Single Camera 3D Lane Detection and Tracking Based on EKF for Urban Intelligent Vehicle

Road boundary detection and tracking is an important and integral function in advanced driver-assistance system. This paper proposes an algorithm, which can follow multi-kinds of lane, straight and curved, quickly and robustly. The algorithm uses several masks to extract blobs of road markings, combining with KNN function to remove the disturbance. Further more, road is modeled as a 3D surface, and some important parameters of current lane are provided on real-time by tracking based on Extended Kalman Filter (EKF). The results of experiments, which have been done in urban road, show that the algorithm is adapted to many road conditions. Even in a complex driving environment, it also has a good performance.