A new hybrid Bayesian-variational particle filter with application to mitotic cell tracking

Tracking algorithms are traditionally based on either a variational approach or a Bayesian one. In the variational case, a cost function is established between two consecutive frames and minimized by standard optimization algorithms. In the Bayesian case, a stochastic motion model is used to maintai...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro pp. 1917 - 1920
Main Authors Delgado-Gonzalo, R, Chenouard, N, Unser, M
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2011
Subjects
Active contour
Active contours
Bayesian methods
ellipse
Estimation
HeLa
mitosis
Monte Carlo methods
motion
Optimization
ovuscule
snake
Target tracking
Online AccessGet full text
ISBN1424441277
9781424441273
ISSN1945-7928
DOI10.1109/ISBI.2011.5872784

Cover

More Information
Summary:Tracking algorithms are traditionally based on either a variational approach or a Bayesian one. In the variational case, a cost function is established between two consecutive frames and minimized by standard optimization algorithms. In the Bayesian case, a stochastic motion model is used to maintain temporal consistency. Among the Bayesian methods we focus on the particle filter, which is especially suited for handling multimodal distributions. In this paper, we present a novel approach to fuse both methodologies in a single tracker where the importance sampling of the particle filter is given implicitly by the optimization algorithm of the variational method. Our technique is capable of outlying nuclei and tracking the lineage of biological cells using different motion models for mitotic and non-mitotic stages of the life of a cell. We validate its ability to track the lineage of HeLa cells in fluorescence microscopy.
ISBN:1424441277
9781424441273
ISSN:1945-7928
DOI:10.1109/ISBI.2011.5872784