대한공간정보학회지 (Journal of Korean Society for Geospatial Information Science)

  • 제21권3호
  • /
  • Pages.19-25
  • /
  • 2013
  • /
  • 1598-2955(pISSN)
  • /
  • 2287-6693(eISSN)
대한공간정보학회 (Korea Spatial Information Society)
권호 표지
DOI QR코드

DOI QR Code

영상인식과 사진측량 기술을 이용한 교통표지 자동측정 방법

Automatic Measurement Method of Traffic Signs Using Image Recognition and Photogrammetry Technology

  • 장상규 (경북대학교 토목공학과) ;
  • 김진수 (안동과학대학교 건설정보과)
  • Chang, Sang Kyu (Dept. of Civil Engineering, Kyungpook National University) ;
  • Kim, Jin Soo (Dept. of Construction Information, Andong Science College)
  • 투고 : 2013.07.11
  • 심사 : 2013.09.16
  • 발행 : 2013.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 도시의 도로시설물 관리에 대한 중요성이 증대됨에 따라 보다 정확한 시설물의 데이터베이스 정보가 요구되고 있다. 본 연구에서는 효율적인 도로시설물 DB 구축에 필요한 교통표지를 자동으로 검출하는 방법을 제안하였다. 검출 방법은 영상에서 특정 교통표지를 인식하여 자동으로 검출한 후 시설물의 중심위치를 찾는 순서로 진행하였다. 최종적으로 검출된 교통표지의 위치 정확도를 평가하기 위해서, 실제 측량한 좌표값과 연구를 통해 교통표지의 좌표값을 비교하였다. 교통표지 인식과 검출 과정에서는 OPEN CV를 이용한 코딩을 통해 컴퓨터 비젼 기술을 이용하였으며, 검출된 교통표지의 정확한 위치 계산은 사진측량 기술을 이용하였다. 다양한 종류의 도로표지판 중에서 원형 교통표지판(주차금지)과 삼각형 교통표지판(횡단보도)을 선택하여 진행하였다. 제안한 연구를 통해 산출된 좌표값과 실제 측량된 좌표값의 차이는 원형 교통표지판이 약 50cm, 삼각형 교통표지판이 약 60cm의 오차값으로 나타났다. 이러한 결과는 만족할 만한 결과는 아니지만 교통표지의 위치를 찾기에는 무리가 없을 것으로 판단된다.

Recently, more accurate database information of facilities is being required, with the increase in importance of urban road facility management. Therefore, this study proposed how to automatically detect particular traffic signs necessary for efficient construction of road facility DB. For this study, central locations of facilities were searched, after recognition and automatic detection of particular traffic signs through an image. Then, coordinate values of traffic signs calculated in the study were compared with real coordinate values, in order to evaluate the accuracy of traffic sign locations which were finally detected. Computer vision technology was used in recognizing and detecting traffic signs through OPEN CV-based coding, and photogrammetry was used in calculating accurate locations of detected traffic signs. For the experiment, circular road signal(No Parking) and triangular road signal(Crosswalk) were chosen out of various kinds of road signals. The research result showed that the circular road signal had a nearly 50cm error value, and the triangular road signal had a nearly 60cm error value, when comparing the calculated coordinates with the real coordinates. Though this result is not satisfactory, it is considered that there would be no problem to find locations of traffic signs.

키워드

참고문헌

  1. Asakura, T. and Aoyagi, Y., 1994, Image recognition of traffic speed marks using neural networks, JSME Trans., Vol.61, No.589, pp.206-212.
  2. Auranuch Lorsakul and Jackrit Suthakorn, 2007, Traffic sign recognition for intelligent vehicle/driver assistance system using neural network on OpenCV, the 4th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI 2007).
  3. C. Kotropoulos and I. Pitas, 1997, Rule-based face detection in frontal views, Proc Int'l Conf. Acoustics, Signal Processing, Vol.4, pp.2537-3541.
  4. Choi, M. S., Lee, J. H., Suk, J. H., Roh, T. M. and Shim, J. C., 2010, Vehicle detection based on the Haar-like feature and image segmentation, Journal of Korea Multimedia Society, Vol.13, No.9, pp.1314-1321.
  5. Di Zenzo, S., 1986, A note on the gradient of a multi image, Vol.33, pp.116-125. https://doi.org/10.1016/0734-189X(86)90223-9
  6. Jeong, M. H., 2000, Blunder detection by matching strength measurement in digital photogrammetry, Master's thesis, Sungkyunkwan University.
  7. Jeong, D. H., Kim, B. K. and Kim, J. H., 2002, Development of car MMS S/W for road facilities DB construction, Korea Spatial Information Society. Proceedings of the '2002 Autumn Meeting, pp.89-93.
  8. Kim, D. H., Im J. H., Kim, D. H., Kim T. K. and Paik, J. K., 2009, Face detection and tracking using skin color information and Haar-like features in real-time video, Korean HCI Society, HCI 2009 Congress, pp.146-149.
  9. Min, J. H., Lee, W. C. and Hong, K. C., 2004, Face detection ＆ amp; Identification system using Haar-like feature/HMM, Korean Institute of Information Scientists and Engineers, Proceedings of the 2004 Autumn Meeting, Vol.31, No.2, pp. 739-741.
  10. Paul R. Wolf and Bon A. Dewitt, 2000, Elements of photogrammetry : with application in GIS. McGraw- Hill Inc.
  11. Park, S. H., Cho, D. H. and Park, K. R., 2008, A study on eye detection using AdaBoost for iris recognition in mobile environments, The Institute of Electronics Engineers of Korea, Vol.45 CI No.4, pp.1-11.
  12. Park, C. H. and Namkung, J. C., 2005, Comparison of recognition rate with distance on stereo face images base PCA, Journal of Semiconductor Technology and Science, Vol.42, SP-1-1, pp.9-16.
  13. R. Lienhart and A. Wemicke, 2002, Localizing and segmenting text in images and videos, IEEE Trans. Circuits Syst. Video Technol, Vol.12, No.4, pp. 256-269. https://doi.org/10.1109/76.999203
  14. Samaria, F., 1994, Face recognition using hidden markov models, Ph.D. dissertation, University of Cambridge.
  15. Shin, M. C., 2006, Traffic sign recognition using color information and neural networks, Master's thesis, Inha University.
  16. Viola, P., and Jones, M., 2001, Rapid object detection using a Boosted cascade of simple features, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol.1, pp.511-518.
  17. Yoo, B. et. al., 2000, The Development of real-time photogrammetric system using digital photogrammetry and GPS, Korea Institute of Construction Technology.
  18. Yoon, C. Y., Jang, S. Y. and Park, M. G., 2009, Real-time road sign detection using vertical plane and AdaBoost, The Institute of Electronics Engineers of Korea, Vol.46, SC-5-5, pp.29-37.