Journal of Information Technology Applications and Management

  • 제30권6호
  • /
  • Pages.69-80
  • /
  • 2023
  • /
  • 1598-6284(pISSN)
  • /
  • 2508-1209(eISSN)
한국데이터전략학회 (Korea Data Strategy Society)
권호 표지
DOI QR코드

DOI QR Code

해상교통 상황인지 향상을 위한 합성 데이터셋 구축방안 연구

A Study on Synthetic Dataset Generation Method for Maritime Traffic Situation Awareness

  • Youngchae Lee (Graduate School of Environmental Engineering, Chungnam National University) ;
  • Sekil Park (KRISO (Korea Research Institute of Ships & Ocean Engineering))
  • 투고 : 2023.11.20
  • 심사 : 2023.12.26
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Ship collision accidents not only cause loss of life and property damage, but also cause marine pollution and can become national disasters, so prevention is very important. Most of these ship collision accidents are caused by human factors due to the navigation officer's lack of vigilance and carelessness, and in many cases, they can be prevented through the support of a system that helps with situation awareness. Recently, artificial intelligence has been used to develop systems that help navigators recognize the situation, but the sea is very wide and deep, so it is difficult to secure maritime traffic datasets, which also makes it difficult to develop artificial intelligence models. In this paper, to solve these difficulties, we propose a method to build a dataset with characteristics similar to actual maritime traffic datasets. The proposed method uses segmentation and inpainting technologies to build a foreground and background dataset, and then applies compositing technology to create a synthetic dataset. Through prototype implementation and result analysis of the proposed method, it was confirmed that the proposed method is effective in overcoming the difficulties of dataset construction and complementing various scenes similar to reality.

키워드

과제정보

This paper was carried out under the basic project "Development of open platform technology for smart marine safety and corporate support" of the Ship & Offshore Plant Research Institute with funding from the Ministry of Oceans and Fisheries (1525014880, PES4880).

참고문헌

  1. Ali, H., Xiong, G., Tianci, Q., Kumar, R., Dong, X., and Shen, Z., "Autonomous ship navigation with an enhanced safety collision avoidance technique", ISA transactions, October, 2023.
  2. Chen, J., Zhang, Y., Zou, Z., Chen, K., and Shi, Z., "Dense Pixel-to-Pixel Harmonization via Continuous Image Representation", arXiv preprint arXiv:2303.01681, 2023.
  3. Er, M. J., Zhang, Y., Chen, J., and Gao, W., "Ship detection with deep learning: a survey", Artificial Intelligence Review, Vol. 56, No. 6, March, 2023, pp. 1-41.
  4. Jeon, M., Park, J., and Woo, J., "Development of HHI's advanced navigation assistance system for safe voyage", IFAC-PapersOnLine, Vol. 52, No. 21, September, 2019, pp. 111-113. https://doi.org/10.1016/j.ifacol.2019.12.292
  5. Kim, D., "A Study on the Causes of Human Error in the OOW Considering the TIPOSC", Korean Association of Maritime Police Science, Vol. 8, No. 1, February, 2018, pp. 1-18. https://doi.org/10.30887/jkmps.2018.8.1.001
  6. Kim, K., Kong, K., and Kang, S., "A Review on Deep Learning-based Image Outpainting", Journal of Broadcast Engineering, Vol. 26, No. 1, January, 2021, pp. 61-69. https://doi.org/10.5909/JBE.2021.26.1.61
  7. Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A., Lo, W., Dollar, P., and Girshick, R., "Segment Anything", arXiv preprint arXiv:2304.02643, 2023.
  8. Kirillov, A., He, K., Girshick, R., Rother, C., and Dollar, P., "Panoptic Segmentation", 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9396-9405.
  9. Lee, G. and Ma, J., "A study on improving weapon system detection performance using sim2real learning", Journal of the Korea Academia-Industrial Cooperation Society, Vol. 24, No. 7, July, 2023, pp. 189-196. https://doi.org/10.5762/KAIS.2023.24.7.189
  10. MathWorks, "What Is Image Segmentation? 3 things you need to know", [cited 2023 October 10], Available from: https://www.mathworks.com/discovery/image-segmentation.html.
  11. MIT Technology Review, "The era of synthetic data is coming", [cited 2023 October 10], Available from: https://www.technologyreview.kr/2022-10-24-synthetic-data/.
  12. Niu, L., Cong, W., Liu, L., Hong, Y., Zhang, B., Liang, J., and Zhang, L., "Making Images Real Again: A Comprehensive Survey on Deep Image Composition", arXiv preprint arXiv:2106.14490, 2021.
  13. Oh, J., Park, S., and Kwon, O. S., "Advanced navigation aids system based on augmented reality", International Journal of e-Navigation and Maritime Economy, Vol. 5, No. 1, December, 2016, pp. 21-31. https://doi.org/10.1016/j.enavi.2016.12.002
  14. TTA, "semi-structured data", Telecommunications Technology Association Information and Communication Terminology Dictionary, [cited 2023 October 6], Available from: http://terms.tta.or.kr/dictionary/dictionaryView.do?word_seq=175129-2.
  15. TTA, "structured data", Telecommunications Technology Association Information and Communication Terminology Dictionary, [cited 2023 October 6], Available from: http://terms.tta.or.kr/dictionary/dictionaryView.do?word_seq=175128-2.
  16. TTA, "unstructured data", Telecommunications Technology Association Information and Communication Terminology Dictionary, [cited 2023 October 6], Available from: http://terms.tta.or.kr/dictionary/dictionaryView.do?word_seq=045801-7.
  17. Yu, T., Feng, R., Feng, R., Liu, J., Jin, X., Zeng, W., and Chen, Z., "Inpaint Anything: Segment Anything Meets Image Inpainting", arXiv preprint arXiv:2304.06790, 2023.