DocumentCode :
231960
Title :
A robust vanishing point estimation method for lane detection
Author :
Yuan Jun ; Tang Shuming ; Pan Xiuqin ; Zhang Hong
Author_Institution :
Inst. of Autom., Beijing, China
fYear :
2014
fDate :
28-30 July 2014
Firstpage :
4887
Lastpage :
4892
Abstract :
Vanishing points are often used as constraints in lane detection or road following systems of intelligent vehicles. This paper proposes a new method for vanishing point estimation in consecutive frames based on computer vision. Parallel lines in the real world converge to vanishing points on an image plane, caused by the perspective projection. According to the duality between points and lines, estimation of vanishing points can be converted to a problem of line parameter estimation in a parameter space. Firstly, straight lines are detected from an extracted edge map of a road image by the Progressive Probability Hough Transform (PPHT) incorporated with gradient orientation constraints. Then, vanishing points are estimated via the Maximum A Posteriori (MAP) estimate, integrating information at the current frame and the vanishing point estimated at the previous frame into a probabilistic framework. For the detected lines are noisy, a weight is put on each line to indicate the probability ofbeing an inlier. But the weights are unknown, which are regarded as hidden variables here. Thus the Expectation Maximum (EM) algorithm is adopted to solve the MAP problem with hidden variables. Experimental results show the efficiency and robustness ofthe proposed method.
Keywords :
Hough transforms; computer vision; expectation-maximisation algorithm; intelligent transportation systems; maximum likelihood estimation; object detection; probability; road vehicles; traffic engineering computing; EM algorithm; MAP estimation; PPHT; computer vision; edge map extraction; expectation maximum algorithm; gradient orientation constraints; image plane; intelligent vehicles; lane detection; line parameter estimation; maximum a posteriori estimation; parallel lines; parameter space; progressive probability Hough transform; road following systems; robust vanishing point estimation method; Accuracy; Decision support systems; Erbium; Transforms; EM algorithm; MAP estimate; Vanishing point estimation; lane detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control Conference (CCC), 2014 33rd Chinese
Conference_Location :
Nanjing
Type :
conf
DOI :
10.1109/ChiCC.2014.6895768
Filename :
6895768
Link To Document :
بازگشت