Granted Patent B2

US 12,536,673 · App. 18/366,155 · Granted Jan 27, 2026

Inventors: Sumedh Vilas Datar (Grapevine, TX); Sailesh Bharathwaaj Krishnamurthy (Irving, TX); Shashipal Reddy Masini (Austin, TX); Shahmeer Ali Mirza (Celina, TX)

Assignee: 7-Eleven, Inc.

G06T7/292G06V10/26G06V20/52G06V20/70H04N7/181H04N7/188

Abstract

Claims (113)

1 . An item tracking system, comprising:

a plurality of cameras, wherein each camera is configured to capture images of at least a portion of a platform;

a memory configured to store associations between item identifiers of respective items; and

one or more processors communicatively coupled to the memory, and configured to:

detect a first triggering event at the platform, wherein the first triggering event corresponds to placement of a first item on the platform;

in response to detecting the first triggering event, capture a plurality of first images of the first item on the platform using two or more cameras of the plurality of cameras;

identify a first item identifier associated with the first item based on the plurality of first images;

assign the first item identifier to the first item captured in the first images;

detect a second triggering event at the platform, wherein the second triggering event corresponds to the placement of a second item on the platform;

in response to detecting the second triggering event, capture a plurality of second images of the second item on the platform using two or more cameras of the plurality of cameras;

generate a plurality of cropped images, wherein each cropped image is associated with a corresponding second image and is generated by editing the corresponding second image to isolate at least a portion of the second item;

for each cropped image, identify an item identifier based on one or more attributes of the second item;

access the associations from the memory;

identify an association between the first item identifier of the first item and a second item identifier;

detect that at least one of the identified item identifiers is the second item identifier; and

in response to detecting that at least one of the identified item identifiers is the second item identifier and based on the identified association between the first item identifier and the second item identifier, assign the second item identifier to the second item.

2 . The item tracking system of claim 1 , wherein the one or more processors are further configured to:

for each cropped image generated for a respective second image:

input the cropped image to a machine learning model, wherein the machine learning model is configured to output whether the cropped image is a back image of an item or a front image of an item;

obtain the output from the machine learning model indicating whether the cropped image is a back image of an item or a front image of an item; and

tag the cropped image as a back image or a front image based on the output, wherein two or more of the cropped images are tagged as front images.

3 . The item tracking system of claim 2 , wherein:

the memory is further configured to store:

an encoded vector library, wherein the encoded vector library comprises a plurality of encoded vectors, wherein each encoded vector describes one or more attributes of a particular item and is associated with an item identifier for the particular item; and

the one or more processors are further configured to identify the item identifier for each cropped image by:

generating a first encoded vector for the cropped image, wherein the first encoded vector describes one or more attributes of the first item based on the cropped image;

comparing the first encoded vector to the encoded vectors in the encoded vector library;

selecting a second encoded vector from the encoded vector library that most closely matches with the first encoded vector, wherein a numerical similarity value indicates a degree of similarity between the first encoded vector and the selected second encoded vector; and

identifying the item identifier in the encoded vector library that is associated with the second encoded vector.

4 . The item tracking system of claim 3 , wherein the one or more processors are further configured to determine that a plurality of the cropped second images are tagged as front images.

5 . The item tracking system of claim 4 , wherein the one or more processors are further configured to:

in response to determining that the plurality of cropped second images are tagged as front images, determine a first set of item identifiers from a plurality of the item identifiers that were identified for the respective plurality of cropped second images based on similarity values that equal or exceed a threshold similarity value; and

determine that a same item identifier from the first set of item identifiers was not identified for a majority of the plurality of cropped second images.

6 . The item tracking system of claim 5 , wherein the one or more processors are further configured to:

in response to determining that the same item identifier from the first set of item identifiers was not identified for the majority of the plurality of cropped second images:

determine a third item identifier from the first set that was identified for a first cropped second image based on a highest similarity value among the similarity values corresponding to the item identifiers in the first set;

determine a fourth item identifier from the first set that was identified for a second cropped second image based on a second highest similarity value among the similarity values corresponding to the item identifiers in the first set; and

determine that a difference between the highest similarity value and the second highest similarity value is below a threshold difference.

7 . The item tracking system of claim 1 , wherein:

the first item and the second item are identified by a same item identifier; and

the first item identifier and the second item identifier are two instances of the same item identifier.

8 . A method for identifying an item, comprising:

detecting a first triggering event at a platform, wherein the first triggering event corresponds to a placement of a first item on the platform;

in response to detecting the first triggering event, capturing a plurality of first images of the first item on the platform using two or more cameras of a plurality of cameras;

identifying a first item identifier associated with the first item based on the plurality of first images;

assigning the first item identifier to the first item captured in the first images;

detecting a second triggering event at the platform, wherein the second triggering event corresponds to a placement of a second item on the platform;

in response to detecting the second triggering event, capturing a plurality of second images of the second item on the platform using two or more cameras of the plurality of cameras;

generating a plurality of cropped images, wherein each cropped image is associated with a corresponding second image and is generated by editing the corresponding second image to isolate at least a portion of the second item;

for each cropped image, identifying an item identifier based on or more attributes of the second item;

accessing from a memory, associations between item identifiers of respective items;

identifying an association between the first item identifier of the first item and a second item identifier;

detecting that at least one of the identified item identifiers is the second item identifier; and

in response to detecting that at least one of the identified item identifiers is the second item identifier and based on the identified association between the first item identifier and the second item identifier, assigning the second item identifier to the second item.

9 . The method of claim 8 , further comprising:

for each cropped image generated for a respective second image:

inputting the cropped image to a machine learning model, wherein the machine learning model is configured to output whether the cropped image is a back image of an item or a front image of an item;

obtaining the output from the machine learning model indicating whether the cropped image is a back image of an item or a front image of an item; and

tagging the cropped image as a back image or a front image based on the output,

wherein two or more of the cropped images are tagged as front images.

10 . The method of claim 9 , further comprising:

storing in a memory an encoded vector library, wherein the encoded vector library comprises a plurality of encoded vectors, wherein each encoded vector describes one or more attributes of a particular item and is associated with an item identifier for the particular item; and

wherein identifying the item identifier for each cropped image comprises:

identifying the item identifier for each cropped image comprises:

generating a first encoded vector for the cropped image, wherein the first encoded vector describes one or more attributes of the first item based on the cropped image;

comparing the first encoded vector to the encoded vectors in the encoded vector library;

selecting a second encoded vector from the encoded vector library that most closely matches with the first encoded vector, wherein a numerical similarity value indicates a degree of similarity between the first encoded vector and the selected second encoded vector; and

identifying the item identifier in the encoded vector library that is associated with the second encoded vector.

11 . The method of claim 10 , further comprising determining that a plurality of the cropped second images are tagged as front images.

12 . The method of claim 11 , further comprising:

in response to determining that the plurality of cropped second images are tagged as front images, determining a first set of item identifiers from a plurality of the item identifiers that were identified for the respective plurality of cropped second images based on similarity values that equal or exceed a threshold similarity value; and

determining that a same item identifier from the first set of item identifiers was not identified for a majority of the plurality of cropped second images.

13 . The method of claim 12 , further comprising:

in response to determining that the same item identifier from the first set of item identifiers was not identified for the majority of the plurality of cropped second images:

determining a third item identifier from the first set that was identified for a first cropped second image based on a highest similarity value among the similarity values corresponding to the item identifiers in the first set;

determining a fourth item identifier from the first set that was identified for a second cropped second image based on a second highest similarity value among the similarity values corresponding to the item identifiers in the first set; and

determining that a difference between the highest similarity value and the second highest similarity value is below a threshold difference.

14 . The method of claim 8 , wherein:

the first item and the second item are identified by a same item identifier; and

the first item identifier and the second item identifier are two instances of the same item identifier.

15 . A non-transitory computer-readable medium storing instructions that when executed by one or more processors cause the one or more processors to:

detect a first triggering event at a platform, wherein the first triggering event corresponds to a placement of a first item on the platform;

in response to detecting the first triggering event, capture a plurality of first images of the first item on the platform using two or more cameras of a plurality of cameras;

identify a first item identifier associated with the first item based on the plurality of first images;

assign the first item identifier to the first item captured in the first images;

detect a second triggering event at the platform, wherein the second triggering event corresponds to a placement of a second item on the platform;

in response to detecting the second triggering event, capture a plurality of second images of the second item on the platform using two or more cameras of the plurality of cameras;

generate a plurality of cropped images, wherein each cropped image is associated with a corresponding second image and is generated by editing the corresponding second image to isolate at least a portion of the second item;

for each cropped image identify an item identifier based on or more attributes of the second item;

access from a memory, associations between item identifiers of respective items;

identify an association between the first item identifier of the first item and a second item identifier;

detect that at least one of the identified item identifiers is the second item identifier; and

in response to detecting that at least one of the identified item identifiers is the second item identifier and based on the identified association between the first item identifier and the second item identifier, assign the second item identifier to the second item.

16 . The non-transitory computer-readable medium of claim 15 , wherein instructions further cause the one or more processors to:

for each cropped image generated for a respective second image:

input the cropped image to a machine learning model, wherein the machine learning model is configured to output whether the cropped image is a back image of an item or a front image of an item;

obtain the output from the machine learning model indicating whether the cropped image is a back image of an item or a front image of an item; and

tag the cropped image as a back image or a front image based on the output, wherein two or more of the cropped images are tagged as front images.

17 . The non-transitory computer-readable medium of claim 16 , wherein the instructions further cause the one or more processors to store in a memory an encoded vector library, wherein the encoded vector library comprises a plurality of encoded vectors, wherein each encoded vector describes one or more attributes of a particular item and is associated with an item identifier for the particular item; and

wherein identifying the item identifier for each cropped image comprises:

generating a first encoded vector for the cropped image, wherein the first encoded vector describes one or more attributes of the first item based on the cropped image;

comparing the first encoded vector to the encoded vectors in the encoded vector library;

selecting a second encoded vector from the encoded vector library that most closely matches with the first encoded vector, wherein a numerical similarity value indicates a degree of similarity between the first encoded vector and the selected second encoded vector; and

identifying the item identifier in the encoded vector library that is associated with the second encoded vector.

18 . The non-transitory computer-readable medium of claim 17 , wherein the instructions further cause the one or more processors to determine that a plurality of the cropped second images are tagged as front images.

19 . The non-transitory computer-readable medium of claim 18 , wherein the instructions further cause the one or more processors to:

in response to determining that the plurality of cropped second images are tagged as front images, determine a first set of item identifiers from a plurality of the item identifiers that were identified for the respective plurality of cropped second images based on similarity values that equal or exceed a threshold similarity value; and

determine that a same item identifier from the first set of item identifiers was not identified for a majority of the plurality of cropped second images.

20 . The non-transitory computer-readable medium of claim 19 , wherein the instructions further cause the one or more processors to:

in response to determining that the same item identifier from the first set of item identifiers was not identified for the majority of the plurality of cropped second images:

determine a third item identifier from the first set that was identified for a first cropped second image based on a highest similarity value among the similarity values corresponding to the item identifiers in the first set;

determine a fourth item identifier from the first set that was identified for a second cropped second image based on a second highest similarity value among the similarity values corresponding to the item identifiers in the first set; and

determine that a difference between the highest similarity value and the second highest similarity value is below a threshold difference.

Assignments (1)

Continuity (3)

References Cited (38)