Abstract: Disclosed herein is an improved method for identifying images containing objects-of-interest from a large set of images. The method comprises mixing two or more of the images to create a grouped image and exposing the grouped image to an object detector trained on grouped images to make an initial determination that the grouped image was formed from at least one image containing an object-of-interest. The images which formed the grouped image are then exposed to regular object detectors to determine a classification of the object-of-interest.

Abstract: The subject matter of this specification can be implemented in, among other things, methods, systems, computer-readable storage medium. A method includes receiving first image data comprising one or more image frames indicative of a state of a meal preparation area. The method further includes determining, based on the first image data, a first set of one or more detections each indicating at least one of a detected meal preparation item or a detected meal preparation action associated with the state of the meal preparation area. The method further includes receiving order data indicating a plurality of pending meal orders and determining associated meal preparation constraints. The method further includes determining, based on the meal preparation constraints, a first association between the first set of detections and a first pending meal order of the plurality of pending meal orders and performing an action based on the first association.