Faulty cart wheel detection

• US 9,002,095 B2
• Filed: 12/20/2012
• Issued: 04/07/2015
• Est. Priority Date: 12/20/2012
• Status: Active Grant

• Current Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Original Assignee: Wal-Mart Stores Texas LLC (WalMart Inc.)
• Inventors: Argue, Stuart, Marcar, Anthony Emile
• Primary Examiner(s): Chang, Jon
• Assistant Examiner(s): Mistry, Oneal R
• Application Number:
  US13/723,117
• Publication Number:
  US 20140177907A1
• Time in Patent Office: 838 Days
• Field of Search: None
• US Class Current: 382/141
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection

Abstract

A system and method of identifying carts exhibiting tendencies that are indicative of damaged or defective wheels. A shopping cart may be identified and tracked visually through one or more surveillance cameras. By comparing the cart'"'"'s tracked movement to known symptomatic movement patterns, the system may identify defective or damaged carts. Alternatively, by analyzing movement and positioning of a cart'"'"'s swiveling wheels, the system may identify defective or damaged carts. Alternatively, by identifying if a customer has abandoned a cart, the system may identify defective or damaged carts. A notification message may be transmitted to an associate to repair or replace the identified problematic cart. The notification may be displayed on a mobile computing device, a workstation, or other like systems.

Claims

1. A computer-implemented method of detecting a faulty wheel, comprising:

receiving, at an image processing module, an image sequence depicting a cart having the faulty wheel, wherein the faulty wheel exhibits one of a swiveling resistance and a wobble;

detecting, by the image processing module, that the cart has the faulty wheel;

wherein detecting, by the image processing module, that the cart has the faulty wheel further comprises identifying, by the image processing module, the cart as an abandoned cart; and

transmitting an alert regarding the abandoned cart.

2. The method of claim 1, wherein identifying, by the image processing module, the cart as an abandoned cart comprises identifying a person associated with the cart.

3. The method of claim 2, further comprising tracking, by the image processing module, the person'"'"'s movement.

4. The method of claim 3, wherein identifying, by the image processing module, the cart as an abandoned cart further comprises:

selectively establishing an abandonment time threshold and determining, by the image processing module, if the person leaves the cart for longer than the abandonment time threshold.

5. The method of claim 3, wherein identifying, by the image processing module, the cart as an abandoned cart further comprises:

selectively establishing an abandonment distance threshold; and

determining, by the image processing module, if the person moves away from the cart farther than the abandonment distance threshold.

6. The method of claim 1, further comprising:

identifying, by the image processing module, an item in the cart;

visually tracking, by the image processing module, the item as the customer removes the item from the cart; and

verifying, by the image processing module, that the cart contains no items.

7. The method of claim 6, further comprising verifying, by the image processing module, that the customer has placed the item into a replacement cart.

8. The method of claim 1, wherein transmitting an alert regarding the abandoned cart comprises transmitting a signal to a mobile computing device.

9. The method of claim 1, wherein transmitting an alert regarding the abandoned cart comprises transmitting a request to remove the cart from use.

10. A system for detecting a faulty wheel, comprising:

a camera;

an image processing module comprising one or more image processing processors and one or more image processing memory devices operably coupled to the one or more image processing processors and storing executable and operational image processing data, the executable and operational image processing data effective to cause the one or more image processing processors to;

analyze a sequence of images captured by the camera to track a movement pattern of a cart having the faulty wheel, wherein the faulty wheel exhibits one of a swiveling resistance and a wobble; and

detect that the cart has the faulty wheel by identifying that the cart is abandoned; and

an application server comprising one or more application server processors and one or more application server memory devices operably coupled to the one or more application server processors and storing executable and operational application server data, the executable and operational application server data effective to cause the one or more application server processors to create an alert if the image processing module detected that the cart is abandoned.

11. The system of claim 10, wherein the executable and operational image processing data is effective to further cause the one or more image processing processors to analyze the sequence of images to identify a person using the cart.

12. The system of claim 10, further comprising computer-readable instructions stored in a memory of a mobile computing device.

13. The system of claim 12, wherein the computer-readable instructions stored in a memory of a mobile computing device are adapted to display the alert on the mobile computing device.

14. The system of claim 10, wherein the executable and operational image processing data is effective to further cause the one or more image processing processors to verify that a customer previously moved at least one item from the cart into a replacement cart.

15. A computer-implemented method of detecting a faulty wheel, comprising:

receiving, at an image processing module, an image sequence depicting a cart having the faulty wheel exhibiting one of a swiveling resistance and a wobble;

verifying, by the image processing module, that the cart contains no items;

detecting, by the image processing module, that the cart has the faulty wheel;

wherein detecting, by the image processing module, that the cart has the faulty wheel further comprises identifying, by the image processing module, the cart as an abandoned cart; and

transmitting an alert regarding the abandoned cart.

16. The method of claim 15, wherein transmitting an alert regarding the abandoned cart comprises transmitting a signal to a mobile computing device.

17. The method of claim 15, further comprising verifying, by the image processing module, that a customer previously moved at least one item from the cart into a replacement cart.