A joint multi-cell tracking method based on tag ant colony

A multi-cell, labeling technology, applied in instruments, complex mathematical operations, artificial life, etc., can solve problems such as cell division and deformation

Active Publication Date: 2021-05-11
JIANGSU SAIKANG MEDICAL EQUIP
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the tracking problems such as cell division, deformation and measurement uncertainty, the present invention proposes a joint tracking method based on label ant colony multi-cell data association and state estimation

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
  • A joint multi-cell tracking method based on tag ant colony
  • A joint multi-cell tracking method based on tag ant colony
  • A joint multi-cell tracking method based on tag ant colony

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0105] 1. Definition and approximation of multi-Bernoulli stochastic finite ant colony:

[0106] Multi-Bernoulli stochastic finite ant colony: Multi-Bernoulli stochastic finite ant colony X is composed of a fixed number (such as M) of single Bernoulli stochastic finite ant colony X (ζ) (ζ=1,...,M) form a union, and each single Bernoulli stochastic finite ant colony X (ζ) Its existence probability r can be used (ζ) ∈(0,1) and its corresponding probability density function π (ζ) to express, then, the multi-Bernoulli stochastic finite ant colony X can use the Bernoulli parameter ant colony To represent. Label multi-Bernoulli stochastic finite ant colony available {(r (ζ) , π (ζ) ):ζ∈Ψ}, where Ψ represents the index ant colony, if a single Bernoulli component returns a non-empty ant colony, it is assigned a label.

[0107] Labeled Dobenoulli stochastic finite ant colony approximation: Labeled Dobenoulli stochastic finite ant colony can be approximated by labeled Dobenoulli ...

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 combined multi-cell tracking method based on tag ant colony. First, a group of cell candidate ant colonies is generated in the current frame by using unlabeled scout ant colonies, and a bipartite graph is constructed on this basis, which is composed of the estimated cell state in the previous frame and the currently generated cell candidate ant colonies; secondly, Using the tagged ant colony and taking the optimal sub-pattern assignment as the objective function to optimally realize the matching between frames, the multi-cell state is obtained by the multiple Bernoulli parameters approximated by the evolved tagged ant colony, and the cell lineage tree is obtained by its The trajectory pheromone field on the determined frame-to-frame matching is extracted; finally, for track breaks, a four-step track recovery method is proposed to realize the association between broken tracks. The invention can use the trajectory pheromone to extract the spectrum coefficient of the cell, and use the food pheromone to estimate the state of the cell; compared with the prior art, the precision rate and recall rate of cell division are obviously improved.

Description

technical field [0001] The invention belongs to the field of automatic tracking, and more specifically relates to a combined multi-cell tracking method based on label ant colonies. Background technique [0002] Quantitative analysis of cell behavior requires reliable automatic tracking techniques that can automatically estimate the state, morphological parameters and corresponding lineage trees associated with each cell. Manual tracking has high requirements on the professional level of experimenters, and is time-consuming, difficult to replicate results, difficult to parallel track, error-prone, etc., so integrated automatic tracking technology is the main research focus of cell tracking in recent years. [0003] At present, there are many methods for multi-cell automatic tracking, such as: segmentation and association methods, model evolution methods, and filtering methods. Segmentation and association method is an effective way to solve the problem of multi-cell division...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/00G06F17/18
CPCG06F17/18G06N3/006
Inventor 徐本连鲁明丽陈庆兰施健孙乙丹
Owner JIANGSU SAIKANG MEDICAL EQUIP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap