Using Machine Vision Cameras for Autonomous and Contactless Retail Shopping System

Image Credit: FLIR Systems

Imagine entering a store, picking up an item and then walking out of the store and simply receiving a receipt for the item via email. It sounds like the future, but it is the present with AWM Frictionless™ shopping experience, a fully contactless and autonomous retail shopping system developed by AWM Smart Shelf.

AWM Frictionless™ enables customers to pick up items and be automatically charged as soon as they leave the store, without the requirement to queue up, scan, or physically pay for their items. This is achieved by using FLIR Blackfly S GigE Machine Vision Cameras.

The first AWM Frictionless™ store was a micro-market convenience store in Santa Ana, California, and was launched in March 2020. It is filled with useful convenience items such as sodas, snacks, and water, and refills on the basic necessities like hygiene products, soap, and milk.

Toilet paper actually was the first purchase when we opened.

Kaitlyn Kempiak, Marketing Director, AWM

How Does An Autonomous Contactless Shopping Experience Work?

First of all, the customer must download the store app and complete their payment information. The app supplies them with a QR code which they are able to scan to get through the electronic doors.

The customer shops as normal once inside and the products they choose are tracked and added to their digital basket. When they are finished they just walk out of the store.

Customers appreciate the convenience of having the store located inside their apartment building, especially during COVID-19 pandemic, there is no scanning, no speaking with a store associate, complete friction-free shopping.

Kaitlyn Kempiak, Marketing Director, AWM

In the future, the store will be open 24/7, enabling customers to enjoy contactless shopping whenever they like. FLIR Blackfly S GigE cameras combined with a deep learning algorithm that is properly trained to identify products correctly and add them to the shopper’s basket are both utilized to track items in an AWM Frictionless™ store.

Image Credit: FLIR Systems

If the customer decides to put it back on the shelf, then the system can also remove an item from the virtual shopping basket. If the customer puts down a shopping bag and wanders into the next aisle, it still keeps track of it.

Why Did AWM Choose FLIR Blackfly S Cameras for Frictionless Checkouts?

AWM chose FLIR machine vision cameras as they cited quality, helpful documentation, reliability, and excellent customer support.

Some key features supplied by Blackfly S cameras for AWM’s application included a color correction matrix to reproduce the same colors in different lighting conditions, the ability to adjust white balance to represent colors accurately, and the ability to process images from multiple cameras quickly with features such as Packet Delay and Chunk Data Timestamp.

“To perform accurate tracking and 3D reconstruction across many cameras (32+ in some cases) it’s important we have accurate time information, down to the millisecond, for when frames were captured, and not necessarily the time when frames arrive at the computer for processing. This is especially true for GigE cameras operating over a network. The Chunk Data Timestamp feature on the Blackfly S cameras allows us to do this,” says AWM.

Numerous cameras can see the complete store as they are installed on the ceiling. If a person tries to take advantage of the system by sneaking a small item into their hand or sleeve without being spotted by a camera, the visual data is also supported by weighted shelving.

This second data input enables it to be more accurate and reliable as the system knows exactly how much each item weighs.

Image Credit: FLIR Systems

Another key feature of FLIR Blackfly S cameras is the Color Correction Matrix. It helps to reproduce colors in different lighting conditions reliably. Obtaining consistent color is extremely vital in Deep Learning applications to optimize the accuracy of the neural network and to decrease the amount of training data required for the neural network.

Touch-Free, Automated Retail Experiences in the Real World

The Frictionless experience is already present in micro-markets and AWM has laid the groundwork for it to expand into other spaces, including convenience stores,  conventional retail stores, and even supermarkets.

AWM Frictionless™ can be adapted to existing stores to provide a fully contactless and autonomous and shopping experience or simply a further easy option for customers to checkout. AWM is currently working on a produce recognition tool for deployment in grocery stores, and the AI is always being trained on new products.

What Do Customers Think?

Image Credit: FLIR Systems

Customers say that the frictionless experience saves time, is extremely easy, and decreases health risks. Considering the value of extended store hours, contactless checkouts, higher security, easier stock management, and reduced checkout times, the AWM Frictionless™ experience is revolutionary.

As the machine learning solution continues to develop, more shopping formats and stores are being added to make shopping easier and even more convenient.

This information has been sourced, reviewed and adapted from materials provided by FLIR Systems.

For more information on this source, please visit FLIR Systems.


Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Teledyne FLIR Systems. (2021, March 22). Using Machine Vision Cameras for Autonomous and Contactless Retail Shopping System. AZoM. Retrieved on February 04, 2023 from

  • MLA

    Teledyne FLIR Systems. "Using Machine Vision Cameras for Autonomous and Contactless Retail Shopping System". AZoM. 04 February 2023. <>.

  • Chicago

    Teledyne FLIR Systems. "Using Machine Vision Cameras for Autonomous and Contactless Retail Shopping System". AZoM. (accessed February 04, 2023).

  • Harvard

    Teledyne FLIR Systems. 2021. Using Machine Vision Cameras for Autonomous and Contactless Retail Shopping System. AZoM, viewed 04 February 2023,

Ask A Question

Do you have a question you'd like to ask regarding this article?

Leave your feedback
Your comment type