BMVC92 pp 538-547 | Cite as

Visibility Scripts for Active Feature-Based Inspection

  • E. Trucco
  • E. Thirion
  • M. Umasuthan
  • A. M. Wallace
Conference paper


We report the first stage of a project aimed at computing visibility scripts for active inspection applications, in which a robot-mounted sensor observes a known object from different viewpoints. Visibility scripts describe the optimal sensor position for a given inspection task and may involve different visibility requirements, e.g. achieving optimal visibility of a single object feature or simultaneous visibility of a set of features. We discuss also stereo visibility, or the optimal placement of a stereo head within the visibility region of a feature. Stereo visibility is a novel feature in the panorama of comparable systems and may prove nontrivial in some situations. Script generation is based on an approximate visibility space, the property sphere. We take into account several constraints imposed by most real systems, for instance the limited workspace of a real sensor or the desired resolution at which a feature must be observed.


Stereo Visibility Sensor Placement Photometric Stereo Inspection Task Aspect Graph 
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]
    S. Sakane, M. Ishii and M. Kakikura: Occlusion Avoidance of Visual Sensors Based on a Hand-Eye Action Simulator System: HEAVEN. Advanced Robotics 2, pp. 149 -165, 1987.Google Scholar
  2. [2]
    S. Sakane and T. Sato: Automatic Planning of Light Source and Camera Placement for an Active Photometric Stereo System. Proc. IEEE Int. Conf. on Robotics and Automation, 1991, pp. 1080 -1087.CrossRefGoogle Scholar
  3. [3]
    G. Fekete and L.S. Davis: Property Spheres: a New Representation for 3-D Object Recognition ,Proc. IEEE Workshop on Computer Vision, Representation and Control, pp. 192 -201, 1984.Google Scholar
  4. [4]
    M.R. Korn and C.R. Dyer: 3-D Multiview Object Representations for Model-Based Object Recognition ,Pattern Recognition 20, pp. 91 -103, 1987.Google Scholar
  5. [5]
    E. Trucco: On Shape-Preserving Boundary Conditions for Diffusion Smoothing. Proc. IEEE Int. Conf. on Robotics and Automation, 1992, pp. 1690 -1694.CrossRefGoogle Scholar
  6. [6]
    K. Bowyer and C.R. Dyer: Aspect Graphs: an Introduction and Survey of Recent Results ,International Journal of Imaging Systems and Technology 2, 1990, pp. 315 -328.CrossRefGoogle Scholar
  7. [7]
    Z. Gigus, J. Canny and Seidel: Efficiently Computing the Aspect Graph of Polyhedral Objects ,Proc. IEEE International Conference on Computer Vision, 1988, pp. 30 -39.Google Scholar
  8. [8]
    S. Petitjean, J. Ponce and D. Kriegman: Computing Exact Aspect Graphs of Curved Objects: Algebraic Surfaces. Tech. Rep. UIUC-BI-AI-RCV-92-02, University of Illinois at Urbana-Champaign, 1992.Google Scholar
  9. [9]
    Kaiser, K. Bowyer and Goldgof: On Exploring the Definition of a Range-Image Aspect Graph ,Proc. 7th Scandinavian Conference on Image Analysis, 1991, pp. 652 -656.Google Scholar
  10. [10]
    J. Ben-Arie: Probabilistic Models of Observed Features and Aspects with Applications to Weighted Aspect Graphs ,Pattern Recognition Letters 11, 1990, pp. 421 -427.CrossRefMATHGoogle Scholar
  11. [11]
    K. Ikeuchi and T. Kanade: Modeling Sensors: Toward Automatic Generation of Object Recognition Program ,Computer Vision, Graphic and Image Processing 48, 1989, pp. 50 -79.CrossRefGoogle Scholar
  12. [12]
    H.-S. Kim, R.C. Jain and R.A. Volz: Object Recognition Using Multiple Views ,Proc. IEEE Conference on Robotics and Automation, 1985, pp. 28 -33.Google Scholar
  13. [13]
    C.K. Cowan and P.D. Kovesi: Automatic Sensor Placement for Vision Task Requirements ,IEEE PAMI 10, 1988, pp. 407 -416.CrossRefGoogle Scholar
  14. [14]
    D. Eggert and K. Bowyer: Perspective Projection Aspect Graphs of Solids of Revolution: an Implementation ,Proceedings 7th Scandinavian Conference on Image Analysis, 1991, pp. 299 -306.Google Scholar
  15. [15]
    S. Dickinson, A. Pentland and A. Rosenfeld: From Volumes to Views: An Approach to 3-D Object Recognition ,Proc. IEEE Workshop on Advances in CAD-Based Vision, Hawaii, 1991, pp. 85 -96.Google Scholar
  16. [16]
    T. M. Silberberg, L. Davis and D. Harwood: An Iterative Hough Procedure for Three Dimensional Object Recognition. Pattern Recognition 17, 1984, pp. 621 -629.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1992

Authors and Affiliations

  • E. Trucco
    • 1
  • E. Thirion
    • 1
  • M. Umasuthan
    • 1
  • A. M. Wallace
    • 1
  1. 1.Department of Computer ScienceHeriot-Watt UniversityEdinburghScotland

Personalised recommendations