Skip to main content

3D Grouping by Viewpoint Consistency Ascent

  • Conference paper
BMVC91
  • 149 Accesses

Abstract

The viewpoint consistency constraint (VCC) provides a powerful way to discover extended feature groups and to test hypotheses in object recognition. Lowe’s incremental method fails in complex scenes, and an exhaustive tree search (eg Grimson &Lozano-Perez) is too expensive. We present a state space approach in which transitions are made which monotonically ascend a measure of viewpoint consistency.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bodington, Sullivan & Baker, “Experiments on the use of the ATMS to label features for object recognition”, Computer Vision-ECCV’90, Spring-Verlag, 1990.

    Google Scholar 

  2. Bray, A., “Recognising and Tracking Polyhedral Objects”, Ph.D Thesis, Sussex University, UK, 1991.

    Google Scholar 

  3. Brooks, A. B., “Model Based Computer Vision”, UMI Research Press, 1984.

    Google Scholar 

  4. Bolles, R., et al, “3DPO:A Three-Dimensional Part Orientation System”, Int. J. of Robotics Research.

    Google Scholar 

  5. Grimson, et al, “The combinatorics of object recognition in cluttered environments using constrained search”, ICCV’88

    Google Scholar 

  6. Grimson, et al, “Model-based Recognition and Localization from Sparse Range or Tactile Data”, Int. J. of Robotics Research.

    Google Scholar 

  7. Chen, et al, “A Robot Vision System for Recognising 3D Objects in Lower-order Polynomial Time”, IEEE PAMI, No 6, 1989.

    Google Scholar 

  8. Goad, C., “Special Purpose Automatic Programming for 3D model-based vision”, Proceeding of the ARPA image understanding Workshop, Arlington, Virginia, 1983.

    Google Scholar 

  9. Kim, W. and Kak, C., “3D Object Recognition Using Bipartite Matching Embedded in Discrete Relaxation”, IEEE PAMI, No 4, 1991.

    Google Scholar 

  10. Lowe, D., “The viewpoint consistency constraint”, International Journal of Computer Vision, 1987

    Google Scholar 

  11. Lowe, D., “Fitting Parameterised 3D Models to Images”, IEEE PAMI, No 5, 1991

    Google Scholar 

  12. Grimson, “The combinatorics of heuristic search termination for object recognition in cluttered environments”, MIT, AI Lab Memo 1111.

    Google Scholar 

  13. Rydz, A., et al, “Model based Vision Using a Planar Representation of the Viewsphere”, Alvey Vision Conference’88, Manchester, 1988.

    Google Scholar 

  14. Worrall, A., et al, “Model Based Tracking”, BMVC’91, Glasgow, 1991

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1991 Springer-Verlag London Limited

About this paper

Cite this paper

Du, L., Sullivan, G.D., Baker, K.D. (1991). 3D Grouping by Viewpoint Consistency Ascent. In: Mowforth, P. (eds) BMVC91. Springer, London. https://doi.org/10.1007/978-1-4471-1921-0_7

Download citation

  • DOI: https://doi.org/10.1007/978-1-4471-1921-0_7

  • Publisher Name: Springer, London

  • Print ISBN: 978-3-540-19715-7

  • Online ISBN: 978-1-4471-1921-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics