DOI QR코드

DOI QR Code

재난재해 분야 드론 자료 활용을 위한 준 실시간 드론 영상 전처리 시스템 구축에 관한 연구

A Study on the Construction of Near-Real Time Drone Image Preprocessing System to use Drone Data in Disaster Monitoring

  • 주영도 (강남대학교 컴퓨터미디어정보공학부)
  • Joo, Young-Do (Dept. of Computer & Media Information, Kangnam University)
  • 투고 : 2018.04.30
  • 심사 : 2018.06.08
  • 발행 : 2018.06.30

초록

최근 전 지구적인 기후변화에 따른 자연재해 피해의 대규모화로 인하여 재해 모니터링과 방재 등 재난재해 분야에서 원격탐사 기술을 적용한 시스템이 구축되고 있다. 다양한 원격탐사 플랫폼 중 드론은 기술의 확산 발전으로 민간분야에서도 활발하게 활용되고 있으며, 적시성, 경제성 등의 장점으로 재난재해 분야에서의 적용이 증대되고 있다. 본 논문은 이러한 드론 기반의 재난재해 모니터링 시스템 구축의 요소 기술인, 준 실시간으로 드론 영상자료를 매핑할 수 있는 전처리 시스템 개발에 관한 것이다. 연구를 위해 컴퓨터 비전 기술 중 SURF 알고리즘을 기반으로 레퍼런스 영상과 촬영 영상 간 특징점 매칭을 통해 보정하는 시스템을 구축하였다. 연구 대상 지역은 가화강 하류 지역과 대청댐 유역으로 선정하였으며, 두 지역은 매칭을 위한 특징점이 많고 적음의 차이가 뚜렷하여 다양한 환경에서 시스템 적용 가능성을 위한 실험에 적합하다. 연구결과 두 지역의 기하보정 정확도가 0.6m와 1.7m로 각각 나타났으며 처리시간 또한 1장당 30초 내외로 나타났다. 이는 적시성을 요하는 재난재해 분야에서 본 연구의 적용 가능성이 높음을 시사한다. 그러나 레퍼런스 영상이 없거나 정확도가 낮은 경우는 보정 결과가 떨어지는 한계점이 있다.

Recently, due to the large-scale damage of natural disasters caused by global climate change, a monitoring system applying remote sensing technology is being constructed in disaster areas. Among remote sensing platforms, the drone has been actively used in the private sector due to recent technological developments, and has been applied in the disaster areas owing to advantages such as timeliness and economical efficiency. This paper deals with the development of a preprocessing system that can map the drone image data in a near-real time manner as a basis for constructing the disaster monitoring system using the drones. For the research purpose, our system is based on the SURF algorithm which is one of the computer vision technologies. This system aims to performs the desired correction through the feature point matching technique between reference images and shot images. The study area is selected as the lower part of the Gahwa River and the Daecheong dam basin. The former area has many characteristic points for matching whereas the latter area has a relatively low number of difference, so it is possible to effectively test whether the system can be applied in various environments. The results show that the accuracy of the geometric correction is 0.6m and 1.7m respectively, in both areas, and the processing time is about 30 seconds per 1 scene. This indicates that the applicability of this study may be high in disaster areas requiring timeliness. However, in case of no reference image or low-level accuracy, the results entail the limit of the decreased calibration.

키워드

참고문헌

  1. IPCC 5th Assessment Report, Intergovernment Panel on Climate Change, 2013. DOI: https://doi.org/10.1071/ec13228
  2. 2017 Disaster Safety Statistical Yearbook, Ministry of the Interior and Safety, 2017.
  3. S. Chae and S. Hong, "The Opportunity and Risk Analysis of Commercial Drones", Proceedings of Summer Conference of the Korean Institute of Communication and Information Science, pp. 736-737, 2015.
  4. M. Kim and H. Yoon, "A Study on Utilization 3D Shape Pointcloud without GCPs using UAV Images", Journal of the Korea Academia-Industrial cooperation Society(JKAIS), Vol. 19, No. 2, pp. 97-104, 2018. DOI: https://doi.org/10.5762/KAIS.2018.19.2.97
  5. S. Lim, "Use of Drone in Disaster Safety Field" Science and Technology Policy, Vol. 203, pp. 16-19, 2015.
  6. Y. Joo, "Drone Image Classification based on Convolutional Neural Networks", The Journal of The Institute of Internet, Broadcasting and Communication (JIIBC), Vol. 17, No. 5, pp. 97-102, 2017. DOI: https://doi.org/10.7236/JIIBC.2017.17.5.97
  7. David G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints" International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110, 2004. DOI: https://doi.org/10.1023/B:VISI.0000029664.99615.94
  8. Herbert Bay, Tinne Tuytelaars and Luc Van Gool, "SURF: Speeded Up Robust Features" Computer Vision and Image Understanding, Vol. 110, No. 3, pp. 346-359, 2008. DOI: https://doi.org/10.1016/j.cviu.2007.09.014
  9. J. Ryu, S. Lee and Y. Jeong, "FPGA Design of the SURF Algorithm based Feature Point Extractor", Journal of Korea Multimedia Society, Vol. 14, No. 3, pp. 368-377, 2011. DOI: https://doi.org/10.9717/kmms.2011.14.3.368
  10. Y. Lee, J. Park and Y. Kim, "A Comparative Analysis of the Performance of SIFT and SURF", The Journal of the Korean Society of Semiconductor and Display Technology, Vol. 12, No. 3, pp. 59-64, 2013.
  11. J. Kim and D. Kim, "Matching Points Filtering Applied Panorama Image Processing Using SURF and RANSAC Algorithm", Journal of the Institute of Electronics and Information Engineers, Vol. 51, No. 4, pp. 144-159, 2014. DOI: https://doi.org/10.5573/ieie.2014.51.4.144
  12. S. Seo, S. Jeong, Y. Han, J. Choi and S. Lee, "Efficient Homography Estimation for Panoramic Image Generation", Journal of the Institute of Electronics and Information Engineers, Vol. 50, No. 8, pp. 214-224, 2013. DOI: https://doi.org/10.5573/ieek.2013.50.8.215