Abstract
This paper presents a methodology for trajectory classification of human activities. The presented framework uses a mixture of non parametric space-variant vector fields to describe pedestrian’s trajectories. An advantage of the proposed method is that the vector fields are not constant and depend on the pedestrian’s localization. This means that the switching motion among vector fields may occur at any image location and should be accurately estimated. In this paper, the model is equipped with a novel methodology to estimate the switching probabilities among motion regimes. More specifically, we propose an iterative optimization of switching probabilities based on the natural gradient vector, with respect to the Fisher information metric. This approach follows an information geometric framework and contrasts with more traditional approaches of constrained optimization in which Euclidean gradient based methods are used combined with probability simplex constraints. We testify the performance superiority of the proposed approach in the classification of pedestrian’s trajectories in synthetic and real data sets concerning far-field surveillance scenarios.
This work was supported by the FCT projects PEst-OE/EEI/LA0009/2011, PEst-OE/EEI/LA0021/2011 and Project ARGUS (PTDC/EEA-CRO/098550/2008).
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
Nascimento, J.C., Figueiredo, M.A.T., Marques, J.S.: Activity recognition using mixture of vector fields. IEEE Trans. on Image Processing (2012), doi:10.1109/TIP.2012.2226899
Barão, M., Lemos, J.M.: An efficient Kullback-Leibler optimization algorithm for probabilistic control design. In: Mediterranean Conf. on Control and Automation, pp. 198–203 (2008)
Rabiner, L.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–286 (1989)
Nascimento, J.C., Marques, J.S., Figueiredo, M.A.T.: Discriminative Model Selection Using a Modified Bayesian Criterion: Application to Trajectory Modeling. In: Int. Conf. Imag. Processing (2011)
Nocedal, J., Wright, S.: Numerical Optimization. Springer, New York (2006)
Duchi, J., Shalev-Shwartz, S., Singer, T.C.Y.: Efficient projections onto the ℓ1-ball for learning in high dimensions. In: Proc. of Int. Conf. on Machine Learning, Helsinki, Finland (2008)
Boult, T., Micheals, R., Gao, X., Eckmann, M.: Into the woods: Visual surveillance of non-cooperative camouflaged targets in complex outdoor settings. Proceedings of the IEEE, 1382–1402 (2001)
Amari, S.-I.: Natural gradient work efficiently in learning. Neural Computation 10(2), 251–276 (1998)
Amari, S.-I., Nagaoka, H.: Methods of Information Geometry. Oxford University Press (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nascimento, J.C., Barão, M., Marques, J.S., Lemos, J.M. (2013). Efficient Optimization Algorithm for Space-Variant Mixture of Vector Fields. In: Sanches, J.M., Micó, L., Cardoso, J.S. (eds) Pattern Recognition and Image Analysis. IbPRIA 2013. Lecture Notes in Computer Science, vol 7887. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38628-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-38628-2_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38627-5
Online ISBN: 978-3-642-38628-2
eBook Packages: Computer ScienceComputer Science (R0)