In this paper, a novel cell segmentation, tracking and dynamic analysis vision-based method is proposed,which can be used to analyze cell population morphology and dynamic change of the cell sequence images obtained by time-lapse-microscopy. Firstly, in process of the segmentation, a new method is introduced to identify touching cells based on the relative position of the same cell region between the adjacent frames. Secondly, a novel cell tracking method, which combines cell local graph structure with motion features, is also presented to track the fast moving cell population and to improve the cell tracking accuracy. Experiment results show that this proposed method can be used to segment the touching cells correctly and has an increase of 10.66% and 5.74% tracking accuracy compared with the two traditional methods. Furthermore, the dynamic analysis results can be further used for biological researches and applications. © 2012 Springer-Verlag.
CITATION STYLE
Zhu, C., Guan, Q., & Chen, S. (2012). A novel cell segmentation, tracking and dynamic analysis method in time-lapse microscopy based on cell local graph structure and motion features. In Communications in Computer and Information Science (Vol. 321 CCIS, pp. 359–366). https://doi.org/10.1007/978-3-642-33506-8_45
Mendeley helps you to discover research relevant for your work.