基于彩色和边缘信息融合的道路分割算法.pdfVIP

40 1 浙 江 大 学 学 报( ) Vol.40 o. 1 2006 1 Journal of Zhejiang University(Engineering Science) Jan. 2006 1 1 2 刘加海 , 白洪欢, 黄微凹 ( 1. , 310028;2. , 310012) : ,, , . ,., , . ,,. : ; ; : T P242. 6 : A : 1008 973X( 2006)01 0029 04 Lane segmentation based on fusion of color and edge information 1 1 2 LIU Jia-hai , BAI Hong-huan , HUA G We-i ao ( 1. College of Comp uter Science, Zhej iang University , H angz hou 310028, China; 2. D ep ar tment of M athematics , Zhej iang Univ ers ity , H angz hou 310012, China Abstract: A new detection method for unstructured off-road scenes was proposed to improve the effective- ness of lane segmentation algorithm. T he color of road and off-road regions were modeled by Gaussian mixtures which were trained in a supervised manner. For a new image, color segmentation was first ap- plied based on the posterior probability. Sobel edge detector was then used to locate candidate edgelets a- long road boundaries. By combining both segmentation and edge information, how likely each edgelet was along the actual road boundaries could be evaluated. Dynamic programming was used to find an optimal concatenation of edgelets that form road boundaries. Experimental results show that this method could segment the lane boundary effectively, and is robust against noise, shadows and illumination variations. Key words: vision-based navigation; mobile robot; lane segmentation , , , : . , . , , , , . [ 1] , . . : :. , , , . . . , , ,. : 2004 08 20. ( ) : www .jour