Adaptive Tracking via Multiple Appearance Models and Multiple Linear Searches

Tuan Nguyen, Tony Pridmore

Abstract

We introduce a unified tracker, named as a feature based multiple model tracker (FMM), which adapts to changes in target appearance by combining two popular generative models: templates and histograms, maintaining multiple instances of each in an appearance pool, and enhances prediction by utilising multiple linear searches. These search directions are sparse estimates of motion direction derived from local features stored in a feature pool. Given only an initial template representation of the target, the proposed tracker can learn appearance changes in a supervised manner and generate appropriate target motions without knowing the target movement in advance. During tracking, it automatically switches between models in response to variations in target appearance, exploiting the strengths of each model component. New models are added, automatically, as necessary. The effectiveness of the approach is demonstrated using a variety of challenging video sequences. Results show that this framework outperforms existing appearance based tracking frameworks.

References

  1. Adam, A., Rivlin, E., and Shimshoni, I. (2006). Robust fragments-based tracking using the integral histogram. In CVPR 2006, volume 1, pages 798-805.
  2. Babenko, B., Yang, M.-H., and Belongie, S. (2011). Robust object tracking with online multiple instance learning.
  3. Birchfield, S. (1998). Elliptical head tracking using intensity gradients and color histograms. In CVPR.
  4. Bouguet, J.-Y. (2000). Pyramidal implementation of the lucas kanade feature tracker.
  5. Collins, R., Liu, Y., and Leordeanu, M. (2005). Online selection of discriminative tracking features. PAMI.
  6. Comaniciu, D., Ramesh, V., and Meer, P. (2003). Kernelbased object tracking. PAMI, 25(5):564 - 577.
  7. Everingham, M., Gool, L., Williams, C., Winn, J., and Zisserman, A. (2010). The pascal visual object classes (voc) challenge. IJCV, 88(2):303-338.
  8. Grabner, H. and Bischof, H. (2006). On-line boosting and vision. In CVPR, volume 1, pages 260-267.
  9. Grabner, H., Leistner, C., and Bischof, H. (2008). Semisupervised on-line boosting for robust tracking. In ECCV, pages 234-247. Springer-Verlag.
  10. He, W., Yamashita, T., Lu, H., and Lao, S. (2009). Surf tracking. In ICCV, pages 1586-1592.
  11. Isard, M. and Blake, A. (1996). Contour tracking by stochastic propagation of conditional density. In ECCV, pages 343-356, London, UK. Springer-Verlag.
  12. Isard, M. and Blake, A. (1998). A mixed-state condensation tracker with automatic model-switching. In ICCV.
  13. Khan, Z., Balch, T., and Dellaert, F. (2005). Mcmc-based particle filtering for tracking a variable number of interacting targets. PAMI, 27(11):1805 -1819.
  14. Kim, Z. (2008). Real time object tracking based on dynamic feature grouping with background subtraction. In CVPR 2008, pages 1-8.
  15. Klein, D., Schulz, D., Frintrop, S., and Cremers, A. (2010). Adaptive real-time video-tracking for arbitrary objects. In IROS 2010, pages 772-777.
  16. Kristan, M., Kovacic, S., Leonardis, A., and Pers, J. (2010). A two-stage dynamic model for visual tracking. 40(6):1505-1520.
  17. Kwon, J. and Lee, K. M. (2010). Visual tracking decomposition. In CVPR.
  18. Kwon, J. and Lee, K. M. (2013). Tracking by sampling and integrating multiple trackers. PAMI, 99:1.
  19. Li, X., Hu, W., Shen, C., Zhang, Z., Dick, A., and Hengel, A. V. D. (2013). A survey of appearance models in visual object tracking. ACM Trans. Intell. Syst. Technol.
  20. Matthews, I., Ishikawa, T., and Baker, S. (2004). The template update problem. PAMI, 26(6):810-815.
  21. Nummiaro, K., Koller-Meier, E., and Gool, L. V. (2002). An adaptive color-based particle filter.
  22. Okuma, K., Taleghani, A., Freitas, N. D., Freitas, O. D., Little, J. J., and Lowe, D. G. (2004). A boosted particle filter: Multitarget detection and tracking.
  23. Prez, P., Hue, C., Vermaak, J., and Gangnet, M. (2002). Color-based probabilistic tracking. In ECCV.
  24. Pridmore, T. P., Naeem, A., and Mills, S. (2007). Managing particle spread via hybrid particle filter/kernel mean shift tracking. In Proc. BMVC, pages 70.1-70.10.
  25. Ross, D. A., Lim, J., Lin, R.-S., and Yang, M.-H. (2008). Incremental learning for robust visual tracking.
  26. Serby, D., Meier, E., and Van Gool, L. (2004). Probabilistic object tracking using multiple features. In ICPR 2004.
  27. Shi, J. and Tomasi, C. (1994). Good features to track. In CVPR, pages 593-600.
  28. Wu, Y., Lim, J., and Yang, M.-H. (2013). Online object tracking: A benchmark. In CVPR 2013.
  29. Yang, F., Lu, H., and Yang, M.-H. (2014). Robust superpixel tracking. Image Processing, IEEE Transactions.
  30. Yilmaz, A., Javed, O., and Shah, M. (2006). Object tracking: A survey.
  31. Zhou, H., Yuan, Y., and Shi, C. (2009). Object tracking using fSIFTg features and mean shift. CVIU.
Download


Paper Citation


in Harvard Style

Nguyen T. and Pridmore T. (2015). Adaptive Tracking via Multiple Appearance Models and Multiple Linear Searches . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 488-495. DOI: 10.5220/0005295004880495


in Bibtex Style

@conference{visapp15,
author={Tuan Nguyen and Tony Pridmore},
title={Adaptive Tracking via Multiple Appearance Models and Multiple Linear Searches},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={488-495},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005295004880495},
isbn={978-989-758-091-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - Adaptive Tracking via Multiple Appearance Models and Multiple Linear Searches
SN - 978-989-758-091-8
AU - Nguyen T.
AU - Pridmore T.
PY - 2015
SP - 488
EP - 495
DO - 10.5220/0005295004880495