US 12,008,808 B1Granted

Location tracking system using a plurality of cameras

AssigneeTP Lab, Inc.

InventorsChi Fai Ho, Benson Junwun Ho

Life of this patent

Estimating the term…

Loading patent…

Abstract

A tracking system obtains first recognized object and associated first information being detected in at least one image captured by camera(s). First information includes first recognized object's first feature(s), first additional feature(s) derived from the first feature(s), first location(s) of first feature(s), and first real-world dimensions. A list of tracking objects is obtained, each including second recognized object and associated second information. Second information including second recognized object's second feature(s), second additional feature(s) derived from second feature(s), second location(s) of second feature(s), and second real-world dimensions. The system compares first additional feature(s) with second additional feature(s) stored in given tracking object, first location(s) with second location(s) stored in given tracking object, and first real-world dimensions with second real-world dimensions stored in given tracking object. When they match, the first information comprising first additional feature(s) are stored in given tracking object.

Claims24

Dependent claims

A method for tracking movements of an object in an area using at least one camera, comprising:

(a) obtaining, by a tracking system, a first recognized object and first information associated with the first recognized object, the first recognized object being detected in at least one image captured by the at least one camera, the first information comprising at least one first feature comprised in the first recognized object, at least one first additional feature derived from the at least one first feature, at least one first location of the at least one first feature, and first real-world dimensions of the first recognized object;
(b) obtaining, by the tracking system, a list of a plurality of tracking objects, each tracking object comprising a second recognized object and second information associated with the second recognized object, the second information comprising at least one second feature comprised in the second recognized object, at least one second additional feature derived from the at least one second feature, at least one second location of the at least one second feature, and second real-world dimensions of the second recognized object;
(c) comparing, by the tracking system, the at least one first additional feature associated with the first recognized object with the at least one second additional feature associated with the second recognized object stored in a given tracking object, comparing the at least one first location of the at least one first feature with the at least one second location of the at least one second feature, and comparing the first real-world dimensions of the first recognized object with the second real-world dimensions of the second recognized object;
and
(d) in response to determining that the at least one first additional feature matches the at least one second additional feature, the at least one first location matches the at least one second location, and the first real-world dimensions matches the second real-world dimensions, storing, by the tracking system, the first information comprising the at least one first additional feature, the at least one first location, and the first real-world dimensions in the given tracking object.

2 more elements

A non-transitory computer readable medium comprising computer readable program code embodied therein for tracking an object in an area using at least one camera, wherein when executed by one or more processors causes the one or more processors to:

(a) obtain a first recognized object and first information associated with the first recognized object, the first recognized object being detected in at least one image captured by the at least one camera, the first information comprising at least one first feature comprised in the first recognized object, at least one first additional feature derived from the at least one first feature, at least one first location of the at least one first feature, and first real-world dimensions of the first recognized object;
(b) obtain a list of a plurality of tracking objects, each tracking object comprising a second recognized object and second information associated with the second recognized object, the second information comprising at least one second feature comprised in the second recognized object, at least one second additional feature derived from the at least one second feature, at least one second location of the at least one second feature, and second real-world dimensions of the second recognized object;
(c) compare the at least one first additional feature associated with the first recognized object with the at least one second additional feature associated with the second recognized object stored in a given tracking object, compare the at least one first location of the at least one first feature with the at least one second location of the at least one second feature, and compare the first real-world dimensions of the first recognized object with the second real-world dimensions of the second recognized object;
and
(d) in response to determining that the at least one first additional feature matches the at least one second additional feature, the at least one first location matches the at least one second location, and the first real-world dimensions matches the second real-world dimensions, store the first information comprising the at least one first additional feature, the at least one first location, and the first real-world dimensions in the given tracking object.

2 more elements

A tracking system for tracking an object in an area using at least one camera, comprising:

one or more processors;
and
a non-transitory computer readable medium comprising computer readable program code embodied therein, wherein when executed by the one or more processors causes the one or more processors to:
(a) obtain a first recognized object and first information associated with the first recognized object, the first recognized object being detected in at least one image captured by the at least one camera, the first information comprising at least one first feature comprised in the first recognized object, at least one first additional feature derived from the at least one first feature, at least one first location of the at least one first feature, and first real-world dimensions of the first recognized object;
(b) obtain a list of a plurality of tracking objects, each tracking object comprising a second recognized object and second information associated with the second recognized object, the second information comprising at least one second feature comprised in the second recognized object, at least one second additional feature derived from the at least one second feature, at least one second location of the at least one second feature, and second real-world dimensions of the second recognized object;
(c) compare the at least one first additional feature associated with the first recognized object with the at least one second additional feature associated with the second recognized object stored in a given tracking object, compare the at least one first location of the at least one first feature with the at least one second location of the at least one second feature, and compare the first real-world dimensions of the first recognized object with the second real-world dimensions of the second recognized object;
and
(d) in response to determining that the at least one first additional feature matches the at least one second additional feature, the at least one first location matches the at least one second location, and the first real-world dimensions matches the second real-world dimensions, store the first information comprising the at least one first additional feature, the at least one first location, and the first real-world dimensions in the given tracking object.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 18/352,330Filed 14 Jul 2023 · continuation
Priority: 25 Feb 2020
Granted: 11 Jun 2024
Term ends: Not estimatedThe source records don’t support an estimate.

Classification10 codes

G06V 20/20
Scenes; Scene-specific elements: in augmented reality scenes
G06F 16/787
Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually: using geographical or…
G06V 20/52
Context or environment of the image: surveillance or monitoring of activities, e.g. for recognising suspicious objects
H04W 4/025
Services making use of location information: using location based information parameters

Family

Application16/799,834Parent of this continuation · filed 25 Feb 2020
Application17/813,347Parent of this continuation · filed 19 Jul 2022
US 11,436,827 B1Parent of this continuation · filed 6 Sep 2022
US 11,741,705 B1Parent of this continuation
US 12,008,808 B1This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key