Abstract
One of the most difficult aspects of visual object tracking is the handling of occlusions and target appearance changes due to variations in illumination and viewing direction. To address these challenges we introduce a novel tracking technique that relies on component-based target representations and on robust fusion to integrate model information across frames. More specifically, we maintain a set of component-based models of the target, acquired at different time instances, and combine robustly the estimated motion suggested by each component to determine the next position of the target. In this paper we allow the target to undergo similarity transformations, although the framework is general enough to be applied to more complex ones. We pay particular attention to uncertainty handling and propagation, for component motion estimation, robust fusion across time and estimation of the similarity transform. The theory is tested on very difficult real tracking scenarios with promising results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Shi, J., Tomasi, C.: Good features to track. In: 1994 IEEE Conf. on Computer Vision and Pattern Recog., San Juan, Puerto Rico, pp. 593–600 (1994)
Sidenbladh, H., Black, M.J., Fleet, D.J.: Stochastic tracking of 3d human figures using 2d image motion. In: 2000 European Conf. on Computer Vision, Dublin, Ireland, vol. 2, pp. 702–718 (2000)
Black, M.J., Jepson, A.D.: Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. International J. of Computer Vision 26, 63–84 (1998)
Edwards, G.J., Cootes, T.F., Taylor, C.J.: Face recognition using active appearance models. In: 1998 European Conf. on Computer Vision, Freiburg, Germany, pp. 581–595 (1998)
Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: Robust online appearance models for visual tracking. IEEE Trans. Pattern Anal. Machine Intell. 25, 1296–1311 (2003)
Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: 1999 IEEE Conf. on Computer Vision and Pattern Recog., vol. 2, pp. 246–252 (1999)
Tao, H., Sawhney, H.S., Kumar, R.: Dynamic layer representation with application to tracking. In: 2000 IEEE Conf. on Computer Vision and Pattern Recog., vol. 2, pp. 134–141 (2000)
Comaniciu, D.: Nonparametric information fusion for motion estimation. In: 2003 IEEE Conf. on Computer Vision and Pattern Recog., Madison, WI, vol. 1, pp. 59–66 (2003)
Freeman, W.T., Adelson, E.H.: The design and use of steerable filters. IEEE Trans. Pattern Anal. Machine Intell. 13, 891–906 (1991)
Collins, R., Liu, Y.: On-line selection of discriminative tracking features. In: 2003Â International Conf. on Computer Vision (2003)
Krahnstoever, N., Sharma, R.: Robust probabilistic estimation of uncertain appearance for model based tracking. In: IEEE Workshop on Motion and Video Computing (2002)
Krahnstoever, N., Sharma, R.: Appearance management and cue fusion for 3d model-based tracking. In: 2003Â IEEE Conf. on Computer Vision and Pattern Recog., Madison, WI (2003)
Julier, S., Uhlmann, J.: A non-divergent extimation algorithm in the presence of unknown correlations. In: Proc. American Control Conf., Alberqueque, NM (1997)
Singh, A., Allen, P.: Image-flow computation: An estimation-theoretic framework and a unified perspective. CVGIP: Image Understanding 56, 152–177 (1992)
Lucas, B., Kanade, T.: An iterative image registration technique with application to stereo vision. In: International Joint Conf. on Artificial Intelligence, Vancouver, Canada, pp. 674–679 (1981)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Georgescu, B., Comaniciu, D., Han, T.X., Zhou, X.S. (2004). Multi-Model Component-Based Tracking Using Robust Information Fusion. In: Comaniciu, D., Mester, R., Kanatani, K., Suter, D. (eds) Statistical Methods in Video Processing. SMVP 2004. Lecture Notes in Computer Science, vol 3247. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30212-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-30212-4_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23989-5
Online ISBN: 978-3-540-30212-4
eBook Packages: Springer Book Archive