Robust Lane Detection and Tracking with Propagated Spatio-temporal Constraints

Road traffic plays an important role in our modern life. Lane detection and tracking system is developed for improving active security in intelligent vehicle. We present an effective method to achieve lane detection based on Bayesian probability framework, which utilizes prior knowledge of lane to decrease error lane detections. Besides, propagated spatio-temporal constraints between frames are applied to a simple and robust tracking strategy. Our tracking strategy can deal with some challenging scenarios, such as worn lane markings and shadows of trees, and reduce the amount of calculation greatly. Experimental results show that the proposed algorithm is robust against noise, shadows and illumination variations in captured road image sequences.