[Univ of Cambridge] [Dept of Engineering]

Georg Klein

Computer Vision and Robotics Group

News: As of October 1st 2005, I have moved to the Active Vision Group at Oxford University. My new web-site is here. These pages will disappear in the future and are no longer maintained.


I am a 4th-year PhD student in the Machine Intelligence Laboratory of the Cambridge University Engineering Department. I work under the supervision of Dr. Tom Drummond. Originally from Austria, I matriculated at King's College in 1997 and obtained an MEng degree in 2001.


Blur Real-Time Visual Tracking

This work combines edge-based visual tracking with inertial sensors. By modifying the behaviour of edge detection according to information from rate gyroscopes, sequences with substantial amounts of motion blur can be tracked.

[2002 BMVC Paper] [2004 IVC Paper] [videos]

Printer HMD-Based Augmented Reality

The above tracking method can be applied to a head-mounted camera. A see-through head-mounted display and a novel calibration technique are used to produce prototype maintenance applications.

[2003 ISMAR Paper] [videos]

Darth Vader Tablet-Based Augmented Reality

Tablet PCs offer an alternative delivery mechanism for augmented reality. A combination of inside-out edge tracking and outside-in LED tracking provides robust registration. Occlusions can be refined to improve the perceived integration of virtual objects in the real world.

[2004 ISMAR Paper] [videos]

Blur A Single-Frame Visual Gyroscope

Instead of using rate gyroscopes to predict camera motion in a frame, we attempt to estimate this information from the video input by analysing the motion blur present in a single video frame. By looking at the parts of the image which remain un-blurred, blur direction and magnitude can be determined very quickly (just over 2 milliseconds per frame on a 2.4GHz machine).

[2005 BMVC Paper]


See my publications.

Contact Information

[Cambridge University | CUED | Machine Intelligence Laboratory]

Updated Sept 2005