DOI QR코드

DOI QR Code

The Method of Wet Road Surface Condition Detection With Image Processing at Night

영상처리기반 야간 젖은 노면 판별을 위한 방법론

  • KIM, Youngmin (Korea Institute of Civil Engineering and Building Technology) ;
  • BAIK, Namcheol (Korea Institute of Civil Engineering and Building Technology)
  • Received : 2014.07.24
  • Accepted : 2015.02.27
  • Published : 2015.06.30

Abstract

The objective of this paper is to determine the conditions of road surface by utilizing the images collected from closed-circuit television (CCTV) cameras installed on roadside. First, a technique was examined to detect wet surfaces at nighttime. From the literature reviews, it was revealed that image processing using polarization is one of the preferred options. However, it is hard to use the polarization characteristics of road surface images at nighttime because of irregular or no light situations. In this study, we proposes a new discriminant for detecting wet and dry road surfaces using CCTV image data at night. To detect the road surface conditions with night vision, we applied the wavelet packet transform for analyzing road surface textures. Additionally, to apply the luminance feature of night CCTV images, we set the intensity histogram based on HSI(Hue Saturation Intensity) color model. With a set of 200 images taken from the field, we constructed a detection criteria hyperplane with SVM (Support Vector Machine). We conducted field tests to verify the detection ability of the wet road surfaces and obtained reliable results. The outcome of this study is also expected to be used for monitoring road surfaces to improve safety.

본 연구의 목적은 도로상에 설치된 CCTV에서 수집되는 영상정보를 이용하여 노면 상태를 판단하는 것이다. 이를 위해 먼저 야간의 젖은 노면을 검지하는 기술을 검증하였다. 지금까지 도로상의 젖음 정보를 추출하는 기술은 편광(polarization) 특성을 활용하는 것이다. 그러나 태양광이 없는 야간 도로상황에서는 편광특성을 활용할 수 없다. 이에 본 연구에서는 CCTV 야간 영상의 특징을 활용하여 마른 노면과 젖은 노면을 판별하는 방법을 제안한다. 노면의 젖음 여부를 판단하는 판별 방법론으로 웨이블릿(wavelet) 패킷 변환을 활용한 질감분석 방법론 및 영상의 명도분포 특성을 반영하기 위한 HSI 색상 모형 기반 명도(intensity) 히스토그램 활용 방법론을 적용하였다. 현장장비에서 취득한 총 200장의 샘플영상을 활용하여 영상을 분석, SVM (Support Vector Machine) 분류기 기반 판별 초평면을 구성한 후, 검지 기법을 검증하기 위한 현장테스트를 수행하였으며 유의한 결과를 얻을 수 있었다. 본 연구결과는 교통류의 안전성 향상을 위한 효율적인 야간 노면상태 수집에 활용될 수 있을 것이다.

Keywords

References

  1. Andrey J., Olley R. (1990), Relationships Between Weather and Road Safety: Past and Future Research Directions, Climatological Bulletin, 24(3).
  2. Arivazhagan S., Ganesan L. (2003), Texture Classification Using Wavelet Transform, Pattern Recognition Letters 24, 1513-1521. https://doi.org/10.1016/S0167-8655(02)00390-2
  3. Han T. H., Ryu S. K. (2008) The Recognition and Segmentation of the Road Surface State using Wavelet Image Processing, Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, 22(4), 26-34. https://doi.org/10.5207/JIEIE.2008.22.4.026
  4. Jokela M., Kutila M., Le L. (2009), Road Condition Monitoring System Based on a Stereo Camera, Intelligent Computer Communication and Processing, IEEE 5th International Conference on, IEEE, Cluj-Napoca, Romania, 423-428.
  5. Lee S. J., Heo G. Y. (2013), Supervised Rank Normalization for Support Vector Machines, Journal of The Korea Society of Computer and Information, 18(11), 31-38. https://doi.org/10.9708/jksci.2013.18.11.031
  6. Lim S. H., Ryu S. K., Yoon Y. H. (2007) Image Recognition of Road Surface Conditions Using Polarization and Wavelet Transform, Journal of the Korans Society of Civil Engineers, 27(4D), 471-477.
  7. Yamada M., Oshima T., Ueda K., Horiba I., Yamamoto S. (2003), A Study of the Road Surface Condition Detection Technique for Deployment on a Vehicle, JSAE REVIEW, 24, 183-188. https://doi.org/10.1016/S0389-4304(03)00006-7