Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Implementation of Point detail Classification System using Few-shot Learning

Few-shot Learning을 이용한 격점상세도 분류 시스템 구현

  • Received : 2022.11.07
  • Accepted : 2022.12.09
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

A digital twin is a technology that creates a virtual world identical to the real world. Problems in the real world can be identified through various simulations, so it is a trend to be applied in various industries. In order to apply the digital twin, it is necessary to analyze the drawings in which the structure of the real world to be made identical is designed. Although the technology for analyzing drawings is being studied, it is difficult to apply them because the rules or standards for drawing drawings are different for each author. Therefore, in this paper, we implement a system that analyzes and classifies the vertex detail, one of the drawings, using artificial intelligence. Through this, we intend to confirm the possibility of analyzing and classifying drawings through artificial intelligence and introduce future research directions.

디지털 트윈이란 현실세계와 동일한 가상세계를 만드는 기술이다. 다양한 시물레이션을 통해 현실 세계의 문제를 파악할 수 있어 여러 산업 분야에서 적용하는 추세이다. 디지털 트윈을 적용하기 위해서는 동일하게 만드려는 현실세계의 구조가 설계된 도면을 분석해야 한다. 도면을 분석하는 기술이 연구되고 있지만 도면을 작성하는 규칙이나 기준이 작성자마다 다르기 때문에 적용하기 어려운 추세다. 따라서 본 논문에서는 인공지능을 이용하여 도면 중 하나인 격점상세도를 분석하여 분류하는 시스템을 구현한다. 이를 통해 인공지능을 이용하여 도면을 분석하고 분류할 수 있는 가능성을 확인하고 추후 연구 방향에 대해 소개하고자 한다.

Keywords

Acknowledgement

This work was supported by Korea Environment Industry & Technology Institute(KEITI) through Project for developing innovative drinking water and wastewater technologies Program, funded by Korea Ministry of Environment (MOE) (RE202101601).

References

  1. K. H. Hwang, "The possibility of new changes in the media industry, Metaverse," Media Issue & Trend, vol. 45, no. 4, pp. 6-15, Aug. 2011.
  2. M. Y. Heo and B. K. Lim, A study on the Direction of Consumer Policy following the Acceleration of Digital Transformation after COVID-19, Republic of Korea, ROK: Korea Consumer Agency, 2022.
  3. Government Excellent Products Association. The technical definition and detailed evolution of the digital twin 5-level model [Internet]. Available: http://www.jungwoo.or.kr/webzine/2021_03/c2.html.
  4. Information and Communication Strategy Committee, "Key to the Korean version of New Deal 2.0 hyper-connected new industry: Digital Twin Revitalization Strategy," Ministry of Science and ICT, Republic of Korea: MSIT, Technical Report, 2021.
  5. J. S. Lee and I. Y. Moon, "Research on Digital Twin Automation Techniques in the Construction Industry through 2D Design Drawing Data Extraction and 3D Spatial Data Construction," in Proceeding of the Korea Institute of Information and Communication Engineering 2021 Autumn Conference, Kunsan, Republic of Korea, pp. 609-612, 2021.
  6. H. B. Sunwoo, G. H. Choi, and S. J. Heo, "Development of Automation Technology for Structural Members Quantity Calculation through 2D Drawing Recognition," in Proceeding of the Korea Institute Building Construction Spring Conference 2022, Naju, Republic of Korea, pp. 227-228, 2022.
  7. J. S. Lee, "Efficient 3D Modeling Automation Technique for Underground Facilities Using 3D Spatial Data," Journal of The Korea Institute and Communication Engineering, vol. 25, no. 11, pp. 1670-1675, Nov. 2021.
  8. H. J. Shin, E. M. Jeon, D. K. Kwon, J. S. Kwon, and C. J. Lee, "Automatic Recognition of Symbol Objects in P&IDs using Artificial Intelligence," Journal of Plant, vol. 17, no. 3, pp. 37-41, Sep. 2011.
  9. F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. S. Torr, and T. M. Hospedales, "Learning to Compare: Relation Network for Few-Shot Learning," in Proceeding of International Conference on Computer Vision and Pattern Recognition 2018, Salt Lake City: UT, USA, pp. 1199-1208, 2018.
  10. Y. Zhang, W. Chen, H. Ling, J. Gao, Y. Zhang, A. Torralba, and S. Fidler, "Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering," in Proceeding of International Conference on Learning Representations 2021, Virtual, pp. 1199-1208, 2018.