System and method for identifying moved items on a platform during item identification

Patent metadata

Field	Value
Publication number	US-12579665-B2
Application number	US-202318476445-A
Country	US
Kind code	B2
Filing date	Sep 28, 2023
Priority date	Jun 29, 2021
Publication date	Mar 17, 2026
Grant date	Mar 17, 2026

Abstract

In response to detecting a first triggering event corresponding to placement of a first item on a platform, a plurality of first images are captured of the first item and a plurality of cropped first images are generated based on the first images. A first item identifier associated with the first item is identified based on the cropped first images. In response to detecting a second triggering event corresponding to placement of a second item on the platform, a plurality of second images of the first item are captured and a plurality of cropped second images are generated from the second images. In response to determining that the cropped first images match with the cropped second images, the first item identifier is assigned to the first item depicted in the second images.

First claim

The invention claimed is:

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 user interface device; and one or more processors communicatively coupled to the user interface device, and configured to:
detect a first triggering event at the 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 the plurality of cameras;
generate a cropped first image for each of the first images by editing the first image to isolate at least a portion of the first item, wherein the cropped first images correspond to the first item depicted in the respective first images;
identify a first item identifier associated with the first item based on the cropped first images;
store, in a memory, the first item identifier associated with the first item;
display, on the user interface device, information associated with the first item identifier;
after detecting the first triggering event, 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 first item on the platform using two or more cameras of the plurality of cameras;
generate a cropped second image for each of the second images by editing the second image to isolate at least a portion of the first item, wherein the cropped second images correspond to the first item depicted in the respective second images;
compare the cropped first images with the cropped second images;
determine, based on the comparing, that the cropped first images match with the cropped second images;
in response to determining that the cropped first images match with the cropped second images, determine that the cropped second images are associated with the first item identified in the first images;
in response to determining that the cropped second images are associated with the first item, assign the first item identifier stored in the memory to the first item captured in the second images;
identify a second item identifier associated with the second item; and
display on the user interface device information associated with the second item identifier along with the information associated with the first item identifier.

2 . The item tracking system of claim 1 , wherein:
each first image is captured by a different camera of the plurality of cameras; and each second image is captured by a different camera of the plurality of cameras; and the one or more processors are further configured to:
generate a first encoded vector for each cropped first image, wherein the first encoded vector describes an attribute of the first item based on the cropped first image; and
generate a second encoded vector for each cropped second image, wherein the second encoded vector describes an attribute of the first item based on the cropped second image.

3 . The item tracking system of claim 2 , wherein the one or more processors are further configured to compare the cropped first images with the cropped second images by:
comparing each first encoded vector of the respective cropped first image associated with a particular camera to a corresponding second encoded vector of the respective cropped second image associated with a same particular camera.

4 . The item tracking system of claim 3 , wherein the one or more processors are further configured to determine that the first cropped images match with the second cropped images by:
determining that a majority of the first encoded vectors match with the corresponding second encoded vectors.

5 . The item tracking system of claim 4 , wherein the one or more processors are is further configured to:
determine that a particular first encoded vector matches with the corresponding particular second encoded vector when a numerical match value corresponding to a comparison between the particular first encoded vector and the particular second encoded vector equals or exceeds a match threshold.

6 . The item tracking system of claim 5 , wherein the one or more processors are further configured to:
for each comparison of the first encoded vector and a corresponding second encoded vector, generate a numerical similarity value indicating a degree of match between the first encoded vector and the second encoded vector; and determine that the first encoded vector matches with the corresponding second encoded vector when the numerical value equals or exceeds the match threshold.

7 . The item tracking system of claim 1 , wherein the one or more processors are further configured to identify the first item identifier associated with the first item by:
identifying a plurality of different item identifiers based on the cropped first images; presenting the plurality of different item identifiers on the user interface device; and receiving a user selection of the first item identifier from the user interface device, wherein the first item identifier is selected from the plurality of different item identifiers.

8 . The item tracking system of claim 1 , wherein the one or more processors are further configured to identify the second item identifier associated with the second item by:
in response to detecting the second triggering event, capture a plurality of third images of the second item on the platform using two or more cameras of the plurality of cameras; generate a cropped third image for each of the third images by cropping the third image to isolate at least a portion of the second item, wherein the cropped third images correspond to the second item in the respective second images; and identify the second item identifier associated with the second item based on the cropped third images.

9 . 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, wherein each camera is configured to capture images of at least a portion of the platform; generating a cropped first image for each of the first images by editing the first image to isolate at least a portion of the first item, wherein the cropped first images correspond to the first item depicted in the respective first images; identifying a first item identifier associated with the first item based on the cropped first images; storing, in a memory, the first item identifier associated with the first item; displaying, on a user interface device, information associated with the first item identifier; after detecting the first triggering event, 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 first item on the platform using two or more cameras of the plurality of cameras; generating a cropped second image for each of the second images by editing the second image to isolate at least a portion of the first item, wherein the cropped second images correspond to the first item depicted in the respective second images; comparing the cropped first images with the cropped second images; determining, based on the comparing, tha

Assignees

• 7 Eleven Inc

Inventors

• Wang Xinan
• Dalal Kyle J
• Mirza Fahad
• Crain Jon Andrew
• Krishnamurthy Sailesh Bharathwaaj

Classifications

• G06V20/52

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

• G06V10/26

  Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion · CPC title

• G06V20/70

  Labelling scene content, e.g. deriving syntactic or semantic representations · CPC title

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title

• H04N7/181

  for receiving images from a plurality of remote sources · CPC title