AfNet: The Affordance Network

  • Karthik Mahesh Varadarajan
  • Markus Vincze
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7724)

Abstract

There has been a growing need to build an object recognition system that can successfully characterize object constancy, irrespective of lighting, shading, occlusions, viewpoint variations and most importantly, deal with the multitude of shapes, colors and sizes in which objects are found. Affordances on the other hand, provide symbolic grounding mechanisms that enable linking features obtained from visual perception with the functionality of the objects, which provides the most consistent and holistic characterization of an object. Recognition by Component Affordances (RBCA) is a recent theory that builds affordance features for recognition. As an extension of the psychophysical theory of Recognition by Components (RBC) to generic visual perception, RBCA is well suited for cognitive visual processing systems which are required to perform implicit cognitive tasks. A common task is to substitute a cup for a mug, bottle, jug, pitcher, pilsner, beaker, chalice, goblet or any other unlabeled object, but with a physical part affording the ability to hold liquid and a part affording grasping by a human hand, given the goal of ’finding an empty cup’ and no cups are available in the work environment of interest. In this paper, we present affordance features for recognition of objects. Using a set of 25 structural and 10 material affordances we define a database of over 250 common household objects. This database called the Affordance Network or AfNet is available as community development framework and is well suited for deployment on domestic robots. Sample object recognition results using AfNet and the associated inference engine that grounds the affordances through visual perception features demonstrate the effectiveness of the approach.

Keywords

Object Recognition Range Image Inference Engine Symbol Grounding Object Recognition System 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Grabner, H., Gall, J., van Gool, L.: What Makes a Chair a Chair? In: CVPR, pp. 1529–1536 (2011)Google Scholar
  2. 2.
    Varadarajan, K.M., Vincze, M.: Holistic Visual Cognitive Recognizer using Part based Local, Global, Semantic and Affordance Features. In: CVPR W (2011)Google Scholar
  3. 3.
    Varadarajan, K.M., Vincze, M.: Affordance based Part Recognition for Grasping and Manipulation. In: ICRA W (2011)Google Scholar
  4. 4.
    Varadarajan, K.M., Vincze, M.: Object Part Segmentation and Classification in Range Images for Grasping. In: ICAR (2011)Google Scholar
  5. 5.
    Varadarajan, K.M., Vincze, M.: Knowledge Representation and Inference for Grasp Affordances. In: Crowley, J.L., Draper, B.A., Thonnat, M. (eds.) ICVS 2011. LNCS, vol. 6962, pp. 173–182. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  6. 6.
    Varadarajan, K.M.: Karmic Tabula Rasa k-TR - A Theory of Visual Perception. In: ISP (2011)Google Scholar
  7. 7.
    Gibson, J.J.: The Theory of Affordances. In: Shaw, R., Bransford, J. (eds.) (1977) ISBN 0-470-99014-7Google Scholar
  8. 8.
    Biederman I.: Recognition - by - components: a theory of human image understanding. Psych. Rev. (1994)Google Scholar
  9. 9.
    MacDorman, K.F.: Responding to affordances: Learning and projecting a sensorimotor mapping. In: ICRA (2000)Google Scholar
  10. 10.
    Fitzpatrick, P., et. al: Learning about objects through action. In: ICRA (2003)Google Scholar
  11. 11.
    Stoytchev, A.: Toward learning the binding affordances of objects. In: AAAI Symposium on Dev. Robotics (2005)Google Scholar
  12. 12.
    Sahin, E., et al.: To afford or not to afford. Adaptive Behavior 15(4), 447–472 (2007)CrossRefGoogle Scholar
  13. 13.
    Varadarajan, K.M., Vincze, M.: Real-Time Depth Diffusion for 3D Surface Reconstruction. In: ICIP (2010)Google Scholar
  14. 14.
    Varadarajan, K.M., Vincze, M.: Surface Reconstruction for RGB-D Data using Real-Time Depth Propagation. In: ICCV W (2011)Google Scholar
  15. 15.
    Varadarajan, K.M., Vincze, M.: 4D Space-Time Mereotopogeometry. In: PCC ICRA (2013)Google Scholar
  16. 16.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between class attribute transfer. In: CVPR (2009)Google Scholar
  17. 17.
    Parikh D., Grauman K.: Relative Attributes. In: ICCV (2011)Google Scholar
  18. 18.
    Gupta, A., Satkin, E., Efros, I., Hebert, M.: From 3D Scene Geometry to Human Workspace. In: CVPR (2011)Google Scholar
  19. 19.
    Winston, P.H., Binford, T.O., Katz, B., Lowry, M.: Learning physical description from functional definitions, examples, and precedents. MIT Press (1984)Google Scholar
  20. 20.
    Stark, L., Bowyer, K.: Achieving generalized object recognition through reasoning about association of function to structure. PAMI (1991)Google Scholar
  21. 21.
    Rivlin, E., Dickinson, S.J., Rosenfeld, A.: Recognition by functional parts. In: CVIU (1995)Google Scholar
  22. 22.
    Varadarajan, K.M., Vincze, M.: K-TR Theory of Semantic Saliency. In: ICPR (2012)Google Scholar
  23. 23.
    Varadarajan, K.M., Vincze, M.: AfkTRAANS: The language of Cognitive Robots. In: AAAI Robotics and Multimedia Satellite Event (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Karthik Mahesh Varadarajan
    • 1
  • Markus Vincze
    • 1
  1. 1.TU WienViennaAustria

Personalised recommendations