Vehicle yaw, pitch, roll and 3D lane shape recovery by vision

Abstract
We present here a set of new road models that allow both 3D lane shape and all extrinsic camera parameters recovery. The assumption that some parts of the road such as markings or the road itself have a constant width leads to very efficient geometric models. These models are used to estimate camera and road parameters : according to available extracted features, we can choose to recover part or the whole parameters.

This publication has 2 references indexed in Scilit: