MLPnP - A Real-Time Maximum Likelihood Solution to the Perspective-n-Point Problem

TL;DR

This paper introduces a real-time, statistically optimal maximum likelihood method for solving the Perspective-n-Point problem, incorporating observation uncertainties and applicable to various camera models.

Contribution

It presents a novel maximum likelihood approach that accounts for observation uncertainties and works with different camera models, enabling real-time and more accurate pose estimation.

Findings

Achieves real-time performance in PnP problem solving.

Incorporates observation uncertainties for improved accuracy.

Works with arbitrary central camera models.

Abstract

In this paper, a statistically optimal solution to the Perspective-n-Point (PnP) problem is presented. Many solutions to the PnP problem are geometrically optimal, but do not consider the uncertainties of the observations. In addition, it would be desirable to have an internal estimation of the accuracy of the estimated rotation and translation parameters of the camera pose. Thus, we propose a novel maximum likelihood solution to the PnP problem, that incorporates image observation uncertainties and remains real-time capable at the same time. Further, the presented method is general, as is works with 3D direction vectors instead of 2D image points and is thus able to cope with arbitrary central camera models. This is achieved by projecting (and thus reducing) the covariance matrices of the observations to the corresponding vector tangent space.