Using projective invariants for constant time library indexing in model based vision

Conference item

Projectively invariant shape descriptors allow fast indexing into model libraries, because recognition proceeds without reference to object pose. This paper describes progress in building a large model based vision system which uses many projectively invariant descriptors. We give a brief account of these descriptors and then describe the recognition system, giving examples of the invariant techniques working on real images. We demonstrate the ease of model acquisition in our system, where models are generated directly from images. We demonstrate fast recognition without determining object pose or camera parameters.

Authors: Rothwell, CA; Zisserman, A; Forsyth, DA; Mundy, JL

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Host title: BMVC91: Proceedings of the British Machine Vision Conference, organised for the British Machine Vision Association by the Turing Institute 24–26 September 1991 University of Glasgow
• Pages: 62-70
• Place of publication: London
• Publication date: 2012-12-06
• Event title: British Machine Vision Conference (BMVC 1991)
• Event location: Glasgow
• Event start date: 1991-09-24
• Event end date: 1991-09-26
• DOI: 10.1007/978-1-4471-1921-0_9
• EISBN: 9781447119210
• ISBN: 9783540197157
• Language: English