3D Wire-Frame Integration from Image Sequences

procedure for integrating 3D positional information for isolated feature-points, extracted from a sequence of images, has been described in a previous paper. The following is a brief outline of the method: When integrating visual features into 3D for a Structure From Motion algorithm, the connectivity and relationships of features are an important adjunct to any quantitative 3D geometry. This paper describes a vision system which aims to perceive and refine this topology, in conjunction with geometry, using edges and vertices extracted from a sequence of monocular images of an unconstrained scene. Rules which tackle the practical difficulties of imperfect image processing and of obscuration features are defined. Results are shown for a rotating view of a polyhedral object, and for an outdoor scene viewed from a moving vehicle.