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:
Aug. 25, 2020

Filed:

May. 19, 2017
Applicant:

Second Spectrum, Inc., Los Angeles, CA (US);

Inventors:

Yu-Han Chang, South Pasadena, CA (US);

Rajiv Maheswaran, Los Angeles, CA (US);

Jeffrey Wayne Su, South Pasadena, CA (US);

Noel Hollingsworth, Sunnyvale, CA (US);

Assignee:

Second Spectrum, Inc., Los Angeles, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2006.01); H04N 21/466 (2011.01); H04N 21/44 (2011.01); H04N 21/434 (2011.01); H04N 21/234 (2011.01); H04N 21/25 (2011.01); H04N 21/4223 (2011.01); H04N 21/45 (2011.01); G06N 20/00 (2019.01); H04N 5/222 (2006.01); A63F 13/60 (2014.01); H04N 13/204 (2018.01); G11B 27/031 (2006.01); G11B 27/28 (2006.01); H04N 21/2187 (2011.01); H04N 21/8549 (2011.01); G06F 3/01 (2006.01); H04N 13/243 (2018.01); H04N 13/117 (2018.01);
U.S. Cl.
CPC ...
G06K 9/00724 (2013.01); A63F 13/60 (2014.09); G06F 3/012 (2013.01); G06F 3/013 (2013.01); G06K 9/00744 (2013.01); G06N 20/00 (2019.01); G11B 27/031 (2013.01); G11B 27/28 (2013.01); H04N 5/2224 (2013.01); H04N 13/204 (2018.05); H04N 21/2187 (2013.01); H04N 21/23418 (2013.01); H04N 21/251 (2013.01); H04N 21/4223 (2013.01); H04N 21/4345 (2013.01); H04N 21/44008 (2013.01); H04N 21/4532 (2013.01); H04N 21/4662 (2013.01); H04N 21/8549 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30221 (2013.01); H04N 13/117 (2018.05); H04N 13/243 (2018.05);
Abstract

Producing an event related video content data structure includes processing a video feed through a spatiotemporal pattern recognition algorithm that uses machine learning to develop an understanding of an event within the video feed. Developing the understanding includes identifying context information relating to the event and identifying an entry in a relationship library at least detailing a relationship between two visible features of the video feed. Content of the video feed that displays the event is automatically extracted by a computer and associated with the context information. A video content data structure that includes the context information is produced.


Find Patent Forward Citations

Loading…