How Does Amazon Go Works?
How Does Amazon Go Works? OR Are you wondering what is it?
Amazon has recently introduced “just walk out technology”.
It’s nothing but a store in Seattle, Washington which is without any cashier or register means it is as simple as grab what you want and go and hence the name “just walk out technology”.
How does it work?
According to amazon, the technology they use is just like the one used in self-driven cars which include computer vision, deep learning algorithms and sensor fusion these all collectively make such an automation possible. It is a revolutionary concept which relies on the prevalence of smartphone and geofencing technology to enhance buying experience by eliminating long queues and the payment issues.
Customers must download the Amazon Go app, which will be linked to their Amazon.com account, before shopping at the store. The app allows users to add others to their Amazon account, so kids and a spouse’s purchases can be charged to the same bill.
The ceiling of the store has multiple cameras and store shelves have weight sensors, to detect which item a customer took. If a customer takes an item off the shelf, it will be added to the person’s virtual cart. If a customer places an item back on the shelf, it is “taken out” of the virtual cart.
For now, Amazon store has prepared foods, meal kits, limited groceries, and liquor available for purchase. In coming days, the market for Amazon will expand and you can expect one in your city too.
The detailed view of technology mentioned:
Computer vision is an interdisciplinary field that deals with how computers can be made for gaining high-level understanding from digital images or videos. It seeks to automate tasks that the human visual system can do. The task operated by computer vision include methods for acquiring processing, analyzing and understanding digital images. Basically, it is concerned with the theory behind artificial systems that extract information from images and this image data can take many forms such as a view from multiple cameras. Which enhance the precision and let computer have a keen knowledge of the object being lifted and by whom (in this case).
Deep learning is a class of machine learning algorithms that use a cascade of multiple layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input learnt in supervised or unsupervised manners. Which basically means learning multiple levels of representations that correspond to different levels of abstraction and these levels form a hierarchy of concepts or learning from the previous output and combining these data for a better analysis.
Sensor fusion is combining of sensory data or data derived from disparate sources such that the resulting information has less uncertainty than would be possible when these sources were used individually. The term uncertainty reduction, in this case, can mean more accurate, more complete, or more dependable, or refer to the result of an emerging view, such as stereoscopic vision (calculation of exact information by combining two-dimensional images from two cameras at slightly different viewpoints).
For more details, check out the link: https://www.youtube.com/watch?v=NrmMk1Myrxc