US 11,810,344 B2
Image recognition system
Jason Lee Ertle, Portland, OR (US); Kevin L. Hofstee, Portland, OR (US); and Shane K. Luke, Portland, OR (US)
Assigned to NIKE, Inc., Beaverton, OR (US)
Filed by NIKE, Inc., Beaverton, OR (US)
Filed on Aug. 13, 2021, as Appl. No. 17/401,814.
Application 17/401,814 is a continuation of application No. 16/169,774, filed on Oct. 24, 2018, granted, now 11,127,157.
Claims priority of provisional application 62/576,250, filed on Oct. 24, 2017.
Prior Publication US 2021/0374992 A1, Dec. 2, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/73 (2017.01); G06V 20/10 (2022.01); G06V 10/28 (2022.01); G06V 10/44 (2022.01); G06F 18/2413 (2023.01); G06V 10/764 (2022.01); G06V 10/141 (2022.01); G06V 10/143 (2022.01); G06F 18/243 (2023.01)
CPC G06V 20/10 (2022.01) [G06F 18/2413 (2023.01); G06T 7/74 (2017.01); G06V 10/28 (2022.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06F 18/24323 (2023.01); G06T 2200/24 (2013.01); G06V 10/141 (2022.01); G06V 10/143 (2022.01); G06V 2201/09 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
extracting, by a computing device, one or more image frames from image data corresponding to an object;
modifying the one or more image frames to extract background information;
determining, based on the one or more modified image frames, object identification information; and
using the object identification information to identify the object.