GEOMETRIC INVARIANTS CONSTRUCTION FROM MULTIPLE VIEWS

Abstract

Geometric invariants have wide applications in computer vision and their precision has long been a hot topic. In most of the existing methods, three-dimensional (3D) invariants have been obtained by reconstruction of the object structure, where fundamental matrices between image pairs should be first established. Consequently, there are additional errors introduced during invariants construction and could be very time consuming. In this paper, a novel algorithm to calculate 3D projective invariants from multiple images has been proposed, without reconstructing the object structures explicitly. We have employed the geometric configuration of points and lines in general position to deduce the formulation of 3D invariants. It has been verified in our experiments that our proposed method is considerably accurate when compared with the ground truth, and more efficient when compared with reconstruction based methods.