Abstract
It has been shown that features can be selected adaptively for object tracking in changing environments [1]. We propose to use the variance of Mutual Information [2] for online feature selection to acquire reliable features for tracking by making use of the images of the tracked object in previous frames to refine our model so that the refined model after online feature selection becomes more robust. The ability of our method to pick up reliable features in real time is demonstrated with multi-view object tracking. In addition, the projective warping of 2D features is used to track 3D objects in non-frontal views in real time. Transformed 2D features can approximate relatively flat object structures such as the two eyes in a face. In this paper, approximations to the transformed features using weak perspective projection are derived. Since features in non-frontal views are computed on-the-fly by projective transforms under weak perspective projection, our framework requires only frontal-view training samples to track objects in multiple views.
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
Collins, R., Liu, Y., Leordeanu, M.: On-Line Selection of Discriminative Tracking Features. PAMI (2005)
Hutter, M.: Distribution of Mutual Information. Advances in Neural Information Processing Systems 14, 399–406 (2002)
Viola, P., Jones, M.: Robust real-time object detection. IJCV (2002)
Matthews, I., Ishikawa, T., Baker, S.: The Template Update Problem. PAMI 26(6), 810–815 (2004)
Jurie, F., Dhome, M.: Hyperplane Approximation for Template Matching. IEEE PAMI 24(7), 996–1000 (2002)
Arulampalam, S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for on-line non-linear/non-gaussian bayesian tracking. Transaction of Signal Processing 50(2), 174–188 (2002)
Isard, M., Blake, A.: CONDENSATION – conditional density propagation for visual tracking. IJCV 29(1), 5–28 (1998)
Shakhnarovich, G., Viola, P.A., Moghaddam, B.: A Unified Learning Framework for Real-Time Face Detection and Classification. In: IEEE FG, pp. 14–21 (May 2002)
Avidan, S.: Support Vector Tracking. PAMI 26(8), 1064–1072 (2004)
Williams, O., Blake, A., Cipolla, R.: A Sparse Probabilistic Learning Algorithm for Real-Time Tracking. In: ICCV, Nice, France (2003)
Black, M.J., Jepson, A.: EigenTracking: Robust matching and tracking of articulated objects using a view-based representation. ICCV 26(1), 63–84 (1998)
Crow, F.: Summed-Area Tables for Texture Mapping. In: SIGGRAPH, pp. 207–212 (July 1984)
Glassner, A.: Adaptive Precision in Texture Mapping. In: SIGGRAPH, vol. 20(4), pp. 297–306 (1986)
CBCL Face Database #1, MIT Center For Biological and Computation Learning, http://www.ai.mit.edu/projects/cbcl
Sinha, P.: Qualitative representations for recognition. In: Bülthoff, H.H., Lee, S.-W., Poggio, T.A., Wallraven, C. (eds.) BMCV 2002. LNCS, vol. 2525, pp. 249–262. Springer, Heidelberg (2002)
Fleuret, F.: Fast Binary Feature Selection with Conditional Mutual Information. Journal of Machine Learning Research 5, 1531–1555 (2004)
Schneiderman, H., Kanade, T.: Object Detection Using the Statistics of Parts. IJCV 56(3), 151–177 (2004)
Torkkola, K.: Feature Extraction by Non-Parametric Mutual Information Maximization. Journal of Machine Learning Research 3, 1415–1438 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leung, A.P., Gong, S. (2005). Online Feature Selection Using Mutual Information for Real-Time Multi-view Object Tracking. In: Zhao, W., Gong, S., Tang, X. (eds) Analysis and Modelling of Faces and Gestures. AMFG 2005. Lecture Notes in Computer Science, vol 3723. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11564386_15
Download citation
DOI: https://doi.org/10.1007/11564386_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29229-6
Online ISBN: 978-3-540-32074-6
eBook Packages: Computer ScienceComputer Science (R0)