【SICE Forum (Session 13,2022)】 Radar approaches for sequential human activity classification

Author:| Time: 2022-12-14 11:22:41|

The "SICE Forum" organized by the School of Information and Communication Engineering (SICE) has invited Prof. Francesco Fioranelli of University of Delft, Netherlands, to deliver an academic webinar. Below are the details for the event, and interested students and faculty members are welcome to attend.

Topic: Radar approaches for sequential human activity classification

Speaker:Francesco Fioranelli (Assistant Professor, University of Delft, Netherlands)

Time:14:35-15.05 (Wednesday), December 14, 2022

Venue: Online platform: ZOOM Meeting

Conference links:

https://tudelft.zoom.us/j/99984743283?pwd=SkdGM2VjcXVEZW5xQ3k1ZXYzWXcwQT09

Host:Shisheng Guo, Associate Researcher

Introduction:

One of the outstanding challenges in the classification of human activities using radar is the processing of continuous sequences of data, where heterogeneous activities can be mixed and start/finish at random times and with undefined transitions between them. In contrast to the more conventional approaches where activities are inherently collected as separated “snapshots”, processing these continuous sequences requires methods to separate the different activities, group them intro macro-activities if needed, and formulate classification algorithms tailored to represent such data more as a sequence than as separated images. The talk will discuss some of these challenges, and present non-exhaustive examples from recent literature where continuous activities in the context of assisted living and gesture recognition are classified.

Speakers’ profiles:

Francesco Fioranelli received his Ph.D. degree from Durham University, U.K., in 2014. He is currently a Tenured Assistant Professor at TU Delft in the Netherlands, and was a Lecturer at the University of Glasgow and a Research Associate at University College London.

His research interests include the development of multistatic radar systems and automatic classification for human signatures analysis in healthcare and security, drones and UAVs detection and classification, and automotive radar. He has authored over 130 publications between book chapters, journal and conference papers, and co-edited two books on micro-Doppler and drone signatures.

Qingshuihe Campus Address: Block B, Scientific Research Building,
University of Electronic Science and Technology of China, No. 2006,
Xiyuan Avenue, High-tech Zone (West), Chengdu

Postcode:611731    Email: xintong@uestc.edu.cn

Telephone:028-61830156  Fax:028-61831665

Share