Abstract: A scalable tracking system includes a camera subsystem, a weight subsystem, and a central server. The camera subsystem includes cameras that capture video of a space, camera clients that determine local coordinates of people in the captured videos, and a camera server that determines the physical positions of people in the space based on the determined local coordinates. The weight subsystem determines when items were removed from shelves. The central server determines which person in the space removed the items based on the physical positions of the people in the space and the determination of when items were removed.

Abstract: A camera array for a scalable tracking system includes cameras that are communicatively coupled to camera clients. The cameras are arranged in a grid such that no camera is directly adjacent in the same row or column of the grid to another camera that is communicatively coupled to the same camera client. Cameras that are arranged along a diagonal of the grid are communicatively coupled to the same camera client.

Abstract: An apparatus includes a display, interface, and processor. The interface receives video from a camera located in a physical store and directed at a first physical rack. The camera captures video of the rack during a shopping session. The processor displays a first virtual rack that emulates the first physical rack and includes first and second virtual shelves. The virtual shelves include virtual items, which include graphical representations of physical items located on the physical rack. The processor displays the rack video, which depicts an event including the person interacting with the first physical rack. The processor also displays a virtual shopping cart. The processor receives information associated with the event, identifying the first virtual item. The rack video depicts that the person selected the first physical item while interacting with the first physical rack. The processor then stores the first virtual item in the virtual shopping cart.

Abstract: An apparatus includes a processor. The processor receives an algorithmic shopping cart that includes a first set of items determined by an algorithm to have been selected by a person during a shopping session in a physical store, based on a set of inputs received from sensors located within the physical store. The processor also receives a virtual shopping cart that includes a second set of items. Video of the shopping session was captured by a set of cameras located in the physical store and depicts the person selecting the second set of items. The processor compares the algorithmic cart to the virtual cart and determines that a discrepancy exists between the algorithmic cart and the virtual cart. The processor determines a subset of the set of inputs associated with the discrepancy and attaches metadata explaining the discrepancy to the subset. The processor uses the subset to train the algorithm.

Abstract: A scalable tracking system processes video of a space to track the positions of people within a space. The tracking system determines local coordinates for the people within frames of the video and then assigns these coordinates to time windows based on when the frames were received. The tracking system then combines or clusters certain local coordinates that have been assigned to the same time window to determine a combined coordinate for a person during that time window.

Abstract: An apparatus includes a processor. The processor receives an algorithmic shopping cart that includes a first set of items determined by an algorithm to have been selected by a person during a shopping session in a physical store, based on a set of inputs received from sensors located within the physical store. The processor also receives a virtual shopping cart that includes a second set of items. Video of the shopping session was captured by a set of cameras located in the physical store and depicts the person selecting the second set of items. The processor compares the algorithmic cart to the virtual cart and determines that a discrepancy exists between the algorithmic cart and the virtual cart. The processor determines a subset of the set of inputs associated with the discrepancy and attaches metadata explaining the discrepancy to the subset. The processor uses the subset to train the algorithm.

Abstract: The present invention comprises a modular telemedicine system with a universal adapter that connects diagnostic, identification and audiovisual communication function modules, at least one of which is present at the patient's location, to a variable process module that performs data transmission, processing and output. The connection of the system, which can be used anywhere, to a physician's receiving center facilitates the mobile telemedical treatment of patients. Preferably, the system comprises a plurality of function modules for the recording of data. Simplified, basic operation of all function modules is made possible through a hard-wired connection between the function module and the universal adapter, and data can be transmitted to corresponding process modules wirelessly or hard-wired. Each function module can be used separately or in combination with the universal adapter and the process module.