US 11,948,401 B2
AI-based physical function assessment system
Chao Bian, Vaughan (CA); Peter Tanugraha, Toronto (CA); and Charlene Chu, Toronto (CA)
Assigned to Nightingale.ai Corp., Surrey (CA)
Filed by Nightingale.ai Corp., Surrey (CA)
Filed on Aug. 17, 2020, as Appl. No. 16/995,523.
Claims priority of provisional application 62/888,469, filed on Aug. 17, 2019.
Prior Publication US 2021/0049353 A1, Feb. 18, 2021
Int. Cl. G06K 9/00 (2022.01); G06F 18/2135 (2023.01); G06N 3/04 (2023.01); G06T 11/20 (2006.01); G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 40/20 (2022.01)
CPC G06V 40/25 (2022.01) [G06F 18/2135 (2023.01); G06N 3/04 (2013.01); G06T 11/20 (2013.01); G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/41 (2022.01); G06V 40/23 (2022.01); G06T 2210/12 (2013.01)] 24 Claims
OG exemplary drawing
 
1. An AI-based method for performing at least one of Person of Interest (POI) and Object of Interest (OOI) tracking, wherein the method is performed by at least one processor and the method comprises:
receiving a video frame;
receiving a bounding box location for a bounding box associated with a target object in the video frame, the target object being one of a POI and an OOI;
receiving bounding box coordinates associated with the bounding box location;
outputting the bounding box location on a display in real time;
determining a predicted location of the target object;
computing intersection over union (IOU) values between the bounding box location and other bounding box locations within the video frame;
selecting the bounding box location having a highest IOU value; and
outputting the selected bounding box location in the video frame on the display.