A robust vanishing point estimation method for lane detection

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.