US 12,087,077 B2
Determining associations between objects and persons using machine learning models
Parthasarathy Sriram, Los Altos, CA (US); Fnu Ratnesh Kumar, Campbell, CA (US); Anil Ubale, Cupertino, CA (US); Farzin Aghdasi, East Palo Alto, CA (US); Yan Zhai, Santa Clara, CA (US); and Subhashree Radhakrishnan, Santa Clara, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Jul. 5, 2023, as Appl. No. 18/347,471.
Application 18/347,471 is a continuation of application No. 17/556,451, filed on Dec. 20, 2021, granted, now 11,741,736.
Application 17/556,451 is a continuation of application No. 16/678,100, filed on Nov. 8, 2019, granted, now 11,205,086, issued on Dec. 21, 2021.
Claims priority of provisional application 62/760,690, filed on Nov. 13, 2018.
Prior Publication US 2023/0351795 A1, Nov. 2, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 40/10 (2022.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06T 7/246 (2017.01); G06V 10/26 (2022.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01); G06V 20/52 (2022.01)
CPC G06V 40/103 (2022.01) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 7/248 (2017.01); G06V 10/26 (2022.01); G06V 10/454 (2022.01); G06V 10/82 (2022.01); G06V 20/52 (2022.01); G06V 40/10 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01); G06T 2207/30232 (2013.01); G06T 2207/30241 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
determining a union region of an image depicting one or more entities and one or more objects, the union region corresponding to a union between a first region corresponding to the one or more entities and a second region corresponding to the one or more objects;
applying the image and coordinates corresponding to the union region in the image to one or more neural networks;
computing, using the one or more neural networks, one or more confidence values corresponding to an association between at least one entity of the one or more entities and at least one object of the one or more objects based at least on the image and the coordinates; and
determining whether the at least one object is associated with the at least one entity based at least on the one or more confidence values.