Advertisement

Semantic Interpretation of Novelty in Images Using Histograms of Oriented Gradients

  • Nicolas Alt
  • Werner Maier
  • Qing Rao
  • Eckehard Steinbach
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7508)

Abstract

An approach for the semantic interpretation of image-based novelty in real-world environments is presented. We measure novelty using the concept of pixel-based surprise, which quantifies how much a new observation changes the robot’s current probabilistic appearance model of the environment. The corresponding surprise maps are utilized as prior information to reduce the search space of a “Histograms of Oriented Gradients” object detector. Specifically, detection windows are scored and selected using surprise values. Several object classes are simultaneously searched for and learned from a low number of manually taken reference images. Experiments are performed on a human-size robot in a cluttered household environment. Compared to object detection based on a search of the complete image, a 35-fold speed-up is observed. Additionally, the detection performance increases significantly.

Keywords

object class detection novelty detection visual attention 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR, San Diego, CA, USA (June 2005)Google Scholar
  2. 2.
    Watanabe, T., Ito, S., Yokoi, K.: Co-occurrence Histograms of Oriented Gradients for Pedestrian Detection. In: Wada, T., Huang, F., Lin, S. (eds.) PSIVT 2009. LNCS, vol. 5414, pp. 37–47. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  3. 3.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. CVPR, Kauai, Hawaii, USA (December 2001)Google Scholar
  4. 4.
    Maier, W., Mair, E., Burschka, D., Steinbach, E.: Visual homing and surprise detection for cognitive mobile robots using image-based environment representations. In: Proc. ICRA, Kobe, Japan (May 2009)Google Scholar
  5. 5.
    Maier, W., Steinbach, E.: A probabilistic appearance representation and its application to surprise detection in cognitive robots. IEEE Trans. on Autonomous Mental Development 2(4), 267–281 (2010)CrossRefGoogle Scholar
  6. 6.
    Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  7. 7.
    Wang, H., Ullah, M.M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: BMVC, London, United Kingdom (September 2009)Google Scholar
  8. 8.
    Chen, Y., Lin, C.: Combining SVMs with Various Feature Selection Strategies. In: Feature Extraction. STUDFUZZ, vol. 207, pp. 315–324. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Itti, L., Baldi, P.: Bayesian surprise attracts human attention. Vision Research 49(10), 1295–1306 (2009)CrossRefGoogle Scholar
  10. 10.
    Ranganathan, A., Dellaert, F.: Bayesian surprise and landmark detection. In: Proc. ICRA, Kobe, Japan (May 2009)Google Scholar
  11. 11.
    Maier, W., Eschey, M., Steinbach, E.: Image-based object detection under varying illumination in environments with specular surfaces. In: Proc. ICIP, Brussels, Belguim (September 2011)Google Scholar
  12. 12.
    Chang, C., Lin, C.: LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2(3) (2011)Google Scholar
  13. 13.
    Shum, H., Chan, S., Kang, S.: Image-Based Rendering. Springer, New York (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Nicolas Alt
    • 1
  • Werner Maier
    • 1
  • Qing Rao
    • 1
  • Eckehard Steinbach
    • 1
  1. 1.Institute for Media TechnologyTechnische Universität MünchenMünchenGermany

Personalised recommendations