Shopping basket monitoring using computer vision and machine learning

Patent metadata

Field	Value
Publication number	US-12106644-B2
Application number	US-202318367930-A
Country	US
Kind code	B2
Filing date	Sep 13, 2023
Priority date	Sep 7, 2018
Publication date	Oct 1, 2024
Grant date	Oct 1, 2024

Abstract

A system for monitoring shopping baskets (e.g., baskets on human-propelled carts, motorized carts, or hand-carried baskets) can include a computer vision unit that can image a surveillance region (e.g., an exit to a store), determine whether a basket is empty or loaded with merchandise, and assess a potential for theft of the merchandise. The computer vision unit can include a camera and an image processor programmed to execute a computer vision algorithm to identify shopping baskets and determine a load status of the basket. The computer vision algorithm can comprise a neural network. The system can identify an at least partially loaded shopping basket that is exiting the store, without indicia of having paid for the merchandise, and execute an anti-theft action, e.g., actuating an alarm, notifying store personnel, activating a store surveillance system, activating an anti-theft device associated with the basket (e.g., a locking shopping cart wheel), etc.

First claim

What is claimed is:

1. An anti-theft system for a retail store environment, the system comprising:
a wheel configured to connect to a human-propelled shopping cart having a basket for merchandise, the wheel comprising:
a radio frequency (RF) cart transceiver; and
a brake configured to inhibit movement of the cart when the brake is actuated;

a computer vision unit (CVU) comprising:
a camera configured to obtain images of an exit of the retail store;
an image processor configured to analyze the images; and
an RF communication node configured to wirelessly communicate with the RF cart transceiver;
the CVU being programmed to:
determine that the basket of the cart contains merchandise;
determine a direction from which the cart is approaching the exit of the retail store;
classify the cart with the basket containing merchandise as authorized to exit the retail store in response to determining that the cart is approaching the exit of the retail store from the direction of a pay point of the retail store; and
communicate a command to the RF cart transceiver that the cart is authorized to pass through the exit.

2. The anti-theft system of claim 1 , wherein the classification that the cart with the basket containing merchandise is authorized to exit the retail store further comprises a determination of whether the cart passed through a checkout lane.

3. The anti-theft system of claim 2 , wherein the determination of whether the cart passed through the checkout lane further comprises a determination of whether the cart spent at least 1 minute in the checkout lane.

4. An anti-theft system for a retail store environment, the system comprising:
a wheel configured to connect to a human-propelled shopping cart having a basket for merchandise, the wheel comprising:
a radio frequency (RF) cart transceiver; and
a brake configured to inhibit movement of the cart when the brake is actuated;

a first camera configured to obtain images of a pay point of the retail store, the first camera having a field of view (FOV);
a second camera configured to obtain images of an exit region of the retail store, the second camera having a FOV that overlaps the FOV of the first camera;
an image processor in communication with the first and second cameras, the image processor configured to analyze the images of the pay point and the images of the exit region, the image processor being programmed to:
identify the cart in the images of the pay point;
determine, using the images of the pay point, a load status of the basket of the cart;
track a path of the cart as the cart leaves the pay point and passes through the exit region toward an exit door of the retail store; and
determine, using the load status and the path of the cart, that the cart is authorized to exit the retail store or is not authorized to exit the retail store; and

an RF communication node configured to communicate with the image processor, the RF communication node further configured to transmit a command to the RF cart transceiver of the cart, wherein:
in response to the determination that the cart is authorized to exit the retail store, the command comprises an exit authorization command; and
in response to the determination that the cart is not authorized to exit the retail store, the command comprises an anti-theft command.

5. The anti-theft system of claim 4 , wherein the image processor is further programmed such that the determination of the path of the cart comprises determining whether the cart passes directly from the pay point to the exit door.

6. The anti-theft system of claim 4 , wherein the image processor is further programmed such that the determination of the load status comprises determining that the basket of the cart does not contain merchandise for sale in the retail store.

7. The anti-theft system of claim 4 , wherein the anti-theft command comprises a command to actuate the brake.

8. The anti-theft system of claim 4 , wherein the exit authorization command comprises a command to not actuate the brake.

9. The anti-theft system of claim 4 , further comprising a housing containing the image processor and the RF communication node.

10. The anti-theft system of claim 4 , wherein the image processor is further programmed to determine, using the images of the pay point, whether the cart was at the pay point for at least a predetermined period.

11. The anti-theft system of claim 1 , wherein the CVU is further programmed to communicate with the pay point.

12. The anti-theft system of claim 11 , wherein the communication with the pay point comprises a determination of whether the merchandise in the basket was paid for.

13. The anti-theft system of claim 1 , wherein the CVU is further programmed to communicate a command to a checkout barrier.

14. The anti-theft system of claim 1 , wherein the CVU is further programmed to recognize the presence of an object located in a child seat of the cart.

15. The anti-theft system of claim 1 , wherein the CVU is further programmed to determine the presence of a child in the cart.

16. The anti-theft system of claim 1 , wherein the pay point comprises a checkout register or a mobile pay point.

17. The anti-theft system of claim 1 , wherein the camera is further configured to obtain images of an exit door of the retail store.

18. The anti-theft system of claim 1 , wherein the camera and the RF communication node are disposed in a housing configured to be mounted to a structure in the facility and the image processor is disposed remotely from the housing.

19. The anti-theft system of claim 1 , further comprising a door manager, wherein the RF communication node is configured to wirelessly communicate with the RF cart transceiver via the door manager.

20. The anti-theft system of claim 1 , wherein the wheel further comprises a very low frequency (VLF) receiver.

Assignees

• Gatekeeper Systems Inc

Inventors

• Ramanathan Narayanan V
• Carter Scott J
• Hannah Stephen E
• James Jesse Michael
• Johnson Jack L
• Harling Robert M

Classifications

• B62B3/1404

  Means for facilitating stowing or transporting of the trolleys; Antitheft arrangements (B62B5/0423 takes precedence) · CPC title

• B62B5/0404

  automatic · CPC title

• G08B13/19652

  Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm · CPC title

• G08B13/19613 Primary

  Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion · CPC title

• G08B13/19602 Primary

  Image analysis to detect motion of the intruder, e.g. by frame subtraction · CPC title