US 12,014,544 B2
Identifying scanning motions during checkout using overhead cameras
Christopher Brakob, Minneapolis, MN (US); and Ethan Sommer, Minneapolis, MN (US)
Assigned to Target Brands, Inc., Minneapolis, MN (US)
Filed by Target Brands, Inc., Minneapolis, MN (US)
Filed on Aug. 1, 2022, as Appl. No. 17/878,644.
Claims priority of provisional application 63/281,436, filed on Nov. 19, 2021.
Claims priority of provisional application 63/235,530, filed on Aug. 20, 2021.
Prior Publication US 2023/0056327 A1, Feb. 23, 2023
Int. Cl. G06V 20/40 (2022.01); G06N 20/00 (2019.01); G06Q 20/20 (2012.01); G06V 20/52 (2022.01)
CPC G06V 20/44 (2022.01) [G06N 20/00 (2019.01); G06Q 20/208 (2013.01); G06V 20/52 (2022.01)] 32 Claims
OG exemplary drawing
 
1. A system for determining whether a scanning motion occurred during a checkout process, the system comprising:
a checkout lane including:
a scanning area configured to receive one or more products to be purchased by a user, the scanning area including one or more scanning devices;
a point of sale (POS) terminal configured to identify a product based on a scan, using the one or more scanning devices, of a product identifier for the product as the product is moved through the scanning area;
an overhead camera having a field of view that includes the scanning area, wherein the overhead camera is configured to:
capture image data of the user's body movements as the user moves the product through the scanning area; and
transmit, to a computing system, the image data of the user's body movements; and
a computing system configured to determine, during runtime, whether the user's body movements are scanning motions, the computing system configured to:
retrieve, from a data store, one or more motion identification models, wherein the one or more motion identification models were previously trained using image training data and one or more machine learning motion identification models;
identify whether a scanning motion occurred during the user's body movements based on application of the one or more motion identification models to the image data;
determine, based on identification of the scanning motion, that the user performed an affirmative scan during the checkout process; and
poll the POS terminal for an indication of a registered scanning event;
determine whether the registered scanning event is within a threshold period of time from the scanning motion based on comparing a timestamp of the registered scanning event with a timestamp of the scanning motion; and
determine, based on the registered scanning event being within the threshold period of time from the scanning motion, that the user performed the affirmative scan during the checkout process.