US 12,450,919 B2
Method, apparatus, and system for providing machine learning-based registration of imagery with different perspectives
Tero Juhani Keski-Valkama, Zürich (CH); and Reinhard Walter Köhn, Berlin (DE)
Assigned to HERE GLOBAL B.V., Eindhoven (NL)
Filed by HERE Global B.V., Eindhoven (NL)
Filed on Jul. 7, 2022, as Appl. No. 17/859,745.
Prior Publication US 2024/0013554 A1, Jan. 11, 2024
Int. Cl. G06T 7/70 (2017.01); G06N 3/08 (2023.01); G06V 10/74 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01)
CPC G06V 20/588 (2022.01) [G06N 3/08 (2013.01); G06T 7/70 (2017.01); G06V 10/761 (2022.01); G06V 10/82 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
retrieving a first training image and a second training image, wherein the first training image depicts a geographic area from a first perspective and the second training image depicts the geographic area from a second perspective, wherein the first training image is associated with a first set of ground truth image space coordinates and the second training image is associated with a second set of ground truth image space coordinates corresponding to the one or more ground truth correspondence masks;
initiating a labeling of one or more ground truth correspondence masks between the first training image and the second training image, wherein the one or more ground truth correspondence masks denote an image region of the first training image that matches a corresponding image region of the second training image or vice versa;
using the one or more ground truth correspondence masks to train a machine learning model to determine one or more predicted correspondence masks between a first input image and a second input image;
using the first set of ground truth image space coordinates and the second set of ground truth image space coordinates to further train the machine learning model to transform a first image space coordinate of the first input image to a second image space coordinate of the second input image or vice versa; and
providing the trained machine learning model as an output to a services platform for localization of at least one of a vehicle and a user equipment device.