US 11,893,514 B2
Contextual-based method and system for identifying and revealing selected objects from video
Garry Anthony Smith, Sydney (AU); Naomi Felina Moneypenny, Bellvue, WA (US); Zachary Oakes, Kochi (JP); Steven Dennis Flinn, Sugar Land, TX (US); and Michael George Renie, Narrabeen (AU)
Assigned to Revealit Corporation, Seattle, WA (US)
Filed by Revealit Corporation, Seattle, WA (US)
Filed on Jul. 5, 2022, as Appl. No. 17/857,921.
Application 17/857,921 is a continuation of application No. 16/492,862, granted, now 11,416,714, previously published as PCT/US2018/024218, filed on Mar. 24, 2018.
Claims priority of provisional application 62/475,942, filed on Mar. 24, 2017.
Prior Publication US 2022/0343119 A1, Oct. 27, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/211 (2020.01); G06F 40/30 (2020.01); G06V 20/40 (2022.01); G06N 5/048 (2023.01); G06F 18/21 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/44 (2022.01); G06V 40/20 (2022.01)
CPC G06N 5/048 (2013.01) [G06F 18/2178 (2023.01); G06F 40/211 (2020.01); G06F 40/30 (2020.01); G06V 10/451 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 40/20 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving a video stream comprising a sequence of images;
directing a focus of attention of a computer-implemented system to a first image of the sequence of images;
using a computer implemented neural network to obtain an interpretation of a plurality of pixels within the first image;
determining automatically a probability that is associated with identifying a representation of an object by the interpretation of the plurality of pixels;
updating the probability to an updated probability in accordance with an automatically inferred context that is associated with the first image; and
delivering to a user a communication that is in accordance with the updated probability, wherein the communication comprises a plurality of syntactical elements that reference attributes of the object.