C-BRIC e-Workshop: An Introduction to Image and 3D Motion Computation Using Event-based Vision

Abstract: Asynchronous event-based sensors allow us to capture the environment fast, under low light or high dynamic range conditions, and without motion blur. However, traditional frame-based vision approaches cannot be applied due to the asynchronous nature of incoming measurements. We present an introduction to event representation and processing, and how it is applied in optical flow computation, feature tracking, and stereo vision.

The recovery of 3D motion and structure is shown using traditional and learning based techniques. We show how event processing differs from frame processing and the outstanding challenges.

 

Bio: Kostas Daniilidis  has been faculty at the University of Pennsylvania since 1998.  He is an IEEE Fellow. He was the director of the GRASP laboratory from 2008 to 2013. He obtained his PhD in Computer Science from the University of Karlsruhe (now KIT), 1992.  He is co-recipient of the Best Conference Paper Award at ICRA 2017 and Best Paper Finalist at IEEE CASE 2015, RSS 2018, and CVPR 2019. Kostas’ main interest today is in geometric deep learning, event-based cameras, and action representations as applied to vision based manipulation and navigation.