Temporal precedence in asynchronous visual indexing

  • Jean -Marc Bost
  • Ruggero Milanese
  • Thierry Pun
3-D Vision
Part of the Lecture Notes in Computer Science book series (LNCS, volume 719)


A recent trend in model-based object recognition is to build efficient systems for primary hypotheses generation. These systems, also called visual indexing, rely on the assumption that object identification can be performed by recovering local invariants. However, reliable and significant local features are difficult to retrieve when the image background is not uniform.

Our solution to this problem takes advantage of a new concept called temporal precedence. The originality of the approach consists in transforming the initial static input image into a dynamic flow of data. Primitives extracted from the image are temporally ranked so as to favor most relevant features for recognition. Most importantly, ranks of features of different kinds may be compared.

The architecture of our indexing system is composed of a set of knowledge sources which update in parallel a blackboard structure. The asynchronism produced by the flow of input primitives is used in the activation strategy of knowledge sources.


Target Object Knowledge Source Relative Precedence Combinatorial Explosion Temporal Precedence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    I. Biedeiman: Aspects and extensions of a theory of human image understanding. In: Z.W. Pylyshyn (ed.): Computational processes in human vision: an interdisciplinary perspective. Ablex Publishing, 1988, pp. 370–428.Google Scholar
  2. 2.
    J.-M. Bost: Discriminating agents for visual indexing. In: Proc. of the 3rd conf. of the Swiss Group for A.I. and Cognitive Science. Bienne, Oct. 1991.Google Scholar
  3. 3.
    P.-Y. Burgi: Understanding the early human visual system through modeling and temporal analysis of neuronal structures. PhD Thesis No 2536, Univ. Geneva, Switzerland, 1992.Google Scholar
  4. 4.
    J.B. Burns, A.R. Hanson and E.D. Riseman: Extracting Straight Lines. IEEE Trans. on PAMI, vol 8(4), 1986, pp. 425–455.Google Scholar
  5. 5.
    D. Clemens and D. Jacobs: Model-group indexing for recognition. In: Proc. of CVPR. Maui, Hawai, Jun. 1991, pp. 4–9.Google Scholar
  6. 6.
    A.K. Jain and P.J. Fynn: 3D object recognition using invariant feature indexing of interpretation tables. In: Proc. of Workshop on Directions in Automated CAD-Based Vision, Maui, Hawai, Jun. 1991, pp. 115–123.Google Scholar
  7. 7.
    D. Lowe: Visual recognition from spatial correspondences and perceptual organization. In: Proc. of the 9th IJCAI. Los Angeles, 1985, pp. 953–959Google Scholar
  8. 8.
    R. Milanese, J.-M. Bost and T. Pun: A bottom-up attention for active vision. In: Proc. of the 10th ECAI. Vienna, Aug. 1992, pp. 808–811.Google Scholar
  9. 9.
    H.P. Nii, E.A. Feigenbaum, J.J. Anton and A.J. Rockmore: Signal-to-symbol transformation: HASP/SIAP case study”. AI mag., vol 3(2), 1982, pp. 23–35.Google Scholar
  10. 10.
    P.L. Rosin and G.A. West: Segmentation of edges into lines and arcs'. Image and Vision Computing, vol 7(2), 1989, pp. 109–114.Google Scholar
  11. 11.
    F. Stein and G. Medioni: Efficient two dimensional object recognition. In: Proc. of the 10th IAPR conf. on Pattern Recognition. Atlantic City, New Jersey, Jun. 1990, pp. 13–17.Google Scholar
  12. 12.
    J. Tsotsos: Analyzing Vision at The Complexity of Level. Behavioral and Brain Sciences, vol 13, 1990, pp. 423–469.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Jean -Marc Bost
    • 1
  • Ruggero Milanese
    • 1
  • Thierry Pun
    • 1
  1. 1.Centre Universitaire InformatiqueUniversité de GenèveGenève 4

Personalised recommendations