Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회지)

Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회)
권호 표지
DOI QR코드

DOI QR Code

Road Area Snowfall Intensity Detection from CCD Imagery

CCD 영상을 이용한 도로 강설강도 탐지

  • 윤준희 (한국건설기술연구원 ICT융합연구실) ;
  • 김기홍 (강릉원주대학교 공과대학 토목공학과) ;
  • 김태훈 (한국건설기술연구원 ICT융합연구실)
  • Received : 2013.02.13
  • Accepted : 2013.02.25
  • Published : 2013.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, economic and social damages are globally increased due to the heavy snowfall caused by global warming. To reduce the damages of sudden regional heavy snow in roads, suitable countermeasures should be established based on the accurate detection of snowfall intensity for each roadway segment. In this paper, we deal with snowfall intensity detecting algorithm in the road area from CCD Imagery. First, we determine the MLZ (MotionLess Zone), which does not contain lane markings and moving cars, in the image space. Next, snow streaks trespassing the MLZ are extracted with Canny operator and proposed algorithm. Also, the concept of SII (Snow Intensity Index), which is the number of snow streaks during one minute in the MLZ, is defined. Finally, the effectiveness of proposed algorithm is proved by visually comparing the imagery and SII value obtained during 69 minutes. In consequence, we figured out that the integration of SII is significantly related to an actual amount of snowfall.

최근, 지구 온난화에 따른 이상기후로 폭설로 인한 사회 경제적인 피해가 확산되고 있다. 국지적 기습 폭설에 의한 도로지역 피해를 저감하기 위해서는 도로 구간별 강설현황을 정확히 파악하여 대책을 마련하는 것이 중요하다. 본 논문은 도로에 설치되어 있는 CCD 영상을 이용하여 도로 강설강도를 탐지하는 알고리즘을 다룬다. 첫째, 전체 영상 공간 중 차량의 움직임 및 차선이 존재하지 않는 MLZ(MotionLess Zone)를 설정한다. 다음으로, 각 영상의 MLZ를 통과하는 눈 궤적을 Canny 연산자와 제안된 알고리즘을 이용하여 추출한다. 또한 1분 동안 MLZ 안의 눈 궤적의 개수를 나타내는 SII(Snow Intensity Index)를 정의한다. 마지막으로, 69분 동안 계산된 SII 값과 영상을 육안 비교함으로써 본 논문에서 제안된 알고리즘의 유효성을 검증한다. 실험결과 SII의 integration은 실제 적설량과 깊은 연관관계를 나타내었다.

Keywords

References

  1. Barnum, P. C., Narasimhan, S. and Kanade, T. (2010), Analysis of rain and snow in f requency space, International Journal of Computer Vision, Springer, Vol. 86, No. 2-3, pp. 256-274. https://doi.org/10.1007/s11263-008-0200-2
  2. Bossu, J., Hautiere, N. and Tarel, J-P. (2011), Rain or snow detection in image sequences through use of a histogram of orientation of streaks, International Journal of Computer Vision, Springer, Vol. 93, No. 3, pp. 348-367. https://doi.org/10.1007/s11263-011-0421-7
  3. Jung, J.I., Jang, G.H., Cha, J.W., Bae, J.Y., Jung, J.W., Yang, H.Y., Choi, Y.J., Cho, Y.H., and Lee, G.W. (2010) A study on estimating an amount of snowfall using a size distribution of snow particle, Proceedings of the Spring Meeting of KMS, pp. 315-316.
  4. Kim, J.W., Cho, Y.B., Kim, H.J., and Jun, T.H. (2011), Introduction of prediction techniques of snowfall and road surface freezing, Magazine of the Korea Institute for Structural Maintenance and Inspection, Vol. 15, No. 1, pp. 29-34.
  5. Park, J.H., Lee, J.K., Lee, C.W., and Lee, N.Y. (2010), Road condition measurement using radar cross section of radar, Journal of the Institute of Signal Processing and Systems, Vol. 11, No. 2, pp. 150-156.
  6. Sharma, A., Bullock, D., Peeta, S. and Krogmeier, J. (2006), Detection of inclement weather conditions at a signalized intersection using a video image processing algorithm, Proceedings of the 12th Digital Signal Processing Workshop, IEEE, pp.150-155.
  7. Yoon, G.Y., Kim, N.H., Choi, H.K., Jung, D.Y., Choi, S.H., and Kim, G.T. (2011), A winter road weather information system using ubiquitous sensor network, Journal of Korea Multimedia Society, Vol. 14, No. 3, pp. 392-402. https://doi.org/10.9717/kmms.2011.14.3.392
  8. Youn, J. and Bethel, J. S. (2004), Adaptive Snakes for Urban Road Extraction, International Archives of Photogrammetry and Remote Sensing, ISPRS, Vol. 35, Part B3, pp. 465-470.