System and method for intelligent pattern recognition

Patent metadata

Field	Value
Publication number	US-11138480-B2
Application number	US-201916541251-A
Country	US
Kind code	B2
Filing date	Aug 15, 2019
Priority date	Jun 6, 2016
Publication date	Oct 5, 2021
Grant date	Oct 5, 2021

Abstract

Embodiments include a system, method, and computer program product for distributed intelligent pattern recognition. Embodiments include a cooperative multi-agent detection system that enables an array of disjunctive devices (e.g., cameras, sensors) to selectively cooperate to identify objects of interest over time and space, and to contribute an object of interest to a shared deep learning pattern recognition system based on a bidirectional feedback mechanism. Embodiments provide updated information and/or algorithms to one or more agencies for local system learning and pattern updating recognition models. Each of the multiple agencies may in turn, update devices (e.g., cameras, sensors) coupled to the local machine learning and pattern recognition models.

First claim

What is claimed is:

1. A system for a camera client computing device, comprising:
a memory; and
one or more processors coupled to the memory, configured to:
electronically receive a search request message for an object of interest;
request a pattern recognition algorithm module based on the object of interest;
in response to the request, receive an object of interest module;
replace an existing algorithm module with the received object of interest module; and
execute the object of interest module to analyze the object of interest with reference data,
wherein the object of interest module and the reference data are adapted according to a confirmation of a first potential match image.

2. The system of claim 1 , wherein the one or more processors are further configured to:
determine a second potential match image;
update the reference data based on the second potential match image; and
electronically transmit the second potential match image.

3. The system of claim 2 , wherein the one or more processors are further configured to:
receive a positive confirmation regarding the second potential match image; and
update the object of interest module based on the positive confirmation received.

4. The system of claim 2 , wherein the one or more processors are further configured to: transmit data to a display device, wherein the data comprises a location of the camera client computing device associated with the second potential match image.

5. The system of claim 1 , wherein the object of interest module is updated based on a bidirectional feedback mechanism.

6. The system of claim 1 , wherein the camera client computing device comprises: a wearable camera or a mobile device.

7. The system of claim 1 , wherein the one or more processors are further configured to:
receive a priority message comprising criteria; and
based on the criteria, adjust: a camera resolution, a camera speed, or a type of the object of interest.

8. The system of claim 1 , wherein the object of interest is an animal, the one or more processors are further configured to:
use the object of interest module to transform the object of interest based on aging or changes in appearance.

9. The system of claim 1 ,
wherein the object of interest is a human, and
wherein the pattern recognition algorithm module comprises a facial recognition algorithm module.

10. The system of claim 1 , wherein the one or more processors are further configured to:
recognize a concept or context in the search request message; and
request the pattern recognition algorithm module based on the concept or context.

11. The system of claim 1 , wherein the search request message comprises: an originating agency, a date and time of an image of the object of interest, a certain time period, last known location of the object of interest, originating agency communications address and/or routing information, a relational ID, a confirmation and request transaction ID, a stored or preformatted formatted message, a message request expiration value, a name, a color, an ethnicity, a gender, a height, a material, a related object, a person related to the object of interest, an identifying number, or an identifying feature of the object of interest.

12. The system of claim 1 , wherein the search request message comprises a first and a second time period, the one or more processors are further configured to:
execute the object of interest module for a duration of the first time period;
after the first time period, request a second pattern recognition algorithm module for a second object of interest;
in response to the request for the second pattern recognition algorithm module, receive a second object of interest module corresponding to the second time period; and
execute the second object of interest module for a duration of the second time period.

13. A method for a camera client, comprising:
electronically receiving a search request message for an object of interest;
requesting a pattern recognition algorithm module based on the object of interest;
in response to the requesting, receiving an object of interest module;
replacing an existing algorithm module with the object of interest algorithm module; and
executing the object of interest module to analyze the object of interest with reference data,
wherein the object of interest module and the reference data are adapted according to a confirmation of a first potential match image.

14. The method of claim 13 , further comprising:
determining a second potential match image;
updating the reference data based on the second potential match image; and
electronically transmitting the second potential match image.

15. The method of claim 14 , further comprising:
receiving a positive confirmation regarding the second potential match image and the object of interest; and
updating the object of interest module based on the positive confirmation received.

16. The method of claim 14 , further comprising:
transmitting data to a display device,
wherein the data comprises a location of the camera client associated with the second potential match image.

17. The method of claim 13 , further comprising: updating the object of interest algorithm based on a bidirectional feedback mechanism.

18. The method of claim 13 , further comprising:
receiving a priority message comprising criteria; and
in response to the criteria, adjusting: a camera resolution, a camera speed, or a type of the object of interest.

19. The method of claim 13 , further comprising:
wherein the object of interest is an animal, transforming the object of interest based on aging or changes in appearance.

20. A non-transitory computer-readable medium having instructions stored therein, which when executed by a processor cause the processor to perform operations, the operations comprising:
electronically receiving a search request message for an object of interest;
requesting a pattern recognition algorithm module based on the object of interest;
in response to the requesting, receiving an object of interest module;
replacing an existing algorithm module with the received object of interest module; and
executing the object of interest module to analyze the object of interest with reference data,
wherein the object of interest module and the reference data are adapted according to a confirmation of a first potential match image.

Assignees

• Mutualink Inc

Inventors

• Mazzarella Joseph R
• Wengrovitz Michael S

Classifications

• G06V20/52 Primary

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G06F16/5838

  using colour · CPC title

• G06V10/70

  using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88) · CPC title

• G06V10/95

  structured as a network, e.g. client-server architectures · CPC title

• G06V30/194

  References adjustable by an adaptive method, e.g. learning · CPC title