Entity detection

• US 10,325,159 B1
• Filed: 08/13/2018
• Issued: 06/18/2019
• Est. Priority Date: 12/06/2013
• Status: Active Grant

• Current Assignee: Vivint Incorporated (NRG Energy, Inc.)
• Original Assignee: Vivint Incorporated (NRG Energy, Inc.)
• Inventors: Nye, James Ellis
• Primary Examiner(s): Azarian, Seyed H
• Application Number:
  US16/101,654
• Time in Patent Office: 309 Days
• Field of Search: 382100, 382103-107, 382155, 382162, 382168, 382173, 382181, 382189, 382199, 382209, 382219, 382224, 382232, 382254, 382274, 382276, 382286-291, 382305, 382312, 348148, 348143, 340 101
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

A computer-implemented method for entity detection is described. In one embodiment, an entity passing through a perimeter of a predefined area is detected via a camera. Upon detecting the entity passing through the perimeter of the predefined area, a type of the entity is classified from an image of the entity captured by the camera. Upon classifying the type of the entity, a feature of the entity is detected from the image of the entity. An identifier is assigned to the entity based on the type and the detected feature of the entity. The identifier distinguishes the entity from another entity of a same type.

Claims

1. A method for entity detection by a processor, comprising:

detecting an entity entering a predefined area based at least in part on camera data,

wherein the entity includes a human or an animal;

detecting a feature of the entity based at least in part on the camera data;

comparing the detected feature to one or more predefined features stored in a database;

matching the detected feature to one or more of the predefined features;

recognizing the entity based at least in part on an image of the entity captured by a camera and the detected feature;

determining an identifier assigned to the entity based at least in part on matching the detected feature to one or more of the predefined features, wherein the identifier was assigned to the entity at a previous time; and

generating a notification indicating the entity based at least in part on determining the identifier.

2. The method of claim 1, wherein the feature of the entity is a facial feature, an audio feature, or a device identifier of a mobile device associated with the entity.

3. The method of claim 1, further comprising:

associating, with the identifier of the entity, a transaction by the entity at the predefined area; and

determining an average value of transaction from the transaction and previous transactions associated with the identifier of the entity, wherein the notification is based at least in part on the average value.

4. The method of claim 1, wherein the predefined area includes a shop, a restaurant, a home, an area of the home, an animal cage, or a wilderness area.

5. The method of claim 1, further comprising:

detecting that a vehicle is positioned in a parking lot based at least in part on second camera data;

identifying the entity exiting the vehicle based at least in part on the second camera data; and

tracking a location of the entity, wherein detecting the entity entering the predefined area is based at least in part on tracking the location of the entity.

6. The method of claim 5, further comprising:

determining an average length of stay of the entity at the predefined area based at least in part on at least one length of a previous stay of the entity at the predefined area, wherein the notification is based at least in part on the average length of stay of the entity.

7. The method of claim 5, wherein tracking the location of the entity further comprises:

tracking the location of the entity relative to the parking lot for a predetermined length of time since an arrival of the vehicle in the parking lot, wherein the notification is based at least in part on a time since the arrival of the vehicle exceeding the predetermined length of time and the tracking.

8. The method of claim 1, further comprising:

classifying a type of the entity based at least in part on the image of the entity captured by a camera, wherein recognizing the entity is based at least in part on the type of the entity.

9. An apparatus for entity detection, comprising:

a processor;

memory in electronic communication with the processer; and

instructions stored in the memory and operable, when executed by the processor, to cause the apparatus to;

detect an entity entering a predefined area based at least in part on camera data, wherein the entity includes a human or an animal;

detect a feature of the entity based at least in part on the camera data;

compare the detected feature to one or more predefined features stored in a database;

match the detected feature to one or more of the predefined features;

recognize the entity based at least in part on an image of the entity captured by a camera and the detected feature;

determine an identifier assigned to the entity based at least in part on matching the detected feature to one or more of the predefined features, wherein the identifier was assigned to the entity at a previous time; and

generate a notification indicating the entity based at least in part on determining the identifier.

10. The apparatus of claim 9, wherein the feature of the entity is a facial feature, an audio feature, or a device identifier of a mobile device associated with the entity.

11. The apparatus of claim 9, wherein the instructions are further executable by the processor to:

associating, with the identifier of the entity, a transaction by the entity at the predefined area; and

determining an average value of transaction from the transaction and previous transactions associated with the identifier of the entity, wherein the notification is based at least in part on the average value.

12. A non-transitory computer readable medium storing code for entity detection, the code comprising instructions executable by a processor to:

detect an entity entering a predefined area based at least in part on camera data, wherein the entity includes a human or an animal;

detect a feature of the entity based at least in part on the camera data;

compare the detected feature to one or more predefined features stored in a database;

match the detected feature to one or more of the predefined features;

recognize the entity based at least in part on an image of the entity captured by a camera and the detected feature;

determine an identifier assigned to the entity based at least in part on matching the detected feature to one or more of the predefined features, wherein the identifier was assigned to the entity at a previous time; and

generate a notification indicating the entity based at least in part on determining the identifier.