The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 11, 2021

Filed:

May. 16, 2019
Applicant:

Naver Corporation, Seongnam-si, KR;

Inventors:

Philippe Weinzaepfel, Montbonnot-Saint-Martin, FR;

Gabriela Csurka, Crolles, FR;

Yohann Cabon, Montbonnot-Saint-Martin, FR;

Martin Humenberger, Gières, FR;

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/62 (2006.01); G06T 7/70 (2017.01); G06T 7/10 (2017.01);
U.S. Cl.
CPC ...
G06K 9/6262 (2013.01); G06K 9/6256 (2013.01); G06T 7/10 (2017.01); G06T 7/70 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30244 (2013.01);
Abstract

A method for training, using a plurality of training images with corresponding six degrees of freedom camera pose for a given environment and a plurality of reference images, each reference image depicting an object-of-interest in the given environment and having a corresponding two-dimensional to three-dimensional correspondence for the given environment, a neural network to provide visual localization by: for each training image, detecting and segmenting object-of-interest in the training image; generating a set of two-dimensional to two-dimensional matches between the detected and segmented objects-of-interest and corresponding reference images; generating a set of two-dimensional to three-dimensional matches from the generated set of two-dimensional to two-dimensional matches and the two-dimensional to three-dimensional correspondences corresponding to the reference images; and determining localization, for each training image, by solving a perspective-n-point problem using the generated set of two-dimensional to three-dimensional matches.


Find Patent Forward Citations

Loading…