Recovering epipolar direction from two affine views of a planar object

The mainstream approach to estimate epipolar geometry from two views requires matching the projections of at least four non-coplanar points in the scene, assuming a full projective camera model. Our work deviates from this in three respects: affine camera, planar scene and active contour tracking. A B-spline is fitted to a planar contour, which is tracked using a Kalman filter. The corresponding control points are used to compute the affine transformation between images. We prove that the affine epipolar direction can be computed as one of the eigenvectors of this affine transformation, provided camera motion is free of cyclorotation. A Staübli robot is used to obtain calibrated image streams, which are used as ground truth to evaluate the performance of the method, and to test its limiting conditions in practice. The fact that our method and the gold standard algorithm produce comparable results shows the potential of our proposal.