The “Frictionless Store” is a Reality with Mobile Computer Vision

by Steve Cunningham, Sales Director – Retail US, Scandit Inc.

The “Just Walk Out” store model like Amazon Go is a smart vision for brick-and- mortar stores, and there’s no doubt this vision is changing the way we shop. The dream for a truly frictionless store promises a digitally enhanced in-store shopping experience for shoppers and store employees. Now mobile computer vision is making the frictionless store a reality for retailers such as Globus. Powering mobile apps on everyday smart devices with enterprise-grade scanning and augmented reality (AR) is a simple, affordable and attainable way to create a frictionless customer experience. It’s a way to create a brand shoppers want to engage with and employees want to work for.

At Scandit, we help retailers be an Amazon Go, but without the pain and cost of ripping out shelves and installing fixed digital infrastructure such as scales on every shelf and cameras in ceilings. Instead, computer vision is enabled through smart devices, turning them into high performing barcode scanners and AR devices. The beauty of the mobile computer vision approach is that it uses the everyday devices already in customers’ hands and is cheaper to deploy than traditional dedicated scanners.

From Scan-and-Go to augmented product information with AR

Retailers use apps powered by Scandit software to make it easy for shoppers to scan barcodes with their own smartphones – and then either pay for goods at a self-checkout kiosk or pay through an app with Scan-and-Go. Customers kitted out with an app on their smartphone powered by Scandit MatrixScan, can point it at a shelf of produce and instantly locate vegan or gluten-free goods, or whatever kind of specified product they’re seeking. An augmented reality (AR) overlay presents the relevant information on the device screen. Careful shoppers can check which products score highest reviews, or bargain hunters can see AR discount coupons.

Blend physical & digital worlds in brick-and-mortar stores – without the hefty price tag

Amazon Go is a laudable concept and it’s good to see Amazon validating the power of computer vision coupled with machine learning. An operation that identifies and tracks individual customers and their goods, and then deducts the correct amount from a bank account is smart. But it’s taken millions of dollars and the custom build of a premises; scaling this model to other retail outlets and smaller shops is just not viable.

A closer look at the Amazon Go model store shows why. The smart operation works by having weight sensors on shelves to detect when an item is removed and is supplemented by cameras to sight objects removed from shelves. Hundreds of infrared ceiling cameras have been trained, using deep learning and Amazon staff as guinea pigs, to distinguish customers and similar-looking items.

Nor is capital expenditure limited to camera and sensors. As retailers learned during the RFID hype days, major cost is incurred through mounting specialist equipment on shelves and ceilings and cabling digital devices and equipment. The sheer number of cameras providing data in such a real-time, business critical operation cannot be battery operated and will need dedicated, hard-wired bandwidth.

Friction goes beyond the queue – think smart personalization meeting specific customer needs

Interestingly, Amazon has opted to deploy this veritable army of cameras, devices and sensors to achieve a single objective: to kill off the queue and let customers pick their goods “and just walk out.” The Amazon Go model assumes the biggest win for customer and retailer is to remove the checkout queue with its hassle of bagging up. Any seasoned shopper, however, knows that the most time is wasted searching for products.

This is especially true if it’s a customer’s first visit to a store, or you’re new in town. In this common situation, a digital shopping experience to meet each customer’s specific needs when they’re in-store is smart personalization. Scanning product barcodes and viewing AR overlays on any smartphone creates differentiated, frictionless shopping – customers in a hurry use in-store navigation and Scan-and-Go to be fast-in-fast-out, while savvy shoppers access product information as an AR-overlay after scanning an item. It cuts down on the time and hassle of grocery shopping or specialist product selection for the consumer, and speeds throughput and profits for the retailer. Computer vision technology enables a whole lot more value.

For example, rather than fitting every shelf with cameras to capture data, a single camera can be mounted on a robot that patrols the aisles at regular intervals, filming shelves and identifying stock gaps to ensure produce is topped up and maximizing the retailer’s sales opportunity. Similarly, camera-fitted drones can be flown over high shelves in giant warehouse outlets for stock checking or answering customer queries.

Case study: avec offers 24/7 cashless convenience stores with Scan-and-Go app powered by Scandit

Computer vision coupled with mobile devices and deep learning delivers frictionless shopping experiences and protects profitability for retailers, and Amazon Go provides an important proof of concept. Other retailers are turning to other technologies to optimize shopping and store operations – at a fraction of the price.

For example, Valora has successfully trialled a new, cashless compact ‘store in a box’ – the avecBox – to see how well it would be accepted by customers. At 50 square metres, the sales area is much smaller than the typical 8-900 square metres for a convenience store, and requires shoppers to use the mobile app to scan and pay for items using personal smartphones.

Valora’s avecX mobile app is available for iOS and Android devices. When customers first use the app, they use their smartphone camera to quickly register personal details from any machine-readable identity document, such as an ID card or passport. From then on, the app is used to simply scan a QR code at the store entrance to enter and start shopping immediately. Self-scanning barcodes on products with the app is easy and when the customer is finished, shopping is completed using the “pay” function on the mobile app.

Valora focused on truly personalized shopping. For example, customers can also have the coffee machine remember their coffee choice for next time, just by using the app to scan the QR code on the coffee machine first.

Valora opened its first cashless 24/7 convenience store in Zurich’s main railway station, using the avecX mobile app powered by Scandit. The core technical solution, including integration into the backend systems, was developed in just five months.

Valora employees were present on site at peak shopping times at the cashless avecBox in Zurich. They helped customers with questions about the app and the shopping experience and kept the shelves full and the store clean. There was a high level of customer satisfaction with the avecX mobile app and the avecBox store. The innovative products, the easy and fast shopping and the 24-hour shopping access were particularly well regarded by customers.

“It was our aim to present the first functional version as quickly as possible, to get customers involved, learn from them and then use this knowledge to develop the model further. The Zurich launch provided important information for further trials at various locations in Switzerland.“ – Felicitas Suter, Senior Digital Innovation Manager at Valora.

While there is little doubt Amazon Go will continue to impress – Valora has shown that mobile computer vision and ordinary smartphones delivery a comparably high level customer experience, with none of the technology or infrastructure challenges with which the Amazon Go model contends.

Create the digital in-store experience your customers want without costly rebuilding

Download the Think Like Amazon whitepaper to find out how to build a frictionless shopping experience that doesn’t require the integration of hundreds of cameras, weight sensors, and other costly infrastructure into a custom-built premises.

Learn how Scandit computer vision software is designed specifically for the smart devices that your customers and employees are already using, so you can easily and affordably blend the digital and physical experiences in-store.

For more information on how Scandit mobile data capture solutions can help you think like Amazon, speak with a Scandit Solutions Representative.