Smart vision system for shelf analysis in intelligent retail environments

This paper aims to propose an innovative idea of an embedded intelligent, multimedia and interactive shop system where embedded vision systems can analyse human behaviours around shelves for interactivity and statistical purposes, mostly devoted to customer behaviour analysis, planogram maintenance and out of stock detection. We discuss the need for new services into the shop, involving consumers more directly and instigating them to increase their satisfaction and, as a consequence, their purchases. To do this, technology is very important and allows making interactions between costumers and products and between customers and the environment of the shop a rich source of marketing analysis. In particular we focus on concepts of monitoring and interactivity, introducing several emerging technologies in the field of retail environments. The main novelty of the paper is the general architecture of the system together with the introduction of a series of intelligent embedded systems, yet implemented and tested in a dataset recorded during the Euro Shop trade fair, in cooperation with Grottini group, a leading company in Retail Design industry based in Italy. Results are convincing and most of all the general architecture is affordable in this specific application. Copyright © 2013 by ASME.