ENTROPY-BASED SALIENCY COMPUTATION IN LOG-POLAR IMAGES

Nadia Tamayo, V. Javier Traver

Abstract

Visual saliency provides a filtering mechanism to focus on a set of interesting areas in the scene, but these mechanisms often overload the computational resources of many computer vision tasks. In order to reduce such an overload and improve the computational performance, we propose to exploit the advantages of log-polar vision to detect salient regions with economy of computational resources and quite stable results. Particularly, in this paper we study the application of the entropy-based saliency to log-polar images. Some interesting considerations are presented in reference to the concept of “scale” and the effects of space-variant sampling on scale selection. We also propose a necessary border extension to detect objects present in peripheral areas. The original entropy-based saliency algorithm can be used in log-polar images, but the results show that our adaptations allow to detect with more precision log-polar salient forms because they consider the information redundancy of space-variant sampling. Compared with cartesian, log-polar salient results allow a significant saving of computational resources.

References

  1. Bolduc, M. and Levine, M. D. (1998). A review of biologically motivated space-variant data reduction models for robotic vision. In Computer Vision and Image Understanding (CVIU), volume 69. Elsevier Press.
  2. Itti, L. (2003). Modelling primate visual attention. In In J. Feng, editor, Computational Neuroscience: A Comprehensive Approach. CRC Press.
  3. Itti, L. and Koch, C. (2000). A saliency-based search mechanism for overt and covert shifts of visual attention. In Vision Research, volume 40. Elsevier Press.
  4. Kadir, T. and Brady, M. (2001). Saliency, scale and image description. In Intl. J. of Computer Vision (IJCV), volume 45.
  5. Manzotti, R., Gasteratos, A., Metta, G., and Sandini, G. (2001). Disparity estimation on log-polar images and vergence control. In Comp. Vision and Image Understanding (CVIU), volume 83. Academic Press.
  6. Mikolajczyk, K., Tuytelaars, T., Schmid, T., Zisserman, A., Mattas, J., Schaffalitzky, F., Kadir, T., and Gool, L. V. (2005). A comparison of affine region detectors. In Int. J. Comput. Vision (IJCV), volume 65.
  7. Orabona, F., Metta, G., and Sandini, G. (2005). Objectbased visual attention: a model for a behaving robot. In In Comp. Vision and Pattern Recognition (CVPR), San Diego, CA, USA.
  8. Pascual, D., Pla, F., and Sánchez, J. S. (2006). Non parametric local density-based clustering for multimodal overlapping distributions. In Lecture Notes in Comp. Science, volume 4224. Springer Press.
  9. Schwartz, E. L. (1977). Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception. In Biological Cybernetics, volume 25.
  10. Shao, L. and Brady, M. (2006). Specific object retrieval based on salient regions. In Journal of the Pattern Recognition Society, volume 39. Elsevier Press.
  11. Suau, P. and Escolano, F. (2007). Exploiting information theory for filtering the Kadir scale-saliency detector. In 3th Iberian Conference on Pattern Recognition and Image Analysis, LNCS (4478). Springer Press.
  12. Traver, V. J. and Pla, F. (2003). Designing the lattice for logpolar images. In 11th International Conf. on Discrete Geometry for Comp. Imagery, LNCS (2886). Springer Press.
  13. Traver, V. J. and Pla, F. (2005). Similarity motion estimation and active tracking through spatial domain projections on log-polar images. In Computer Vision and Image Understanding (CVIU), volume 97. Elsevier Press.
Download


Paper Citation


in Harvard Style

Tamayo N. and Javier Traver V. (2008). ENTROPY-BASED SALIENCY COMPUTATION IN LOG-POLAR IMAGES . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 501-506. DOI: 10.5220/0001076405010506


in Bibtex Style

@conference{visapp08,
author={Nadia Tamayo and V. Javier Traver},
title={ENTROPY-BASED SALIENCY COMPUTATION IN LOG-POLAR IMAGES},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={501-506},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001076405010506},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - ENTROPY-BASED SALIENCY COMPUTATION IN LOG-POLAR IMAGES
SN - 978-989-8111-21-0
AU - Tamayo N.
AU - Javier Traver V.
PY - 2008
SP - 501
EP - 506
DO - 10.5220/0001076405010506