Artificial Intelligence and Computer Vision Help Prevent Indigestion

June 1, 2020 Max Maxfield

Unfortunately, we don’t always have sufficient time to enjoy a leisurely lunchtime meal. Suppose some of your workmates invite you to join them for lunch at a local fast-food restaurant. You all typically have a limited amount of time for your lunchtime break and you need to use this time wisely and efficiently. First, you have to get to the restaurant, either by walking or perhaps by taking a short drive. When you reach the restaurant, you have to select your food, pay for it, and eat it. Finally, you have to return to work before your lunchtime break is over.

Research shows that a large portion of one’s time in a fast-food restaurant—often 15 minutes or more—is spent queuing in the checkout line to pay for one’s meal (see Are American workers playing ‘ketchup’ with their lunch breaks?). One of the main causes of this delay is the time taken for the human cashier to look at all of the items you’ve selected on your tray—in some cases scanning their barcodes—and entering them into the till individually. At a regular checkout, this activity can easily take 16 seconds or more (see Proppos: Computer Vision Self-Checkout). Although this may not seem like a lot of time on an individual basis, there is a ripple-on-effect as more and more people enter the eatery.

Identifying different foods on a tray can be a non-trivial task (Image source: Chris A. Tweten on Unsplash)

If you happen to find yourself at the back of an oh-so-slow-moving checkout queue waiting to pay for your meal, the result can be anger, frustration, and—possibly—indigestion should you end up having to gulp your food down or even leave some of your meal sitting on your plate uneaten.

Artificial Intelligence and Computer Vision Save the Day

The owners of a self-service restaurant in Spain found themselves with this exact problem. Many of their customers’ lunch breaks were only 30 to 60 minutes long, but they could easily spend 15 minutes queuing in the checkout line. As a result, even those customers with longer lunch breaks left feeling agitated and frustrated, while potential customers with shorter lunch breaks didn’t even bother coming in at all, thereby resulting in loss of income for the restaurant.

The restaurant turned to solution provider Proppos. In turn, Proppos turned to Pervasive Technologies to provide the artificial intelligence software and opted to use ADLINK’s DLAP-201-JT2 industrial-grade edge AI platform, which was designed from the ground up to address size, weight, and power (SWaP) constraints faced by edge AI applications, and which meets all of the requirements laid down by the Proppos team. The result was the Proppos FastPay system.

Proppos FastPay (Image source: Proppos)

From the software perspective, the development, deployment, and management of the Proppos FastPay AI checkout system is made easy with ADLINK’s DLAP-201-JT2. The secret is the built-in NVIDIA® Jetson™ TX2, a supercomputer-on-module that not only provides the computing power required for real-time AI inferencing, but also comes with NVIDIA’s comprehensive edge-to-cloud solution for AI applications.

Using this system, all a user has to do is slide their tray under the camera. In only 1.5 seconds—which is ten times faster than a standard checkout—Proppos FastPay automatically identifies all of the items on the tray and present the total for the customer’s approval. With a quick tap of their credit card, or by means of a smartphone application, the customer is on their way to enjoy their meal.

Proppos FastPay is just the first step in what promises to be an exciting future. This system could also be employed by canteens and restaurants in hospitals, schools, bus stations, train stations, and airports. Hopefully, it won’t be long before you find yourself using such a system, resulting in a significantly more satisfying dining experience and no more indigestion caused by racing your meals.

Previous White Paper
AI and Computer Vision Drive Fleet Safety
AI and Computer Vision Drive Fleet Safety

A public bus system in Taipei needed to improve public safety. Its approach? In-vehicle computers processin...

Next Article
Embedded Insiders: Tech in the Age of Pandemic-Driven Telecommuting
Embedded Insiders: Tech in the Age of Pandemic-Driven Telecommuting

Brandon and Rich wonder how the COVID-19 pandemic has been affecting the tech sector, both from a financial...