Andrew Zisserman

Last updated

Andrew Zisserman
Born1957 (age 6667) [1]
Alma mater
Known forMultiple-view geometry
Awards
Scientific career
Fields Computer Science
Institutions University of Oxford
Thesis Fresh approaches to magnetostatic field calculations, with the emphasis on analytical techniques  (1984)
Doctoral advisor James Caldwell [3]
Website www.robots.ox.ac.uk/~az/

Andrew Zisserman FRS [2] (born 1957) is a British computer scientist and a professor at the University of Oxford, and a researcher in computer vision. [4] As of 2014 he is affiliated with DeepMind. [5]

Contents

Education

Zisserman received the Part III of the Mathematical Tripos, and his PhD in theoretical physics from the Sunderland Polytechnic. [6]

Career and research

In 1984, he started to work in the field of computer vision at the University of Edinburgh. Together with Andrew Blake they wrote the book Visual reconstruction published in 1987, which is considered one of the seminal works in the field of computer vision. According to Fitzgibbon (2008) this publication was "one of the first treatments of the energy minimisation approach to include an algorithm (called "graduated non-convexity") designed to directly address the problem of local minima, and furthermore to include a theoretical analysis of its convergence." [7]

In 1987, he moved back to England to the University of Oxford, where he joined Mike Brady's newly founded robotics research group as a University Research Lecturer, [8] [9] and started to work on multiple-view geometry. According to Fitzgibbon (2008) his "geometry was successful in showing that computer vision could solve problems which humans could not: recovering 3D structure from multiple images required highly trained photogrammetrists and took a considerable amount of time. However, Andrew's interests turned to a problem where a six-year-old child could easily beat the algorithms of the day: object recognition." [7]

Publications

Zisserman has published several articles, [10] some of the most highly cited works in the field, and has edited a series of books. A selection:

  • 1987. Visual reconstruction. With Andrew Blake.
  • 1992. Geometric invariance in computer vision. Edited with Joseph Mundy.
  • 1994. Applications of invariance in computer vision : second joint European-US workshop, Ponta Delgada, Azores, Portugal, 9–14 October 1993 : proceedings. With Joseph L. Mundy and David Forsyth (eds).
  • 1996. ECCV '96 International Workshop (1996 : Cambridge, England) Object representation in computer vision II : ECCV '96 International Workshop, Cambridge, UK, 13–14 April 1996 : proceedings. With Jean Ponce, and Martial Hebert (eds.).
  • 1999. International Workshop on Vision Algorithms (1999 : Corfu, Greece) Vision algorithms : theory and practice : International Workshop on Vision Algorithms, Corfu, Greece, 21–22 September 1999 : proceedings. With Bill Triggs and Richard Szeliski (eds.).
  • 2000. Multiple view geometry in computer vision. With Richard Hartley. Second edition 2009. [11]
  • 2008. Computer vision – ECCV 2008 : 10th European conference on computer vision, Marseille, France, 12–18 October 2008, proceedings, part I. Edited with David Forsyth and Philip Torr.

Awards and honours

Zisserman is an ISI Highly Cited researcher. He is the only person to have been awarded the Marr Prize three times, in 1993, in 1998, and in 2003. He was elected Fellow of the Royal Society in 2007. [2] [7] In 2008 he was awarded BMVA Distinguished Fellowship. [7] In 2013 he received the Distinguished Researcher Award at ICCV. [12] Zisserman received the 2017 Royal Society Milner Award “in recognition of his exceptional achievements in computer programming which includes work on computational theory and commercial systems for geometrical images.” [13]

Related Research Articles

Random sample consensus (RANSAC) is an iterative method to estimate parameters of a mathematical model from a set of observed data that contains outliers, when outliers are to be accorded no influence on the values of the estimates. Therefore, it also can be interpreted as an outlier detection method. It is a non-deterministic algorithm in the sense that it produces a reasonable result only with a certain probability, with this probability increasing as more iterations are allowed. The algorithm was first published by Fischler and Bolles at SRI International in 1981. They used RANSAC to solve the Location Determination Problem (LDP), where the goal is to determine the points in the space that project onto an image into a set of landmarks with known locations.

<span class="mw-page-title-main">Motion estimation</span> Process used in video coding/compression

In computer vision and image processing, motion estimation is the process of determining motion vectors that describe the transformation from one 2D image to another; usually from adjacent frames in a video sequence. It is an ill-posed problem as the motion happens in three dimensions (3D) but the images are a projection of the 3D scene onto a 2D plane. The motion vectors may relate to the whole image or specific parts, such as rectangular blocks, arbitrary shaped patches or even per pixel. The motion vectors may be represented by a translational model or many other models that can approximate the motion of a real video camera, such as rotation and translation in all three dimensions and zoom.

<span class="mw-page-title-main">Automatic image annotation</span>

Automatic image annotation is the process by which a computer system automatically assigns metadata in the form of captioning or keywords to a digital image. This application of computer vision techniques is used in image retrieval systems to organize and locate images of interest from a database.

In computer vision, the fundamental matrix is a 3×3 matrix which relates corresponding points in stereo images. In epipolar geometry, with homogeneous image coordinates, x and x′, of corresponding points in a stereo image pair, Fx describes a line on which the corresponding point x′ on the other image must lie. That means, for all pairs of corresponding points holds

Structure from motion (SfM) is a photogrammetric range imaging technique for estimating three-dimensional structures from two-dimensional image sequences that may be coupled with local motion signals. It is studied in the fields of computer vision and visual perception.

<span class="mw-page-title-main">Bundle adjustment</span> Technique in photogrammetry and computer vision

In photogrammetry and computer stereo vision, bundle adjustment is simultaneous refining of the 3D coordinates describing the scene geometry, the parameters of the relative motion, and the optical characteristics of the camera(s) employed to acquire the images, given a set of images depicting a number of 3D points from different viewpoints. Its name refers to the geometrical bundles of light rays originating from each 3D feature and converging on each camera's optical center, which are adjusted optimally according to an optimality criterion involving the corresponding image projections of all points.

Caltech 101 is a data set of digital images created in September 2003 and compiled by Fei-Fei Li, Marco Andreetto, Marc 'Aurelio Ranzato and Pietro Perona at the California Institute of Technology. It is intended to facilitate computer vision research and techniques and is most applicable to techniques involving image recognition classification and categorization. Caltech 101 contains a total of 9,146 images, split between 101 distinct object categories and a background category. Provided with the images are a set of annotations describing the outlines of each image, along with a Matlab script for viewing.

<span class="mw-page-title-main">Pedestrian detection</span> Computer technology

Pedestrian detection is an essential and significant task in any intelligent video surveillance system, as it provides the fundamental information for semantic understanding of the video footages. It has an obvious extension to automotive applications due to the potential for improving safety systems. Many car manufacturers offer this as an ADAS option in 2017.

The International Conference on Computer Vision (ICCV) is a research conference sponsored by the Institute of Electrical and Electronics Engineers (IEEE) held every other year. It is considered to be one of the top conferences in computer vision, alongside CVPR and ECCV, and it is held on years in which ECCV is not.

The European Conference on Computer Vision (ECCV) is a biennial research conference with the proceedings published by Springer Science+Business Media. Similar to ICCV in scope and quality, it is held those years which ICCV is not. It is considered to be one of the top conferences in computer vision, alongside CVPR and ICCV, with an 'A' rating from the Australian Ranking of ICT Conferences and an 'A1' rating from the Brazilian ministry of education. The acceptance rate for ECCV 2010 was 24.4% for posters and 3.3% for oral presentations.

Richard I. Hartley is an Australian computer scientist and an Emeritus professor at the Australian National University, where he is a member of the Computer Vision group in the Research School of Computing.

<span class="mw-page-title-main">J. Michael Brady</span> Researcher in medical-image analysis

Sir John Michael Brady is an emeritus professor of oncological imaging at the University of Oxford. He has been a Fellow of Keble College, Oxford, since 1985 and was elected a foreign associate member of the French Academy of Sciences in 2015. He was formerly BP Professor of Information Engineering at Oxford from 1985 to 2010 and a senior research scientist in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) in Cambridge, Massachusetts, from 1980 to 1985.

Stefano Soatto is professor of computer science at the University of California, Los Angeles (UCLA), in Los Angeles, CA, where he is also professor of electrical engineering and founding director of the UCLA Vision Lab.

Andrew Fitzgibbon is an Irish researcher in computer vision. Since 2022, he has worked at Graphcore.

<span class="mw-page-title-main">Alan Yuille</span> English academic

Alan Yuille is a Bloomberg Distinguished Professor of Computational Cognitive Science with appointments in the departments of Cognitive Science and Computer Science at Johns Hopkins University. Yuille develops models of vision and cognition for computers, intended for creating artificial vision systems. He studied under Stephen Hawking at Cambridge University on a PhD in theoretical physics, which he completed in 1981.

<span class="mw-page-title-main">Michael J. Black</span> American-born computer scientist

Michael J. Black is an American-born computer scientist working in Tübingen, Germany. He is a founding director at the Max Planck Institute for Intelligent Systems where he leads the Perceiving Systems Department in research focused on computer vision, machine learning, and computer graphics. He is also an Honorary Professor at the University of Tübingen.

Sanja Fidler is an associate professor at the University of Toronto and Director of AI at Nvidia. She is also a co-founder of the Vector Institute, University of Toronto and Canada CIFAR AI Chair. Her research is in the areas of computer vision and artificial intelligence.

Lourdes de Agapito Vicente is British computer scientist and academic. She is Professor of 3D Vision in the department of computer science at University College London (UCL), where she leads a research group with a focus on 3D dynamic scene understanding from video. Agapito is the co-founder of the software company Synthesia, and an elected member of the Executive Committee of the British Machine Vision Association.

<span class="mw-page-title-main">Philip Torr</span>

Philip Torr FREng, FRS, is a British scientist and a professor at the University of Oxford, and a researcher in machine learning and computer vision.

References

  1. Zisserman, Andrew. at viaf.org
  2. 1 2 3 "Professor Andrew Zisserman FRS". London: Royal Society. Archived from the original on 17 November 2015.
  3. Andrew Zisserman at the Mathematics Genealogy Project
  4. Andrew Zisserman at videolectures.net
  5. "Google's DeepMind Acqui-Hires Two AI Teams in the UK, Partners with Oxford".
  6. Zisserman, A. (1984). Fresh approaches to magnetostatic field problems with the emphasis on analytical techniques (PhD thesis). Sunderland Polytechnic.
  7. 1 2 3 4 Andrew Fitzgibbon (2008) "Andrew Zisserman, BMVA Distinguished Fellow 2008 Archived 21 September 2013 at the Wayback Machine " Bmva.org
  8. Kadir, Timor; Zisserman, Andrew; Brady, Michael (2004). "An Affine Invariant Salient Region Detector". Computer Vision - ECCV 2004. Lecture Notes in Computer Science. Vol. 3021. pp. 228–241. doi:10.1007/978-3-540-24670-1_18. ISBN   978-3-540-21984-2. ISSN   0302-9743.
  9. VIBES EU Project Annex 1(2000) "VIBES EU Project Consortium Description"
  10. Andrew Zisserman List of publications from the DBLP Bibliography Server. Retrieved 20 May 2009.
  11. Multiple View Geometry in Computer Vision Second Edition. Retrieved 20 May 2009.
  12. "Awards – ICCV 2013". Iccv2013.org. Retrieved 30 March 2016.
  13. Royal Society Milner Award