US 11,710,306 B1
Machine learning inference user interface
Shabab Bazrafkan, Graz (AT); Martin Presenhuber, Graz (AT); and Stefan Habenschuss, Graz (AT)
Assigned to Blackshark.ai GmbH, Graz (AT)
Filed by Blackshark.ai GmbH, Graz (AT)
Filed on Jun. 24, 2022, as Appl. No. 17/849,397.
Int. Cl. G06V 10/94 (2022.01); G06V 10/70 (2022.01); G06V 10/22 (2022.01); G06F 3/04842 (2022.01); G06T 11/40 (2006.01); G06V 10/776 (2022.01)
CPC G06V 10/945 (2022.01) [G06F 3/04842 (2013.01); G06T 11/40 (2013.01); G06V 10/235 (2022.01); G06V 10/776 (2022.01); G06V 10/87 (2022.01); G06T 2200/24 (2013.01); G06T 2210/62 (2013.01)] 26 Claims
OG exemplary drawing
 
1. A method of displaying results of an inference on a user interface, said method comprising:
displaying a geo-referenced image within a user interface of a user computer that includes a plurality of two-dimensional objects;
receiving user input via said user interface that selects an area of said image that includes a subset of fewer objects than said plurality of objects;
receiving user input via said user interface that selects a machine learning model for execution;
executing said machine learning model upon said selected area of said image that includes said subset of said objects, wherein said machine learning model processes said selected area of said image; and
displaying results of said execution of said machine learning model as an overlay over said subset of said objects on said user interface, wherein said overlay displays for each of said objects in said subset at least a shape that indicates a location on the surface of the Earth, a crosshatching within said shape that indicates an accuracy of said machine learning model, and an outline of each of said objects in said subset as determined by said execution of said machine learning model.