Skip to main content

On the Computation of Visual Events in Aspect Graph Generation

  • Conference paper
Mustererkennung 1997

Part of the book series: Informatik aktuell ((INFORMAT))

  • 150 Accesses

Abstract

Aspect graphs are well known multiview object representations employed in object recognition tasks. Polyhedra in many applications have shown to be adequate approximative models for real — especially man-made — objects. Aspect graphs of polyhedral objects are generated by a structural analysis of the observed object to derive the visual events which define the partitioning surfaces of the viewing space into regions showing the same object appearance. The kinds of visual events used within this analysis are defined by polyhedral surfaces, vertex-edge pairs and triples of edges. We have found a new type of visual event which is defined by pairs of edges and is not mentioned explicitly in all other approaches on this topic. We show that the exhaustive list of types of visual events derived in our approach is complete and that the new edge-edge event is not a special case of the other well known visual events of polyhedral scenes.

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 44.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 59.99
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

  • Bowyer, K. (1992): Workshop Panel Report: Why Aspect Graphs are not (yet) Practical for Computer Vision. CVGIP: Image Understanding, 55 (2): 212 – 214, 1992.

    Article  MATH  Google Scholar 

  • Chakravarty, I.; Freeman, H. (1982): Characteristic-Views as a Basis for 3dimensional Object Recognition. In: Proc. Soc. Photo-Optical Instrumentation, Conf. on Robot Vision, Vol. 336, 37 – 45. SPIE Bellingham, WA, 1982.

    Google Scholar 

  • Gigus, Z.; Canny, J.; Seidel, R. (1991): Efficiently Computing and Representing the Aspect Graphs of Polyhedral Objects. IEEE PAMI, 13 (6): 542 - 551, 1991.

    Article  Google Scholar 

  • Koenderink, J. J.; van Doorn, A. J. (1976): Visual Perception of Rigidity of Solid Shape. Journal of math. Biology, 3: 79–85, 1976.

    Article  MATH  Google Scholar 

  • Korn, M. R.; Dyer, C. R. (1987): 3-D Multiview Object Representation for Model-Based Object Recognition. Pattern Recognition, 20: 91 – 103, 1987.

    Article  Google Scholar 

  • Marr, D. (1982): Vision. Freman, San Francisco, 1982.

    Google Scholar 

  • Plantinga, W. H.; Dyer, C. R. (1990): Visibility, Occlusion, and Aspect Graph. In: Int. Journ. of Computer Vision, 137 – 160, 1990.

    Google Scholar 

  • Stewman, J.; Bowyer, K. (1988): Creating the Perspective Projection Aspect Graph of Polyhedral Objects. In: 2nd Int. Conf. on Comp. Vision, 494 – 500, 1988.

    Google Scholar 

  • Wang, R.; Freeman, H. (1990): The Use of Characteristic-View Classes for 3D Object Recognition. In: Machine Vision for Three-Dimensional Scenes, 109–162. H. Freeman, 1990.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Fischer, A., Steinhage, V. (1997). On the Computation of Visual Events in Aspect Graph Generation. In: Paulus, E., Wahl, F.M. (eds) Mustererkennung 1997. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60893-3_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-60893-3_15

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63426-3

  • Online ISBN: 978-3-642-60893-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics