Method and device for identifying commodities in container

Abstract

The embodiment of the invention provides a method and device for identifying commodities in a container, and the method comprises the steps of obtaining a fisheye image for any shelf layer, carrying out the target detection of the fisheye image, determining the commodity type of each commodity in the fisheye image and the commodity channel where each commodity is located, counting the number of the commodities which are located in the same commodity channel and belong to the same commodity type, and determining the commodity type with the maximum number as the commodity type of each commodity on the same commodity channel, wherein each layer of goods shelf in the container is provided with an image acquisition device, each layer of goods shelf is provided with a plurality of goods channels, and all goods on the same goods channel belong to the same type. Due to the fact that the commodity types arranged on different commodity channels are different, and the commodities on the same commodity channel belong to the same type, the commodity type with the largest number on the same commodity channel can be determined as the commodity type of each commodity on the commodity channel, the commodity type of each commodity in the container can be accurately recognized in time, and the diversity of the commodities in the container and the flexibility of commodity loading combination can be improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of smart containers, and in particular, to a method and device for identifying commodities in a container. Background technique [0002] At present, there are widely used smart vending cabinets on the market, which can be sold automatically without sales personnel. This kind of intelligent vending cabinet generally includes four to five layers of shelves (the height of each layer can be equal or different), which is used to place retail goods, and there is a fisheye camera on the top of each layer to determine the products purchased by users. One way is to use the target detection technology to calculate the number of products of each type in the product photos taken after each customer closes the door, and compare them with the number of products calculated after the last time the door was closed to obtain The type and quantity of goods purchased by the customer this time will be auto...

AI Technical Summary

Problems solved by technology

However, this processing method will reduce the diversity of commodities in the smart vending cabinet and the flexibility of commodity loading combinations

Images