<p>A planogram is the graphic representation of the way in which a certain number of products are positioned within the shelves in a store. The &nbsp;construction &nbsp;of &nbsp;a &nbsp;correct &nbsp;planogram &nbsp;is &nbsp;a &nbsp;fundamental tool for the performance of a store: in fact it helps to increase sales and to obtain maximum customer satisfaction, reducing out of stock. For this purpose, this work aims to provide an automatic system, based on object detection, to allow operators to verify the correctness of a planogram. For image acquisition it is possible to use either low-cost battery-powered cameras positioned on the opposite side of the shelf, or simply a tablet with a special app installed. These tools are connected to the cloud where the detection and matching phases are carried out. The experimental results derive from a real environment.&nbsp; The number of products that have been identified by the network is greater than the number of products actually labeled: this shows that the network is able to identify small objects even if they are not labeled through human intervention. The values reached&nbsp;are concentrated on a very high probability: in fact, the probability of 70 %&nbsp;is exceeded in &nbsp;80%&nbsp;of the products. The products that have a lower probability, i.e. between 40 %&nbsp;and 60 %&nbsp;are those that are not present in the labels.</p>

A Deep Learning Approach for Product Detection in Intelligent Retail Environment

Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2021/volume/85369

ASME 2021 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.