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

Feedback weight fusion method based on track quality

A technology of track quality and fusion method, applied in the field of target tracking, can solve the problems of system tracking accuracy and reliability decline, and achieve the effect of achieving target tracking, easy engineering implementation, and small amount of calculation.

Inactive Publication Date: 2015-04-22
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If allocated properly, the fusion effect will be excellent; otherwise, it will lead to a decrease in system tracking accuracy and reliability

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
  • Feedback weight fusion method based on track quality
  • Feedback weight fusion method based on track quality
  • Feedback weight fusion method based on track quality

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] like figure 1 As shown, the method of the present invention first predicts the fusion state of the fusion center at the previous moment in one step, and feeds back to each local sensor. Based on this feedback information, the quality of the track observed by the sensor is updated, thereby further updating the weight factor of the local track to achieve weighted fusion; and then smoothing the fused track through a filter to obtain the temporal correlation and smoothness of the data and improve the fusion accuracy. The concrete steps of the inventive method are as follows:

[0022] Assume that the dynamic equations and measurement equations of the multi-sensor system are:

[0023] x j (k+1)=F j (k)X j (k)+w j (k), Z(k)=H j (k)X j (k)+v j (k),j=1,2,…,N, where N is the number of models, X j (k) is the state vector under model j, the Fth j (k) is the one-step state transition matrix from time k to k+1 under model j, and the system process noise w j (k) is a Gauss...

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 feedback weight fusion method based on track quality. According to the invention, track quality and a fuzzy clustering method are used in multi-sensor information fusion, and a real-time and dynamic feedback weight track fusion method is provided. A one-step prediction value of a previous-time infused track is fed back to local sensors; local track qualities are obtained by the local sensors based on the feedback information; and weight factors of the local tracks are further undated. The method has the advantages that: the weight factors are determined with the track quality and the fuzzy clustering method; measuring errors and performances of all sensors are integrated; a calculation amount is low; the method is easy to realize in projects; weight factors can be dynamically undated in real time in infusion; and target tracking can be effectively realized. Compared with single-sensor local state estimation, the method provided by the invention has good tracking precision. Especially, in a target maneuvering environment, a tracking effect is outstanding.

Description

technical field [0001] The invention relates to the technical field of target tracking, in particular to a track quality-based feedback weighted fusion method. Background technique [0002] How to achieve precise tracking of the target is one of the important issues concerned by various fields. With the development of information fusion technology, the use of multiple sensors to achieve fusion tracking of targets has aroused extensive interest of researchers. Information fusion is a comprehensive information processing technology, that is to make full use of the complementarity and redundancy of multi-sensor or multi-source data to improve data quality and achieve a reliable solution to the problem of target tracking. Therefore, a series of track fusion algorithms have been proposed successively to realize the precise tracking of the target. The existing fusion algorithms include simple variance convex combination algorithm, track fusion algorithm based on step-by-step fil...

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): G01C21/20
Inventor 张可王泽阳张伟曾庆瑾陈龙
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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