Advertisement

International Journal of Computer Vision

, Volume 69, Issue 2, pp 251–261 | Cite as

A Critical View of Context

  • Lior WolfEmail author
  • Stanley Bileschi
Short Paper

Abstract

In this study, a discriminative detector for object context is designed and tested. The context-feature is simple to implement, feed-forward, and effective across multiple object types in a street-scenes environment.

Using context alone, we demonstrate robust detection of locations likely to contain bicycles, cars, and pedestrians. Furthermore, experiments are conducted so as to address several open questions regarding visual context. Specifically, it is demonstrated that context may be determined from low level visual features (simple color and texture descriptors) sampled over a wide receptive field. At least for the framework tested, high level semantic knowledge, e.g, the nature of the surrounding objects, is superfluous. Finally, it is shown that when the target object is unambiguously visible, context is only marginally useful.

Keywords

context learning streetscenes object detection scene understanding 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bar, M., Aminoff, E., Boshyan, J., Fenske, M., Gronauo, N., and Kassam, K. 2005. The contribution of context to visual object recognition. Journal of Vision, 5(8):88a.CrossRefGoogle Scholar
  2. Biederman, I., Mezzanotte, R.J., and Rabinowitz, J.C. 1982. Scene perception: Detecting and judging objects undergoing relational violations. Cognitive Psychology, l4.Google Scholar
  3. Belongie, S., Malik, J., and Puzicha J. 2002. Shape Matching and Object Recognition Using Shape Contexts. PAMI.Google Scholar
  4. Bergboer, N.H., Postma, E.O., and van den Herik, H.J. 2003. Context-enhanced object detection in natural images. In Proc. of the Belgian-Netherlands AI Conference (BNAIC).Google Scholar
  5. Bileschi, S.M. and Heisele, B. 2003. Advances in Component Based Face Detection. In Int. Workshop on Analysis and Modeling of Faces and Gestures.Google Scholar
  6. Carbonetto, P., Freitas, N., and Barnard, K. 2004. A Statistical Model for General Contextural Object Recognition. ECCV.Google Scholar
  7. Carson, C., Belongie, S., Greenspan, H., and Malik, J. 1998. Color- and Texture-Based Image Segmentation Using EM and Its Application to Content-Based Image Retrieval, ICCV.Google Scholar
  8. Cox, D., Meyers, E., and Sinha, P. 2004. Contextually Evoked Object-Specific Responses in Human Visual Cortex. Science, 304:115–117.CrossRefGoogle Scholar
  9. Fink, M. and Perona, P. 2003. Mutual Boosting for Contextual Inference. NIPS, 17.Google Scholar
  10. Hanson, A.R. and Riseman, E.M. 1978. Visions: A Computer System for Interpreting Scenes. In Computer Vision Systems, Academic Press.Google Scholar
  11. Haralick, R.M. 1983. Decision making in context, PAMI.Google Scholar
  12. Kruppa, H. and Schiele, B. 2003. Using Context To Improve Face Detection. British machine Vision Conference (BMCV).Google Scholar
  13. Kumar, S. and Hebert, M. 2003. Discriminative random fields: A Discriminative Framework for Contextual Interaction in Classification, ICCV.Google Scholar
  14. LeCun, Y. and Jie Huang, F. 2004. Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting. CVPRGoogle Scholar
  15. Murphy, K., Torralba, A., and Freeman, W. 2003. Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes. NIPS, 16.Google Scholar
  16. Schneiderman, H. 2004. Learning a restricted Bayesian network for object detection. CVPR.Google Scholar
  17. Singhal, A., Luo, J., and Zhu, W. 2003. Probabilistic Spatial Context Models for Scene Content Understanding. CVPR.Google Scholar
  18. Strat, T.M. and Fischler, M.A. 1991. Context-based vision: Recognizing Objects Using Information from Both 2D and 3D imagery. PAMI, 13:1050–1065.Google Scholar
  19. Torralba, A., Murphy, K., and Freeman, W. Contextual models for object-detection using boosted random fields. NIPS’04.Google Scholar
  20. Torralba, A., Murphy, K.P., and Freeman, W.T. 2004. Contextual Models for Object Detection using Boosted Random Fields. NIPS.Google Scholar
  21. Torralba, A. and Sinha, P. 2001. Statistical Context Priming for Object Detection. ICCV, pp. 763–770.Google Scholar
  22. Vapnik, V. 1999. The Nature of Statistical Learning Theory. Springer-Verlag.Google Scholar
  23. Viola, P. and Jones, P. 2001. Rapid object detection using a boosted cascade of simple features. CVPR.Google Scholar

Copyright information

© Springer Science + Business Media, LLC 2006

Authors and Affiliations

  1. 1.The Center for Biological and Computational LearningMassachusetts Institute of TechnologyCambridge

Personalised recommendations