Exploiting Context in Function-Based Reasoning

  • Melanie A. Sutton
  • Louise Stark
  • Ken Hughes
Conference paper
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2238)

Abstract

This paper presents the framework of the new context-based reasoning components of the GRUFF (Generic Recognition Using Form and Function) system. This is a generic object recognition system which reasons about and generates plans for understanding 3-D scenes of objects. A range image is generated from a stereo image pair and is provided as input to a multi-stage recognition system. A 3-D model of the scene, extracted from the range image, is processed to identify evidence of potential functionality directed by contextual cues. This recognition process considers the shape-suggested functionality by applying concepts of physics and causation to label an object’s potential functionality. The methodology for context-based reasoning relies on determining the significance of the accumulated functional evidence derived from the scene. For example, functional evidence for a chair or multiple chairs along with a table, in set configurations, is used to infer the existence of scene concepts such as “office” or “meeting room space.” Results of this work are presented for scene understanding derived from both simulated and real sensors positioned in typical office and meeting room environments.

This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 4.
    Binford, T. O.: Survey of model-based image analysis systems, Int. J. of Robotics Research, 1, (1982) 18–64CrossRefGoogle Scholar
  2. 5.
    Bogoni, L. and Bajcsy, R.: Interactive Recognition and Representation of Functionality, Computer Vision and Image Understanding, special issue on Functionality in Object Recognition, Vol. 62, No. 2, (1995) 194–214MATHCrossRefGoogle Scholar
  3. 6.
    Connell, J. H.: Get Me That Screwdriver! Developing a Sensory-action Vocabulary for Fetch-and-Carry Tasks, IBM Cyber Journal Research Report, RC 19473 (April 1994)Google Scholar
  4. 7.
    Cooper, P., Birnbaum, L., and Brand, E.: Causal Scene Understanding, Computer Vision and Image Understanding, special issue on Functionality in Object Recognition, Vol. 62, No. 2, (1995) 215–231MATHCrossRefGoogle Scholar
  5. 8.
    Di Manzo, M., Trucco, E., Giunchiglia, F., Ricci, F.: FUR: Understanding FUnctional Reasoning, Int. J. of Intelligent Systems, 4, (1989) 431–457CrossRefGoogle Scholar
  6. 9.
    Doermann, D., Rivlin, E. and Rosenfeld, A.: The Function of Documents, Int. J. on Computer Vision, 16, (1998) 799–814CrossRefGoogle Scholar
  7. 10.
    Duric, Z., Fayman, J. A., and Rivlin, E.: Function from Motion, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 6, (1996) 579–591CrossRefGoogle Scholar
  8. 11.
    Fischler, M. A. and Strat, T. M.: Recognizing objects in a natural environment: a contextual vision system (CVS), Proceedings: Image Understanding Workshop, (May 1989) 774–788Google Scholar
  9. 12.
    Green, K., Eggert, D., Stark, L. and Bowyer, K.: Generic Recognition of Articulated Objects through Reasoning about Potential Function, Computer Vision and Image Understanding, special issue on Functionality in Object Recognition, Vol. 62, No. 2, (1995) 177–193MATHCrossRefGoogle Scholar
  10. 13.
    Hodges, J.: Functional and Physical Object Characteristics and Object Recognition in Improvisation, Computer Vision and Image Understanding, special issue on Functionality in Object Recognition, Vol. 62, No. 2, (1995) 147–163MATHCrossRefMathSciNetGoogle Scholar
  11. 14.
    Hoogs, A. and Hackett, D.: Model-Supported Exploitation as a Framework for Image Understanding, Proceedings of the ARPA IU Workshop, (November 1994) 265–268Google Scholar
  12. 15.
    Hoover, A., Goldgof, D. and Bowyer, K. W.: Building a B-rep from a segmented range image, IEEE Second CAD-Based Vision Workshop, Champion, Pennsylvania (February 1994), 74–81Google Scholar
  13. 16.
    Jensen, F., Christensen, H. and Nielsen, J.: Bayesian Methods for Interpretation and Control in Multi-agent Vision Systems, in Proceedings of SPIE Conference on Application of AI X: Machine Vision and Robotics, Kevin W. Bowyer, editor, Vol. 1708, (1992) 536–548Google Scholar
  14. 17.
    Kim, D. and Nevatia, R.: A Method for Recognition and Localization of Generic Objects for Indoor Navigation, IEEE Workshop on Applications of Computer Vision, (1994), 280–288Google Scholar
  15. 18.
    Kise, K., Hattori, H., Kitahashi, T., and Fukunaga, K.: Representing and Recognizing Simple Hand-tools Based on Their Functions, Asian Conference on Computer Vision, Osaka, Japan (November, 1993), 656–659Google Scholar
  16. 19.
    Konolige, K., Beymer, D.: SRI small vision system user’s manual (software version 1.4). Stanford Research Institute. (December 1999)Google Scholar
  17. 20.
    Hanson, A. and Riseman, E.: The VISIONS Image-Understanding System Advances in Computer Vision (2 vols), Erlbaum, Vol. 1, (1988), 1–114Google Scholar
  18. 21.
    Stark, L., Hoover, A. W., Goldgof, D. B. and Bowyer, K. W.: Function-based object recognition from incomplete knowledge of object shape, IEEE Workshop on Qualitative Vision, New York (June 1993), 11–22Google Scholar
  19. 22.
    Minsky, M.: The Society of Mind, Simon and Shuster, New York, (1985)Google Scholar
  20. 23.
    Rivlin, E., Dickinson, S. and Rosenfeld, A.: Recognition by Functional Parts, Computer Vision and Image Understanding, special issue on Functionality in Object Recognition, Vol. 62, No. 2, (1995) 164–176MATHCrossRefGoogle Scholar
  21. 24.
    Rivlin, E. and Rosenfeld, A.: Navigational Functionalities, Computer Vision and Image Understanding, special issue on Functionality in Object Recognition, Vol. 62, No. 2, (1995) 232–244MATHCrossRefGoogle Scholar
  22. 25.
    Rivlin, E., Rosenfeld, A. and Perlis, D.: Recognition of Object Functionality in Goal-Directed Robotics, in Working Notes on Reasoning About Function, (1993) 126–130Google Scholar
  23. 26.
    Stark, L. and Bowyer, K.: Generic Object Recognition using Form and Function, Series in Machine Perception Artificial Intelligence, Vol. 10, World Scientific, New York, (1996)Google Scholar
  24. 27.
    Stark, L., and Bowyer, K. W.: Achieving generalized object recognition through reasoning about association of function to structure, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 3, No. 10, (1991) 1097–1104CrossRefGoogle Scholar
  25. 28.
    Stark, L., and Bowyer, K. W.: Indexing function-based categories for generic object recognition, Computer Vision and Pattern Recognition (CVPR’ 92), Champaign, Illinois (June 1992) 795–797Google Scholar
  26. 29.
    Stark, L. and Bowyer, K.: Function-based generic recognition for multiple object categories, CVGIP: Image Understanding, 59 (1), (January 1994) 1–21CrossRefGoogle Scholar
  27. 30.
    Stark, L., Hall, L. O. and Bowyer, K. W.: An investigation of methods of combining functional evidence for 3-D object recognition, International Journal of Pattern Recognition and Artificial Intelligence 7 (3), (June 1993) 573–594CrossRefGoogle Scholar
  28. 31.
    Stark, L., and Bowyer, K. W.: Functional Context in Vision, Proceedings of the Workshop on Context-Based Vision, Cambridge, Massachusetts, (1995) 63–74Google Scholar
  29. 32.
    Strat, T. M. and Fischler, M. A.: The Role of Context in Computer Vision, Proceedings of the Workshop on Context-Based Vision, Cambridge, Massachusetts, (1995) 2–12Google Scholar
  30. 33.
    Sutton, M., Stark, L., Bowyer, K. W.: Function from visual analysis and physical interaction: A methodology for recognition of generic classes of objects. Image and Vision Computing. 16 (11) (August 1998) 745–763CrossRefGoogle Scholar
  31. 34.
    Stansfield, R. A.: Robotic grasping of unknown objects: A knowledge-based approach, Int. Journal of Robotics Research, 10, (1991) 314–326CrossRefGoogle Scholar
  32. 35.
    Sutton, M., Stark, L. and Bowyer, K. W.: Function-based generic recognition for multiple object categories, in Three-dimensional Object Recognition Systems, A. K. Jain and P. J. Flynn, editors, Elsevier Science Publishers, (1993) 447–470Google Scholar
  33. 37.
    Weisbin, C. R., et al.: Autonomous mobile robot navigation and learning, IEEE Computer, Vol. 22, (1989) 29–35Google Scholar
  34. 38.
    Winston, P., Binford, T., Katz, B., and Lowry, M.: Learning Physical Description from Functional Deffinitions, Examples, and Precedents, AAAI’ 83 (1983) 433–439Google Scholar
  35. 39.
    Winston, P. and Rao, S.: Repairing learned knowledge using experience, in AI at MIT: Expanding Frontiers, P. H. Winston and S. A. Shellard, editors, MIT Press (1990) 363–379Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Melanie A. Sutton
    • 1
  • Louise Stark
    • 2
  • Ken Hughes
    • 2
  1. 1.University of West FloridaPensacolaUSA
  2. 2.University of the PacificStocktonUSA

Personalised recommendations