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

Multi-target tracking method for solving distributed label fusion

A multi-target tracking and tag fusion technology, applied in the field of distributed multi-sensor multi-target detection and tracking, can solve the problems of ineffective fusion of sensors and inconsistency of sensor tags

Active Publication Date: 2020-12-22
GUILIN UNIV OF ELECTRONIC TECH
View PDF12 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is the technical problem in the prior art that the information between the sensors cannot be effectively fused and the labels of the sensors are inconsistent

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-target tracking method for solving distributed label fusion
  • Multi-target tracking method for solving distributed label fusion
  • Multi-target tracking method for solving distributed label fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] This embodiment provides a multi-target tracking method that solves distributed label fusion, and the multi-target tracking method is based on including:

[0047] Step 1. Run the LMB filter on each local sensor separately to obtain the locally estimated LMB posterior information, and set a threshold for the local information to perform pruning and truncation to reduce computational complexity;

[0048] Step 2, for each sensor label, carry out label consistency through label matching;

[0049] Step 3, share the LMB posterior information of each sensor and adjacent sensors, and perform arithmetic mean fusion on the shared information according to the label;

[0050] Step 4: Extract the target state and target track according to the fusion result.

[0051] All steps, conclusions, and simulation diagrams of this embodiment are verified and confirmed on MATLAB-R2018a. Such as figure 1 , the specific implementation steps are as follows:

[0052] Step 1: Initialize system ...

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 relates to a multi-target tracking method for solving distributed label fusion, wherein the method solves the technical problem of poor information fusion due to non-uniform labels, andcomprises the steps: step 1, independently operating a label multi-Bernoulli filter on each local sensor to obtain locally estimated LMB posteriori information; and setting a threshold value for the local information, and performing LMB posteriori pruning and truncation operation to reduce the calculation complexity; step 2, performing label matching for inconsistency of posteriori labels of the sensors, so as to enable the labels to be consistent; step 3, sharing the information of each sensor and the adjacent sensor, and performing arithmetic average fusion on the shared information according to a label mode; and step 4, performing target state and target track extraction according to the fusion result. The problem is well solved, and the method can be used for distributed multi-sensor multi-target detection and tracking.

Description

technical field [0001] The invention relates to the field of distributed multi-sensor multi-target detection and tracking, in particular to a multi-target tracking method for solving distributed tag fusion. Background technique [0002] On the basis of random finite set (RFS), a series of filters are developed for multi-target tracking, which can effectively solve complex data association problems and effectively estimate the target state, but it cannot estimate the target trajectory. Therefore, in 2014, the BaBgu Vo team introduced the label concept based on RFS, thus proposing the label random finite set (LRFS) theory. On this basis, the generalized label multi-Bernoulli (GLMB) filter, the δ-generalized label multi-Bernoulli (δ-GLMB) filter and the label multi-Bernoulli (LMB) filter have been proposed successively, which not only inherit It not only achieves excellent estimation performance for multi-target states and numbers, but also realizes the output of target tracks...

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 Applications(China)
IPC IPC(8): G01C21/20G06K9/62
CPCG01C21/20G06F18/2415G06F18/253Y02A10/40Y02D30/70
Inventor 薛秋条王力吴孙勇樊向婷邹宝红孙希妍纪元法蔡如华符强严肃清王守华
Owner GUILIN UNIV OF ELECTRONIC TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com