Google has announced it has developed a new artificial intelligence tool designed to help big-box retailers better track the inventory on their shelves.
Google Cloud said its algorithm can recognize and analyze the availability of products on shelves from both videos and images provided by the retailer’s own ceiling-mounted cameras, camera-equipped self-driving robots or store associates.
The new system is still being tested but it is expected to be offered to retailers before the end of the year if not sooner.
Google Cloud said its product has a database of over a billion products, including images that are publicly available, licensed and provided directly by manufacturers. Its algorithm is also designed to recognize those products, whether the image is coming from a ceiling-mounted camera or mobile-phone video.
The company says it is similar to how the human eye understands it is seeing a cereal box regardless of what angle it is looking at the box. It can be identified from above or the side or straight on.
Giant Eagle has been a partner with Google Cloud and has provided continuous feedback to about where the tool isn’t working so that it can fine-tuned. If the camera is too high or too low then the algorithm can’t identify the product, Giant Eagle provides that image to Google Cloud so it can train the algorithm to recognize that angle the next time.