Computer vision for drones.
Friedrich Fraundorfer
(TU Graz, 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 3D
reconstruction from drone imagery including semantic 3D and finally show
application scenarios for drones that we developed.
Bio:
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.