On the Contribution of Saliency in Visual Tracking

Iman Alikhani, Hamed R.-Tavakoli, Esa Rahtu, Jorma Laaksonen

2016

Abstract

Visual target tracking is a long-standing problem in the domain of computer vision. There are numerous methods proposed over several years. A recent trend in visual tracking has been target representation and tracking using saliency models inspired by the attentive mechanism of the human. Motivated to investigate the usefulness of such target representation scheme, we study several target representation techniques for mean-shift tracking framework, where the feature space can include color, texture, saliency, and gradient orientation information. In particular, we study the usefulness of the joint distribution of color-texture, color-saliency, and color-orientation in comparison with the color distribution. The performance is evaluated using the visual object tracking (VOT) 2013 which provides a systematic mechanism and a database for the assessment of tracking algorithms. We summarize the results in terms of accuracy & robustness; and discuss the usefulness of saliency-based target tracking.

References

  1. Borji, A., Frintrop, S., Sihite, D., and Itti, L. (2012). Adaptive object tracking by learning background context. In CVPRW, pages 23-30.
  2. Comaniciu, D., Ramesh, V., and Meer, P. (2003). Kernelbased object tracking. IEEE Trans. Pattern Anal. Mach. Intell., 25(5):564-577.
  3. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In CVPR, volume 1, pages 886-893 vol. 1.
  4. Frintrop, S. and Kessel, M. (2009). Most salient region tracking. In ICRA.
  5. Fukunaga, K. and Hostetler, L. (1975). The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inf. Theory, 21(1):32-40.
  6. Ning, J., Zhang, L., Zhang, D., and Wu, C. (2009). Robust object tracking using joint color-texture histogram. International Journal of Pattern Recognition and Artificial Intelligence, 23(07):1245-1263.
  7. Ojala, T., Pietikäinen, M., and Mäenpää, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell., 24(7):971-987.
  8. Plataniotis, K. N. and Venetsanopoulos, A. N. (2000). Color Image Processing and Applications. Springer-Verlag New York, Inc., New York, NY, USA.
  9. Tavakoli, H. and Moin, M. (2010). Mean-shift video tracking using color-lsn histogram. In Telecommunications (IST), 2010 5th International Symposium on, pages 812-816.
  10. Tavakoli, H. R., Moin, M. S., and Heikkila, J. (2013). Local similarity number and its application to object tracking. Int J Adv Robot Syst, 10(184):1-6.
  11. Yilmaz, A., Javed, O., and Shah, M. (2006). Object tracking: A survey. ACM Computing Surveys, 38(14).
Download


Paper Citation


in Harvard Style

Alikhani I., R.-Tavakoli H., Rahtu E. and Laaksonen J. (2016). On the Contribution of Saliency in Visual Tracking . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 17-21. DOI: 10.5220/0005648900170021


in Bibtex Style

@conference{visapp16,
author={Iman Alikhani and Hamed R.-Tavakoli and Esa Rahtu and Jorma Laaksonen},
title={On the Contribution of Saliency in Visual Tracking},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={17-21},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005648900170021},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - On the Contribution of Saliency in Visual Tracking
SN - 978-989-758-175-5
AU - Alikhani I.
AU - R.-Tavakoli H.
AU - Rahtu E.
AU - Laaksonen J.
PY - 2016
SP - 17
EP - 21
DO - 10.5220/0005648900170021