Cell motion analysis contributes to research the mechanism of the inflammatory process and to the development of anti-inflammatory drugs. To gain full dynamics of multiple cells, a hybrid cell detection algorithm is first designed, which is combined with several methods, such as threshold processing, distance transform, watershed negative transform, and shape and boundary constraint, to reduce over-segmentation and contour missing. By exploiting temporal information and prior knowledge, a particle-filter-based tracking technique is then proposed for image sequences to estimate individual state of multiple cells. Simulation results are presented to support obtained favorable performance of our algorithm.

Unable to display preview. Download preview PDF.

Authors and Affiliations

1. School of Automation, Nanjing University of Science & Technology, 210094, Nanjing, China

   Mingli Lu & Andong Sheng

2. School of Electrical & Automatic Engineering, Changshu Institute of Technology, 215500, Changshu, China

   Mingli Lu & Benlian Xu

Editors and Affiliations

1. Key Laboratory of Machine Perception (MOE), Peking University, Department of Machine Intelligence, School of Electronics Engineering and Computer Science, Peking University, 100871, Beijing, China

   Ying Tan

2. Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou, China

   Yuhui Shi

3. Shenzhen City Key Laboratory of Embedded System Design, College of Computer Science and Software Engineering, Shenzhen University, 518060, Shenzhen, China

   Zhen Ji

Reprints and permissions

© 2012 Springer-Verlag Berlin Heidelberg

Policies and ethics