Associate Professor of Computer Vision
Dipartimento di Ingegneria dell’Informazione – DII
Prof. Emanuele Frontoni is Professor Computer Vision and Deep Learning at the Department of Information Engineering (DII) of the Università Politecnica delle Marche, Ancona – Italy. His research activity is focused in the field of Computer Vision and Artificial Intelligence with applications in multimedia, novel distributed data architectures for video analysis and human behavior analysis. He is also involved in several AI projects in the field of health data interoperability, cloud based deep learning technologies and big data analysis. He coordinated and participated to several industrial R&D projects in collaboration with ICT and mechatronics companies in the field of Industry 4.0, HBA and Robotic Vision. He is an expert for EU Commission in H2020 project evaluations and is currently involved in 2 ongoing EU projects (DWC and ROSIN sub-call). He published more than 150 international’s papers in his fields. He is a member of the European Association for Artificial Intelligence, of the European AI Alliance and of the International Association for Pattern Recognition.
Deep Understanding of Shopper Behaviors and Interactions Using Computer Vision
In retail environments, there’s great value in understanding how shoppers move in the space and interact with products. And, while the retail environment has some favorable characteristics for computer vision, the large number and diversity of products sold, along with the potential ambiguity of shopper movements, mean that accurately measuring shopper behavior is challenging. In this lecture, Frontoni explores some of these challenges and present a set of deep learning algorithms that are designed to address them. These algorithms have been proposed and tested for multiple consumers tracking, social interactions, shopper-shelf interaction, trajectory predictions and have been used to measure the activity of more than 5 million shoppers worldwide. Novel deep networks, GANs and architectures for edge processing will be the scientific topics of this talk.