Abstract
Tracking serves as a means to prepare data for pose estimation and action recognition. The CONDENSATION algorithm is a conditional density propagation method for motion tracking. This algorithm combines factored sampling with learned dynamic models to propagate an entire probability distributes for object position and shape over time. It can accomplish highly robust tracking of object motion. However, it usually requires a large number of samples to ensure a fair maximum likelihood estimation of the current state. In this paper, we use the mutation and crossover operators of the genetic algorithm to find appropriate samples. With this approach, we are able to improve robustness, accuracy and flexibility in CONDENSATION for visual tracking.
Similar content being viewed by others
References
Isard M, Blake A (1998) Condensation–conditional density propagation for visual tracking. Int J Comput Vis 29(1): 5–28
Doucet A, de Freitas N, Gordon N (2001) Sequential Monte Carlo methods in practice. Springer, Berlin Heidelberg New York
Holland JH (1975) Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor
Gordon NJ (1994) Bayesian methods for tracking. PhD Thesis. Imperial College, University of London
Eiben AE, Smith JE (2003) Introduction to evolutionary computing. Springer Berlin, Heidelberg Newyork
Arulampalam MS, Maskell S, Gordon N, Clapp T (2002) A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans Signal Process 50(2):174–188
Pereira de Araújo AF (1998) Requirements for protein folding potentials: perspectives from lattice model simulations. PhD Thesis, Brandeis University
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ye, Z., Liu, ZQ. Genetic CONDENSATION for motion tracking. Soft Comput 11, 349–354 (2007). https://doi.org/10.1007/s00500-006-0088-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-006-0088-0