Object pose by affine iterations

Abstract

The problem of a real-time pose estimation between a 3D scene and a camera is a fundamental task in most 3D computer vision and robotics applications such as object tracking, visual servoing, and virtual reality. In this paper we present a fast method for estimating the 3D pose using 2D to 3D point and line correspondences. This method is inspired by DeMenthon's method (1995) which consists of determining the pose from point correspondences. In this method the pose is iteratively improved with a weak perspective camera model, at convergence the computed pose corresponds to the perspective camera model. Our method is based on the iterative use of a paraperspective camera model which is a first order approximation of perspective. Experiments involving synthetic data as well as real range data indicate the feasibility and robustness of this method.