Stony Brook University Computer Science

Dr. Fabio Morbidi from University of Picardie Jules Verne, France will be giving a talk on "Event-based Vision: A New Sensing Paradigm for Mobile Robots and Intelligent Cars".

Please find the seminar details below:
Title: Event-based Vision: A New Sensing Paradigm for Mobile Robots and Intelligent Cars
Date & Time: Friday, November 29, 2 PM
Venue: SUNY Korea Academic Building B206

Abstract

Event cameras are emerging vision sensors which allow the camera to capture the appearance of a 3D scene in an asynchronous fashion. Compared to the traditional frame-based cameras, they enjoy a number of attractive properties: very low latency (in the order of microseconds), low energy consumption (a few tens of milliwatts), and a large dynamic range (in excess of 120 dB). As the human eye, these bio-inspired sensors only record the brightness changes occurring within a scene, and they go beyond the acquisition mechanism of standard cameras, based on time-indexed frames. For all these reasons, event cameras have recently risen to prominence in computer vision and mobile robotics. 
In this talk, I will present the recent research activities of my group on event-based vision for robotic and intelligent vehicle applications. In particular, I will describe an omnidirectional event-based visual gyroscope for agile robots, and monocular and stereo event-based algorithms for moving object detection and 3D depth estimation in real-world driving scenarios. I will conclude my presentation with preliminary results on 360-degree event-based target tracking and optical communication for aerial robots.
This work has been carried out within the framework of the ANR CERBERE (2022-2025) and DEVIN (2024-2028) projects. It has also been supported by the EVENTO (2021-2024) and PHC STAR NasDroVie (2023-2024) projects. 

Speaker Bio

Fabio Morbidi received his PhD degree in control engineering and robotics from the University of Siena, Italy, in 2009. He was a visiting researcher at the University of California, Santa Barbara, USA, in 2008, and he held post-doctoral positions at Northwestern University, University of Texas at Arlington, USA, and at Inria Grenoble Rhone-Alpes, France. Since 2014, he has been an Associate Professor of robotics with the University of Picardie Jules Verne, Amiens, France, and a member of the MIS laboratory. He currently serves as Associate Editor for the IEEE Transactions on Robotics and for the IEEE Robotics and Automation Letters. He is the co-editor of the book « Omnidirectional Vision: From Theory to Applications », ISTE-Wiley, 2023. His main research interests include multi-robot systems and robotic vision.