DocumentCode :
2568482
Title :
Trajectory retrieval from Monte Carlo data association samples for tracking in fluorescence microscopy images
Author :
Gress, Oliver ; Posch, Stefan
Author_Institution :
Inst. of Comput. Sci., Martin Luther Univ. Halle-Wittenberg, Halle, Germany
fYear :
2012
fDate :
2-5 May 2012
Firstpage :
374
Lastpage :
377
Abstract :
The dynamic behavior of sub-cellular structures is of great interest to bio-medical research. We propose to use probabilistic multi-target tracking to analyze the dynamics of stress granules (SGs) to alleviate the effort of manual analysis. Inherent to multi-target tracking approaches is the combinatorial problem to associate observations to underlying targets. Rao-Blackwellized Monte Carlo Data Association circumvents this problem by sampling in the space of associations. As each sample provides its own hypothesis of SG trajectories, we employed a graph partitioning algorithm to extract one single set of trajectories. This is shown to outperform the sample with maximum probability on both synthetic data and fluorescence microscopy images.
Keywords :
Monte Carlo methods; biomedical optical imaging; cellular biophysics; fluorescence; medical image processing; optical microscopy; probability; target tracking; Monte Carlo data association samples; Rao-Blackwellized Monte Carlo data association circumvents; fluorescence microscopy image tracking; graph partitioning algorithm; manual analysis; probabilistic multitarget tracking; probability; stress granule dynamics; subcellular structures; synthetic data; trajectory retrieval; Clutter; Joints; Microscopy; Monte Carlo methods; Probabilistic logic; Target tracking; Trajectory; Data Association; Fluorescence Microscopy; Monte Carlo; Multiple Targets; Probabilistic Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on
Conference_Location :
Barcelona
ISSN :
1945-7928
Print_ISBN :
978-1-4577-1857-1
Type :
conf
DOI :
10.1109/ISBI.2012.6235562
Filename :
6235562
Link To Document :
بازگشت