Robust multiple lane road modeling based on perspective analysis

Marcos Nieto, Luis Salgado, Fernando Jaureguizar, Jon Arrospide
2008 2008 15th IEEE International Conference on Image Processing  
Road modeling is the first step towards environment perception within driver assistance video-based systems. Typically, lañe modeling allows applications such as lañe departure warning or lañe invasión by other vehicles. In this paper, a new monocular image processing strategy that achieves a robust múltiple lañe model is proposed. The identification of múltiple lañes is done by firstly detecting the own lañe and estimating its geometry under perspective distortion. The perspective analysis and
more » ... curve fitting allows to hypothesize adjacent lañes assuming some a priori knowledge about the road. The verification of these hypotheses is carried out by a confidence level analysis. Several types of sequences have been tested, with different illumination conditions, presence of shadows and significant curvature, all performing in realtime. Results show the robustness of the system, delivering accurate múltiple lañe road models in most situations.
doi:10.1109/icip.2008.4712275 dblp:conf/icip/NietoSJA08 fatcat:ifmy2bzjlvarld6hg67jcrjrya