Agenda

Speaker: ​Rita Cucchiara, University of Modena and Reggio Emilia

Abstract

Human behavior understanding (HBU) is so important, and for so many applications, to become one of the most studied topics for many computer science disciplines. Recent advances in motion analysis, graph-based pattern recognition and machine/deep learning make HBU research a true success story. This talk focuses on HBU for a very important application area, namely automotive, where cameras are becoming a unavoidable sensing component. They are used for supporting assisted/semi-automatic and automatic guidance and for improving the safety and comfort of drivers and passengers. HBU can be used to understand pedestrians and persons around moving cars, or to understand the behavior of drivers in the car. Most of the traditional computer vision techniques are exploited and in particular pedestrian detection and tracking for outside and face detection and pose estimation inside. In this talk, after a general overview on classical multiple-target tracking methods, I will present some very new research activities at Imagelab focused on the driver. These new approaches are mostly based on 3D information, saliency analysis and video segmentation that are commonly characterized by a deep use of deep networks.

Bio sketch

Rita Cucchiara is Professor of Computer Architecture and Computer Vision at Engineering Department “Enzo Ferrari” of the university of Modena and Reggio Emilia, Italy. She is Responsible of the Imagelab research lab at UNIMORE and Director of the Inter-departmental Centre of Research in ICT for Enterprise Softech-ICT, cofunded by UNIMORE and Regione Emilai Romagna under EU FESR programs. She is working on computer vision, multimedia pattern recognition, machine learning and intelligent sensing. She is President of GIRPR, the Italian association of Pattern Recognition. Research projects regard multiple person tracking, 2D and 3D reconstruction of cultural heritage building for egocentric vision and video annotation and captioning. Recent activities concerns the adoption of the GPUs powers and Deep Learning for research in fields such as video understanding, human behavior in surveillance and automotive together with international companies, such as Panasonic, Rai, Ferrari. In 2016 she has been awarded by the Facebook Artificial intelligence Research and the Cineca Italian SuperComputing Resource Allocation grants. Rita Cucchiara is in the Advisory Board of the Computer Vision Foundation. She covers also the role of deputy-president of the Italian Groups of Computer Engineering Professors GII, for scientific research. She is author or more than 300 publications, with a H-index 39 and more than 9000 citations (Google scholar oct 2016). She is IAPR fellow.