Skip to main content
Springer Nature Link
Log in

Saliency-Guided Object Candidates Based on Gestalt Principles

  • Conference paper
  • First Online:
Computer Vision Systems (ICVS 2015)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 9163))

Included in the following conference series:

Abstract

We present a new method for generating general object candidates for cluttered RGB-D scenes. Starting from an over-segmentation of the image, we build a graph representation and define an object candidate as a subgraph that has maximal internal similarity as well as minimal external similarity. These candidates are created by successively adding segments to a seed segment in a saliency-guided way. Finally, the resulting object candidates are ranked based on Gestalt principles. We show that the proposed algorithm clearly outperforms three other recent methods for object discovery on the challenging Kitchen dataset.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Code: http://www.iai.uni-bonn.de/~frintrop/vocus2.html.

References

  1. Achanta, R., Hemami, S., Estrada, F., Süsstrunk, S.: Frequency-tuned salient region detection. In: Proceedings of the CVPR (2009)

    Google Scholar 

  2. Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. Trans. on PAMI 34(11), 2198–2202 (2012)

    Article  Google Scholar 

  3. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. of Comput. Vis. 88(2), 303–338 (2010)

    Article  Google Scholar 

  4. Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int J. of Comput. Vis. 59(2), 167–181 (2004)

    Article  Google Scholar 

  5. Frintrop, S., Martín García, G., Cremers, A.B.: A cognitive approach for object discovery. In: Proceedings of ICPR (2014)

    Google Scholar 

  6. Frintrop, S.: 6 sensor fusion. In: Frintrop, S. (ed.) VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search. LNCS (LNAI), vol. 3899, pp. 129–147. Springer, Heidelberg (2006)

    Chapter  Google Scholar 

  7. Frintrop, S., Werner, T., Martín García, G.: Traditional saliency reloaded: a good old model in new shape. In: Proceedings of CVPR (2015)

    Google Scholar 

  8. Horbert, E., Martín García, G., Frintrop, S., Leibe, B.: Sequence level object candidates based on saliency for generic object recognition on mobile systems. In: Proceedings of ICRA (2015). Dataset: http://www.mmp.rwth-aachen.de/projects/kod/

  9. Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. Trans. on PAMI 20(11), 1254–1259 (1998)

    Article  Google Scholar 

  10. Kanizsa, G., Gerbino, W.: Convexity and Symmetry in Figure-Ground Organization. Vision and artifact, New York (1976)

    Google Scholar 

  11. Karpathy, A., Miller, S.: Object discovery in 3D scenes via shape analysis. In: Proceedings of ICRA (2013)

    Google Scholar 

  12. Klein, D.A., Frintrop, S.: Salient pattern detection using \(W_2\) on multivariate normal distributions. In: Proceedings of DAGM-OAGM (2012)

    Google Scholar 

  13. Kootstra, G., Kragic, D.: Fast and bottom-up object detection, segmentation, and evaluation using Gestalt principles. In: Proceedings of ICRA (2011)

    Google Scholar 

  14. Manén, S., Guillaumin, M.: Prime object proposals with randomized prim’s algorithm. In: Proceedings of ICCV (2013)

    Google Scholar 

  15. Pashler, H.: The Psychology of Attention. MIT Press, Cambridge (1997)

    Google Scholar 

  16. Richtsfeld, A., Zillich, M., Vincze, M.: Implementation of Gestalt principles for object segmentation. In: Proceedings of ICPR (2012)

    Google Scholar 

  17. Wagemans, J., Elder, J.H., Kubovy, M., Palmer, S.E., Peterson, M., Singh, M., von der Heydt, R.: A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure-ground organization. Psychol. Bull. 138(6), 1172–1217 (2012)

    Article  Google Scholar 

  18. Werner, T.: Saliency-driven object dicovery based on gestalt principles. Master thesis, Rheinische Friedrich-Wilhelms-Universität Bonn (2015)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Fraunhofer Institut Für Intelligent Analyse- und Informationssysteme Schloss Birlinghofen, 53757, Sankt Augustin, Germany

    Thomas Werner

  2. Computer Science Department III, Rheinische Friedrich-Wilhelms Universität, Römerstr. 164, 53117, Bonn, Germany

    Thomas Werner, Germán Martín-García & Simone Frintrop

Authors
  1. Thomas Werner
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Germán Martín-García
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Simone Frintrop
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Thomas Werner .

Editor information

Editors and Affiliations

  1. Aalborg University, Copenhagen, Denmark

    Lazaros Nalpantidis

  2. Aalborg University, Copenhagen, Denmark

    Volker Krüger

  3. Royal Institute of Technology - KTH, Stockholm, Sweden

    Jan-Olof Eklundh

  4. Democritus University of Thrace, Xanthi, Greece

    Antonios Gasteratos

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Werner, T., Martín-García, G., Frintrop, S. (2015). Saliency-Guided Object Candidates Based on Gestalt Principles. In: Nalpantidis, L., Krüger, V., Eklundh, JO., Gasteratos, A. (eds) Computer Vision Systems. ICVS 2015. Lecture Notes in Computer Science(), vol 9163. Springer, Cham. https://doi.org/10.1007/978-3-319-20904-3_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-20904-3_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-20903-6

  • Online ISBN: 978-3-319-20904-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics