Road area detection based on texture orientations estimation and vanishing point detection

摘要

Estimating a proper location of the road area from a single road image plays an essential role in autonomous driving systems and driver assistant systems. In this paper, we propose a new road area detection method based on texture orientations estimation and vanishing point detection. This method first estimates a vanishing point using a texture-based soft voting algorithm proposed in our recent study. After that, texture orientations and color information are combined in order to generate a histogram for estimating two most dominant road borders. The road area is defined as a region between the two detected road borders and below the estimated vanishing point. The proposed method has been imple- mented and tested in 1000 road images which contain large variations in color, texture, lighting condition and surrounding environment. The experimental results demonstrate that our method performs well in challenging conditions.