Self-checkout anti-theft vehicle systems and methods

A method comprising:

• receiving, by a processor coupled to a self-checkout vehicle, an image captured by a camera coupled to the self-checkout vehicle, wherein the image depicts an item;
• receiving, by the processor of the self-checkout vehicle, location data associated with the image of the item, the location data describing a location within a store where the image was captured and wherein the location data is captured by a location sensor coupled to the self-checkout vehicle;
• identifying, by the processor of the self-checkout vehicle, a set of candidate items located near the location where the image was captured based on the location data captured by the location sensor coupled to the self-checkout vehicle, wherein the set of candidate items are identified by:
• filtering a set of items at the store based on whether each item in the set of items is within a threshold distance of the location within the store where the image was captured;
• calculating, by the processor of the self-checkout vehicle, a score for each of the set of candidate items based on the location data and the image, wherein the score for a candidate item represents a likelihood that the candidate item is depicted in the image, wherein calculating the score for a candidate item of the set of candidate items comprises:
• generating a set of features describing the image, and
• applying a classifier to the set of features to compute the score;
• identifying, by the processor of the self-checkout vehicle, the item depicted in the image based on the calculated scores of the set of candidate items;
• and
• updating a display of the self-checkout vehicle based on the identified item.