The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Oct. 01, 2019

Filed:

Sep. 19, 2017
Applicant:

Gumgum, Inc., Santa Monica, CA (US);

Inventors:

Jeffrey Benjamin Katz, Brookeville, MD (US);

Cambron Neil Carter, Santa Monica, CA (US);

Brian Jongmin Kim, Los Angeles, CA (US);

Assignee:

GumGum, Inc., Santa Monica, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2006.01); G06N 20/00 (2019.01); H04H 60/59 (2008.01); H04H 60/48 (2008.01); G06Q 30/02 (2012.01); G06F 16/783 (2019.01); H04N 21/232 (2011.01); H04N 21/2387 (2011.01); H04N 21/24 (2011.01); H04N 21/2547 (2011.01); H04N 21/81 (2011.01); H04N 21/2187 (2011.01); H04N 21/234 (2011.01); H04N 21/442 (2011.01); G06T 7/62 (2017.01); G06T 7/70 (2017.01); G06K 9/62 (2006.01); G06K 9/68 (2006.01); H04H 60/66 (2008.01); H04N 21/44 (2011.01); H04N 21/262 (2011.01); H04N 21/414 (2011.01); H04H 60/63 (2008.01); H04N 21/2665 (2011.01); H04N 21/658 (2011.01); G06F 3/0484 (2013.01); G06F 3/0488 (2013.01); H04H 60/47 (2008.01);
U.S. Cl.
CPC ...
G06K 9/00744 (2013.01); G06F 16/783 (2019.01); G06F 16/7837 (2019.01); G06K 9/00718 (2013.01); G06K 9/00724 (2013.01); G06K 9/6256 (2013.01); G06K 9/6267 (2013.01); G06K 9/6274 (2013.01); G06K 9/6878 (2013.01); G06N 20/00 (2019.01); G06Q 30/0242 (2013.01); G06Q 30/0273 (2013.01); G06Q 30/0275 (2013.01); G06T 7/62 (2017.01); G06T 7/70 (2017.01); H04H 60/48 (2013.01); H04H 60/59 (2013.01); H04H 60/63 (2013.01); H04H 60/66 (2013.01); H04N 21/2187 (2013.01); H04N 21/232 (2013.01); H04N 21/2387 (2013.01); H04N 21/23418 (2013.01); H04N 21/2407 (2013.01); H04N 21/2547 (2013.01); H04N 21/2665 (2013.01); H04N 21/26241 (2013.01); H04N 21/41415 (2013.01); H04N 21/44008 (2013.01); H04N 21/44204 (2013.01); H04N 21/6581 (2013.01); H04N 21/812 (2013.01); H04N 21/8133 (2013.01); G06F 3/04842 (2013.01); G06F 3/04883 (2013.01); G06K 2209/01 (2013.01); G06K 2209/25 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30224 (2013.01); H04H 60/47 (2013.01);
Abstract

Systems and methods are described for training machine learning models to detect objects in image or video data. A system may select a first sample set of frames from one or more video files. Indications of a location of an object of interest in each of at least two sample frames may be received, then the system may determine the location of the object of interest across a number of intermediary frames using a tracker. Annotation data may be stored identifying the objects of interest in the sample frames, and the annotation data may be used in training a machine learning model to identify the object of interest in subsequently provided image or video data.


Find Patent Forward Citations

Loading…