• Mark R. Stevens
  • J. Ross Beveridge
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 589)


Occlusion greatly hinders the performance of algorithms since it is not a phenomena which can be predicted in isolation: occlusion is a function of an object’s relationship to the scene in which it is embedded. Even though occlusion is determined by an object’s relationship to other objects in the scene, automatic recognition algorithms seldom approach the problem in terms of multi-object interaction. Instead, algorithms focus on locating a single object in a single image. These techniques often explore possible matches between model features and homogeneous data features (e.g., matching model lines to data lines (Lowe, 1985)). The search for correspondences takes place in feature space and is plagued by combinatorics: the number of possible model-to-data feature pairings grows exponentially with the total number of features (Grimson, 1990c).


Computer Graphic Object Recognition Feature Pairing Object Occlusion Integrate Graphic 
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.

Copyright information

© Springer Science+Business Media New York 2001

Authors and Affiliations

  • Mark R. Stevens
    • 1
  • J. Ross Beveridge
    • 2
  1. 1.Worcester Polytechnic InstituteUSA
  2. 2.Colorado State UniversityUSA

Personalised recommendations