US 12,148,213 B2
Object ingestion and recognition systems and methods
Kamil Wnuk, Playa del Rey, CA (US); David McKinnon, San Francisco, CA (US); Jeremi Sudol, New York, NY (US); Bing Song, La Canada, CA (US); and Matheen Siddiqui, Culver City, CA (US)
Assigned to NANT HOLDINGS IP, LLC, Culver City, CA (US)
Filed by Nant Holdings IP, LLC, Culver City, CA (US)
Filed on Aug. 3, 2023, as Appl. No. 18/230,120.
Application 18/230,120 is a continuation of application No. 17/830,252, filed on Jun. 1, 2022, granted, now 11,748,990.
Application 17/830,252 is a continuation of application No. 17/040,000, filed on Sep. 30, 2020, granted, now 11,380,080, issued on Jul. 5, 2022.
Application 17/040,000 is a continuation of application No. 16/123,764, filed on Sep. 6, 2018, granted, now 10,832,075, issued on Nov. 10, 2020.
Application 16/123,764 is a continuation of application No. 15/297,053, filed on Oct. 18, 2016, granted, now 10,095,945, issued on Oct. 9, 2018.
Application 15/297,053 is a continuation of application No. 14/623,435, filed on Feb. 16, 2015, granted, now 9,501,498, issued on Nov. 22, 2016.
Claims priority of provisional application 61/940,320, filed on Feb. 14, 2014.
Prior Publication US 2023/0377340 A1, Nov. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/40 (2022.01); G06F 16/532 (2019.01); G06F 16/58 (2019.01); G06F 16/583 (2019.01); G06T 7/13 (2017.01); G06T 7/60 (2017.01); G06V 20/64 (2022.01)
CPC G06V 20/46 (2022.01) [G06F 16/532 (2019.01); G06F 16/5838 (2019.01); G06F 16/5854 (2019.01); G06F 16/5866 (2019.01); G06T 7/13 (2017.01); G06T 7/60 (2013.01); G06V 20/64 (2022.01); G06T 2207/20061 (2013.01); G06T 2207/20116 (2013.01)] 25 Claims
OG exemplary drawing
 
1. An object recognition and ingestion system comprising:
an object recognition database comprising a plurality of sets of recognition information;
at least one non-transitory computer readable memory storing executable object recognition and ingestion software instructions; and
at least one processor coupled with the at least one non-transitory computer readable memory that, upon execution of the object recognition and ingestion software instructions, performs operations to:
obtain digital data representing at least one real-world object, wherein the digital data is obtained from at least one sensor of a computing device and further includes image data of the at least one real-world object;
derive one or more sets of edges related to the at least one real-world object from the image data;
request one or more shape objects from a shape database, the one or more shape objects having shape attributes satisfying criteria determined at least as a function of the one or more sets of edges;
select at least one target shape object from the one or more shape objects based on one or more scores associated with a degree to which the one or more shape objects satisfy the criteria;
generate at least one three-dimensional object model of the at least one real-world object from the at least one target shape object and the one or more sets of edges;
compile a set of recognition information based on the three-dimensional object model; and
update the object recognition database with the set of recognition information.