US 11,869,201 B2
Systems and methods for identifying a unified entity from a plurality of discrete parts
Soumitri Kolavennu, Blaine, MN (US); and Nathaniel Kraft, Minnetonka, MN (US)
Assigned to ADEMCO INC., Golden Valley, MN (US)
Filed by Ademco Inc., Golden Valley, MN (US)
Filed on May 2, 2022, as Appl. No. 17/734,303.
Application 17/734,303 is a continuation of application No. 16/859,214, filed on Apr. 27, 2020, granted, now 11,335,112.
Prior Publication US 2022/0262155 A1, Aug. 18, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/246 (2017.01); G06T 7/20 (2017.01); G06N 5/04 (2023.01); G06V 40/10 (2022.01); G06V 10/25 (2022.01); G06T 7/70 (2017.01); G06N 20/00 (2019.01); G06F 18/214 (2023.01); G06V 10/774 (2022.01)
CPC G06T 7/251 (2017.01) [G06F 18/214 (2023.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06T 7/20 (2013.01); G06T 7/70 (2017.01); G06V 10/25 (2022.01); G06V 10/774 (2022.01); G06V 40/10 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
capturing a sequence of images of a monitored region that includes a pool;
processing the sequence of images using heuristics and rules of an artificial intelligence model to identify body parts of a person;
using the heuristics and the rules of the artificial intelligence model to identify occluded body parts that are at least partially occluded by water in the pool based on visible body parts; and
processing the sequence of images using the heuristics and the rules of the artificial intelligence model to virtually link together a group of the body parts that correspond to the person who is present in the pool, wherein the heuristics and the rules of the artificial intelligence model are developed from a training process that includes the artificial intelligence model receiving sample images delineating exemplary human body parts, and virtually linking together the group of the body parts comprises extrapolating from exemplary groupings of the exemplary human body parts delineated in the exemplary human body parts as identified in the sample images; and
using the heuristics and the rules of the artificial intelligence model to determine an emergency situation or an alarm situation based on a position of the body parts relative to the water in the pool.
 
10. A system comprising:
a camera that captures a sequence of images of a monitored region that includes a pool; and
a processor that receives the sequence of images and processes the sequence of images using heuristics and rules of an artificial intelligence model that are developed from a training process that includes the artificial intelligence model receiving sample images delineating exemplary human body parts, the processor using the heuristics and the rules of the artificial intelligence model to:
identify visible body parts of a person in the pool,
identify occluded body parts of the person in the pool based on the visible body parts, the occluded body parts being at least partially occluded by water in the pool,
virtually link together the visible body parts and the occluded body parts based on extrapolating from exemplary groupings of the exemplary human body parts delineated in the exemplary human body parts as identified in the sample images, and
determine an emergency situation or an alarm situation based on a position of the visible body parts and the occluded body parts relative to the water in the pool.
 
19. A method comprising:
capturing a sequence of images of a monitored region that includes a pool;
processing the sequence of images using heuristics and rules of an artificial intelligence model to identify body parts of a person;
using the heuristics and the rules of the artificial intelligence model to identify occluded body parts that are at least partially occluded by water in the pool based on visible body parts; and
processing the sequence of images using the heuristics and the rules of the artificial intelligence model to virtually link together a group of the body parts that correspond to the person who is present in the pool, wherein the heuristics and the rules of the artificial intelligence model are developed from a training process that includes the artificial intelligence model receiving sample images delineating exemplary human body parts, and virtually linking together the group of the body parts comprises:
identifying a respective type of each of the body parts,
identifying a respective location of each of the body parts, and
identifying each of the body parts for which the respective type and the respective location conform to a model of the person developed from the training process; and
using the heuristics and the rules of the artificial intelligence model to determine an emergency situation or an alarm situation based on a position of the body parts relative to the water in the pool.