US 11,790,540 B2
Object tracking and redaction
Chad Steelberg, Costa Mesa, CA (US); and Lauren Blackburn, Costa, CA (US)
Assigned to VERITONE, INC., Irvine, CA (US)
Filed by VERITONE, INC., Costa Mesa, CA (US)
Filed on May 1, 2020, as Appl. No. 16/865,288.
Claims priority of provisional application 62/843,256, filed on May 3, 2019.
Prior Publication US 2020/0388030 A1, Dec. 10, 2020
Int. Cl. G06T 7/246 (2017.01); G06T 7/00 (2017.01); G06N 3/02 (2006.01); G06V 20/40 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 40/16 (2022.01)
CPC G06T 7/248 (2017.01) [G06N 3/02 (2013.01); G06T 7/0012 (2013.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/41 (2022.01); G06V 20/46 (2022.01); G06V 40/161 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for detecting an object across frames of a video, the method comprising:
detecting a first group of one or more objects, using a first neural network, in each frame of the video using a first layer of a two-layer detection scheme;
clustering each of the detected one or more objects of the first group in each frame into one or more clustered-object groups;
identifying one or more frames of the video without one of the one or more clustered-object groups; and
analyzing the identified one or more frames, using an optical image classification engine, to detect a second group of one or more objects in the identified one or more frames using a second layer of the two-layer detection scheme.