A Real-time Lane Detection Algorithm Based on a Hyperbola-Pair Model

Abstract

In this paper; we propose a real-time lane detection algorithm based on a hyperbola-pair lane boundary model. In stead of modeling each road boundary separately, we propose a model to describe the road boundary as two parallel hyperbolas on ground plane. By fitting points on pair road boundaries into this model, our method is able to make full use of road boundaries with existence of partial occlusion. Experiment in many different conditions, including various weather and road, demonstrates its high performance and accuracy.