Amazon has announced it has developed a new camera system that can identify products at its warehouse facilities and eliminating the need for barcodes.
The company says the system is already in use at certain distribution facilities in Europe and currently uses cameras to ensure items on a conveyor belt match the its reference images. The images captured are also added to the database, helping to train the system to be more accurate. Currently it’s at 99% accuracy, Amazon says.
Eventually, the company wants to introduce robots that’ll be able to pick up the items and recognise them without having to scan a barcode. It turns out robots can’t do that very well, so the image recognition tech is key. Amazon calls this technology multimodal identification, or MMID. Amazon says this will eventually result in items getting through the system and out to customers faster and more efficiently.
It says the cameras can “extracting the appearance and dimensions of an item from an image of that item — to automate identification.”
“Our north star vision is to use this in robotic manipulation. Solving this problem, so robots can pick up items and process them without needing to find and scan a barcode, is fundamental,” said Nontas Antonakos, the applied science manager in Amazon’s computer vision group in Berlin in a blog post. “It will help us get packages to customers more quickly and accurately.”
As barcodes can be damaged or missed off completely, it will iron out the kinks as it passes through the journey on the way to the delivery vehicle. The idea will eventually be rolled out to Amazon businesses, but we imagine the barcodes will still be present once the item is packaged and leaves the warehouse. How the hell are Hermes going to cope without them?
