Journal of Advanced Navigation Technology (한국항행학회논문지)

The Korean Navigation Institute (한국항행학회)
권호 표지
DOI QR코드

DOI QR Code

Robust Real-Time Lane Detection in Luminance Variation Using Morphological Processing

형태학적 처리를 이용한 밝기 변화에 강인한 실시간 차선 검출

  • Kim, Kwan-Young (Information & Telecommunication Engineering, Korea Aerospace University) ;
  • Kim, Mi-Rim (Information & Telecommunication Engineering, Korea Aerospace University) ;
  • Kim, In-Kyu (Information & Telecommunication Engineering, Korea Aerospace University) ;
  • Hwang, Seung-Jun (Information & Telecommunication Engineering, Korea Aerospace University) ;
  • Beak, Joong-Hwan (Information & Telecommunication Engineering, Korea Aerospace University)
  • 김관영 (한국항공대학교 정보통신공학부) ;
  • 김미림 (한국항공대학교 정보통신공학부) ;
  • 김인규 (한국항공대학교 정보통신공학부) ;
  • 황승준 (한국항공대학교 정보통신공학부) ;
  • 백중환 (한국항공대학교 정보통신공학부)
  • Received : 2012.11.14
  • Accepted : 2012.12.30
  • Published : 2012.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we proposed an algorithm for real-time lane detecting against luminance variation using morphological image processing and edge-based region segmentation. In order to apply the most appropriate threshold value, the adaptive threshold was used in every frame, and perspective transform was applied to correct image distortion. After that, we designated ROI for detecting the only lane and established standard to limit region of ROI. We compared performance about the accuracy and speed when we used morphological method and do not used. Experimental result showed that the proposed algorithm improved the accuracy to 98.8% of detection rate and speed of 36.72ms per frame with the morphological method.

본 논문에서는 형태학적 처리와 에지 가반 영역 분할을 이용해 환경변화에 강인한 실시간 차선 검출 알고리즘을 제안한다. 매 프레임마다 가장 적절한 임계값을 적용시키기 위해 적응적 임계값을 사용하고 투사변환을 통해 영상의 왜곡을 보정한다. 이 후, 관심영역을 지정하고 에지를 검출해 실시간적으로 차선을 검출한다. 형태학적 처리의 유무에 따른 차선 검출 정확도와 연산 속도를 비교한다. 실험 결과 제안한 알고리즘을 통해 98.8%의 차선 검출율과 프레임 당 36.72ms의 실시간 처리가 가능함을 확인하였다.

Keywords

References

  1. "World Car Accident Statistics", WHO(World Health Organization) 2008.
  2. Sunji Han,Youngjoon Han, Hernsoo Hahn, "Lane and Curvature Detection Algorithm based on the Curve Template Matching Method using Top View Image", The Institute of Electronics Engineers of Korea(IEEK)-SP, 47(6), pp. 97-106. Nov, 2010.
  3. Adrian N. Evans, "Morphological Gradient Operations For Images", IEEE, 2004.
  4. Arnaldo Camara Lara and Roberto Hirata Jr, "A morphological gradient-based method to motion segmentation", Proceedings of the 8th International Symposium on Mathematical Morphology, RiodeJaneiro, Brazil, MCT/INPE, Vol. 2, pp. 71-72. Oct. 10-13, 2007.
  5. Aroop Mukherjee, Soumen Kanrar "Enhancement of Image Resolution by Binarization" International Journal of Computer Applications (0975 - 8887)
  6. G.Y. Jiang, T.Y. Cho, S.K. Hong, J.W. Bae, and B.S. Song, "Lane and Obstacle Detection Based on Fast Inverse Perspective Mapping Algorithm," Systems, Man, and Cybernetics, 2000 IEEE International Conference on Vol. 4, pp. 2969-2974, October, 2000.
  7. H. Freeman. On the encoding of arbitrary geometric configurations, IRE Transactions on Electronic Computers EC- 10, pp. 260-268. 1961.
  8. Bongsob Song, The Korean Society of Automative Engineers, Auto Journal, pp. 35-40, June, 2012.