Abstract
This work presents a computational framework for the adaptive integration of information from different visual algorithms. The approach takes advantage of the richness of visual information by adaptively considering a variety of visual properties such as color, depth, motion, and shape. Using a probabilistic approach and uncertainty metrics, the resulting framework makes appropriate decisions about the most relevant visual attributes to consider. The framework is based on an agent paradigm. Each visual algorithm is implemented as an agent that adapts its behavior according to uncertainty considerations. These agents act as a group of experts, where each agent has a specific knowledge area. Cooperation among the agents is given by a probabilistic scheme that uses Bayesian inference to integrate the evidential information provided by them. To deal with the inherent no linearity of visual information, the relevant probability distributions are represented using a stochastic sampling approach. The estimation of the state of relevant visual structures is performed using an enhanced version of the particle filter algorithm. This enhanced version includes novel methods to adaptively select the number of samples used by the filter, and to adaptively find a suitable function to propagate the samples. We show the advantages of our approach by applying it to the task of tracking targets in a real video sequence.
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
Collett, T.: Insect navigation en route to the goal: Multiple strategies for the use of landmarks. Journal of Experimental Biology 235, 199–227 (1996)
Zeki, M.: A Vision of the Brain. Blackwell scientific publications, Oxford (1993)
Nourbakhsh, I., Bobenage, J., Grange, S., Lutz, R., Meyer, R., Soto, A.: An affective mobile educator with a full-time job. Artificial Intelligence 114, 95–124 (1999)
Darrell, T., Gordon, G., Harville, M., Woodfill, J.: Integrated person tracking using stereo, color, and pattern detection. In: IEEE Computer Vision and Pattern Recognition, Santa Barbara pp. 601–609 (1998)
Kanade, T., Collins, R., Lipton, A., Burt, P., Wixson, L.: Advances in cooperative multisensor video surveillance. In: Darpa Image Understanding Workshop, pp. 3–24. Morgan Kaufmann, San Francisco (1998)
Lipton, A., Fujiyoshi, H., Patil, R.: Moving target classification and tracking from real-time video. In: Proceedings of the 1998 DARPA Image Understanding Workshop (1998)
Fox, D.: KLD-Sampling: Adaptive particle filters. In: Advances in Neural Information Processing Systems (NIPS) 14 (2001)
Owen, A.: Empirical Likelihood. Monographs on Statistics and Applied Probability. Stanford University, California (2001)
Geweke, J.: Bayesian inference in econometric models using Monte Carlo integration. Econometrica 57, 1317–1339 (1989)
Doucet, A., de Freitas, N., Gordon, N.: An introduction to sequential Monte Carlo methods. In: Sequential Monte Carlo Methods in Practice, pp. 3–14. Springer, Heidelberg (2001)
Soto, A.: A probabilistic approach for the adaptive integration of multiple visual cues using an agent framework. Tech. report CMU-RI-TR-02-30, Carnegie Mellon University (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Soto, A., Khosla, P. (2003). A Probabilistic Approach for Dynamic State Estimation Using Visual Information. In: Günter, A., Kruse, R., Neumann, B. (eds) KI 2003: Advances in Artificial Intelligence. KI 2003. Lecture Notes in Computer Science(), vol 2821. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39451-8_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-39451-8_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20059-8
Online ISBN: 978-3-540-39451-8
eBook Packages: Springer Book Archive