Journal of the Korean Association of Geographic Information Studies (한국지리정보학회지)

The Korean Association of Geographic Information Studies (한국지리정보학회)
권호 표지
DOI QR코드

DOI QR Code

Implementation of virtual reality for interactive disaster evacuation training using close-range image information

근거리 영상정보를 활용한 실감형 재난재해 대피 훈련 가상 현실 구현

  • KIM, Du-Young (Dept. of Civil Engineering, Kumoh National Institute of Technology) ;
  • HUH, Jung-Rim (Asia Infrastructure Research Center, Konkook University) ;
  • LEE, Jin-Duk (Dept. of Civil Engineering, Kumoh National Institute of Technology) ;
  • BHANG, Kon-Joon (Dept. of Civil Engineering, Kumoh National Institute of Technology)
  • 김두영 (금오공과대학교 토목공학과) ;
  • 허정림 (건국대학교 아시아시설물연구센터) ;
  • 이진덕 (금오공과대학교 토목공학과) ;
  • 방건준 (금오공과대학교 토목공학과)
  • Received : 2019.03.22
  • Accepted : 2019.03.27
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Cloase-range image information from drones and ground-based camera has been frequently used in the field of disaster mitigation with 3D modeling and mapping. In addition, the utilization of virtual reality(VR) is being increased by implementing realistic 3D models with the VR technology simulating disaster circumstances in large scale. In this paper, we created a VR training program by extracting realistic 3D models from close-range images from unmanned aircraft and digital camera on hand and observed several issues occurring during the implementation and the effectiveness in the case of a VR application in training for disaster mitigation. First of all, we built up a scenario of disaster and created 3D models after image processing with the close-range imagery. The 3D models were imported into Unity, a software for creation of augmented/virtual reality, as a background for android-based mobile phones and VR environment was created with C#-based script language. The generated virtual reality includes a scenario in which the trainer moves to a safe place along the evacuation route in the event of a disaster, and it was considered that the successful training can be obtained with virtual reality. In addition, the training through the virtual reality has advantages relative to actual evacuation training in terms of cost, space and time efficiencies.

드론 및 지상에서 촬영된 근거리 영상 정보는 3D 모델링 및 매핑 등을 통해 재해 저감 분야에서 자주 사용되어 왔다. 게다가 실사와 같은 3D 모델을 이용하여 가상현실과 함께 대규모 재난재해 상황을 모의할 수 있는 가상현실 구현 기술을 통해 그 활용도가 증가하고 있다. 본 논문에서는 무인 항공기 및 디지털 카메라 영상으로부터 실사와 같은 3D 모델을 추출하여 가상현실 훈련 프로그램을 구현하였으며, 이 과정에서 발생하는 다양한 문제점과 가상현실을 재난재해 훈련 상황에 적용했을 경우의 효과에 대해 검토하였다. 먼저 재해 발생 상황의 시나리오를 만들고, 근거리 이미지를 획득한 후 이미지 처리를 사용하여 3D 모델을 만들었으며, 완성된 3D 모델은 증강/가상현실 개발 프로그램인 Unity를 이용하여 가상현실의 배경으로 설정하고, 안드로이드 휴대폰을 위한 가상현실 환경을 C# 기반 스크립트를 이용하여 생성하였다. 생성된 가상현실은 재해 발생 시, 훈련자가 가상현실에서 대피 요령에 맞는 대피 경로를 따라 안전 장소까지 이동하는 시나리오를 포함하고 있으며, 성공적으로 가상훈련이 가능할 것으로 판단되었다. 또 구성된 가상현실을 통한 훈련은 비용, 공간, 시간적 효율성에 있어서 실제 대피 훈련보다 우위에 있는 것으로 확인하였다.

Keywords

GRJBBB_2019_v22n1_140_f0001.png 이미지

FIGURE 1. Settings of PIX4DCapture for collection of aerial photos

GRJBBB_2019_v22n1_140_f0002.png 이미지

FIGURE 2. Method of image capture according to the shape of aisles

GRJBBB_2019_v22n1_140_f0003.png 이미지

FIGURE 3. 3D modeling process with Bentley ContextCapture

GRJBBB_2019_v22n1_140_f0004.png 이미지

FIGURE 4. Creation of WayPoint and Point

GRJBBB_2019_v22n1_140_f0005.png 이미지

FIGURE 5. Deployment of 3D model and WayPoint after import

GRJBBB_2019_v22n1_140_f0006.png 이미지

FIGURE 6. Comparison of 3D model results according to the amount of sunshine

GRJBBB_2019_v22n1_140_f0007.png 이미지

FIGURE 7. 3D models from photos with sparse keypoints

GRJBBB_2019_v22n1_140_f0008.png 이미지

FIGURE 8. 3D models from photos with dense keypoints

GRJBBB_2019_v22n1_140_f0009.png 이미지

FIGURE 9. Before and after modification of the 3D model for the lab. room

GRJBBB_2019_v22n1_140_f0010.png 이미지

FIGURE 10. Before and after of 3D models for 2nd floor aisle

GRJBBB_2019_v22n1_140_f0011.png 이미지

FIGURE 11. Division of sections into tiles

GRJBBB_2019_v22n1_140_f0012.png 이미지

FIGURE 12. 3D models for each section

GRJBBB_2019_v22n1_140_f0013.png 이미지

FIGURE 13. Screen captures of 3D scenes by smartphone application

TABLE 1. Number of photos from handheld camera

GRJBBB_2019_v22n1_140_t0001.png 이미지

TABLE 2. Environment of VR implementation

GRJBBB_2019_v22n1_140_t0002.png 이미지

TABLE 3. Section, tile, and number of photos

GRJBBB_2019_v22n1_140_t0003.png 이미지

TABLE 4. Creation of Scenes

GRJBBB_2019_v22n1_140_t0004.png 이미지

References

  1. Andreatta, P.B., E. Maslowski, S. Petty, W. Shim, M. Marsh, T. Hall, S. Stern, and J. Frankel. 2010. Virtual reality triage training provides a viable solution for disaster-preparedness. Academic Emergency Medicine 17(8):870-876. https://doi.org/10.1111/j.1553-2712.2010.00728.x
  2. Bruno, F., S. Bruno, G. Sensi, M. Luchi, S. Mancuso, M. Muzzupappa. 2010. From 3D reconstruction to virtual reality: A complete methodology for digital archaeological exhibition. Journal of Cultural Heritage 11(1):42-49. https://doi.org/10.1016/j.culher.2009.02.006
  3. Chae, J. 2018. Study on Firefighting Education and Training Applying Virtual Reality. Fire Science and Engineering 32(1):108-115. https://doi.org/10.7731/KIFSE.2018.32.1.108
  4. Durlach, N. and A. Mavor. 1995. Virtual Reality: Scientific and Technological Challenges. National Academies Press, 1995.
  5. Farra, S,, E. Miller, N. Timm, J. Schafer. 2012. Improved training for disasters using 3-D virtual reality simulation. Western Journal of Nursing Research 35(5):655-671. https://doi.org/10.1177/0193945912471735
  6. Hsu, E.B., Y. Li, J.D. Bayram, D. Levinson, S. Yang and C. Monahan. 2013. State of Virtual Reality Based Disaster Preparedness and Response Training. PLOS Currents Disasters, 2013.
  7. Hwang, W. and D. Park. 2018. A study on the planning of content for children disaster safety environment : focusing on the virtual-reality(VR) based Experiential Contents. Procedings of Korea Environmental Policy And Administration Society pp.63-64.
  8. Lee, J.H. 2018. Review and Analysis on VR Disaster Education Simulation - Derivation of Required Technology through Analysis of Domestic Disaster Experience. Journal of the Korean Society of Design Culture 24(3): 511-522. https://doi.org/10.18208/ksdc.2018.24.3.511
  9. Lowe, D.G. 2004. Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision 60(2):91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  10. Ministry of the Interior and Safety. 2017. Statistical yearbook of natural disaster. 242pp.
  11. Park, H.J., and M.B. Seo. 2017. A Development of Disaster Evacuation Simulation in Underground Space based on Virtual Reality. Proceedings of Korea Information Science Society. pp. 29-30.
  12. Song, Y.S., P.S. Lee, Y. Yeu, G.H. Kim. 2012. Flood Risk Mapping using 3D Virtual Reality Based on Geo-Spatial Information. The Korean Society for Geospatial Information Science 20(4):97-104. https://doi.org/10.7319/kogsis.2012.20.4.097
  13. Westody, M.J., J. Brasington, N.F. Glasser, M.J. Hambrey, and J.M. Reynolds. 2012. Structure-from-Motion photogrammetry: A low-cost, effective tool for geoscience applications. Geomorphology 179:300-314. https://doi.org/10.1016/j.geomorph.2012.08.021
  14. Zhang, L. and W.J. Tam 2005. Stereoscopic image generation based on depth images for 3D TV. IEEE Transactions on Broadcasting 51:191-199. https://doi.org/10.1109/TBC.2005.846190
  15. Zheng, E. and C. Wu. Structure from Motion Using Structure-less Resection. Procedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 7-13 December, 2015. pp. 2075-2083.