Lane Boundary Detection and Tracking using NNF and HMM Approaches

In this communication we present a new algorithm of lane detection and tracking. In the detection step, from the first frame of a video sequence, a linear-parabolic model is used to smooth the estimated trajectories, obtained by using the NNF approach. In the step of tracking, assuming a small change in the model, we use the HMM to update each parameter of the model. The results obtained are satisfactory.