| CPC G06V 10/764 (2022.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01)] | 18 Claims |
|
1. A method of obtaining images and data to train an AI model for product detection, the method comprising:
generating, with an image collection system at a first product source, a first annotation package including one or more images of and data about a first product, further comprising:
placing the first product in a first enclosure located at the first product source;
initiating, in the first enclosure, a process for obtaining the one or more images of the first product;
obtaining the one or more images of the first product with one or more cameras positioned in the first enclosure;
providing the one or more images of the first product to an edge compute device;
inputting, using an input device, data about the first product into the edge compute device;
creating an annotation package for the first product that includes the one or more images and the data;
generating, with an image collection system at a second product source, a second annotation package including one or more images of and data about a second product;
providing, from the first product source, the first annotation package to a product detector;
providing, from the second product source, the second annotation package to the product detector;
training an artificial intelligence model to detect the first product based on the first annotation package and to detect the second product based on the second annotation package, wherein the artificial intelligence model is implemented on the product detector;
receiving, at the product detector from a first retailer, a first image;
detecting, by executing the artificial intelligence model, the first product and/or the second product in the first image;
receiving, at the product detector from a second retailer, a second image; and
detecting, by executing the artificial intelligence model, the first product and/or the second product in the second image.
|