DOI QR코드

DOI QR Code

Lane Detection in Complex Environment Using Grid-Based Morphology and Directional Edge-link Pairs

복잡한 환경에서 Grid기반 모폴리지와 방향성 에지 연결을 이용한 차선 검출 기법

  • 림청 (숭실대학교 전자공학과) ;
  • 한영준 (숭실대학교 전자공학과) ;
  • 한헌수 (숭실대학교 전자공학과)
  • Received : 2010.07.16
  • Accepted : 2010.11.19
  • Published : 2010.12.25

Abstract

This paper presents a real-time lane detection method which can accurately find the lane-mark boundaries in complex road environment. Unlike many existing methods that pay much attention on the post-processing stage to fit lane-mark position among a great deal of outliers, the proposed method aims at removing those outliers as much as possible at feature extraction stage, so that the searching space at post-processing stage can be greatly reduced. To achieve this goal, a grid-based morphology operation is firstly used to generate the regions of interest (ROI) dynamically, in which a directional edge-linking algorithm with directional edge-gap closing is proposed to link edge-pixels into edge-links which lie in the valid directions, these directional edge-links are then grouped into pairs by checking the valid lane-mark width at certain height of the image. Finally, lane-mark colors are checked inside edge-link pairs in the YUV color space, and lane-mark types are estimated employing a Bayesian probability model. Experimental results show that the proposed method is effective in identifying lane-mark edges among heavy clutter edges in complex road environment, and the whole algorithm can achieve an accuracy rate around 92% at an average speed of 10ms/frame at the image size of $320{\times}240$.

본 논문은 복잡한 도로 환경에서 차선을 정확하게 찾는 실시간 차선 검출법을 보인다. 기존의 많은 방법들은 대게 후처리 과정에서 차선 안쪽에 존재하는 잡음을 찾아 차선의 위치를 찾지만, 제안하는 방법은 특징 추출 단계에서 가능한 많은 잡음을 제거하므로 후처리 과정에서 검색 영역을 최소화한다. grid기반 모폴로지 연산은 우선 관심영역을 능동적으로 생성한 후, 모폴로지의 닫기 연산을 통해 에지 들을 연결한다. 그리고 방향성 에지 연결 기법을 통하여 유효한 방향에지를 찾고 사전에 구해진 영상 내 차선의 높이와 두 차선 간의 폭 관계를 이용하여 두 개의 차선을 군집화한다. 마지막으로 차선의 색상은 YUV색상 공간에서 두 개의 연결된 에지 안쪽을 검사하여 Bayesian확률 모델을 사용하여 추정한다. 제안하는 방법의 실험 결과는 다수의 불필요한 에지 군집이 존재하는 복잡한 도로 환경에서 효과적으로 도로 에지를 감별하였으며, 제안하는 알고리즘은 해상도 $320{\times}240$ 영상으로 10ms/frame의 속도에서 약92%의 정확도를 보였다.

Keywords

References

  1. J. C. McCall and M. M. Trivedi, “Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation,” IEEE Trans. Intell. Transp. Syst., vol. 7, no. 1, pp.20-37, 2006. https://doi.org/10.1109/TITS.2006.869595
  2. J. McDonald, “Detecting and tracking road markings using the hough transform,” Proc. of the Irish Machine Vis. and Image Processing Conf., pp. 1-9, 2001.
  3. K. Kaliyaperumal, S. Lakshmanan, K. Kluge, “An algorithm for detecting roads and obstacles in radar images,” IEEE Trans. Veh. Tech., vol. 50, no.1, pp.170-182,2001. https://doi.org/10.1109/25.917913
  4. Y. Wang, E. K. Teoh, D. Shen, “Lane detection and tracking using B-snake,” Image Vis. Comput., vol. 22, no. 4, pp.269-280, 2004. https://doi.org/10.1016/j.imavis.2003.10.003
  5. Z. Kim, “Robust lane detection and tracking in challenging scenarios,” IEEE Trans. on Intell. Transp. Syst., vol. 8, no. 1, pp. 16-26, 2008. https://doi.org/10.1109/TITS.2007.908582
  6. Q. Li, N. Zheng, and H. Cheng, “Springrobot: A prototype autonomous vehicle and its algorithms for lane detection,” IEEE Trans. Intell. Transp.Syst., vol. 5, no. 4, pp. 300-308, 2004. https://doi.org/10.1109/TITS.2004.838220
  7. J. W. Park, K. Y. Jhang, J. W. Lee, “Detection of lane curve direction by using image processing based on neural network and feature extraction,” Journal of imag. sci. and tech., vol. 45, no. 1, pp.69-75, 2001.
  8. J. Park , J. Lee and K. Jhang, “A lane-curve detection based on an LCF,” Pattern Recognit. Lett, vol. 24, no. 14, pp.2301-2313, 2003. https://doi.org/10.1016/S0167-8655(03)00056-4
  9. M. Sotelo, F. Rodriguez, L. Magdalena, “VIRTUOUS : vision-based road transportation for unmanned operation on urban-like scenarios,” IEEE Trans. Intell. Transp. Syst, vol. 5, no. 2, pp.69-83, 2004. https://doi.org/10.1109/TITS.2004.828175
  10. J. Yu, Y. Han, H. Hahn, “A scheme of extracting forward vehicle area using the acquired lane and road area information,” Journal of Korean Institute of Intell. Syst, vol. 18, no. 6, pp: 797-807, 2008.

Cited by

  1. Lane Detection for Parking Violation Assessments vol.16, pp.1, 2016, https://doi.org/10.5391/IJFIS.2016.16.1.13
  2. Infrared Image Segmentation by Extracting and Merging Region of Interest vol.26, pp.6, 2016, https://doi.org/10.5391/JKIIS.2016.26.6.493