Skip to main content
Journal of the Brazilian Computer Society
Download PDF

NLOOK: a computational attention model for robot vision

Journal of the Brazilian Computer Society volume 15, pages 3–17 (2009)Cite this article

Abstract

The computational models of visual attention, originally proposed as cognitive models of human attention, nowadays are being used as front-ends to some robotic vision systems, like automatic object recognition and landmark detection. However, these kinds of applications have different requirements from those originally proposed. More specifically, a robotic vision system must be relatively insensitive to 2D similarity transforms of the image, as in-plane translations, rotations, reflections and scales, and it should also select fixation points in scale as well as position. In this paper a new visual attention model, called NLOOK, is proposed. This model is validated through several experiments, which show that it is less sensitive to 2D similarity transforms than other two well known and publicly available visual attention models: NVT and SAFE. Besides, NLOOK can select more accurate fixations than other attention models, and it can select the scales of fixations, too. Thus, the proposed model is a good tool to be used in robot vision systems.

References

  1. Ando S. Image field categorization and edge/corner detection from gradient covariance.IEEE Transactions on Pattern Analysis and Machine Intelligence 2000; 22(2):179–190.

    Article  Google Scholar 

  2. Burt PJ, Hong T and Adelson EH. The laplacian pyramid as a compact image code.IEEE Transactions on Communications 1983; 31(4):532–540.

    Article  Google Scholar 

  3. Connor CE, Egeth HE and Yantis S. Visual attention: bottom-up versus top-down.Current Biology 2004; 14(19):850–852.

    Article  Google Scholar 

  4. Crowley JL, Riff O and Piater J. Fast computation of characteristic scale using a half octave pyramid. In:Proceedings of International Workshop on Cognitive Vision; 2002; Zurich, Switzerland. Berlin, Germany: Springer-Verlag; 2002. p. 1–8.

    Google Scholar 

  5. Daugman JG. Complete discrete 2-d gabor transforms by neural networs for image analysis and compression.Proceedings of IEEE Transactions on Acoustics, Speech, and Signal 1988; 36(7):1169–1179.

    Article  MATH  Google Scholar 

  6. Desimone R and Duncan J. Neural mechanisms of selective visual attention.Annual Reviews Neuroscience 1995; 18(1):193–222.

    Article  Google Scholar 

  7. Draper BA, Baek K and Boody J. Implementing the expert object recognition pathway. In:Proceedings of International Conference on Computer Vision Systems; 2003; Graz, Austria. Berlin, Germany: Springer-Verlag; 2003. p. 1–11.

    Google Scholar 

  8. Draper BA and Lionelle A. Evaluation of selective attention under similarity transformations.Computer Vision and Image Understanding 2002; 100(1):152–171.

    Article  Google Scholar 

  9. Engel PM.INBC: an incremental algorithm for dataflow segmantation based on a probabilistic approach. Porto Alegre: Universidadade Federal do Rio Grande do Sul; 2009. (Technical Report RP-3690)

    Google Scholar 

  10. Engel S, Zhang X and Wandell B. Colour tuning in human visual cortex measured with functional magnetic resonance imaging.Nature 1997; 388(6637):68–71.

    Article  Google Scholar 

  11. Frintrop S. VOCUS: a visual attention system for object detection and goal-directed search. [PhD thesis]. Bonn:Universität Bonn; 2006.

    Book  Google Scholar 

  12. Greenspan S, Belongie S, Goodman R, Perona P, Rakshit S and Anderson CH. Overcomplete steerable pyramid filters and rotation invariance. In:Proceedings of IEEE Computer Vision and Pattern Recognition; 1994; Seattle, WA. Los Alamitos, CA: IEEE Press; 1994. p. 222–228.

    Chapter  Google Scholar 

  13. Harel J and Koch C. On the optimality of spatial attention for object detection. In:Proceedings of 5 International Workshop on Attention in Cognitive Systems; 2009; Santorini, Grécia. Berlin, Germany: Springer-Verlag; 2009. p. 1–14. (v. 5395).

    Chapter  Google Scholar 

  14. Heinen MR and Engel PM. Visual selective attention model for robot vision. In:Proceedings of 5 IEEE Latin American Robotics Symposium; 2008; Salvador, Brazil. Los Alamitos, CA: IEEE Press; 2008. p. 1–6.

    Google Scholar 

  15. Heinen MR and Engel PM. Evaluation of visual attention models under 2d similarity transformations. In:Proceedings of 24 ACM Symposium on Applied Computing; 2009; Honolulu, Hawaii. New York, NY: ACM press; 2009. (Special Track on Intelligent Robotic Systems).

    Google Scholar 

  16. Indiveri G, Mürer R and Kramer J. Active vision using an analog VLSI model of selective attention.IEEE Transactions on Circuits and Systems 2001; 48(5):492–500. (parte II, Analog and digital signal processing).

    Article  Google Scholar 

  17. Itti L. Models of bottom-up attention and saliency. San Diego: Elsevier Press; 2005. p. 576–582.

    Google Scholar 

  18. Itti L and Koch C. Computational modeling of visual attention.Nature Reviews. 2001; 2(3):194–203.

    Article  Google Scholar 

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

    Article  Google Scholar 

  20. Kentridge R, Heywood C and Davidoff J. Color perception. In: Arbib MA. (Ed.).The handbook of brain theory and neural networks. 2 ed. Cambridge: MIT Press; 2003. p. 230–233.

    Google Scholar 

  21. Klein RM. Inhibition of return.Trends in Cognitive Sciences. 2000; 4(4):138–147.

    Article  Google Scholar 

  22. Koch C and Ullman S. Shifts in selective visual attention: toward the underlying neural circuitry.Human Neurobiology 1985; 4(4):219–227.

    Google Scholar 

  23. Lee KW, Buxton H and Jianfeng F. Cue-guided search: a computational model of selective attention.IEEE Trans. Neural Networks 2005; 16(4):910–924.

    Article  Google Scholar 

  24. Leventhal AG.The neural basis of visual function. Boca Raton: CRC Press; 1991. (v. 4, Vision and visual dysfunction).

    Google Scholar 

  25. Lindeberg T. Feature detection with automatic scale selection.International Journal of Computer Vision 1998; 30(2):79–116.

    Article  Google Scholar 

  26. Liu YH and Wang XJ. Spike-frequency adaptation of a generalized leaky integrate-and-fire model neuron.Journal of Computational Neuroscience 2001; 10(1):25–45.

    Article  Google Scholar 

  27. Lowe DG. Distinctive image features from scale-invariant keypoints.International Journal of Computer Vision 2004; 60(2):91–110.

    Article  Google Scholar 

  28. Marfil R, Bandera A, Rodríguez JA and Sandoval F. A novel hierarchical framework for object-based visual attention. In:Proceedings of 5 International Workshop on Attention in Cognitive Systems; 2009; Santorini, Grécia. Berlin, Germany: Springer-Verlag; 2009. p. 27–40. (v. 5393).

    Chapter  Google Scholar 

  29. Marques O, Mayron L, Borba G and Gamba H. An attentiondriven model for similar images with image retrieval applications.EURASIP Journal on Advances in Signal Processing 2007; (1):1–17.

    Article  Google Scholar 

  30. Mozer MC and Sitton M. Computational modeling of spatial attention. In: Pashler H. (Ed.).Attention. London: Psychology Press, London; 1998. p. 341–395.

    Google Scholar 

  31. Nagai Y. From bottom-up visual attention to robot action learning. In:Proceedings of 8 IEEE International Conference on Development and Learning; 2009; Shanghai, China. Los Alamitos, CA: IEEE Press.

    Google Scholar 

  32. Niebur E and Koch C. Control of selective visual attention: modeling the “where” pathway.Neural Information Processing System 1996; 8(1):802–808.

    Google Scholar 

  33. Orabona F, Metta G, and Sandini G. Object-based visual attention: a model for a behaving robot. In:Proceedings of 3 Attention and Performance in Computational Vision; 2005; San Diego, CA. Los Alamitos, CA: IEEE Press; 2005.

    Google Scholar 

  34. Ouerhani N, Bur A and Hügli H. Visual attention-based robot self-localization. In:Proceedings of European Conference on Mobile Robots; 2005; Ancona, Italy. Los Alamitos, CA: IEEE Press; 2005. p. 8–13.

    Google Scholar 

  35. Pashler, H.The Psycology of Attention. Cambridge: MIT Press; 1997.

    Google Scholar 

  36. Perko R, Wojek C, Schiele B and Leonardis A. Integrating visual context and object detection within a probabilistic framework. In:Proceedings of 5 International Workshop on Attention in Cognitive Systems; 2009; Santorini, Grécia. Berlin, Germany: Springer-Verlag; 2009. p. 54–68. (v. 5395).

    Chapter  Google Scholar 

  37. Treisman AM. Features and objects: the fourteenth bartlett memorial lecture.The Quarterly Journal of Experimental Psychology 1988; 40(2):201–237.

    Google Scholar 

  38. Treisman AM and Gelade G. A feature integration theory of attention.Cognitive Psychology 1980; 12(1):97–136.

    Article  Google Scholar 

  39. Tsotsos JK, Culhane SM, Wai WYK, Lai Y, Davis N, and Nuflo F. Modeling visual attention via selective tuning.Artificial Intelligence 1995; 78(1/2):507–545.

    Article  Google Scholar 

  40. Vieira-Neto H.Visual novelty detection for autonomous inspection robots. [PhD thesis]. Essex: University of Essex; 2006.

    Google Scholar 

  41. Vieira-Neto H and Nehmzow U. Visual novelty detection with automatic scale selection.Robotics and Autonomous Systems 2007; 55(9):693–701.

    Article  Google Scholar 

  42. Wang T, Zheng N and Mei K. A visual brain chip based on selective attention for robot vision application. In:Proceedings of IEEE International Conference on Space Mission Challenges for Information Technology; 2009. Los Alamitos, CA: IEEE Press; 2009. p. 93–97.

    Chapter  Google Scholar 

  43. Witkin AP. Scale-space filtering. In:Proceedings of International Joint Conference on Artificial Intelligence; 1983; Karlsruhe, Germany. San Fransisco, CA: Morgan Kaufman; 1983. p. 1019–1022.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Informatics Institute, Federal University of Rio Grande do Sul, Av. Bento Gonçalves 9500, Agronomia, P.O. Box 15064, 91501-970, Porto Alegre, RS, Brazil

    Milton Roberto Heinen & Paulo Martins Engel

Authors
  1. Milton Roberto Heinen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Paulo Martins Engel
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License ( https://creativecommons.org/licenses/by/2.0 ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and Permissions

About this article

Cite this article

Heinen, M.R., Engel, P.M. NLOOK: a computational attention model for robot vision. J Braz Comp Soc 15, 3–17 (2009). https://doi.org/10.1007/BF03194502

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03194502

Keywords

  • robot vision
  • visual attention
  • selective attention
  • focus of attention
  • biomimetic vision