Euclidean reconstruction from an image triplet: a sensitivity analysis

This paper studies the sensitivity in Euclidean reconstruction from an image triplet taken by an uncalibrated camera mounted on a robot arm. The idea of such a reconstruction is closely related to that proposed by Zisserman et al. (1995). In this paper, we focus on an intermediate step of the reconstruction procedure which requires estimating the screw axis that corresponds to the defective eigenvector of a 4×4 matrix. Hundreds of the conducted synthetic tests show that the algorithm is very sensitive to image noise and perturbations on camera motions and that if the matrix is perturbed by Gaussian noise then the reliability of the computed screw axis can be estimated