Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-bernoulli random stochastic finite ant colony multi-cell tracking method

A multi-cell, ant colony technology, applied in the field of cell tracking, can solve problems such as difficult to apply cell data

Active Publication Date: 2018-12-07
JIANGSU SAIKANG MEDICAL EQUIP
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the case of cell division, there are probabilistic model methods, spatial topology nearest neighbor methods, etc. These methods rely on prior information and design special models, making it difficult for these methods to be applied to other cell data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-bernoulli random stochastic finite ant colony multi-cell tracking method
  • Multi-bernoulli random stochastic finite ant colony multi-cell tracking method
  • Multi-bernoulli random stochastic finite ant colony multi-cell tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] Such as figure 1 As shown, will figure 2 The original cell image sequence of the multi-Bernoulli stochastic finite ant colony system is input as the input. On this basis, the multi-Bernoulli stochastic finite ant colony parameter item, the corresponding ant colony state and its pheromone field are predicted and updated. For the first frame, there is no prediction link, only the update process, and all that is needed is the initial distribution of the multi-Bernoulli stochastic finite ant colony. In the prediction stage, a new ant generation method is used as the initial value of the ant decision in the next frame, and its corresponding pheromone field is predicted to the next frame with a normalized Gaussian function, and the Dobe value of each ant colony is given. The prediction expression of the existence probability of the Effort term and its distribution. In the update stage, using a new ant colony decision-making method and pheromone field update method, the pre...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-bernoulli random stochastic finite ant colony multi-cell tracking method. Firstly, a multi-bernoulli stochastic finite ant colony is proposed, the existence probabilityof the stochastic finite ant colony and the corresponding probability density function are given, on the basis, a related tracking problem is divided into prediction and update stages, in the prediction stage, prediction of the pheromone field and a sub ant colony state from a previous frame to a next frame is realized, the existence probability and discrete probability density distribution of the multi-Bennuoli stochastic finite ant colony in the prediction stage are given, in the update stage, the pheromone field is updated through multi-Bennuoli stochastic finite sub ant colony decision making, the multi-cell status is extracted, and thereby precise multi-cell tracking is achieved.

Description

technical field [0001] The invention belongs to the field of cell tracking, and more specifically relates to a multi-Bernoulli stochastic finite ant colony multi-cell tracking method. Background technique [0002] Quantitative analysis of cell behavior requires reliable automated tracking techniques that can estimate the state of the cell and the lineage tree of each cell. Manual tracking is still the main method in the laboratory. It has the following disadvantages, such as: time-consuming, difficult to replicate results, and difficult to track in parallel. Therefore, automatic tracking technology is the main research focus of cell tracking in recent years. [0003] At present, multi-cell tracking can be roughly divided into three categories, one is model evolution method, detection tracking method and pre-detection tracking method. The model tracking method requires high time accuracy, and the detection tracking method has high requirements for cell density and data assoc...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/246G06N3/00
CPCG06N3/006G06T7/246
Inventor 徐本连陈庆兰鲁明丽施健孙乙丹
Owner JIANGSU SAIKANG MEDICAL EQUIP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products