US 11,869,234 B2
Subject tracking systems for a movable imaging system
Sammy Omari, Zurich (CH); and Joseph A. Enke, Campbell, CA (US)
Assigned to GoPro, Inc., San Mateo, CA (US)
Filed by GoPro, Inc., San Mateo, CA (US)
Filed on May 19, 2020, as Appl. No. 16/878,240.
Application 16/878,240 is a continuation of application No. 15/918,694, filed on Mar. 12, 2018.
Application 15/918,694 is a continuation in part of application No. 15/656,559, filed on Jul. 21, 2017, granted, now 10,636,150, issued on Apr. 28, 2020.
Claims priority of provisional application 62/372,549, filed on Aug. 9, 2016.
Claims priority of provisional application 62/364,960, filed on Jul. 21, 2016.
Prior Publication US 2020/0349721 A1, Nov. 5, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 23/695 (2023.01); B64U 101/30 (2023.01); G06V 20/13 (2022.01); G06T 7/246 (2017.01); B64D 47/08 (2006.01); B64C 39/02 (2023.01); G01S 13/76 (2006.01); G01S 13/87 (2006.01); G06V 20/17 (2022.01)
CPC G06V 20/13 (2022.01) [B64C 39/024 (2013.01); B64D 47/08 (2013.01); G01S 13/76 (2013.01); G01S 13/878 (2013.01); G06T 7/248 (2017.01); G06V 20/17 (2022.01); H04N 23/695 (2023.01); B64U 2101/30 (2023.01); B64U 2201/104 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
capturing successive video image frames to generate a video;
processing the video image frames from an imaging device to determine previous positions of multiple subjects;
obtaining motion information of the multiple subjects from one or more sensors physically attached to the multiple subject respectively;
determining a predicted position of the multiple subjects respectively from the motion information of the multiple subjects, and the previous positions of the multiple subjects;
adjusting the imaging device based on the predicted position of the multiple subjects respectively so that the multiple subjects are subject is framed within the successive video image frames;
determining a region of interest of a subsequent image of the multiple subjects in a predefined spatial relationship relative to the predicted position;
obtaining subsequent successive video image frames with the imaging device;
processing the successive video image frames to determine an updated position of the multiple subjects so that the multiple subjects are automatically tracked by the imaging device;
monitoring a voice recognition system and interpreting audio or voice commands;
adjusting the trajectory based upon the audio or the voice commands;
identifying the multiple subjects within the successive video image frames; and
providing live videos being captured to a sharing service via an application of the imaging device.