view all speakers

Prof. Luc Van Gool BE

electro-mechanical engineering professor at ETH Zurich & KU Leuven

Luc Van Gool got a degree in electro-mechanical engineering at the Katholieke Universiteit Leuven in '81. Currently, he is a full professor for Computer Vision at the ETH in Zurich & the Katholieke Universiteit Leuven in Belgium. He leads research & teaches at both places. He has authored over 200 papers in his field & he has been a program committee member of several, major computer vision conferences. His main interests include 3D reconstruction & modeling, object recognition, tracking & gesture analysis. He is co-founder of 5 spin-off companies.

Over the last decade the area of computer vision has achieved an important goal of automated image understanding, namely the capacity to identify objects as belonging to a certain class. This is a crucial achievement of which the effect in the long run can be expected to go far beyond telling which objects are in a picture. 

Many other tasks can benefit from it. For example, it makes it easier to track traffic agents if one knows their type & therefore how they behave. And it is possible to get better quality 3D city reconstructions with a system that understands the structure of buildings. Knowing the object type even makes it doable to infer 3D from a single image. 

Luc’s research into the role of invariance in geometrical transformations has resulted in the development of models that are still being used for research into image recognition. His current research covers several aspects of computer vision, imaging, & image processing. It has been used in technology for movies, security, archaeology, & the digitization of cultural heritage.