Abstract
We propose a novel Multiple Instance Learning (MIL) framework to perform target localization from image sequences. The proposed approach consists of a softmax logistic regression MIL algorithm using log covariance features to automatically learn the model of a target that persists across input frames. The approach makes no assumptions about the target’s motion model and can be used to learn models for multiple targets present in the scene. The learned target models can also be updated in an online manner. We demonstrate the validity and usefulness of the proposed approach to localize targets in various scenes using commercial-grade surveillance cameras. We also demonstrate its applicability to bootstrap conventional tracking systems and show that automatic initialization using our technique helps to achieve superior performance.
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
Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: Proc. IEEE CVPR (2005)
Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean-shift. In: Proc. IEEE CVPR (2000)
Porikli, F., Tuzel, O., Meer, P.: Covariance tracking using model update based on means on Riemannian manifolds. In: Proc. IEEE CVPR (2006)
Kalman, R.E.: A new approach to linear filtering and prediction problems. Transactions of the ASME–Journal of Basic Engineering 82, 35–45 (1960)
Arulampalam, A., Clapp, T.: A tutorial on particle filters for online nonlinear bayesian tracking. IEEE Transactions on Signal Processing 50, 174–188 (2002)
Dietterich, T., Lozano-Perez, T.: Solving the multiple-instance problem with axis-parallel rectangles. In: Artificial Intelligence (1997)
Maron, O., Lozano-Perez, T.: A framework for multiple instance learning. In: Proc. NIPS (1998)
Zhang, Q., Goldman, S.: Em-dd: An improved multiple instance learning technique. In: Proc. NIPS (2001)
Andrews, S., Hofmann, T.: Support vector machines for multiple instance learning. In: Proc. NIPS (2003)
Settles, B., Craven, M., Ray, S.: Multiple-instance active learning. In: Proc. NIPS (2007)
Nigam, K., Lafferty, J., McCallum, A.: Using maximum entropy for text classification. In: Proc. IJCAI (1999)
Fletcher, R.: Practical methods of optimization. In: Unconstrained Optimization, ch. 3, vol. 1 (1980)
Jost, J.: Riemannian geometry and geometric analysis. Springer, Berlin (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sankaranarayanan, K., Davis, J.W. (2010). Attention-Based Target Localization Using Multiple Instance Learning. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2010. Lecture Notes in Computer Science, vol 6453. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17289-2_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-17289-2_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17288-5
Online ISBN: 978-3-642-17289-2
eBook Packages: Computer ScienceComputer Science (R0)