Mainly in the last years the analysis of the behaviour of shoppers inside a store is becoming a very attracting issue. Thanks to the use of technologies and artificial intelligence based approaches novel methods are applied to automatically evaluate the movement of shopper in the store, the interactions with the products on the shelves, the time spent inside the store, and more, in a passive mode without interviewing the consumers and preserving their privacy. The aim of this paper is to propose a method based on a Support Vector Machine classifier that classifies the interactions of the shopper with products solving the problem of unclassifiable interactions, when carts, baskets, or other objects are temporarily placed in front of the shelves. The implemented system is also able to solve the overcrowding problem that emerges when several shoppers are close to each other, and entering the analysis area of the camera together, were detected as a single person and not as distinct persons.

To understand human behavior, a fundamental aspect is the analysis of the face and movement. This aspect is particularly important in the context of sales, where to know the shopper also means to guide purchases. A major challenge for vending environment is to predict the shopper behavior, with the aim to influence and increase purchases. In this ambit, vending machine industry is actually an interesting and growing data-driven marketing area of research. In this context, the aim of this paper is to propose an innovative architecture that is able to integrate face and movement understanding in a common strategy for real time consumer modeling. The vending machine and the decision support system process multimedia data to smartly respond with dynamic pricing and product proposal to the particular shopper which is in front of a vending machine. The aim is to build an intelligent vending machine which in real time is able to suitably propose products to a labelled shopper. The results come from real environments vending lab with 30 locations and about 1 million consumers in Italy, and have the aim to demonstrate the good performances and high efficiency of our solution in recognizing the age and the gender of consumer and different interactions with the vending machine.

The shelf out-of-stock (SOOS) problem is relevant for retailers and producers since the absence of products on the shelf can lead to a significant reduction of shoppers and a consequent drop on sales. For this purpose, it is necessary to study and introduce approaches able to measure and prevent the lack of products on the shelves and thereby promptly ensuring their refill. In this context, the paper describes the design of an embedded wireless sensor network able to detect in real time a shelf out-of-stock event. In particular, we present a shelf detector sensor based on a novel, low cost and low power wireless sensor network design that can automatically discover out-of-stock in a shelf for all the stores of a retail chain. The use of an automatic method for detecting products not available on the shelf is the first being installed for a long time in a high number of stores. This paper aims to present the hardware infrastructure of the embedded sensor network devoted to real time shelf out-of-stock management and to demonstrate the feasibility and the scalability of the system discussing interesting results about scalability, long life battery based installations and data analysis.

The paper reports on a use case of vertical integration and predictive maintenance, two concepts that fall within the wider "Industry 4.0" domain. We designed an Internet of Things based system for the collection, processing and management of data coming from central vacuum cleaners. The developed embedded system for data retrieval from the vacuum via MODBUS and for sending them to a cloud server via WiFi is described in detail. We also present the software techniques used to manage data and the application developed for the presentation of collected data to several types of users: administrators, customers and distributors. Finally, they are highlighted the advantages for using information stored in optimizing the assistance service, marketing opportunities and market analysis.

This paper proposes a tracking system based on Ultra-wideband technology. The system provides the use of several Ultra-Wide Band (UWB) antennas properly positioned inside a predetermined area and powered battery tags free to move inside the area. This system finds wide application in retail field. In fact, through the analysis of the collected tracking data, it allows to derive several information on the shoppers behaviour inside the store. Behaviours that concern flows of walking, most visited areas inside the space dedicated to the shopping and average travel times.

The development of reliable and precise indoor localization systems would considerably improve the ability to investigate shopper movements and behavior inside retail environments. Previous approaches used either computer vision technologies or the analysis of signals emitted by communication devices (beacons). While computer vision approaches provide higher level of accuracy, beacons cover a wider operational area. In this paper, we propose a sensor fusion approach between active radio beacons and RGB-D cameras. This system, used in an intelligent retail environment where cameras are already installed for other purposes, allows an affordable environment set-up and a low operational costs for customer indoor localization and tracking. We adopted a Kalman filter to fuse localization data from radio signals emitted by beacons are used to track users' mobile devices and RGB-D cameras used to refine position estimations. By combing coarse localization datasets from active beacons and RGB-D data from sparse cameras, we demonstrate that the indoor position estimation is strongly enhanced. The aim of this general framework is to provide retailers with useful information by analyzing consumer activities inside the store. To prove the robustness of our approach, several tests were conducted into a real indoor showroom by analyzing real customers behavior with encouraging results. (C) 2016 Elsevier B.V. All rights reserved.

The aim of this work is to describe an innovative smart floor based on a self powered system able to allow the localization and analysis of the movement of the users in a specific area. The solution presented involves the use of capacitive sensors on a polymeric support to be inserted between solid wood and a wooden part of a floating parquet. A detailed architecture and implementation of the smart floor is proposed together with an exhaustive test phase. In this paper we first describe the measurement system used to perform reliability and efficiency test of the system. Then the results are discussed and compared with the expected results and the performance of other solutions already known to the state of art. The proposed system is part of HDOMO, an Ambient Assisted Living (AAL) project aimed at developing smart solutions for active ageing.

The success of pervasive smart environments lies in the capacity to involve visitors to interact with them. It is essential for retail stores. In this paper we describe the setting-up of a low cost system for the indoor localization and customer interaction, developed with a complex infrastructure of wireless embedded sensors. The creation of a responsive store allows customers to connect the real world to their smart devices and will overcome the lack of ubiquity in public spaces; furthermore, from in-venue analytics and proximity sensor it is possible to customize the user experience. First of all we describe the whole sensor network. We go in deep into the active beacon technology adopted for this study. Then, thanks to the analytics, we present a data evaluation with the aim of determining the best sensor arrangement, according to several user tests. Beside the strong enhancement of human interaction, the results of our essay demonstrate how embedded localization systems could be a useful source for data collection beside the strong enhancement of human interaction. This paper is focused to help retailers and insiders for many purposes such as products development or improvement, segmentation strategies and human behaviour analyses into such stores where the embedded computing augment the environment.

The aim of this paper is to present an integrated system consisted of a RGB-D camera and a software able to monitor shoppers in intelligent retail environments. We propose an innovative low cost smart system that can understand the shoppers’ behavior and, in particular, their interactions with the products in the shelves, with the aim to develop an automatic RGB-D technique for video analysis. The system of cameras detects the presence of people and univocally identifies them. Through the depth frames, the system detects the interactions of the shoppers with the products on the shelf and determines if a product is picked up or if the product is taken and then put back and finally, if there is not contact with the products. The system is low cost and easy to install, and experimental results demonstrated that its performances are satisfactory also in real environments.

In the recent years, different kind of intelligent floors have been proposed but they are expensive and in many cases difficult to install and manage. In this paper, we previously describe the state of the art concerning smart floors designed to satisfy different applications and then we present an intelligent floor realized for localizing and tracking people in an indoor environment. The aim of this work is to propose an innovative smart floor based on an energy harvesting system able to allow the localization and analysis of the movement of the users in a specific space. The solution presented in this paper involves the use of capacitive sensors on a polymeric support to insert between solid wood and a wooden part of a floating parquet. The proposed system is part of HDOMO, an Ambient Assisted Living (AAL) project developing smart solutions for active aging. A detailed architecture of the smart floor is proposed together with a preliminary test phase.

Planogram is a detailed visual map of products in a retail store and establishes the position of products in order to increase sales and to supply the best location for suppliers. So, the aims of “correct” planogram are several and are: increasing sales, increasing profits, introducing a new item, supporting an innovative merchandising approach, and better manages the shelves. Deviating from the planogram defeats the purpose of any of those goals. A fundamental aspect in the retail operations is to maintain the integrity of the planogram. This work intends to provide a solution to this problem, proposing a system that individually identifies the presence of a specific product in the image of a shelf. This even though the product is moved, rotated, misplaced, or even in poor lighting conditions. This paper presents a method to find and count multiple instances of the same object that occurs into an image of a shelf in a store without using classifiers. The procedures here described are based on a heuristic algorithm that involves morphological operation, template matching and histogram comparison. Experimental results are presented in order to verify the effectiveness of the proposed approach. They demonstrate that the algorithm provides satisfactory results when the user manually chooses the most significant label of the product to find in the shelf image.