We present a stratification of geometric information available from stereo in three levels: Euclidean, affine and projective, depending upon the kind of calibration that has been obtained for a stereo rig. We focus on the last two levels since they are mostly unexplored. We show how projective and affine calibration can be achieved from real images without the need of calibration patterns. We also show how to use this calibration to determine, for example, whether an obstacle is coming too close to the stereo rig or such useful information as the middle of a corridor or a road.