A Stereovision-Based Lane Detector for Marked and Non-Marked Urban Roads

This paper presents a lane detection system that combines stereovision-specific techniques with grayscale image processing for maximizing the robustness and applicability against the difficult conditions found on the urban roads, marked or non marked. The lane marking features are extracting using a fast and robust dark-light-dark transition detector that's aware of the perspective effect. The clothoid lane model is matched to the extracted features using line segment fitting for two distance intervals, under special constraints that ensure correctness. Freeform lane border detection, independent of the geometry constraints, driven by lane marking features only, is used to solve the situations not suited for clothoid representation. Intensive validation techniques are used for tracking initialization, and for monitoring of the noise level on the road, in order to avoid false positives. The results of each detection method are fused together in a Kalman filter based framework.