Centroid tracking framework based particle filter and mean shift cell tracking method

Abstract

The invention discloses a centroid tracking framework based particle filter and mean shift cell tracking method, which mainly solves the problem of low accuracy rate of the traditional cell tracking method. The cell tracking method comprises the following steps of: performing binary segmentation to a video image, and extracting the central position of each cell; tracking the centroid of the cell, and recording the tracking trace of the cell; respectively recording the starting coordinates and the terminating coordinates of the trace into a starting coordinate set and a terminating coordinate set, and selecting a cell to be tracked; further predicting the trace of the cell to be tracked by using particle filter to obtain a predicted coordinate point in the next frame of image; selecting the subsequent tracking trace of the cell to be tracked by using the mean shift method in good time according to the predicted coordinate point; and circulating the steps of prediction and selection till the last frame of image, and completing the tracking of all cells. Compared with other traditional tracking methods, the cell tracking method has improvement in the aspects of tracking effect and accuracy rate and can be used for analyzing motor cells in a medical microscope video image.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, relates to automatic tracking of moving cells in video microscopic images, and can be used for analyzing moving cells in medical microscopic video images. Background technique [0002] As a research direction in biology, cell image processing has become a new research hotspot in biology because of its important guiding significance for cell research, especially cancer cell research. The development of microscopic technology provides a very important tool for observing and studying cell cycle activities. However, the traditional manual data analysis method has very limited effect on processing this kind of cell microscopic image data, which is time-consuming, laborious and inaccurate. Nowadays, as an emerging research direction in biological research, the automatic cell tracking system used in video microscopic images has important guiding significance for cell research. [0003...

AI Technical Summary

Problems solved by technology

Kachouie et al. proposed a maximum posterior probability based on the probability criterion for cell tracking, but because the algorithm requires a large number of assumptions, the number of cells that the system can track is limited

In fact, due to the nonlinear motion of the cells themselves, it is impossible to find an ideal model to better simulate the motion of all cells, and the number of cells to be tracked in the video image is relatively large, which increases the complexity of tracking. Traditional random filtering and probabilistic and statistical methods are not very ideal for cell tracking

[0007] In summary, the existing cell tracking methods have the following disadvantages: (1) Some methods cannot make accurate judgments on cell movement changes, such as the appearance or disappearance of cells. Even if the judgment is made, the complex movement cannot be ideal (2) Some methods have a certain limit on the number of targets to track, and cannot track all cells in the video image, but can only track a certain number of cells; (3) Some methods do not have good robustness, It only has an ideal tracking effect on cells with specific characteristics or movement rules in certain video images

Images