CPC G06T 7/75 (2017.01) [G06T 19/006 (2013.01); G06T 2207/30244 (2013.01)] | 14 Claims |
1. A method, executed by one or more processors, of determining a pose of an augmented reality device, comprising:
capturing an image of a scene having a number of features;
extracting descriptors of features of the scene represented in the image;
matching the descriptors to landmarks in an existing 3D model of the scene to generate sets of matches between the descriptors and the landmarks;
determining an observed location measurement;
generating estimated poses of the augmented reality device from at least some of the sets of matches between the descriptors and the landmarks;
determining deviations between an aspect of each of the estimated poses and the observed location measurement; and
eliminating estimated poses having deviations from the observed location measurement that are greater than a threshold value,
wherein the deviations are horizontal distances between the estimated poses and the observed location measurement and the threshold value is a horizontal accuracy of the observed location measurement, or wherein the deviations are vertical distances between the estimated poses and the observed location measurement and the threshold value is a vertical accuracy of the observed location measurement.
|