Towards a General Abstraction through Sequences of Conceptual Operations

  • Gregor Miller
  • Steve Oldridge
  • Sidney Fels
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6962)


Computer vision is a complex field which can be challenging for those outside the research community to apply in the real world. To address this we present a novel formulation for the abstraction of computer vision problems above algorithms, as part of our OpenVL framework. We have created a set of fundamental operations which form a basis from which we can build up descriptions of computer vision methods. We use these operations to conceptually define the problem, which we can then map into algorithm space to choose an appropriate method to solve the problem. We provide details on three of our operations, Match, Detect and Solve, and subsequently demonstrate the flexibility of description these three offer us. We describe various vision problems such as image registration and tracking through the sequencing of our operations and discuss how these may be extended to cover a larger range of tasks, which in turn may be used analogously to a graphics shader language.


OpenVL Computer Vision Abstraction Language Vision Shader 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Afrah, A., Miller, G., Fels, S.: Vision system development through separation of management and processing. In: Workshop on Multimedia Information Processing and Retrieval. IEEE, Los Alamitos (2009)Google Scholar
  2. 2.
    Afrah, A., Miller, G., Parks, D., Finke, M., Fels, S.: Hive a distributed system for vision processing. In: Proc. 2nd International Conference on Distributed Smart Cameras (September 2008)Google Scholar
  3. 3.
    Bradski, G., Kaehler, A.: Learning OpenCV: Computer Vision with the OpenCV Library, 1st edn. O’Reilly Media, Inc., Sebastopol (2008)Google Scholar
  4. 4.
    Brown, M., Lowe, D.G.: Recognising panoramas. In: Proceedings of the Ninth IEEE International Conference on Computer Vision, October 16, vol. 2, pp. 1218–1225 (2003)Google Scholar
  5. 5.
  6. 6.
    Clouard, R., Elmoataz, A., Porquet, C., Revenu, M.: Borg: A knowledge-based system for automatic generation of image processing programs. IEEE Trans. Pattern Anal. Mach. Intell. 21, 128–144 (1999)CrossRefGoogle Scholar
  7. 7.
    Day, J.D., Zimmermann, H.: The OSI reference model. Proceedings of the IEEE 71, 1334–1340 (1983)CrossRefGoogle Scholar
  8. 8.
    Firschein, O., Strat, T.M.: Radius: Image Understanding For Imagery Intelligence. Morgan Kaufmann, San Francisco (1997)Google Scholar
  9. 9.
    Fitzgibbon, A.W.: Stochastic rigidity: Image registration for nowhere-static scenes. In: IEEE International Conference on Computer Vision, vol. 1, p. 662 (2001)Google Scholar
  10. 10.
  11. 11.
    Gupta, S., Gupta, E.N., Prince, J.L.: Stochastic formulations of optical flow algorithms under variable brightness conditions. In: Proceedings of IEEE International Conference on Image Processing, vol. III, pp. 484–487 (1995)Google Scholar
  12. 12.
    Horn, B.K., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17(1-3), 185–203 (1981)CrossRefGoogle Scholar
  13. 13.
    Kohl, C., Mundy, J.: The development of the image understanding environment. In: in Proceedings 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 443–447. IEEE Computer Society Press, Los Alamitos (1994)Google Scholar
  14. 14.
    Konstantinides, K., Rasure, J.R.: The khoros software development environment for image and signal processing. IEEE Transactions on Image Processing 3, 243–252 (1994)CrossRefGoogle Scholar
  15. 15.
    Matsuyama, T., Hwang, V.: Sigma: a framework for image understanding integration of bottom-up and top-down analyses. In: Proceedings of the 9th International Joint Conference on Artificial Intelligence, vol. 2, pp. 908–915. Morgan Kaufmann, San Francisco (1985)Google Scholar
  16. 16.
    Miller, G., Fels, S.: Uniform access to the cameraverse. In: International Conference on Distributed Smart Cameras. IEEE, Los Alamitos (2010)Google Scholar
  17. 17.
    Miller, G., Fels, S., Oldridge, S.: A conceptual structure for computer vision. In: Conference on Computer and Robot Vision (May 2011)Google Scholar
  18. 18.
    Miller, G., Oldridge, S., Fels, S.: Towards a computer vision shader language. In: Proceedings of International Conference on Computer Graphics and Interactive Techniques, Poster Session, SIGGRAPH 2011. ACM, New York (2011)Google Scholar
  19. 19.
    Mundy, J.: The image understanding environment program. IEEE Expert: Intelligent Systems and Their Applications 10(6), 64–73 (1995)CrossRefGoogle Scholar
  20. 20.
    Neider, J., Davis, T.: OpenGL Programming Guide: The Official Guide to Learning OpenGL, Release 1, 1st edn. Addison-Wesley Longman Publishing Co., Inc., Boston (1993)Google Scholar
  21. 21.
    Oldridge, S., Miller, G., Fels, S.: Mapping the problem space of image registration. In: Conference on Computer and Robot Vision (May 2011)Google Scholar
  22. 22.
    Panin, G.: Model-based Visual Tracking: the OpenTL Framework, 1st edn. John Wiley and Sons, Chichester (2011)CrossRefzbMATHGoogle Scholar
  23. 23.
    Peterson, J., Hudak, P., Reid, A., Hager, G.: Fvision: A declarative language for visual tracking (2001)Google Scholar
  24. 24.
    Pope, A.R., Lowe, D.G.: Vista: A software environment for computer vision research (1994)Google Scholar
  25. 25.
  26. 26.
  27. 27.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, p. 511 (2001)Google Scholar
  28. 28.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Gregor Miller
    • 1
  • Steve Oldridge
    • 1
  • Sidney Fels
    • 1
  1. 1.Human Communication Technologies LaboratoryUniversity of British ColumbiaVancouverCanada

Personalised recommendations