A goods sensing system includes: a sample collector that collects a plurality of sets of image samples, where each set of the image samples comprise sample images of a type of goods at multiple angles, where a set of the image samples of a same type of goods are provided with a same group identification, and the group identification is the type of the goods corresponding to the set of image samples; a model trainer that trains a convolutional neural network model according to each sample image and a group identification of the sample image to obtain a goods identification model; a real-time image collector that continuously acquires at least one real-time image of space in front of a shelf, each real-time image including part or all of images of goods; and a goods category deriver that obtains a type and quantity of the goods displayed in the real-time.

A system and method for interaction monitoring in a retail environment that includes executing a first monitoring system and thereby generating a first evaluation of customer selection of items; executing a second monitoring system and thereby generating a second evaluation of customer selection of items; determining monitoring alignment between the first evaluation and the second evaluation of a first customer; and triggering an action in response to the monitoring alignment.

Embodiments of the present invention provide a skip-scanning identification method and apparatus, a self-service cash register terminal and system. The method includes: obtaining a video of a user scanning an item; determining posture data of the user based on the obtained video; determining, according to the posture data of the user, a time period in which a scanning action of the user takes place; receiving a scanning result of the item; and determining whether the user has skipped scanning the item based on the scanning result and the time period.

A system and method for interaction monitoring in a retail environment that includes executing a first monitoring system and thereby generating a first evaluation of customer selection of items; executing a second monitoring system and thereby generating a second evaluation of customer selection of items; determining monitoring alignment between the first evaluation and the second evaluation of a first customer; and triggering an action in response to the monitoring alignment.

Disclosed in the present specification is a self-checkout device to which hybrid product recognition technology is applied and which helps a user to more conveniently and quickly make a payment. The self-checkout device according to the present specification photographs a product with a plurality of cameras, and then recognizes a barcode by detecting a barcode region from the captured images and, simultaneously, extracts a feature point of the images such that a product can be recognized through the calculation of the proportion that matches with a reference image of the product. Thus, a product can be quickly recognized through barcode recognition and packaging paper recognition in a product image.

Disclosed are systems and methods for determining whether an unknown product matches a scanned barcode during checkout. The system includes a checkout lane having a flatbed scanning area with scanning devices and a point of sale (POS) terminal that scans a product identifier of an unknown product, identifies a product associated with the scanned product identifier, and transmits, to a computing system, product information. An overhead camera idnentifies, based on detecting an optical signal from the POS terminal, that a scanning event occurred, captures image data of the unknown product, and transmits, to the computing system, the image data. The computing system generates machine learning product identification models for identifying unknown products, identifies candidate product identifications for the unknown product based on applying the models to the image data, and determines, based on the candidate product identifications and the information about the product, whether the unknown product matches the product.

An information processing method according to an aspect of the present disclosure includes: acquiring, from a video, flow line information of a customer; detecting that the customer acquires an item; and storing, in a storage, flow line information of the customer and information on a number of items acquired by the customer, in association with each other.

A self-checkout system can include a plurality of telescoped bagging arm segments moveably coupled together in an order according to respective diameters of the plurality of telescoped bagging arm segments. A scanning system can be configured to provide a characteristic of an item purchased by a user of the self-checkout system and a processor circuit can be operatively coupled to the plurality of telescoped bagging arm segments and to the scanning system, where the processor circuit can be configured to move the plurality of telescoped bagging arm segments relative to one another based on the characteristic of the item to be placed in a bag in use with the self-checkout system.

An information processing device acquires, from an accounting machine, product information generated when the accounting machine reads a code on a product identifies a first feature amount related to first number of times indicating number of products purchased, based on the acquired product information acquires an image obtained by capturing an image of an object disposed in a certain area adjacent to the accounting machine and containing the product identifies a second feature amount related to second number of times indicating number of times of taking out operations of a product placed in the object and notifies with an alert based on the first feature amount and the second feature amount.

Techniques for training an item recognition machine learning (ML) model are disclosed. An image of a first item for purchase is received. The image is captured by a point of sale (POS) system. A purchaser selection of a second item for purchase is also received. The purchaser makes the selection at the POS system. It is determined that the first item for purchase matches the second item for purchase, and in response training data is generated for an image recognition ML model, based on the image and the determination that the first item for purchase matches the second item for purchase. The ML model is trained using the training data, and the trained ML model is configured to recognize items for purchase in a plurality of images captured by a plurality of POS systems.