A robust image processing method with modified Otsu algorithm to recognize the road lane for a real-time autonomous vehicle was presented. The main objective of a proposed method was to drive an autonomous vehicle safely irrespective of road image qualities. For a possible real-time controlled autonomous vehicle steering, a detection area was predefined by lane segment, with previously obtained frame data, and the edges are detected on the basis of a lane width. For stable as well as psudo-robust autonomous driving with "good", "shady" or even "bad" road profiles, the variable threshold with modified Otsu algorithm in the image histogram, is utilized to obtain a binary image from each frame. Also Hough transform was utilized to extract the lane segment. Whether the image is "good", "shady" or "bad", always robust and reliable edges were obtained from the algorithms applied in this paper in a real-time basis. For verifying the adaptability of the proposed algorithm, a miniature vehicle with a camera was constructed and tested with various road conditions to prove its adaptability. Also, many highway road images were analyzed with proposed algorithm to prove its usefulness.

Date Published: 20 February 2006
PDF: 6 pages
Proc. SPIE 6041, ICMIT 2005: Information Systems and Signal Processing, 60412G (20 February 2006); doi: 10.1117/12.664375

Published in SPIE Proceedings Vol. 6041:
ICMIT 2005: Information Systems and Signal Processing
Yunlong Wei; Kil To Chong; Takayuki Takahashi, Editor(s)