Recovering the epipolar direction from two affine views of a planar object

Abstract

The mainstream approach to estimate epipolar geometry from two views requires matching the projections of at least 4 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 instead of point matching. Using results in Projective Geometry, we prove that the affine epipolar direction can be recovered provided camera motion is free of cyclorotation. A setup consisting of a Staubli robot holding a planar object in front of a camera 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 (applicable to planar, poorly textured scenes) and the Gold Standard algorithm (applicable to highly textured scenes with significant relief) produce comparable results shows the potential of our proposal.