Jump to content

Andrew Fitzgibbon (engineer)

Add links
From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by Perspicax (talk | contribs) at 10:23, 12 October 2023 (Adding Category:Alumni of the University of Edinburgh using Cat-a-lot). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Andrew Fitzgibbon
Born1968 (age 55–56)
Dublin, Ireland
Alma mater
Awards
Scientific career
FieldsComputer science
InstitutionsUniversity of Oxford
ThesisStable Segmentation of 2D Curves (1997)
Doctoral advisorRobert B Fisher
Websitewww.fitzgibbon.ie

Andrew Fitzgibbon FREng (born 1968) is an Irish researcher in computer vision. Since 2022, he has worked at Graphcore.

Education

Fitzgibbon went to school at Coláiste Chríost Rí in Cork, and then studied Computer Science and Mathematics (Joint Honours) at University College, Cork, graduating in 1989. He pursued a one-year Masters' in Knowledge-based Systems at Heriot-Watt University. Rather than start a PhD, he began work as a research assistant at the Department of Artificial Intelligence, University of Edinburgh, writing computer programs for 3D shape modelling and 3D scanning.[1] In 1992 he registered for a part-time PhD, which was awarded in 1997.[2]

Career and research

In 1996 he moved to the robotics research group at the Department of Engineering Science, University of Oxford, working with Andrew Zisserman, and in 1998 their work on Structure from motion, jointly with Phillip Torr, was awarded the International Conference on Computer Vision Marr Prize. This work led to the foundation of the company 2d3 in 1999, and the product "boujou", which won a Primetime Emmy Award for technical achievement.[3][4] In 1999, he was awarded a Royal Society University Research Fellowship, and continued to work with Zisserman.[citation needed] Their work on applying machine learning to image-based rendering (with Yonatan Wexler) led to the award in 2003 of a second conference paper Marr Prize.[5]

In 2005, he moved to Microsoft Research, and began work on human body tracking, and later contributed to the group development of the machine learning component of the human motion capture software in the Kinect system.[3][6] This group work was honoured with the MacRobert Award of the Royal Academy of Engineering for Microsoft Cambridge team in 2011.[7]

Since 2022, he has worked at Graphcore.

Awards and honours

References

  1. ^ a b "Andrew Fitzgibbon". BMVA Distinguished Fellow 2017. The British Machine Vision Association. September 2017. Archived from the original on 6 December 2017. Retrieved 4 December 2017.
  2. ^ "UKCRC Successful PhDs: Andrew Fitzgibbon". UK Computing Research Committee. 2009. Retrieved 7 December 2017.
  3. ^ a b c "Four engineers: four silver medals". Ingenia. No. 56. Magazine of the Royal Academy of Engineering. September 2013. Retrieved 4 December 2017.
  4. ^ a b "2d3 Boujou wins Primetime Emmy Engineering Award". The CGSociety. 19 August 2002. Archived from the original on 14 July 2014. Retrieved 4 December 2017.
  5. ^ a b ICCV Best Paper Award (Marr Prize) Archived 26 November 2018 at the Wayback Machine, IEEE computer society
  6. ^ Kohli, Pushmeet; Shotton, Jamie (2013). Consumer Depth Cameras for Computer Vision. Springer, London. pp. 63–70. CiteSeerX 10.1.1.296.3916. doi:10.1007/978-1-4471-4640-7_4. ISBN 978-1-4471-4639-1.
  7. ^ Microsoft Research Cambridge wins MacRobert Award, Business Weekly, 6 June 2011
  8. ^ "Roger Needham lecture 2006". British Computer Society. 2006. Retrieved 5 December 2017.
  9. ^ "Feature: 2012 IAPR Fellows". IAPR Newsletter. Vol. 35, no. 1. International Association for Pattern Recognition. January 2013. Retrieved 5 December 2017.
  10. ^ "Stars of industry and academia elected to the Royal Academy of Engineering". The Royal Academy of Engineering. 16 September 2014. Archived from the original on 4 December 2014. Retrieved 5 December 2017.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Andrew_Fitzgibbon_(engineer)&oldid=1179774352"