Abstract: Multiple cameras capture videos within a secure room. When individuals are detected as entering the room, identities of the individuals are resolved. When an asset is exposed in a field of view of one of the cameras, the individuals' eye and head movements are tracked from the videos with respect to one another and the asset. Additionally, touches made by any of the individuals on the asset are tracked from the videos. The eye and head movements are correlated with the touches or lack of touches according to a security policy for the asset. Any violations of the security policy are written to a secure audit log for the room and the asset.

Abstract: A three-dimensional image (3D) image for a shape of an orientation of an item is captured when an item barcode for the item is captured by a scanner during item checkout at a terminal. Edges for the shape and dimensions for the shape are calculated from the 3D image based on the orientation. The shape dimensions are compared against expected dimensions for a candidate item that is identified from item information in the item barcode and a decision is made as to whether to validate the item barcode for the item during item checkout or as to whether to invalidate the item barcode and suspend item checkout at the terminal for an audit of the item checkout.

Abstract: Images are captured of a customer during a transaction at a transaction terminal along with images associated with items of the transaction and any bags or cart used to hold the items. The images are processed to track any movement and locations of the customer, items, bags, and cart relative to a known location of the transaction terminal. When a transaction payment is required for the transaction and movement is detected in a direction that is moving away from the transaction terminal before a payment notification is received for the transaction, one or more alerts are raised as an indication to staff and/or security systems of a potential in-progress walk-away theft.

Abstract: A three-dimensional image (3D) image for a shape of an orientation of an item is captured when an item barcode for the item is captured by a scanner during item checkout at a terminal. Edges for the shape and dimensions for the shape are calculated from the 3D image based on the orientation. The shape dimensions are compared against expected dimensions for a candidate item that is identified from item information in the item barcode and a decision is made as to whether to validate the item barcode for the item during item checkout or as to whether to invalidate the item barcode and suspend item checkout at the terminal for an audit of the item checkout.

Abstract: One embodiment, in the form of a method, includes capturing at least one image with an imaging device of a machine vision device. The at least one image is captured within an environment within which the machine vision device is deployed. This method then queries a color scheme model based on the captured at least one image to identify a color scheme to utilize within the machine vision device and may subsequently implement the identified color scheme on the machine vision device for processing images captured by the imaging device.

Abstract: Item images and item information for an item identified as being associated with a potential theft during a transaction at a transaction terminal are sent in real time to an alert controller of a management terminal. The item images and item information with transaction details are presented on a display for resolution by a clerk operating the management terminal. A timer is also set and a confidence score calculated representing a confidence level that the item is the subject of theft. When the timer expires and there is still no resolution provided by the clerk a decision is made as to whether to interrupt the transaction processing on the transaction terminal for assistance or whether to permit the transaction to complete on the transaction terminal based on the calculated confidence score.

Abstract: Decentralized cameras perform video tracking on captured video. The cameras produce metadata representing tracking of objects from the captured video. The metadata is passed between the cameras as the object moves within the captured video. Final metadata from at least one of the cameras is sent to a server, the server processes the final metadata to produce a summary of the object tracking and process one or more automated actions based on the summary.

Abstract: A group of consumers are identified before the members of the group enter a frictionless store on an outside premises of the store. In an embodiment, a registered account holder for a member of the group is passed to an indoor tracking system of the frictionless store when the group enters the store. In an embodiment, attributes of a potential group of consumers is passed to an indoor tracking system when the group enters the store without a registered account being identified.

Abstract: During a transaction at a Point-Of-Sale (POS) terminal an image of produce placed in the field of view of a scanner or camera. The image is processed for characteristics associated with the produce and the characteristics are scored and compared against a threshold to determine whether the produce is to receive a discounted price during the transaction.

Abstract: Embodiments of a symbol for identification of a property of a presented item at a Point-Of-Sale Terminal (POS) are generally described herein. A method can include a detecting a presence of a symbol other than a barcode within at least one image captured by a scanner of the POS of an item presented to the scanner, the symbol indicating that the presented item has a property, and when the presence of the symbol is detected, outputting an indication that the presented item has the property.

Abstract: One embodiment, in the form of a method, includes capturing at least one image with an imaging device of a machine vision device. The at least one image is captured within an environment within which the machine vision device is deployed. This method then queries a color scheme model based on the captured at least one image to identify a color scheme to utilize within the machine vision device and may subsequently implement the identified color scheme on the machine vision device for processing images captured by the imaging device.

Abstract: A group of consumers are identified before the members of the group enter a frictionless store on an outside premises of the store. In an embodiment, a registered account holder for a member of the group is passed to an indoor tracking system of the frictionless store when the group enters the store. In an embodiment, attributes of a potential group of consumers is passed to an indoor tracking system when the group enters the store without a registered account being identified.

Abstract: A terminal includes an item scanner. The item scanner determines whether an item that passes within a field of view of the scanner during a transaction has a properly noted barcode recorded for the transaction. When the item fails to have a properly noted barcode an alert is raised in real time for assistance and/or investigation of the transaction.

Abstract: Disclosed herein are systems and methods for configuring a service terminal. The systems and methods may include reading a code located on a component of the service terminal using a scanner and updating a process executable by the service terminal using data associated with the component. The scanner may be in electrical communication with the service terminal. The code may include data associated with the component.

Abstract: Various embodiments each include at least one of systems, devices, methods, and software for multi-camera simultaneous imaging for multiple processes. Some such embodiments may be embodied in a dedicated appliance or chip while other embodiments may be embodied in a product scanner, in software, or in a combination of hardware and software. One method embodiment includes receiving images from a plurality of cameras, the images from each device captured at various illumination and exposure levels. This method then sorts the images based on illumination and exposure levels for distribution to a plurality of image processing services that each perform at least one task with regard to a received image and then presents the images to respective services for which they are sorted.

Abstract: The various embodiments herein each include at least one of systems, methods and software for item location detection on scales, such as on scanner/scales that may be deployed at checkout terminals. One such embodiment is in the form of a method that includes processing data with regard to an item present on a scale of a checkout terminal to locate the item on the scale. The data that is processed is captured in some embodiments upon a steady weight condition greater than zero. This method further includes outputting a message from the terminal when an item is not located within a defined acceptable area of the scale.

Abstract: Various embodiments herein each include at least one of systems, methods, and software to enable depth-based image element removal. Some embodiments may be implemented in a store checkout context, while other embodiments may be implemented in other contexts such as at price-checking kiosks or devices that may be deployed within a store or other retail establishment, a library at a checkout terminal, and the like. Some embodiments include removing elements of images based at least in part on depth data.

Abstract: Embodiments of a symbol for identification of a property of a presented item at a Point-Of-Sale Terminal (POS) are generally described herein. A method can include a detecting a presence of a symbol other than a barcode within at least one image captured by a scanner of the POS of an item presented to the scanner, the symbol indicating that the presented item has a property, and when the presence of the symbol is detected, outputting an indication that the presented item has the property.

Abstract: Various embodiments herein each include at least one of systems, methods, and software to enable depth-based image element removal. Some embodiments may be implemented in a store checkout context, while other embodiments may be implemented in other contexts such as at price-checking kiosks or devices that may be deployed within a store or other retail establishment, a library at a checkout terminal, and the like. Some embodiments include removing elements of images based at least in part on depth data.