US 12,307,768 B2
Video processing for embedded information card localization and content extraction
Mihailo Stojancic, San Jose, CA (US); Warren Packard, Palo Alto, CA (US); and Dennis Kanygin, Sunnyvale, CA (US)
Assigned to STATS LLC, Chicago, IL (US)
Filed by Stats LLC, Chicago, IL (US)
Filed on Jan. 29, 2024, as Appl. No. 18/425,744.
Application 18/425,744 is a continuation of application No. 18/188,926, filed on Mar. 23, 2023.
Application 18/188,926 is a continuation of application No. 17/449,882, filed on Oct. 4, 2021, granted, now 11,615,621, issued on Mar. 28, 2023.
Application 17/449,882 is a continuation of application No. 16/411,713, filed on May 14, 2019, granted, now 11,138,438, issued on Oct. 5, 2021.
Claims priority of provisional application 62/746,454, filed on Oct. 16, 2018.
Claims priority of provisional application 62/712,041, filed on Jul. 30, 2018.
Claims priority of provisional application 62/680,955, filed on Jun. 5, 2018.
Claims priority of provisional application 62/673,411, filed on May 18, 2018.
Claims priority of provisional application 62/673,413, filed on May 18, 2018.
Claims priority of provisional application 62/673,412, filed on May 18, 2018.
Prior Publication US 2024/0169729 A1, May 23, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/12 (2017.01); G06F 16/908 (2019.01); G06V 20/40 (2022.01); G06V 30/148 (2022.01); G06V 40/20 (2022.01); H04N 21/435 (2011.01); H04N 21/44 (2011.01); H04N 21/458 (2011.01); H04N 21/81 (2011.01); H04N 21/84 (2011.01)
CPC G06V 20/42 (2022.01) [G06F 16/908 (2019.01); G06T 7/12 (2017.01); G06V 20/41 (2022.01); G06V 20/46 (2022.01); G06V 20/48 (2022.01); G06V 30/153 (2022.01); G06V 40/20 (2022.01); H04N 21/435 (2013.01); H04N 21/44008 (2013.01); H04N 21/458 (2013.01); H04N 21/8133 (2013.01); H04N 21/84 (2013.01); G06T 2207/20132 (2013.01); G06V 20/44 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for extracting metadata from a video stream, the computer-implemented method comprising:
receiving, by one or more processors, a video stream that includes a video frame;
selecting, by the one or more processors, a video frame region that forms a portion of the video frame;
identifying, by the one or more processors, a card image embedded in the video frame;
extracting, by the one or more processors, the card image from the video frame;
generating, by the one or more processors, metadata based on the extracted card image;
selecting, by the one or more processors, a metadata subset based on one or more user preferences; and
outputting, by the one or more processors, the video frame and the selected metadata subset to a display.