Feature associated cell tracking method based on centroid tracking frame

Abstract

The invention discloses a feature associated cell tracking method based on a centroid tracking frame, which mainly solves the problem of low correct rate of the current cell tracking method. The method of the invention comprises the following steps: carrying out binary segmentation on a video image and extracting the central position of each cell; carrying out centroid tracking on the cells and recording the tracking path of the cells; respectively recording the origin coordinate and the terminal coordinate of the path into an origin coordinate set and a terminal coordinate set, selecting a cell to be tracked, and selecting a cell to be associated from a neighborhood matching area of the cell to be tracked; carrying out feature association on the cell to be tracked and the cell to be associated by a feature associating method and updating the path of the cell to be tracked; and finally, cycling the steps to the image at the last frame to finish tracking all the cells. Compared with other traditional tracking methods, the invention is improved in the aspects of the tracking effect and correct rate, and can be used for analyzing motor cells in medical microscopic video images.

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 video microscopic images of cells. Background technique [0002] As a new research hotspot in biology, cell image processing has very important guiding significance for cell research. The development of microscopic technology provides a very important tool for observing and studying cell cycle activities. In the process of developing new drugs, it is often necessary to observe the reaction of living cells after drug injection under a microscope. When the experiment is mature, it will be further tested in vivo. When studying the diffusion mode and degree of certain virus cells, the same method will be used. Ways to observe the process of virus cells invading normal cells, of course, there are many places that need to study cell movement, and its application ran...

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