Linear Regression and Adaptive Appearance Models for Fast Simultaneous Modelling and Tracking
- First Online:
- 531 Downloads
This work proposes an approach to tracking by regression that uses no hard-coded models and no offline learning stage. The Linear Predictor (LP) tracker has been shown to be highly computationally efficient, resulting in fast tracking. Regression tracking techniques tend to require offline learning to learn suitable regression functions. This work removes the need for offline learning and therefore increases the applicability of the technique. The online-LP tracker can simply be seeded with an initial target location, akin to the ubiquitous Lucas-Kanade algorithm that tracks by registering an image template via minimisation.
A fundamental issue for all trackers is the representation of the target appearance and how this representation is able to adapt to changes in target appearance over time. The two proposed methods, LP-SMAT and LP-MED, demonstrate the ability to adapt to large appearance variations by incrementally building an appearance model that identifies modes or aspects of the target appearance and associates these aspects to the Linear Predictor trackers to which they are best suited. Experiments comparing and evaluating regression and registration techniques are presented along with performance evaluations favourably comparing the proposed tracker and appearance model learning methods to other state of the art simultaneous modelling and tracking approaches.
KeywordsRegression tracking Online appearance modelling
Unable to display preview. Download preview PDF.
- Bray, M., Kohli, P., & Torr, P. H. S. (2006). Posecut: Simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts. In ECCV (2) (pp. 642–655). Google Scholar
- Cootes, T. F., Edwards, G. J., & Taylor, C. J. (1998). Active appearance models. In ECCV (2) (pp. 484–498). Google Scholar
- Dowson, N., & Bowden, R. (2006). N-tier simultaneous modelling and tracking for arbitrary warps (Vol. II, p. 569). Google Scholar
- Ellis, L., Matas, J., & Bowden, R. (2008). Online learning and partitioning of linear displacement predictors for tracking. In BMVC (1) (pp. 33–42). Google Scholar
- Grabner, H., Grabner, M., & Bischof, H. (2006). Real-time tracking via on-line boosting. In BMVC06 (pp. 47–56). British Machine Vision Association. Google Scholar
- Grabner, H., Leistner, C., & Bischof, H. (2008). Semi-supervised on-line boosting for robust tracking. In ECCV ’08: Proceedings of the 10th European conference on computer vision (pp. 234–247). Berlin: Springer. Google Scholar
- Hansen, B. B., & Morse, B. S. (1999). Multiscale image registration using scale trace correlation. In IEEE computer society conference on computer vision and pattern recognition (Vol. 2, p. 2202). Google Scholar
- Jepson, A. D., Fleet, D. J., & El-Maraghi, T. F. (2001). Robust online appearance models for visual tracking. In CVPR (1) (pp. 415–422). Google Scholar
- Jurie, F., & Dhome, M. (2002). Real time robust template matching. In British machine vision conference 2002 (pp. 123–131). Google Scholar
- Kalal, Z., Matas, J., & Mikolajczyk, K. (2010). P-N learning: bootstrapping binary classifiers by structural constraints. In CVPR. Google Scholar
- Lucas, B. D., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. In IJCAI (pp. 674–679). Google Scholar
- Marchand, É., Bouthemy, P., Chaumette, F., & Moreau, V. (1999). Robust real-time visual tracking using a 2d-3d model-based approach. In ICCV (pp. 262–268). Google Scholar
- Matas, J., Zimmermann, K., Svoboda, T., & Hilton, A. (2006). Learning efficient linear predictors for motion estimation. In ICVGIP (pp. 445–456). Google Scholar
- Ong, E. J., & Bowden, R. (2009). Robust facial feature tracking using selected multi-resolution linear predictors (pp. 1483–1490). Google Scholar
- Sheikh, Y. A., Khan, E. A., & Kanade, T. (2007). Mode-seeking by medoidshifts. In Eleventh IEEE international conference on computer vision (ICCV 2007) (p. 141). Google Scholar
- Williams, O. M. C., Blake, A., & Cipolla, R. (2003). A sparse probabilistic learning algorithm for real-time tracking. In ICCV (pp. 353–361). Google Scholar
- Zimmermann, K. (2008). Fast learnable methods for object tracking. PhD thesis, Center for Machine Perception (CMP), Czech Technical University, Prague, Czech Republic. Google Scholar