Methods of identifying barcoded items by evaluating multiple identification hypotheses, based on data from sensors including inventory sensors and ceiling-mounted cameras

Abstract

A variety of technologies having practical application in retail stores are detailed. One is an improved method of identifying items selected by customers. This method includes receiving sensor data from plural sensors, including (a) ceiling-mounted cameras that monitor tracks of customers through aisles of the store, and (b) inventory sensors that are positioned to monitor removal of stock from store shelves. This received sensor data is employed in evaluating plural alternate item identification hypotheses. These hypotheses include a first hypothesis that a customer selected an item having a first identity, and a second hypothesis that the customer selected an item having a second identity. A confidence score is associated with each of the first and second item selection hypotheses. These confidence scores are refined as sensor data is received, e.g., increasing a confidence score of one hypothesis, and reducing a confidence score of another. Such refining continues until one of the hypotheses becomes a winner, due to an associated confidence score fulfilling a predetermined criterion (e.g., reaching a threshold value), at which time the item can be added to a tally for that individual. The winning item identification hypothesis may identify a barcoded item, without that item's barcode ever having been read by a barcode reader. A great number of other features and arrangements are also detailed.