top of page

AI Case Study

Standard Cognition aims to predict and prevent shoplifting in supermarkets using machine vision

Standard Cognition has opened a new completely automated cashierless store, Standard Market. Using the store's app, shoppers can enter the store, grab items and leave without going through a check-in or check-out process. Cameras on the ceiling identify shoppers and their items and can track where items are going and when customers leave the shop. In this way, by analysing behavioural data such as movements, speed, stride length and gaze, the system aims to detect, and thus prevent, shoplifting. This first store is a prototype of the technology which is based on machine vision.

Industry

Consumer Goods And Services

Retail General

Project Overview

"San Francisco got its first completely automated cashierless store, Standard Market. Shoppers who have downloaded the store’s app can go into the 1,900-square-foot space, grab items and simply leave. There is no check-in gate, and there is no checkout swipe. Ceiling cameras identify the shopper and the items, and determine when said items leave with said shopper.

Standard Cognition’s approach is different. It relies exclusively on the ceiling cameras and artificial intelligence software to figure out what you are buying. The cameras document shoppers’ movements, speed, stride length and gaze.

Once the system decides it has detected potential theft behavior, a store attendant will get a text and walk over for “a polite conversation.”

Function

Operations

General Operations

Background

"Standard Market is the latest entry in the emerging fray of retail automation, where companies are throwing cameras, sensors and machine learning into grocery stores to replace the checkout line. In January, Amazon opened its first cashierless Go market in Seattle to the public; it has since opened more of the stores. In China, experiments in cashierless stores abound, using radio frequency identification tags and a self-checkout process that involves scanning a Quick Response code or your face."

Reported Results

Proof of Concept; results not yet available. However, the journalist reporting on it did accidentally leave the store with an extra item without paying so the technology is not fool proof in its current incarnation.

Benefits

Technology

Visual tracking

Data

Behavioural data: "Cameras document shoppers’ movements, speed, stride length and gaze."

bottom of page