Abstract
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.
CAR acknowledges the support of General Electric. AZ acknowledges the support of the United Kingdom Science and Engineering Research Council. DAF acknowledges the support of Magdalen College, Oxford. JLM acknowledges the support of the General Electric Coolidge Fellowship. The General Electric Corporate Research and Development Laboratory is supported in part by the following: DARPA contract DACA-76-86-C-007, AFOSR contract F49620-89-C-003.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bookstein, F. “Fitting Conic Sections to Scattered Data.” CVGIP-9, p.56-71, 1979.
Canny J.F. “Finding Edges and Lines in Images,” TR 720, MIT AI Lab, 1983.
Connolly, C.I., Mundy, J.L, Stenstrom, J.R. and Thompson, D.W. “Matching From 3-D Range Models into 2-D Intensity Scenes,” Proceedings ICCV1, p.65-72, 1987.
Ettinger, G.J. “Large Hierarchical Object Recognition Using Libraries of Parameterized Model Subparts,” Proceedings CVPR, p.32-41, 1988.
Forsyth, D.A., Mundy, J.L., Zisserman, A.P., Coelho, C., Heller, A. and Rothwell, C.A. “Invariant Descriptors for 3-D Object Recognition and Pose,” To appear PAMI, 1991.
Lamdan, Y., Schwartz, J.T. and Wolfson, H.J. “Object Recognition by Affine Invariant Matching,” Proceedings CVPR, p.335-344, 1988.
Lowe, D.G. Perceptual Organization and Visual Recognition, Klewer Academic Publishers, 1985.
Mohr, R. and Morin, L. “Relative Positioning from Geometric Invariants,” Proceedings CVPR, p.139-144, 1991.
Nielsen, L. and Sparr, G. “Projective Area-Invariants as an Extension of the Cross-Ratio,” Proceedings First DARPA-ESPRIT Workshop on Invariance, p.455-480, March 1991.
Pridmore, A.P., Porrill, J. and Mayhew, J.E.W. “Segmentation and Description of Binocularly Viewed Contours,” IVC-5, No. 2, p.132-138, 1987.
Rothwell, C.A., Zisserman, A.P., Marinos, C.I., Forsyth, D.A. and Mundy, J.L. “Relative Motion and Pose From Arbitrary Plane Curves,” IVC in press, 1991.
Rothwell, C.A. “Model Based Computer Vision Using Projective Invariants”, First Year Report, Department of Engineering Science, Oxford University, Oxford, 1991.
Semple, J.G. and Kneebone, G.T. Algebraic Projective Geometry, Oxford University Press, 1952.
Van Gool, L. Kempenaers, P. and Oosterlinck, A. “Recognition and Semi-Differential Invariants,” Proceedings CVPR, p.454-460, 1991.
Wayner, P.C. “Efficiently Using Invariant Theory for Model-based Matching,” Proceedings CVPR, p.473-478, 1991.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag London Limited
About this paper
Cite this paper
Rothwell, C.A., Zisserman, A., Forsyth, D.A., Mundy, J.L. (1991). Using Projective Invariants for Constant Time Library Indexing in Model Based Vision. In: Mowforth, P. (eds) BMVC91. Springer, London. https://doi.org/10.1007/978-1-4471-1921-0_9
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1921-0_9
Publisher Name: Springer, London
Print ISBN: 978-3-540-19715-7
Online ISBN: 978-1-4471-1921-0
eBook Packages: Springer Book Archive