Séminaire ASTRE : Francesco Fioranelli
Titre du séminaire et orateur
Software Radar Fall Detection and Human Indoor Activities Classification.
Francesco Fioranelli, University of Glasgow.
Date et lieu
Lundi 4 décembre 2017, 15h.
ENSEA, salle 384.
In this presentation, we will introduce the research interests in the communications, sensing and imaging (CSI) group at University of Glasgow focusing specifically on radar activities. This will be followed by a presentation on Feature Diversity for Fall Detection and Human Indoor Activities Classification Using Radar Systems . This paper presents a preliminary analysis of radar signatures for fall detection and classification of human indoor actions, to monitor the daily activity patterns of individuals at risk of deteriorating physical or cognitive health. Two datasets of signatures in different environments have been collected, one of which included signatures generated from signals simultaneously collected from a radar and an RGB-D Kinect sensor, on a couple of older individuals. This preliminary analysis shows the potential effectiveness of different features and classifiers, and highlights the need of additional investigation to exploit the diversity in terms of overall classification accuracy achieved with different features and classification methods, in different environments and datasets.
Francesco Fioranelli graduated in Telecomm Engineering (summa cum laude) at the Università Politecnica delle Marche, Ancona, Italy for my Bachelor (2007) and Master (2010). He received my PhD on through-wall radar imaging at Durham Unviersity (UK) in January 2014, and worked as a Research Associate on multistatic radar with Prof Hugh Griffiths at University College London between February 2014 and March 2016.
He then joined the University of Glasgow in April 2016 as a Lecturer in the Glasgow College UESTC, between the University of Glasgow and the University of Electronic Science and Technology of China (UESTC) in Chengdu.
He is a member of the IEEE and IET, Chartered Engineer (CEng), and a reviewer for several academic journals including IET Radar, Sonar & Navigation, IEEE Transactions on Aerospace and Electronic Systems and IEEE Sensors. His research interests are in:
- Testing and using bistatic and multistatic radar systems.
- Human micro-Doppler signatures for security and healthcare applications (gait recognition, activity identification, gesture recognition)
- UAVs and drones detection and classification
- Machine learning algorithms for radar target classification
- Through-wall radar imaging
- Wind farm clutter characterization and mitigation
- Maritime targets and sea clutter characterization
- Multipurpose and diverse waveforms for radar and communication purposes