Affine reconstruction from translational motion under various autocalibration constraints

In this paper algorithms for affine reconstruction from translational motion under various auto calibration constraints are presented. A general geometric constraint, expressed using the camera matrices, is derived and this constraint is used in a least square solution to the problem. Necessary and sufficient conditions for critical motions are derived and shown to depend on the knowledge of the intrinsic parameters of the camera. Experiments on simulated data are performed to evaluate the noise sensitivity of the algorithms and the reconstruction quality for motions close to being critical. An experiment is performed on real data to illustrate that the method works in practice