SCALE ROBUST ADAPTIVE FEATURE DENSITY APPROXIMATION FOR VISUAL OBJECT REPRESENTATION AND TRACKING

C. Liu, N. H. C. Yung, R. G. Fang

2009

Abstract

Feature density approximation (FDA) based visual object appearance representation is emerging as an effective method for object tracking, but its challenges come from object’s complex motion (e.g. scaling, rotation) and the consequent object’s appearance variation. The traditional adaptive FDA methods extract features in fixed scales ignoring the object’s scale variation, and update FDA by sequential Maximum Likelihood estimation, which lacks robustness for sparse data. In this paper, to solve the above challenges, a robust multi-scale adaptive FDA object representation method is proposed for tracking, and its robust FDA updating method is provided. This FDA achieve robustness by extracting features in the selected scale and estimating feature density using a new likelihood function defined both by feature set and the feature’s effectiveness probability. In FDA updating, robustness is achieved updating FDA in a Bayesian way by MAP-EM algorithm using density prior knowledge extracted from historical density. Object complex motion (e.g. scaling and rotation) is solved by correlating object appearance with its spatial alignment. Experimental results show that this method is efficient for complex motion, and robust in adapting the object appearance variation caused by changing scale, illumination, pose and viewing angel.

References

  1. Arulampalam M. S., Maskell S., Gordon N., Clapp T., 2002. “A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking”. IEEE Transactions on Signal Processing, Vol. 50(2), pp.174-188.
  2. Carreira-Perpinan M.A., 2007. “Gaussian Mean-Shift Is an EM Algorithm”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29(5), pp.767 - 776.
  3. Comaniciu D., Meer P., 2002. “Mean Shift: A Robust Approach toward Feature Space Analysis”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24(5), pp. 603-619.
  4. Comaniciu D., Ramesh V., Meer P., 2003. “Kernel based object tracking”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25(5), pp. 564 - 577.
  5. Dempster A. P., Laird N. M., Rubin D. B., 1977. "Maximum Likelihood from Incomplete Data via the EM Algorithm". Journal of the Royal Statistical Society, Series B, Vol. 39, No. 1, pp.1-38.
  6. Gamerman D., 1997. “Markov chain Monte Carlo: stochastic simulation for Bayesian inference”. CHAPMAN & HALL/CRC.
  7. Gauvain J. L., Lee C.H., 1994. “Maximum a Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains”. IEEE Transactions on Speech and Audio Processing, 2(2):291-298.
  8. Goldberger J., Greenspan H., 2006. “Context-based segmentation of image sequences”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28(3), pp. 463 - 468.
  9. Han B., Comaniciu D., Zhu Y., Davis L., 2008. “Sequential Kernel Density Approximation and Its Application to Real-Time Visual Tracking”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30(7), pp. 1186 - 1197.
  10. Jepson A. D., D. Fleet J., El-Maraghi T. F., 2003. “Robust online appearance models for visual tracking”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25(10), pp.1296- 1311.
  11. Lindeberg T., 1994. “Scale-Space Theory in Computer Vision”. Kluwer Academic Publishers, Dordrecht, the Netherlands.
  12. Liu C.Y., Yung N.H.C., 2008. “Multi-scale feature density approximation for object representation and tracking”. IASTED Signal Processing, Pattern Recognition and Applications.
  13. Raja Y., Mckenna S. J., Gong S., 1999. “Tracking color objects using adaptive mixture models”. Image and Vision Computing, Vol. 17(3-4), pp.225-231.
  14. Timor K., Michael B.,2001. “Saliency, Scale and Image Description”, International Journal of Computer Vision, 45(2), 83-105.
  15. Yu T., Wu Y., 2006. “Differential Tracking based on Spatial-Appearance Model (SAM)”, Proceedings of the IEEE CVPR2006, Vol.1(17-22), pp.720-727, New York City, NY.
Download


Paper Citation


in Harvard Style

Liu C., Yung N. and G. Fang R. (2009). SCALE ROBUST ADAPTIVE FEATURE DENSITY APPROXIMATION FOR VISUAL OBJECT REPRESENTATION AND TRACKING . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 535-540. DOI: 10.5220/0001802805350540


in Bibtex Style

@conference{visapp09,
author={C. Liu and N. H. C. Yung and R. G. Fang},
title={SCALE ROBUST ADAPTIVE FEATURE DENSITY APPROXIMATION FOR VISUAL OBJECT REPRESENTATION AND TRACKING},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={535-540},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001802805350540},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)
TI - SCALE ROBUST ADAPTIVE FEATURE DENSITY APPROXIMATION FOR VISUAL OBJECT REPRESENTATION AND TRACKING
SN - 978-989-8111-69-2
AU - Liu C.
AU - Yung N.
AU - G. Fang R.
PY - 2009
SP - 535
EP - 540
DO - 10.5220/0001802805350540