Granted Patent B1

US 12,374,078 · App. 18/404,518 · Granted Jul 29, 2025

Inventors: Bernd Schoner (New York, NY); Thibault Priquel (Zurich, CH); Oliver Akermann (Zurich, CH); Luc Humair (Zurich, CH)

Assignee: Scandit AG

G06V10/751G06K7/1417G06K7/1443G06K7/1447G06T7/73G06T11/00G06V10/42G06V30/248

Abstract

Claims (50)

1. A system comprising:

one or more cameras;

one or more processors; and

one or more computer readable storage media storing instructions which, when executed by the one or more processors, cause the system to perform operations comprising:

acquiring a plurality of images of a plurality of objects in an environment;

down sampling at least one image of the plurality of images, wherein down sampling the at least one image causes the at least one image to have a lower resolution than at least one other image of the plurality of images;

detecting locations of a plurality of labels in the plurality of images, each label of the plurality of labels corresponding to a respective object of the plurality of objects;

cropping the plurality of images to obtain a plurality of image segments, each image segment of the plurality of image segments corresponding to a respective label of the plurality of labels, depicting product information, and depicting a barcode associated with the product information; and

for each respective image segment of the plurality of image segments:

analyzing the product information of the respective image segment to obtain a catalog description for the respective image segment, wherein analyzing the product information comprises analyzing lines of text of the product information;

storing the catalog description in a database, wherein the catalog description is stored as an entry in a catalog of product descriptions stored in the database;

decoding the barcode to obtain a product identifier for the respective image segment; and

storing the product identifier in the database in association with the catalog description.

2. The system of claim 1 , wherein each object of the plurality of objects corresponds to a product for sale in a retail environment.

3. The system of claim 1 , wherein the database stores a plurality of catalog descriptions of the plurality of objects, each catalog description of the plurality of catalog descriptions comprising at least one of a product identifier for an object of the plurality of objects and product information for an object of the plurality of objects.

4. The system of claim 1 , wherein each object of the plurality of objects is represented as a separate entry in the catalog of product descriptions.

5. The system of claim 1 , wherein the environment is a retail environment, and wherein the plurality of objects is located on a plurality of shelf displays in the retail environment.

6. The system of claim 1 , wherein analyzing the product information comprises performing optical character recognition on the lines of text.

7. The system of claim 1 , the system further comprising a vehicle coupled to the one or more cameras, and wherein acquiring the plurality of images comprises capturing the plurality of images using the one or more cameras as the vehicle moves within the environment.

8. The system of claim 1 , wherein the respective image segment is associated with an object of the plurality of objects and the product identifier for the respective image segment is a stock keeping unit for the object.

9. A method comprising:

acquiring, using one or more cameras coupled to a vehicle, a plurality of images of a plurality of products in a retail environment;

down sampling at least one image of the plurality of images, wherein down sampling the at least one image causes the at least one image to have a lower resolution than at least one other image of the plurality of images;

detecting locations of a plurality of labels in the plurality of images, each label of the plurality of labels corresponding to a respective object of the plurality of products;

cropping the plurality of images to obtain a plurality of image segments, each image segment of the plurality of image segments corresponding to a respective label of the plurality of labels, depicting product information, and depicting a barcode associated with the product information; and

for each respective image segment of the plurality of image segments:

analyzing the product information of the respective image segment to obtain a catalog description for the respective image segment, wherein analyzing the product information comprises analyzing lines of text of the product information;

storing the catalog description in a database, wherein the catalog description is stored as an entry in a catalog of product descriptions stored in the database;

decoding the barcode to obtain a product identifier for the respective image segment; and

storing the product identifier in the database in association with the catalog description.

10. The method of claim 9 , wherein each object of the plurality of products corresponds to a product for sale in a retail environment.

11. The method of claim 9 , wherein the database stores a plurality of catalog descriptions of the plurality of products, each catalog description of the plurality of catalog descriptions comprising at least one of a product identifier for a product of the plurality of products and product information for a product of the plurality of products.

12. The method of claim 9 , wherein each object of the plurality of products is represented as a separate entry in the catalog of product descriptions.

13. The method of claim 9 , wherein analyzing the product information comprises performing optical character recognition on the lines of text.

14. The method of claim 9 , wherein the respective image segment is associated with an object of the plurality of products and the product identifier for the respective image segment is a stock keeping unit for the object.

15. The method of claim 9 , wherein the plurality of products is located on a plurality of shelf displays in the retail environment.

16. The method of claim 15 , wherein acquiring the plurality of images comprises capturing the plurality of images using the one or more cameras as the vehicle moves between two or more shelf displays of the plurality of shelf displays.

17. One or more non-transitory computer-readable media storing computer-readable instructions which, when executed by one or more processors of a system, cause the system to perform operations comprising:

acquiring, using one or more cameras coupled to a vehicle, a plurality of images of a plurality of objects in an environment;

down sampling at least one image of the plurality of images, wherein down sampling the at least one image causes the at least one image to have a lower resolution than at least one other image of the plurality of images;

detecting locations of a plurality of labels in the plurality of images, each label of the plurality of labels corresponding to a respective object of the plurality of objects;

cropping the plurality of images to obtain a plurality of image segments, each image segment of the plurality of image segments corresponding to a respective label of the plurality of labels, depicting product information, and depicting a barcode associated with the product information;

for each respective image segment of the plurality of image segments:

analyzing the product information of the respective image segment to obtain a catalog description for the respective image segment, wherein analyzing the product information comprises analyzing lines of text of the product information;

storing the catalog description in a database, wherein the catalog description is stored as an entry in a catalog of product descriptions stored in the database;

decoding the barcode to obtain a product identifier for the respective image segment; and

storing the product identifier in the database in association with the catalog description.

18. The one or more non-transitory computer-readable media of claim 17 , wherein acquiring the plurality of images comprises capturing the plurality of images using the one or more cameras as the vehicle move within a retail environment.

19. The one or more non-transitory computer-readable media of claim 17 , wherein each object of the plurality of objects corresponds to a product for sale in a retail environment.

20. The one or more non-transitory computer-readable media of claim 17 , wherein each object of the plurality of objects corresponds to a product for sale in a retail environment.

Assignments (1)

Continuity (12)

References Cited (201)