Skip to main content
SpringerLink
Log in

Learning What Matters: Combining Probabilistic Models of 2D and 3D Saliency Cues

  • Conference paper
Computer Vision Systems (ICVS 2011)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 6962))

Included in the following conference series:

Abstract

In this paper we address the problem of obtaining meaningful saliency measures that tie in coherently with other methods and modalities within larger robotic systems. We learn probabilistic models of various saliency cues from labeled training data and fuse these into probability maps, which while appearing to be qualitatively similar to traditional saliency maps, represent actual probabilities of detecting salient features. We show that these maps are better suited to pick up task-relevant structures in robotic applications. Moreover, having true probabilities rather than arbitrarily scaled saliency measures allows for deeper, semantically meaningful integration with other parts of the overall system.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 54.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 69.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Achanta, R., Estrada, F., Wils, P., Süsstrunk, S.: Salient region detection and segmentation. In: 6th Int. Conf. on Computer Vision Systems, pp. 66–75 (2008)

    Google Scholar 

  2. Akman, O., Jonker, P.: Computing saliency map from spatial information in point cloud data. In: Advanced Concepts for Intelligent Vision Systems, pp. 290–299 (2010)

    Google Scholar 

  3. Boykov, Y.Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in n-d images. In: 8th IEEE Int. Conf. on Computer Vision, pp. 105–112 (2001)

    Google Scholar 

  4. Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 24(5), 603–619 (2002)

    Article  Google Scholar 

  5. Enns, J.T., Rensink, R.A.: Influence of scene-based properties on visual search. Science 247(4943), 721–723 (1990)

    Article  Google Scholar 

  6. Enns, J.T., Rensink, R.A.: Sensitivity to three-dimensional orientation in visual search. Psychological Science 1(5), 323–326 (1990)

    Article  Google Scholar 

  7. Fischler, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. of the ACM 24, 381–395 (1981)

    Article  MathSciNet  Google Scholar 

  8. Frintrop, S., Backer, G., Rome, E.: Goal-directed search with a top-down modulated computational attention system. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds.) DAGM 2005. LNCS, vol. 3663, pp. 117–124. Springer, Heidelberg (2005)

    Chapter  Google Scholar 

  9. Frintrop, S., Rome, E., Nüchter, A., Surmann, H.: A bimodal laser-based attention system. Computer Vision and Image Understanding 100, 124–151 (2005)

    Article  MATH  Google Scholar 

  10. Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. Advances in Neural Information Processing Systems 19, 545–552 (2007)

    Google Scholar 

  11. Hou, X., Zhang, L.: Saliency detection: A spectral residual approach. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1–8 (2007)

    Google Scholar 

  12. Itti, L., Koch, C.: Computational modelling of visual attention. Nature Reviews Neuroscience 2(3), 194–203 (2001)

    Article  Google Scholar 

  13. Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 20(11), 1254–1259 (1998)

    Article  Google Scholar 

  14. Ko, B.C., Nam, J.Y.: Object-of-interest image segmentation based on human attention and semantic region clustering. J. Opt. Soc. Am. A 23(10), 2462–2470 (2006)

    Article  Google Scholar 

  15. Lee, D.K., Itti, L., Koch, C., Braun, J.: Attention activates winner-take-all competition among visual filters. Nature Neuroscience 2(4), 375–381 (1999)

    Article  Google Scholar 

  16. Maki, A., Nordlund, P., Eklundh, J.O.: A computational model of depth-based attention. In: 13th Int. Conf. on Pattern Recognition, pp. 734–739 (1996)

    Google Scholar 

  17. Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. Int. Journal of Computer Vision 43(1), 7–27 (2001)

    Article  MATH  Google Scholar 

  18. Mishra, A., Aloimonos, Y., Fah, C.L.: Active Segmentation with Fixation. In: Twelfth IEEE Int. Conf. on Computer Vision (2009)

    Google Scholar 

  19. Nakayama, K., Silverman, G.H.: Serial and parallel processing of visual feature conjunctions. Nature 320, 264–265 (1986)

    Article  Google Scholar 

  20. Navalpakkam, V., Itti, L.: An integrated model of top-down and bottom-up attention for optimizing detection speed. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2049–2056 (2006)

    Google Scholar 

  21. Ouerhani, N., Huegli, H.: Computing visual attention from scene depth. In: 15th Int. Conf. on Pattern Recognition, pp. 375–378 (2000)

    Google Scholar 

  22. Ouerhani, N., Archip, N., Hügli, H., Erard, P.J.: Visual attention guided seed selection for color image segmentation. In: 9th Int. Conf. on Computer Analysis of Images and Patterns, pp. 630–637 (2001)

    Google Scholar 

  23. Tsotsos, J.K., Shubina, K.: Attention and Visual Search: Active Robotic Vision Systems that Search. In: 5th Int. Conf. on Computer Vision Systems (2007)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Automation and Control Institute, Vienna University of Technology, Austria

    Ekaterina Potapova, Michael Zillich & Markus Vincze

Authors
  1. Ekaterina Potapova
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michael Zillich
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Markus Vincze
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. INRIA Grenoble Rhône-Alpes Research Centre, 655 Avenue de l’Europe, 38330, Montbonnot, France

    James L. Crowley

  2. Department of Computer Science, Colorado State University, 80523, Fort Collins, CO, USA

    Bruce A. Draper

  3. INRIA Sophia Antipolis,, 2004 route des Lucioles, BP 93, 06902, Sophia Antipolis, France

    Monique Thonnat

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Potapova, E., Zillich, M., Vincze, M. (2011). Learning What Matters: Combining Probabilistic Models of 2D and 3D Saliency Cues. In: Crowley, J.L., Draper, B.A., Thonnat, M. (eds) Computer Vision Systems. ICVS 2011. Lecture Notes in Computer Science, vol 6962. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23968-7_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-23968-7_14

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-23967-0

  • Online ISBN: 978-3-642-23968-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation