산업융합연구 (Journal of Industrial Convergence)

  • 제20권12호
  • /
  • Pages.195-202
  • /
  • 2022
  • /
  • 2635-8875(pISSN)
  • /
  • 2672-0124(eISSN)
대한산업경영학회 (DAEHAN Society of Industrial Management)
권호 표지
DOI QR코드

DOI QR Code

모바일 환경에서 지하공간객체의 경량화를 위한 단순화 방법

Simplification Method for Lightweighting of Underground Geospatial Objects in a Mobile Environment

  • 투고 : 2022.10.31
  • 심사 : 2022.12.20
  • 발행 : 2022.12.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

지하공간정보지도 관리 시스템은 지하공간의 다양한 지하시설물을 3D 메쉬 데이터로 통합하고, 모바일 환경에서 지하시설물의 3D 이미지와 위치를 확인할 수 있도록 지원한다. 그러나 모바일 환경에서 실행되는 일정 지역 안에는 다양한 지하시설물이 존재할 수 있고 층층히 겹쳐 보일 수 있어서 모바일 환경에서 실행하는데 시간이 오래 걸리는 문제가 있다. 본 논문에서는 가시성에서 문제가 되지 않는 범위 내에서 3D 메쉬 데이터의 정점의 개수를 줄여서 데이터의 크기를 줄임으로써 모바일 환경에서 실행 시간을 줄일 수 있는 방법으로 딥러닝 기반 K-means 정점 클러스터링 알고리즘을 제안한다. 첫번째로 우리가 제안하는 방법은 딥러닝 Encoder-Decoder 기반의 모델을 통하여 정재된 정점의 특징 정보를 얻고, 두번째로 특징 정보를 K-means 정점 클러스터링을 통하여 서로 비슷한 정점끼리 묶어서 단순화를 하였다. 실험결과 제안한 방법으로 다양한 지하시설물들의 정점을 30%까지 줄였을 때, 이미지 모형이 약간의 변형은 발생하였지만 사라지는 부분은 없어서 모바일 환경에서 확인하는데 문제가 없었다.

Underground Geospatial Information Map Management System(UGIMMS) integrates various underground facilities in the underground space into 3D mesh data, and supports to check the 3D image and location of the underground facilities in the mobile app. However, there is a problem that it takes a long time to run in the app because various underground facilities can exist in some areas executed by the app and can be seen layer by layer. In this paper, we propose a deep learning-based K-means vertex clustering algorithm as a method to reduce the execution time in the app by reducing the size of the data by reducing the number of vertices in the 3D mesh data within the range that does not cause a problem in visibility. First, our proposed method obtains refined vertex feature information through a deep learning encoder-decoder based model. And second, the method was simplified by grouping similar vertices through K-means vertex clustering using feature information. As a result of the experiment, when the vertices of various underground facilities were reduced by 30% with the proposed method, the 3D image model was slightly deformed, but there was no missing part, so there was no problem in checking it in the app.

키워드

과제정보

This article is supported by the Korea Agency for Infrastructure Technology Advancement (KAIA)/Ministry of Land, Infrastructure and Transport(MOLIT) (Grant : 22DCRU-C158169-03)

참고문헌

  1. MOLIT. (2020). Development of technology for renewal automation and field utilization on the integrated underground geospatial information map. R&D plan, 1-30. 
  2. S. K. Cho & Y. J. Cho & Y. T. Kim & J. Y. Choi & Y. G. Jang. (2020). A Design of Mobile Service System on the Integrated Underground Geospatial Information Map, Proceedings of the Korean Society of Computer Information Conference, 28(2). 557-558. 
  3. S. K. Cho & Y. T. Kim & J. Y. Choi. (2020). Design and Implementation of Mobile 3D Visualization Service System on the Integrated Underground Geospatial Information Map, Journal of The Korea Society of Computer and Information, 25(12). 173-186. DOI : 10.9708/jksci.2020.25.12.173 
  4. Y. T. Kim & H. J. Kouh. (2022). Design of Caching Scheme for Mobile Underground Geospatial Information Map System. Journal of Convergence for Information Technology, 12(1). 7-14. DOI : 10.22156/CS4SMB.2022.12.01.007 
  5. H. K. Choi & H. S. Kim & K. H. Lee. (2010). An improved mesh simplification method using additional attributes with optimal positioning, International Journal of Advanced Manufacturing Technology, 50(1), 235-252. DOI : 10.1007/s00170-009-2484-y 
  6. J. Y. Lee & T. J. Jang. (2005). Volume Conserving Mesh Simplification Using Face Constriction, Journal of the Institute of Electronics and Information Engineers, 42(5), 87-96. 
  7. J. H. Wu & S. M. Hu & C. L. Tai & J. G. Sun. (2001). An effective feature-preserving mesh simplification scheme based on face constriction, Proceedings Ninth Pacific Conference on Computer Graphics and Applications, 12-21. DOI : 10.1109/PCCGA.2001.962853 
  8. Y. Wang & J. Zheng & H. Wang. (2019). Fast mesh simplification method for three-dimensional geometric models with feature-preserving efficiency, Scientific Programming, 3(1). 1-12. DOI:10.1155/2019/4926190 
  9. R. Ronfard & J. Rossignac. (1996). Full-Range Approximation of Triangulated Polyhedra, Proceedings of Eurographics '96, Computer Graphics Forum, 15(3). 67-76. DOI : 10.1111/1467-8659.1530067 
  10. H. Hoppe & T. DeRose & T. Dunchamp & J. McDonald & W. Stuetzle. (1993). Mesh Optimization, SIGGRAPH '93: Proceedings of the 20th annual conference on Computer graphics and interactive techniques, 19-26. DOI : 10.1145/166117.166119 
  11. P. Cignoni & C. Montani & R. Scopigno. (1998). A comparison of mesh simplification algorithms, Computers and Graphics, 22(1). 37-54. DOI : 10.1016/S0097-8493(97)00082-4 
  12. A. Voulodimos & N. Doulamis & D. Fritsch & K. Makantasis & A. Doulamis & M. Klein. (2016). Four-dimensional reconstruction of cultural heritage sites based on photogrammetry and clustering, Journal of Electronic Imaging, 26(1). 1-18. DOI : 10.1117/1.JEI.26.1.011013 
  13. S. Kumar & D. Manocha & W. Garrett & M. Lin. (1999). Hierarchical Back-Face Culling, Computer and Graphics, 23(5). 681- 692.  https://doi.org/10.1016/S0097-8493(99)00091-6
  14. M. Garland & A. Willmott & P.S. Heckbert. (2001). Hierarchical Face Clustering on Polygonal Surfaces, Proceeding of ACM Symposium Interactive 3D graphics, 49-58. DOI : 10.1145/364338.364345 
  15. Z. Yinhao Zhu & Z. Nicholas. (2018). Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification, Journal of Computational Physics, 366: 415-447. DOI:10.48550/arXiv.1801.06879 
  16. B. Yang & X. Fu, & N. D. Sidiropoulos & M, Hong. (2017). Towards k-means-friendly spaces: Simultaneous deep learning and clustering, In international conference on machine learning, 3861- 3870. DOI : 10.48550/arXiv.1610.04794