How Walmart Uses Computer Vision

Jamie Grill-Goodman
Editor in Chief
Jamie goodman

Walmart has found a use for computer vision technology at the checkout and has been using it for the last two years.

Computer vision plays an important role in facial recognition, cashierless stores, inventory visibility, and visual search, four vital areas retailers are already putting the technology to work in.

Walmart has been using computer vision technology in more than 1,000 stores to monitor checkouts and deter potential theft, the company confirmed to Business Insider, in a surveillance program Walmart refers to internally as Missed Scan Detection.

The technology monitors both self-checkout kiosks and traditional registers, using cameras to help identify checkout scanning errors and failures, according to BI. The cameras watch as items move across the register and, if an unusual activity occurs, such as an item moving into a bag without being scanned, a checkout attendant will be notified to take action. In the two years since the system was deployed, Walmart says it has reduced rates of theft, inventory loss, fraud, and scanning errors.

Walmart has also been testing computer vision technology in its Sam’s Club Now test store in Dallas, TX. The mobile-first test lab store powered by the Sam’s Club Now app allows customers a cashierless, grab and go experience. The store makes use of available technologies ― including computer vision, AR, machine learning, artificial intelligence, robotics.

In Walmart’s new IRL store, the retailer expects in the near future a combination of cameras and real-time analytics will automatically trigger out-of-stock notifications to internal apps that alert associates when to re-stock. To do this the store has to detect the product on the shelf, recognize the specific product and compare the quantities on the shelf to the upcoming sales demand. The result is that associates will know what to bring out of the back room before customers show up.

Walmart has noted IRL will be in data-gathering mode in its early days, with a focus on learning from the technology, not implementing changes to operations in haste. IRL’s more than 100 associates will be undertaking these retail experiments every day.

Today 3% of retailers have computer vision technology in place, according to RIS’ “29th Annual Retail Technology Study: Retail Accelerates.” However, 40% plan to start or finish implementing the tech within the next two years.

Other retailer who are currently using computer vision technology include Schnuck Markets, which uses an autonomous shelf-scanning robot to capture real-time insights into on-shelf operations; and of course Amazon, which debuted its cashierless Amazon Go pilot in late 2016. For a deeper look into computer vision technology in retail check out RIS’ feature “The Brave New World of Computer Vision: 4 Things Retailers Need to Know.”

This ad will auto-close in 10 seconds