ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume III-3
https://doi.org/10.5194/isprs-annals-III-3-131-2016
https://doi.org/10.5194/isprs-annals-III-3-131-2016
03 Jun 2016
 | 03 Jun 2016

MLPNP – A REAL-TIME MAXIMUM LIKELIHOOD SOLUTION TO THE PERSPECTIVE-N-POINT PROBLEM

S. Urban, J. Leitloff, and S. Hinz

Keywords: pose estimation, perspective-n-point, computer vision, photogrammetry, maximum-likelihood estimation

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.