Lane boundary detection based on parabola model

To improve lane detection accuracy under different road conditions for intelligent vehicles, we propose a new kind of lane boundary detection algorithm based on parabola model. The innovation lies in the algorithm is the combination of parabola model of road and the Hough transform. In this paper we proposed some constraints on the road model, making the algorithm with a high anti-interference performance. The algorithm consists of the initial road edge detection and the follow-up tracking of road borders. In the initial edge detection the Hough transform is used. In the path tracking we use mid-to-side strategy to detect the road boundary points, then use parabola model to fit the boundaries of the road. After testing, we can see that this algorithm has high efficiency and resistance to interference.