Abstract
This paper conceives of tracking as the developing distinction of a foreground against the background. In this manner, fast changes in the object or background appearance can be dealt with. When modelling the target alone (and not its distinction from the background), changes of lighting or changes of viewpoint can invalidate the internal target model. As the main contribution, we propose a new model for the detection of the target using foreground/background texture discrimination. The background is represented as a set of texture patterns. During tracking, the algorithm maintains a set of discriminant functions each distinguishing one pattern in the object region from background patterns in the neighborhood of the object. The idea is to train the foreground/background discrimination dynamically, that is while the tracking develops. In our case, the discriminant functions are efficiently trained online using a differential version of Linear Discriminant Analysis (LDA). Object detection is performed by maximizing the sum of all discriminant functions. The method employs two complementary sources of information: it searches for the image region similar to the target object, and simultaneously it seeks to avoid background patterns seen before. The detection result is therefore less sensitive to sudden changes in the appearance of the object than in methods relying solely on similarity to the target. The experiments show robust performance under severe changes of viewpoint or abrupt changes of lighting.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Avidan, S. 2004. Support vector tracking. IEEE Trans. on PAMI, 26(8):1064–1072.
Black, M.J. and Jepson, A.D. 1996. Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. In Proc. of European Conf. on Computer Vision, pp. 329–342.
Chen, H.T., Liu, T.L., and Fuh, C.S. 2004. Probabilistic tracking with adaptive feature selection. In Proc. of Int. Conf. on Pattern Recogn. ICPR04, pp. II: 736–739.
Chomat, O. and Crowley, J.L. 1999. Probabilistic recognition of activity using local appearance. In Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., pp. II: 104–109.
Collins, R. and Liu, Y. 2003. On-line selection of discriminative tracking features. In Proc. IEEE Conf. on Computer Vision, pp. 346–352.
Comaniciu, D., Ramesh, V., and Meer, P. 2000. Real-time tracking of non-rigid objects using mean shift. In CVPR00, pp. II: 142–149.
Cootes, T.F., Wheeler, G.V., Walker, K.N., and Taylor, C.J. 2002. View-based active appearance models. Image and Vision Computing, 20(9–10):657–664.
Daugman, J.G. 1993. High confidence visual recognition of persons by a test of statistical independence. IEEE Trans. on PAMI, 15(11):1148–1161.
Davon, D. 1977. Forest before the trees: The precedence of global features in visual perception. Cognitive Psychology, 9:353–383.
Duda, P. O., Hart, P. E., and Stork, D. G. 2001. Pattern Classification. Wiley: New York.
Friedman, N. and Russell, S. 1997. Image segmentation in video sequences: A probabilistic approach. In Proc. of 13th Conf. on Uncertainty in Artificial Intelligence, pp. 175–181.
Gong, S., McKenna, S.J., and Collins J.J. 1996. An investigation into face pose distributions. In Proc. of 2nd Inter. Conf. on Automated Face and Gesture Recognition, pp. 265. Killington, Vermont.
Hayman, E. and Eklundh, J.O. 2003. Statistical background subtraction for a mobile observer. In Proc. IEEE Conf. on Computer Vision, pp. 67–74.
Isard, M., and MacCormick, J.P. 2001. BraMBLe: A Bayesian multiple-blob tracker. In Proc. IEEE Conf. on Computer Vision, pp. II: 34–41.
Jain, A.K. and Farrokhnia, F. 1991. Unsupervised texture segmentation using Gabor filters. Pattern Recognition, 24(12): 1167–1186.
Jepson, A.D., Fleet, D.J., and El-Maraghi, T.F. 2001. Robust online appearance models for visual tracking. In Proc. IEEE Conf. on Computer Vision and Pattern Recogn., CVPR01, pp. I: 415–422.
Jojic, N., Frey, B.J., and Kannan, A. 2003. Epitomic analysis of appearance and shape. In Proc. IEEE Conf. on Computer Vision, pp. 34–41.
Lucas, B.D. and Kanade, T. 1981. An iterative image registration technquie with an application to stereo vision. In Proc. DARPA Imaging Understanding Workshop, pp. 121–130.
Matthews, I., Ishikawa, T., and Baker, S. 2004. The template update problem. IEEE Trans. on PAMI, 26(6):810–815.
Nguyen, H.T. and Smeulders, A.W.M. 2004. Fast occluded object tracking by a robust appearance filter. IEEE Trans. on PAMI, 26(8):1099–1104.
Nguyen, H.T. and Smeulders, A.W.M. 2004. Tracking aspects of the foreground against the background. In Proc. of European Conf. on Computer Vision, pp. Vol II: 446–456.
Ravela, S., Draper, B.A., Lim, J., and Weiss, R. 1996. Tracking object motion across aspect changes for augmented reality. In ARPA Image Understanding Workshop, pp. 1345–1352.
Rittscher, J., Kato, J., Joga, S., and Blake, A. 2000. A probabilistic background model for tracking. In Proc. of European Conf. on Computer Vision, pp. II: 336–350.
Ross, D., Lim, J., and Yang, M.H. 2004. Adaptive probabilistic visual tracking with incremental subspace update. In Proc. of European Conf. on Computer Vision, pp. Vol II: 470–482.
Roth, S., Sigal, L., and Black, M.J. 2004. Gibbs likelihoods for bayesian tracking. In Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., pp. I: 886–893.
Sidenbladh, H. and Black, M.J. 2003. Learning the statistics of people in images and video. Int. J. Computer Vision, 54(1):181–207.
Stauffer, C. and Grimson, W.E.L. 1999. Adaptive background mixture models for real-time tracking. In Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., pp. II: 246–252.
Sullivan, J., Blake, A., and Rittscher, J. 2000. Statistical foreground modelling for object localisation. In Proc. of European Conf. on Computer Vision, pp. II: 307–323.
Tao, H., Sawhney, H.S., and Kumar, R. 2000. Dynamic layer representation with applications to tracking. In Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., CVPR00, pp. II:134–141.
Torralba, A. and Sinha, P. 2001. Statistical context priming for object detection. In Proc. IEEE Conf. on Computer Vision.
Wren, C.R., Azarbayejani, A., Darrell, T.J., and Pentland, A.P. 1997. Pfinder: Real-time tracking of the human body. IEEE Trans. on PAMI, 19(7):780–785.
Wu, Y. and Huang, Th. S. 2000. Color tracking by transductive learning. In Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., pp. I:133–138, 2000.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was done while the first author was at the Intelligent Sensory Information Systems group, Faculty of Science, University of Amsterdam, The Netherlands.
Rights and permissions
About this article
Cite this article
Nguyen, H.T., Smeulders, A.W.M. Robust Tracking Using Foreground-Background Texture Discrimination. Int J Comput Vision 69, 277–293 (2006). https://doi.org/10.1007/s11263-006-7067-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-006-7067-x