Andrew Zisserman

from Wikipedia, the free encyclopedia

Andrew Zisserman (* 1957 ) is a British computer scientist who deals with computer vision . He is a professor at Oxford University .

Zisserman received a PhD in theoretical physics from the University of Cambridge and then began studying computer vision at the University of Edinburgh , collaborating with Andrew Blake , which led to the book Visual Reconstruction , which pursued an approach on energy minimization in image reconstruction an algorithm ( graduated non convexity ) for local minima.

In 1987 he moved back to Oxford to join the newly founded robotics group of Michael Brady (* 1945). There he developed the Multiple View Geometry in computer vision. He applied this to object recognition, to 3D reconstruction and reconstruction of movement from individual images. Software that his group developed in the company 2d3 was used for special effects in films and won a Technology Emmy in 2002 .

He is a Fellow of the Royal Society (2007), won the Marr Prize three times and is one of the ISI Highly Cited Researchers. In 2008 he became a Distinguished Fellow of the British Machine Vision Association (BMVA).

Fonts

  • with Andrew Blake: Visual Reconstruction, MIT Press 1987
  • Editor with Joseph Mundy: Geometric Invariance in Computer Vision, MIT Press 1992
  • with Richard Hartley: Multiple View Geometry in Computer Vision, Cambridge University Press 2000, 2nd edition 2009
  • with J. Visic: Video Google: A text retrieval approach to object matching in videos , Proc. 9. IEEE Conf. Computer Vision, 2003

Web links