By Justin Corbell, Vice President of Sales, Scandit Inc.
Since Amazon Go debuted to the public in 2018, retailers have been investigating ways to emulate this type of smart vision for brick-and-mortar stores, to drive new innovations and customer experiences in their businesses. However, the “Just walk out” store, as Amazon calls it, represents the tip of the iceberg of retail automation and digitally enhanced shopping experiences awaiting consumers and store assistants. Having spent millions on technology and infrastructure, working within the constraints of existing and different types of store spaces and across thousands of locations, means Amazon Go isn’t seen as affordable or realistic for most. But mobile computer vision can be deployed more simply, and cheaply to innovate, optimize shopping experiences and boost retailer profits.
Progressive Retail Automation – Gain Without Pain
At Scandit, we help all types of retailers – whether grocery, fashion, electronics, department stores – create an Amazon Go-style experience with affordable automation, but without the pain of reconfiguring stores and cost of implementing fixed digital infrastructure that includes scales on every shelf. Instead, computer vision is enabled through smartphones – or any smart device with a camera, which can include robots and drones; or where desirable, wearables. The beauty of this approach is that it is cheaper and augments human workers, rather than replacing them and losing their knowledge; while taking advantage of the near ubiquitous smartphones in your shoppers hands to drive superior in-store experiences.
By transforming smartphones into enterprise-grade barcode scanners, in-store and back-office workflows are enhanced through computer vision and augmented reality technology, unlocking massive savings and new efficiencies. Customer-facing apps powered by computer vision barcode scanning can also create fantastic customer experiences with services like Self-Scanning cashierless shopping. Customers kitted out with their normal smartphone, for example, can point it at a shelf of products and instantly locate vegan or gluten-free goods, or whatever kind of specified product they’re seeking. Other information that’s useful to display to shoppers to augment the reality includes reviews and ratings, or suggested products based on a consumer’s personal shopping history.
The best part is that this incremental approach to innovation can be deployed today, without disruption, and building on your existing investments – see Think Like Amazon. First let’s look at how Amazon Go does it.
Computer vision and machine learning helps frictionless shopping gather momentum
The Amazon Go experiment is gaining strength with over thirteen locations now open and it’s good to see Amazon validating the power of computer vision coupled with machine learning.
A recent McKinsey ‘Automation in Retail’ report stated that,“the profit-and-loss impact of Amazon Go hints at a high ROI. Amazon can expect a 5 to 10 percent top-line improvement thanks to additional traffic from reduced wait times and the use of customer insights to optimize assortments and personalize promotions.”
An operation that identifies individual customers and their goods, tracks them and deducts the correct amount from their bank account is undeniably 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 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 over the past year, 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, the 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.
Same objectives, different approaches, vastly different budgets.
Interestingly, Amazon has opted to deploy this veritable army of cameras, devices and sensors to achieve a single objective: to kill off the queue/line 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 data service that superimposes a product search and find over the camera vision capture is a quick win. It cuts down on the time and hassle of grocery shopping or specialized product selection for the consumer, and speeds throughput and profits for the retailer, too. Computer vision enables a whole lot more value besides.
For example, rather than fitting every shelf with cameras in order 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.
Computer vision coupled with mobile devices and deep learning is the way to go for retailers and shoppers, and Amazon Go provides an important proof of concept. Happily for mainstream retailers, many other diverse applications are available to optimize shopping and store operations – incrementally and at a fraction of the price. The Amazon Go stores will wow – but for everyday jobs such as inventory checking and finding the right product, look no further than your smartphone. With mobile computer vision, you won’t require a disruptive, ‘big bang’ project to achieve the benefits of retail automation, self-scanning or a better in-store experience using augmented reality, it can be achieved with the smart devices and customer apps already ubiquitous in your shoppers and employees hands.
For more information on how Scandit turns the humble smartphone into a powerful barcode scanner and helps you think like Amazon click here. To speak with a Scandit Solutions Representative click here.