Monitoring and tracking interactions with inventory in a retail environment

A method includes receiving a first time series of video frames depicting a first area of interest that includes a display area in a retail environment, and using classification by a convolutional neural network to detect instances of people picking up inventory items from the display area. The meth...

Full description

Saved in:
Bibliographic Details
Main Authors Sinha, Somnath, Sanyal, Abhijit
Format Patent
LanguageEnglish
Published 21.11.2023
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:A method includes receiving a first time series of video frames depicting a first area of interest that includes a display area in a retail environment, and using classification by a convolutional neural network to detect instances of people picking up inventory items from the display area. The method also includes receiving a second time series of video frames depicting a second area of interest in the retail environment, and determining, based upon one or more portions of the second time series of video frames, that at least one inventory item picked up at the display area was not, or will not likely be, checked out. The method also includes causing one or more alert messages to be displayed, including causing an alert message to be displayed based on the determining.
Bibliography:Application Number: US202217693719