US 11,656,749 B2
Machine learning in video classification with schedule highlighting
Reza Zadeh, Emerald Hills, CA (US); Dong Wang, San Jose, CA (US); Deepak Menghani, Mountain View, CA (US); John Goddard, Mountain View, CA (US); and Ryan Tobin, Sacramento, CA (US)
Assigned to MATROID, INC., Palo Alto, CA (US)
Filed by Matroid, Inc, Palo Alto, CA (US)
Filed on May 7, 2022, as Appl. No. 17/739,077.
Application 17/739,077 is a continuation of application No. 16/916,121, filed on Jun. 30, 2020, granted, now 11,354,024.
Application 16/916,121 is a continuation of application No. 15/905,706, filed on Feb. 26, 2018, granted, now 10,754,514, issued on Aug. 25, 2020.
Claims priority of provisional application 62/465,790, filed on Mar. 1, 2017.
Claims priority of provisional application 62/465,788, filed on Mar. 1, 2017.
Prior Publication US 2022/0261128 A1, Aug. 18, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 17/00 (2019.01); G06F 3/04842 (2022.01); G11B 27/34 (2006.01); G11B 27/36 (2006.01); G06F 16/74 (2019.01); G06F 16/783 (2019.01); G06F 16/2457 (2019.01); G06F 3/00 (2006.01); G06F 16/738 (2019.01); G06V 20/40 (2022.01); G06F 18/241 (2023.01); G06V 10/764 (2022.01); G06F 3/0484 (2022.01)
CPC G06F 3/04842 (2013.01) [G06F 3/00 (2013.01); G06F 16/24578 (2019.01); G06F 16/738 (2019.01); G06F 16/74 (2019.01); G06F 16/7837 (2019.01); G06F 18/241 (2023.01); G06V 10/764 (2022.01); G06V 20/41 (2022.01); G11B 27/34 (2013.01); G11B 27/36 (2013.01); G06F 3/0484 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
causing display, by a client device, of an interface comprising a first interface portion and a second interface portion;
receiving, from the client device, a request to monitor a video displayed within the first interface portion for an object, the video comprising a plurality of frames, each frame associated with a timestamp;
identifying a set of frames of the video that includes the object by, for each of a plurality of frames, classifying the frame using a set of detectors trained using a machine learned model configured to identify a set of visual features representing the object within a set of training images;
identifying one or more counts of occurrences of the object using the identified set of frames and timestamps associated with the identified set of frames;
modifying the second interface portion to include the one or more identified counts of occurrences of the object; and
in response to receiving a selection of a count of occurrences of the object included within the second interface portion, causing playback, by the client device, of one or more portions of the video corresponding to the selected count of occurrences of the object within the first interface portion.