Multi-lane detection in urban driving environments employing omni-directional camera

Lane detection is crucial part of vision driver assistance system of intelligent vehicles. In this paper we present a multi-lane detection method using omni-directional camera. The contribution of this paper is twofold. Firstly, we present an anisotropy steerable filter with the aim of get more reliable lane markings feature extraction under adverse circumstance. Secondly, an optimization method to fit the parameter of lane model is proposed. The proposed method is tested on different road images taken by omni-directional camera. Experimental results indicate the good performance of the proposed method.