Context-based, partial edge intelligence facial and vocal characteristic recognition

• US 10,535,145 B2
• Filed: 07/14/2017
• Issued: 01/14/2020
• Est. Priority Date: 07/14/2017
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Motorola Solutions, Inc.
• Inventors: Lim, Chew How, Lim, Bing Qin, Abdullah, Mohd Faisal, Gan, Guo Dong, Ramanathan, Rm Muthaiah
• Primary Examiner(s): Entezari, Michelle M
• Application Number:
  US15/650,676
• Publication Number:
  US 20190019297A1
• Time in Patent Office: 914 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/95 structured as a network, e.g. client-server architectures
• CPC Class Codes: G06V 20/49 Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
• CPC Class Codes: G06V 2201/07 Target detection
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/67 by interactive indications to the user
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence

Abstract

A recognition device and method for recognizing a target. The recognition device includes a sensor and an electronic processor. The electronic processor configured to receive the characteristic from the sensor. The electronic processor identifies a profile based on the characteristic and compares the profile to a plurality of predetermined profiles to determine an identity profile. The electronic processor identifies the target based on the identity profile and determines, based on at least one selected from the group consisting of a location of the target, speed of the target, and a direction of movement of the target, a virtual geographic boundary. The electronic processor causes a transmission of the at least one selected from the group consisting of the identity profile and the characteristic to at least one associated device located in the virtual geographic boundary.

Claims

1. A recognition device comprising:

a sensor configured to sense a characteristic of a target, wherein the sensor is at least one selected from the group consisting of an audio sensor, a camera, and a video sensor; and

an electronic processor configured to

receive the characteristic from the sensor;

identify a profile based on the characteristic;

compare the profile to a plurality of predetermined profiles to determine an identity profile, the identity profile corresponding to an identity of a person or an inanimate object;

store the identity profile on a memory of the recognition device;

identify the target based on the identity profile;

determine either or both of a speed of the target and a direction of movement of the target based on an input from the sensor;

determine a virtual geographic boundary around the target based on at least one selected from the group consisting of the speed of the target and the direction of movement of the target;

determine, based on the speed of the target, a hold duration indicative of how long to store the identity profile in the memory;

cause a transmission of the hold duration and at least one selected from the group consisting of the identity profile and the characteristic to at least one associated device located in the virtual geographic boundary; and

delete the identity profile from the memory of the recognition device in response to at least one selected from the group consisting of an absence of receiving a second characteristic of the target during the hold duration and the target leaving the virtual geographic boundary.

2. The recognition device of claim 1, wherein the plurality of predetermined profiles are stored on either a memory of the recognition device or a remote server and the electronic processor is further configured to, when the identity profile is found on the remote server, store the identity profile in the memory of the recognition device.

3. The recognition device of claim 1, wherein the electronic processor is further configured to cause a transmission of the hold duration to the at least one associated device located in the virtual geographic boundary.

4. The recognition device of claim 1, wherein the transmission is performed by a remote server or the recognition device.

5. The recognition device of claim 1, wherein the characteristic is at least one from the group consisting of a facial feature, a vocal feature, and a feature of a wearable article.

6. The recognition device of claim 1, wherein a shape of the virtual geographic boundary is based on the direction of movement of the target.

7. The recognition device of claim 1, wherein a size of the virtual geographic boundary is based on a speed of the target.

8. The recognition device of claim 1, wherein the electronic processor is further configured to update the virtual geographic boundary based on at least one selected from the group consisting of a location of the target, speed of the target, and a direction of movement of the target.

9. A method of recognizing a target, the method comprising:

receiving, from a sensor selected from the group consisting of an audio sensor, a camera, and a video sensor, a characteristic of the target;

identifying a profile based on the characteristic;

comparing the profile to a plurality of predetermined profiles to determine an identity profile, the identity profile corresponding to an identity of a person or an inanimate object;

storing the identity profile on a memory;

identifying the target based on the identity profile;

determining either or both of a speed of the target and a direction of movement of the target based on an input from the sensor;

determining a virtual geographic boundary based on at least one selected from the group consisting of the speed of the target and the direction of movement of the target;

determining, based on the speed of the target, a hold duration indicative of how long to store the identity profile in the memory;

causing a transmission of the hold duration and at least one selected from the group consisting of the identity profile and the characteristic to at least one associated device located in the virtual geographic boundary; and

deleting the identity profile from the memory of the recognition device in response to at least one selected from the group consisting of an absence of receiving a second characteristic of the target during the hold duration and the target leaving the virtual geographic boundary.

10. The method of claim 9, wherein the plurality of predetermined profiles are stored on either a memory of a recognition device or a remote server and the method further comprises when the identity profile is found on the remote server, storing the identity profile in the memory of the recognition device.

11. The method of claim 9, further comprising transmitting the hold duration to the at least one associated device located in the virtual geographic boundary.

12. The method of claim 9, wherein the transmission is performed by a remote server or a recognition device.

13. The method of claim 9, wherein the characteristic is at least one from the group consisting of a facial feature, a vocal feature, and a feature of a wearable article.

14. The method of claim 9, wherein a shape of the virtual geographic boundary is based on the direction of movement of the target.

15. The method of claim 9, wherein a size of the virtual geographic boundary is based on a speed of the target.

16. The method of claim 9, the method further comprising updating the virtual geographic boundary based on at least one selected from the group consisting of a location of the target, speed of the target, and a direction of movement of the target.