US 11,696,011 B2
Predictive field-of-view (FOV) and cueing to enforce data capture and transmission compliance in real and near real time video
Matthew J. Tacy, Boston, MA (US); John A. Cogliandro, Dedham, MA (US); and Allan Mayorga, Salem, MA (US)
Assigned to Raytheon Company, Waltham, MA (US)
Filed by Raytheon Company, Waltham, MA (US)
Filed on Oct. 21, 2021, as Appl. No. 17/507,111.
Prior Publication US 2023/0131642 A1, Apr. 27, 2023
Int. Cl. G06V 20/20 (2022.01); H04N 19/00 (2014.01); G06T 7/20 (2017.01); H04N 23/61 (2023.01); H04N 23/60 (2023.01); H04N 23/63 (2023.01); H04N 23/695 (2023.01)
CPC H04N 23/61 (2023.01) [G06T 7/20 (2013.01); G06V 20/20 (2022.01); H04N 23/634 (2023.01); H04N 23/64 (2023.01); H04N 23/695 (2023.01)] 28 Claims
OG exemplary drawing
 
1. A method of preventing capture and transmission of excluded data in a local scene from a video signal, said method comprising:
generating a ground truth map (GTM) of the local scene including one or more objects;
identifying one or more of the objects in the GTM as disallowed;
using a video camera to capture a video signal at a frame rate within a camera field-of-view (CFOV) in a pointing direction in the local scene, said camera FOV capturing a portion of the local scene within the GTM without any disallowed objects;
determining a pose including a location and an orientation of the video camera within the local scene for a current frame;
receiving measurements of velocity and acceleration of the video camera's pointing direction;
computing one or more predicted FOV (PFOV) for one or more future frames from the pose for the current frame and the measurements of velocity and acceleration, said one or more PFOV capturing one or more different portions of the local scene within the GTM;
comparing the one or more PFOV to the GTM to recognize and locate disallowed objects outside the CFOV for the current frame; and
if a disallowed object is recognized, controlling the video camera to prevent capture of disallowed objects within the CFOV and their inclusion in the one or more future frames of the video signal.