Systems and methods for detecting vehicle attributes

Patent metadata

Field	Value
Publication number	US-10410067-B2
Application number	US-201816209361-A
Country	US
Kind code	B2
Filing date	Dec 4, 2018
Priority date	Jul 14, 2016
Publication date	Sep 10, 2019
Grant date	Sep 10, 2019

Abstract

Described in detail herein are methods and systems for detecting attributes of vehicles using an images captured by an image capturing device disposed at a facility. The system detects attributes of the vehicles from the image, retrieves information associated with each vehicle based on the attributes and generates a score for each vehicle based on the information associated with each vehicle. Based on the score a distribution of physical objects is triggered to the facility.

First claim

We claim:

1. A system for detecting vehicle attributes, the system comprising:
a first image capture device;
a processor communicatively coupled to the first image capture device, one or more third party systems, and a plurality of databases, the processor configured to:
extract a plurality of vehicle attributes associated with a first vehicle from a first image captured by the image capture device at a first facility, using a machine vision algorithm;
interface with at least one of the one or more third party systems to retrieve features associated with the first vehicle using the plurality of vehicle attributes;
access a first one of the plurality of databases to retrieve information associated with at least one of the plurality of vehicle attributes and features associated with the first vehicle;
generate a first score based on the information associated with the at least one of the plurality of vehicle attributes and features;
query a second one of the plurality of databases for physical objects based on the first score;
query a third one of the plurality of databases for a quantity of the physical objects disposed at the first facility; and
in response to determining the quantity of the physical objects is less than a predetermined quantity trigger distribution of a first quantity of physical objects to the first facility,
wherein the machine vision algorithm includes one or more of: Stitching, Registration, Filtering, Thresholding, Pixel counting, Segmentation, Inpainting, Edge detection, Color Analysis, Blob discovery and manipulation, Neural net processing, Pattern recognition, Optical character recognition, Gauging, or Metrology, and
wherein the processor is further configured to generate a second score associated with a second vehicle based on a plurality of vehicle attributes from a second image of the second vehicle.

2. The system of claim 1 , wherein at least one of the plurality of vehicle attributes includes a body type, a cleanliness, custom parts, a condition of the vehicle, a type of rims on the vehicle, or a type of tire on the vehicle.

3. The system of claim 1 , wherein the processor is communicatively coupled to a second image capture device and the second image capturing device is configured to capture the second image of the second vehicle at a second facility.

4. The system of claim 1 , wherein in response to determining the second score is equal to the score of the first vehicle, querying the third one of the plurality of databases to determine whether a second quantity of the physical objects at the second facility.

5. The system of claim 4 , wherein in response to determining the second quantity of the physical objects is less than the predetermined quantity, trigger distribution of the first quantity to the second facility.

6. The system of claim 5 , wherein the information associated with the first and second vehicle includes a value of the first vehicle or a value of at least one of the plurality of vehicle attributes.

7. The system of claim 1 , wherein the first vehicle is detected by the first image capture camera based on a change to at least one pixel in the first field of view.

8. A method for detecting vehicle attributes, the method comprising:
extracting, via a processor, a plurality of vehicle attributes associated with a first vehicle from a first image captured by an image capture device at a first facility using a machine vision algorithm;
interfacing, via the processor, with at least one third party system to retrieve features associated with the first vehicle using the plurality of attributes;
accessing, via the processor, a first database to retrieve information associated with the at least one of the plurality of vehicle attributes and features associated with the first vehicle;
generating, via the processor, a first score based on the information associated with the at least one of the plurality of vehicle attributes and features;
querying, via the processor, a second database for physical objects based on the first score;
querying, via the processor, a third database for a quantity of the physical objects disposed at the first facility; and
in response to determining the quantity of the physical objects is less than a predetermined quantity triggering, via the processor, distribution of a first quantity of physical objects to the first facility,
wherein the machine vision algorithm includes one or more of: Stitching, or Registration, Filtering, Thresholding, Pixel counting, Segmentation, Inpainting, Edge detection, Color Analysis, Blob discovery and manipulation, Neural net processing, Pattern recognition, Optical character recognition, Gauging, or Metrology, and
wherein a second score associated with a second vehicle is generated, via the processor, based on a plurality of vehicle attributes from a second image of the second vehicle.

9. The method of claim 8 , wherein at least one of the plurality of vehicle attributes includes a body type, a cleanliness, custom parts, a condition of the vehicle, a type of rims on the vehicle, or a type of tire on the vehicle.

10. The method of claim 8 , wherein the second image of the second vehicle is captured by a second image capture device at a second facility.

11. The method of claim 10 , further comprising querying, via the processor, the third database to determine whether a second quantity of the physical objects is at the second facility.

12. The method of claim 11 , further comprising, triggering, via the processor, distribution of the first quantity to the second facility, in response to determining the second quantity of the physical objects is less than the predetermined quantity.

13. The method of claim 12 , wherein the information associated with the first and second vehicles includes a value of the first vehicle or a value of at least one of the plurality of vehicle attributes.

14. The method of claim 8 , wherein the first vehicle is detected by the first image capture device based on a change to at least one pixel in the first field of view.

Assignees

• Walmart Apollo Llc

Inventors

• Jones Nicholaus Adam
• Taylor Robert James
• Vasgaard Aaron James
• Jones Matthew Allen

Classifications

• G07B15/00

  Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points (handling coins or valuable papers, e.g. banknotes, G07D; apparatus for vending or hiring articles or services activated by coins, credit cards, paper currency or the like G07F7/00, G07F17/00) · CPC title

• G07C5/08

  Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time · CPC title

• G06Q30/0278 Primary

  Product appraisal · CPC title

• G06K9/00771 Primary

  Physics · mapped topic

• G06V20/52 Primary

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