Robust and affordable retail customer profiling by vision and radio beacon sensor fusion

Sturari, Mirco; Liciotti, Daniele; Pierdicca, Roberto; Frontoni, Emanuele; Mancini, Adriano; Contigiani, Marco; Zingaretti, Primo

doi:10.1016/j.patrec.2016.02.010

Cited by 68 publications

(33 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, they leverage on labeled paired couple of samples depicting the same item in the Street and Shop domain to learn a cross domain embedding at training time while our proposal leverages only on labeled images from one domain, thereby vastly relaxing the applicability constraint. Moreover, computer vision has been successfully applied in the retail environments for costumer profiling ( [30]), automatic shelf surveying ( [17]), visual market basket analysis ( [23]) and automatic localization inside the store ( [37]).…”

Section: Related Workmentioning

confidence: 99%

Domain invariant hierarchical embedding for grocery products recognition

Tonioni

Stefano

2019

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Recognizing packaged grocery products based solely on appearance is still an open issue for modern computer vision systems due to peculiar challenges. Firstly, the number of different items to be recognized is huge (i.e., in the order of thousands) and rapidly changing over time. Moreover, there exist a significant domain shift between the images that should be recognized at test time, taken in stores by cheap cameras, and those available for training, usually just one or a few studio-quality images per product. We propose an end-to-end architecture comprising a GAN to address the domain shift at training time and a deep CNN trained on the samples generated by the GAN to learn an embedding of product images that enforces a hierarchy between product categories. At test time, we perform recognition by means of K-NN search against a database consisting of just one reference image per product. Experiments addressing recognition of products present in the training datasets as well as different ones unseen at training time show that our approach compares favourably to state-ofthe-art methods on the grocery recognition task and generalize fairly well to similar ones.

show abstract

Section: Related Workmentioning

confidence: 99%

Domain invariant hierarchical embedding for grocery products recognition

Tonioni

Stefano

2019

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…The recent availability of affordable RGB-D cameras, together with depth information, has enabled significant improvement in scene modeling, estimation of human poses and obtaining good action recognition performance (Jiang and Saxena, 2013) (Liciotti et al, 2014) (Sturari et al, 2016). This topic is very challenging and important because understanding and tracking human behaviour through videos has several useful applications.…”

Section: Related Workmentioning

confidence: 99%

HMM-based Activity Recognition with a Ceiling RGB-D Camera

Liciotti

Frontoni

Zingaretti

et al. 2017

Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods

Self Cite

View full text Add to dashboard Cite

Abstract:Automated recognition of Activities of Daily Living allows to identify possible health problems and apply corrective strategies in Ambient Assisted Living (AAL). Activities of Daily Living analysis can provide very useful information for elder care and long-term care services. This paper presents an automated RGB-D video analysis system that recognises human ADLs activities, related to classical daily actions. The main goal is to predict the probability of an analysed subject action. Thus, abnormal behaviour can be detected. The activity detection and recognition is performed using an affordable RGB-D camera. Human activities, despite their unstructured nature, tend to have a natural hierarchical structure; for instance, generally making a coffee involves a three-step process of turning on the coffee machine, putting sugar in cup and opening the fridge for milk. Action sequence recognition is then handled using a discriminative Hidden Markov Model (HMM). RADiaL, a dataset with RGB-D images and 3D position of each person for training as well as evaluating the HMM, has been built and made publicly available.

show abstract

“…To enable this interaction, it is enough to pair with commonly used mobile devices. Some examples of networks of sensors, which can process the context through user interaction in real time, can be found in [8][9][10]. Thus, the development and standardization of new low power consumption and short range wireless technologies has enabled the concept of the Wireless Sensor Network (WSN) [11].…”

Section: Introductionmentioning

confidence: 99%

A Smartphone-Based System for Outdoor Data Gathering Using a Wireless Beacon Network and GPS Data: From Cyber Spaces to Senseable Spaces

Osaba

Pierdicca

Malinverni

et al. 2018

IJGI

Self Cite

View full text Add to dashboard Cite

Information and Communication Technologies (ICTs) and mobile devices are deeply influencing all facets of life, directly affecting the way people experience space and time. ICTs are also tools for supporting urban development, and they have also been adopted as equipment for furnishing public spaces. Hence, ICTs have created a new paradigm of hybrid space that can be defined as Senseable Spaces. Even if there are relevant cases where the adoption of ICT has made the use of public open spaces more "smart", the interrelation and the recognition of added value need to be further developed. This is one of the motivations for the research presented in this paper. The main goal of the work reported here is the deployment of a system composed of three different connected elements (a real-world infrastructure, a data gathering system, and a data processing and analysis platform) for analysis of human behavior in the open space of Cardeto Park, in Ancona, Italy. For this purpose, and because of the complexity of this task, several actions have been carried out: the deployment of a complete real-world infrastructure in Cardeto Park, the implementation of an ad-hoc smartphone application for the gathering of participants' data, and the development of a data pre-processing and analysis system for dealing with all the gathered data. A detailed description of these three aspects and the way in which they are connected to create a unique system is the main focus of this paper. recognition of an added value need to be further developed. This is one of the main motivations for the research presented here.Digital services provided for experiencing a POS are now mainly employed through the use of map or web-based applications, which force users to search for their preferred path or location. Furthermore, the space is not smart enough to collect the information from users, apart from the main Big Data Players, such as Google, which do not provide public access to these data. Hence, a space that can sense users' presence and provide according information is still broadly missing.In line with this, the adoption of ICTs provides users with new instruments to enhance their experience of visiting and discovering a place; at the same time, they represent a valuable source of information that could be used for the planning process. This research addresses the topic of exploring the relationship between space, users, and technologies, investigating how pervasive digital tools can augment our environments and can leverage new interactivity. Modern technological applications can dynamically deliver different kinds of data to the users, but they also allow for the extraction of data from them. Thus, we have coined the term Senseable Space to define these kinds of spaces capable of providing users with contextual services, to measure and analyze their dynamics, and to react accordingly, in a seamless exchange of information. This new paradigm of hybridized space is, in part, inspired by the work of the Senseable City Lab at the MIT of Boston (h...

show abstract

Robust and affordable retail customer profiling by vision and radio beacon sensor fusion

Cited by 68 publications

References 19 publications

Domain invariant hierarchical embedding for grocery products recognition

Domain invariant hierarchical embedding for grocery products recognition

HMM-based Activity Recognition with a Ceiling RGB-D Camera

A Smartphone-Based System for Outdoor Data Gathering Using a Wireless Beacon Network and GPS Data: From Cyber Spaces to Senseable Spaces

Contact Info

Product

Resources

About