View article

In this paper, we propose a method for recognition of road markings from in-vehicle camera images. A road marking in in-vehicle camera images has a variety of appearance due to the change of position and distance between the camera and the road marking, blur effect, and so on. Therefore, accurate recognition of road markings becomes difficult in real environment. Our method generates numerous learning images with the appearance variation in order to recognize road markings in real environment accurately. The effectiveness of the proposed method was confirmed through a recognition experiment using actual in-vehicle camera images.