Tracking of Active Cells Based on Kalman Filter in Time Lapse of Image Sequences of Neuron Stem Cells

In multi-cells’ tracking of time-lapse image sequences imaged by optical microscope, problem of tracking active cells correctly is still unsolved. It affects tracking accuracy and speed whether an algorithm can predict the position of the active cells or not. The tracking strategy is guided by Kalman forecast in image Cartesian coordinates systems, which may search target cells via minimizing their cost function of characteristics and updating their state equations. Prediction and tracking results from six active cells in three image sequences show that the algorithm can track segmented active cells accurately. And the errors between the tracking estimate values and the practical observation values are no more than 10 pixels.