Lecture Notes in Computer Science vol:2351 pages:837-851
European conference on computer vision - ECCV 2002 edition:7 location:Copenhagen, Denmark date:28-31 May 2002
In this paper we address the problem of uncalibrated structure and motion recovery from image sequences that contain dominant planes in some of the views. Traditional approaches fail when the features common to three consecutive views are all located on a plane. This happens because in the uncalibrated case there is a fundamental ambiguity in relating the structure before and after the plane. This is, however, a situation that is often hard to avoid in man-made environments. We propose a complete approach that detects the problem and defers the computation of parameters that are ambiguous in projective space (i.e. the registration between partial reconstructions only sharing a common plane and poses of cameras only seeing planar features) till after self-calibration. Also a new linear self-calibration algorithm is proposed that couples the intrinsics between multiple subsequences. The final result is a complete metric 3D reconstruction of both structure and motion for the whole sequence. Experimental results on real image sequences show that the approach yields very good results.
Pollefeys M., Verbiest F., Van Gool L., ''Surviving dominant planes in uncalibrated structure and motion recovery'', Lecture notes in computer science, vol. 2351, pp. 837-851, 2002 (Proceedings 7th European conference on computer vision - ECCV 2002, part II, May 28-31, 2002, Copenhagen, Denmark).