Event

Lockheed Martin Robotics Seminar: Friedrich Fraundorfer, "Computer vision for drones"

Friday, September 6, 2019
3:30 p.m.
2121 JM Patterson
Ania Picard
301 405 4358
appicard@umd.edu
https://vid.umd.edu/detsmediasite/Play/e97653b051f946069178665f4cb8255a1d

Lockheed Martin Robotics Seminar 

Computer vision for drones

Friedrich Fraundorfer
Assistant Professor
Graz University of  Technology
Austria

Abstract
Drones are small scale flying robots and it is predicted that the drone  market will see a major growth in the near future. Computer vision will  play a major role in controlling and developing autonomous drones. In my talk I will give an overview of computer vision techniques that  are used for drones in my lab. I will start by presenting IMU-assisted  computer vision algorithms for ego-motion estimation, then talk about  using semantics for drone navigation and go through various projects  running at our lab.

Host

Mumu Xu and Cornelia Fermuller

Biography
Friedrich Fraundorfer is Assistant Professor at Graz University of  Technology, Austria since October 2014. He received the Ph.D. degree in computer science from TU Graz, Austria in 2006 working at the Institute  of Computer Graphics and Vision headed by Franz Leberl and Horst Bischof. He had post-doc stays at the University of Kentucky (US), at  the University of North Carolina at Chapel Hill (US) and at ETH Zürich  (Switzerland). From 2012 to 2014 he acted as Deputy Director of the Chair of Remote Sensing Technology at the Faculty of Civil, Geo and Environmental Engineering at the Technische Universität München.

Friedrich Fraundorfer has been involved in multiple international and  multinational research projects as project leader, investigator and  collaborator, the EU project SFly (http://www.sfly.org/), a 4-year SNF  project about autonomous micro UAV’s, the EU project VCHARGE  (http://www.v-charge.eu/). Currently he acts as PI of an ongoing DACH  project VMAV about autonomous micro UAV’s, as PI for the H2020 project  SLIM (http://www.slim-project.eu/) and RESIST and as project leader for  various industry collaborations. His main research areas are 3D Computer  Vision, 3D Modeling, Robot Vision, Multi View Geometry, Visual-Inertial  Fusion, Micro Aerial Vehicle, Autonomous Systems, Aerial Imaging, Image  Analysis. He is the author of a well perceived two-part tutorial about  visual odometry in the IEEE Robotics and Automation Magazine.

https://www.tugraz.at/institute/icg/research/team-fraundorfer/