Deep Learning 키워드: 해저지형, 합성곱 신경망, 특징점 추출, 딥러닝

References


1.	S. Y. Yang, J. H. Kim, B. J. Kim and K. S. Kim, “A Study on the 3-D Digital Modeling of the Sea Bottom Topography,” Journal of the Korea Institute of Military Science and Technology, Vol. 5, No. 2, pp. 50-61, 2002.
2.	S. C. Yoo, J. Y. Mun, W. Park, G. H. Seo, S. J. Gwon and R. Heo, “Development of Bathymetric Data for Ocean Numerical Model Using Sea-floor Topography Data: BADA Ver. 1,” Journal of Korean Society of Coastal and Ocean Engineers, Vol. 31, No. 3, pp. 146-157, 2019.
3.	H. S. Kim, C. H, S. K. Lee, C. H. Kim and J. Y. Go, “Development of High-resolution Seafloor Topograph Map Generation Techniques Applying Feature Point Detection Algorithm,” Journal of Korean Society for Naval Science and Technology, Vol. 7, No. 1, pp. 11-16, 2024.
4.	D. G. Lee, Y. G. Sun, S. H. Kim, I. S. Sim, K. S. Lee, M. N. Song and J. Y. Kim, “CNN-based Image Rotation Correction Algorithm to Improve Image Recognition Rate”, The Journal of the Institute of Internet, Broadcasting and Communication, Vol. 20, No. 1, pp. 225-229, 2020.
5.	S. B. Yang and S. J. Lee, “Improved CNN Algorithm for Object Detection in Large Images,” Journal of the Korea Society of Computer and Information, Vol. 25, No. 1, pp. 45-53, 2020.
6.	D. S. Park, S. G. Hong and J. M. Park, “Implementation of AI-based Object Recognition Model for Improving Driving Safety of Electric Mobility Aids,” The Journal of Korea Institute of Convergence Signal Processing, Vol. 24, No. 2, 2023.