This paper addresses a key problem for autonomous road driving. A large number of implementations of autonomous driving systems developed worldwide rely on the strong assumption of moving on a flat road. This assumption is of basic importance since in the great majority of these systems the first stage of the processing is based on the Inverse Perspective Mapping (IPM), which removes the perspective effect from the acquired image. This paper presents an extension to the IPM that removes the assumption of a flat road ahead of the vehicle and allows to recover the road texture even in presence of bumps and hills. The paper discusses the results of the application of this technique to synthetic images; it is now being integrated into the GOLD system on the ARGO autonomous vehicle.