Unlock instant, AI-driven research and patent intelligence for your innovation.

Design method of GM-PHD filter

A design method and filter technology, applied in the field of GM-PHD filter design, can solve problems such as loss of new targets

Active Publication Date: 2021-04-20
NO 63921 UNIT OF PLA
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The object of the present invention is to provide a kind of design method of GM-PHD filter, solve the new target loss problem that traditional GM-PHD filter exists

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
  • Design method of GM-PHD filter
  • Design method of GM-PHD filter
  • Design method of GM-PHD filter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0038] According to an embodiment of the present invention, the GM-PHD filter takes the Gaussian component as the basic unit, and usually has the following three assumptions:

[0039] First, both the state transition density function and the observation likelihood function of the target obey the linear Gaussian distribution. Among them, both the state transition model and the observation model of the target boresight pointing vector satisfy the linear Gaussian condition, and the Gaussian distribution form can be expressed as:

[0040]

[0041] In the formula, N( ) represents the Gaussian distribution function; x is the state parameter, F is the state transition matrix, Q is the covariance matrix of the state transition noise; z is the observation parameter, H is the observation matrix, and U is the covariance of the observation noise matrix. ;

[0042] Second, the survival probability and detection probability of the target have nothing to do with the target state and are...

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 design method of a GM-PHD filter, which comprises the following steps: S1, determining whether prior distribution is in a Gaussian mixture form under a linear Gaussian distribution condition based on assumed conditions of the GM-PHD filter, and if so, assuming that posterior probability assumes a Gaussian mixture form of density Dk-1 [2jeemaa2] k-1(x) at k-1 moment, and S2, utilizing a prediction equation and a state transition matrix F at k moment, obtaining predicted Dk [2jeemaa2] k-1(x), S3, carrying out state updating by utilizing the predicted Dk [2jeemaa2] k-1 (x), so as to obtain an updated Dk [2jeemaa2] k(x), S4, obtaining the correlation between the Gaussian component weight of the PHD and the measurement zk at the current moment based on the updated PHD; and S5, replacing the prediction function of the new target with the zk1 measured at the previous moment to obtain a new Gaussian component weight of the new target of the filter and a state updating formula thereof. The improved GMPHD filter can realize new target detection more quickly, converges the number of targets, and has better performance.

Description

technical field [0001] The invention relates to a design method of a GM-PHD filter. Background technique [0002] Random Finite Sets (RFS, Random Finite Sets) theory is a new method for solving multi-target tracking problems. It establishes the target state set model and the measurement set model, and recurses the target posterior probability density in real time under the Bayesian framework, which can effectively avoid the "combination explosion" problem in the relationship between measurement and target, so that the target track association. GM-PHD filter is a typical implementation method of stochastic finite set theory, which improves computational efficiency through Gaussian item management and clipping, but this method usually assumes that the target generation location is known (such as aircraft carrier, airport, etc.), for sudden, strong For targets in an unknown state whose launch time and spatial position are unpredictable, this clipping method is easy to cut out...

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): H03H21/00
Inventor 薛永宏韩晓亚乔凯樊士伟
Owner NO 63921 UNIT OF PLA