Model-Based Object Pose in 25 Lines of Code

Abstract

We find the pose of an object from a single image when the relative geometry of four or more noncoplanar visible feature points is known. We first describe an algorithm, POS (Pose from Orthography and Scaling), that solves for the rotation matrix and the translation vector of the object by a linear algebra technique under the scaled orthographic projection approximation. We then describe an iterative algorithm, POSIT (POS with ITerations), that uses the pose found by POS to remove the “perspective distortions” from the image, then applies POS to the corrected image instead of the original image. POSIT generally converges to accurate pose measurements in a few iterations. Mathematica code is provided in an Appendix.