An aspect is to provide a scanning device, a system, and a method in which an available communication band is not used up even if a plurality of scanning devices are connected to one unit of dedicated hardware. According to one embodiment, a scanning device includes: a camera configured to pick up an image; a reduction unit configured to reduce a data volume of an image corresponding to a merchandise to be outputted to an image recognition device from the image picked up by the camera; and an output unit configured to output the image with the reduced data volume to the image recognition device.

Systems and methods for detecting potential shrink events via RFID technology are provided. The systems include a point of sale (POS) system that includes an optical scanner, an RFID transceiver arrangement, a user interface and a controller. The controller is configured to perform example methods disclosed herein. For example, the controller may detect that the optical scanner has decoded a barcode, trigger the RFID transceiver arrangement to write a data string to an RFID tag located within the object scanning area, conduct a detection operation to detect the RFID tag with the data string in the bagging area. Responsive to detecting the RFID tag with the data string, the method involves the user interface performing a first operation. Responsive to not detecting the RFID tag with the data string, the method involves the user interface performing a second operation.

A machine-learning algorithm is trained with features relevant to basket data for items of transactions. The trained algorithm is trained to predict whether a given transaction is more or less likely to be associated with theft being engaged in by a transaction operator for the transaction. The trained algorithm is then provided basket data for a given transaction and produces as output a theft prediction value. When the theft prediction value exceeds a configured threshold value, the transaction is flagged for manual intervention or the transaction is flagged for subsequent manual verification.

A technique capable of preventing a purchased commodity from being forgotten to be passed to a customer is provided. An information processing apparatus includes a determination unit, an update unit, and a display control unit. The determination unit determines a change in weight of commodities measured by a weight sensor provided in a placing portion. The update unit updates a first total placement number of commodities on the placing portion based on the determination of the change in weight by the determination unit. The display control unit causes a display unit to display the first total placement number updated by the update unit.

A method, computer program product, and system to perform a sale transaction are provided. The method includes identifying each item of a plurality of items, based on at least one image of the plurality of items, determining a cost for each item, optionally identifying a person based on an image of the person, adding each of the items and each of the costs to a sale transaction, and charging the person for the sale transaction.

Described herein are systems and methods for determining whether a scanning motion occurred during a checkout process. The system includes a checkout lane having a scanning area that receives products to be purchased by a user, scanning devices, a point of sale (POS) terminal that identifies a product based on a scan, using the scanning devices, of a product identifier for the product as the product is moved through the scanning area, and an overhead camera that captures image data of the user's body movements and transmits, to a computing system, the image data. The computing system can, during runtime, identify whether a scanning motion occurred during the user's body movements based on application of one or more motion identification models to the image data and determine, based on identification of the scanning motion, that the user performed an affirmative scan during the checkout process.

A tracking system includes a camera subsystem that includes cameras that capture vide of a space. Each camera is coupled with a camera client that determines local coordinates of people in the captured video. The camera clients generate frames that include color frames and depth frames labeled with an identifier number of the camera and their corresponding timestamps. The camera clients generate tracks that include metadata describing historical people detections, tracking identifications, timestamps, and the identifier number of the camera. The camera clients send the frames and tracks to cluster servers that maintain the frames and tracks such that they are retrievable using their corresponding labels. A camera server queries the cluster servers to receive the frames and tracks using their corresponding labels. The camera server determines the physical positions of people in the space based on the determined local coordinates.

An electronic medication storage cabinet includes a plurality of drawers configured with a plurality of sensors arranged to identify a positioning of storage pockets within the drawers. Upon receiving an indication of a new medicine container to be loaded in the cabinet, a sequence of steps to load the medicine container into the cabinet is generated based on a mapping algorithm. A first step is displayed on a display the cabinet, and a determination is made as to whether the first step is associated with one of the plurality of drawers. In response to determining that the first step is associated with one of the plurality of drawers, the drawer is automatically unlocked. In response to determining that the first step is successfully completed, a determination of whether execution of any additional steps is pending and indicated on the display.

A tracking system includes a camera subsystem that includes cameras that capture vide of a space. Each camera is coupled with a camera client that determines local coordinates of people in the captured video. The camera clients generate frames that include color frames and depth frames labeled with an identifier number of the camera and their corresponding timestamps. The camera clients generate tracks that include metadata describing historical people detections, tracking identifications, timestamps, and the identifier number of the camera. The camera clients send the frames and tracks to cluster servers that maintain the frames and tracks such that they are retrievable using their corresponding labels. A camera server queries the cluster servers to receive the frames and tracks using their corresponding labels. The camera server determines the physical positions of people in the space based on the determined local coordinates.

A machine-learning algorithm is trained with features relevant to basket data for items of transactions. The trained algorithm is trained to predict whether a given transaction is more or less likely to be associated with theft being engaged in by a transaction operator for the transaction. The trained algorithm is then provided basket data for a given transaction and produces as output a theft prediction value. When the theft prediction value exceeds a configured threshold value, the transaction is flagged for manual intervention or the transaction is flagged for subsequent manual verification.