The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

A Development of The Road Surface Decision Algorithm Using SVM(Support Vector Machine) Clustering Methods

SVM(Support Vector Machine) 기법을 활용한 노면상태 판별 알고리즘 개발

  • Received : 2013.08.09
  • Accepted : 2013.10.11
  • Published : 2013.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Road's accidents caused by Ice, snow, Wet of roads surface conditions and weather conditions situations that are constantly occurring. That is, driver's negligence and safe driving ability of individuals due to lack of awareness, and Road management main agent(the government and the public, etc.) due to road conditions, if there is insufficient information. So Related research needs is a trend that is required. In this study, gather Camera(Stereo camera)'s image data, and analysis polarization coefficients and wavelet transform. And unlike traditional single-dimensional classification algorithms as multi-dimensional analysis by using SVM classification techniques, develop an algorithm to determine road conditions. Four on the road conditions (dry, wet, snow, ice) recognition success rate for the detection and analysis of experiments.

도로의 결빙, 적설, 젖음 등 기상상황 및 표면 상태에 의한 안전사고 발생은 지속적으로 발생하고 있는 상황이다. 이는 운전자 본인의 부주의 및 안전 운전의식 부족 등 개인의 역량에 기인하는 부문도 있지만, 도로관리 주체(정부 및 공공 등)의 도로 상태 정보제공 미흡으로 인한 경우도 있어 이와 관련된 연구의 필요성이 대두되고 있는 추세이다. 본 연구는 카메라(Stereo camera)의 영상 정보를 수집하여, 편광계수 및 웨이블릿 변환(Wavelet transform) 등을 통해 기존의 단일 차원 분류알고리즘과 달리 다차원 분석이 가능한 SVM 분류기법을 활용하여 노면상태 판별 알고리즘을 개발하였으며, 실제 도로상에서 4개의 상태(마른노면, 젖은노면, 적설노면, 결빙노면)에 대한 검지 인식 성공률을 실험 및 분석하였다.

Keywords

References

  1. Road Traffic Authority, http://taas.koroad.or.kr
  2. Kim, Doo Gyu, Kim, Ja Young, Lee, Ji Hong, Choi, Dong Geol, Kwon, In so, "Using Visual Information for Non-contract Predicting Method of Friction Coefficient", Journal of the Institute of Electronics Engineers of Korea, 2010-47SP-4-4. pp.399-405. 2010.
  3. Lim, Sung Han, Ryu, Seung Ki, Yoon, Yeo Hwan, "Image Recognition of Road Surface Conditions using Polarization and Wavelet Transform", Journal of the Korans Society of Civil Engineers, vol. 27, no. 4D, pp.471-477, 2007.
  4. Maria Jokela, Matti Kutila and Long Le,"Road Condition Monitoring System Based on a Stereo Camera", Intelligent Computer Communication and Processing, IEEE 5th International Conference on. pp.423-428 , 2009.
  5. Per-Olof Sjolander, Swedish Road Administration, "SRIS-Slippery Road Information System", IVSS Project Report, December 2008.
  6. Han, Tae-Hwan, Ryu, Seung-Ki, "The Recognition and Segmentation of the Road Surface State using Wavelet Image Processing", Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, vol. 22, no. 4, pp.26-34, 2008. https://doi.org/10.5207/JIEIE.2008.22.4.026
  7. Muneo Yamada, Toshihiro Oshima, Koji Udea, Isao Horiba and Shin Yamamoto, "A study of the road surface condition detection technique for deployment on a vehicle", JSAE Review 24, pp.183-188. 2003 https://doi.org/10.1016/S0389-4304(03)00006-7
  8. Choi, Young Jin, Multi Class pattern Classification Using Single SVM, Hanyang Graduate school of Master's Thesis. 2004
  9. Seok, Kyung ha, Ryu Tae Wook, "The Efficiency of Bloosting on SVM, Journal of Korean Data & Information Science Society. vol. 13, no2. pp.55-64. 2002.
  10. kanng, shin moon, Kim, Han jo, Oh, Won seok, Kim, Sun young, No , Kyoung Tai, "Development of Classification Model for hERG Ion Channel Inhibitors Using SVM Method, Journal of the Korean Chemical Society, vol. 53, no. 6. 2009 https://doi.org/10.5012/jkcs.2009.53.6.653