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

Target extinction judgment method applied to RBMCDA tracking algorithm

A tracking algorithm and target technology, applied in the field of multi-target tracking, can solve problems such as unintuitive adjustment of target extinction model parameters, wrong target extinction judgment, and model parameter mismatch.

Active Publication Date: 2020-03-24
HARBIN ENG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that in the RBMCDA algorithm, the parameter adjustment of the target extinction model is not intuitive, and the model parameters do not match the actual situation, which leads to the problem that the judgment of the target extinction is wrong, and a tracking algorithm applied to RBMCDA is proposed. The target demise judgment method of

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
  • Target extinction judgment method applied to RBMCDA tracking algorithm
  • Target extinction judgment method applied to RBMCDA tracking algorithm
  • Target extinction judgment method applied to RBMCDA tracking algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] The target orientation is used as the state quantity and quantity measurement to carry out simulation verification. The existing RBMCDA algorithm is based on the target extinction mode of continuous unrelated duration, and 25 groups of parameters are selected. The method of the present invention is based on the target extinction model of the predicted target state value variance. 30 groups of parameters. Taking multi-target tracking accuracy (MOTA) as the evaluation standard, the missing rate of multi-target tracking p miss , misjudgment rate p fp and the mismatch rate p mme For statistics, MOTA can be expressed as

[0046] MOTA=1-(p miss +p fp +p mme )

[0047] The closer the MOTA value is to 1, the better the multi-target tracking performance is. The MOTA value is 1 only when the missing rate, false positive rate, and false match rate are all zero.

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 provides a target extinction judgment method applied to an RBMCDA tracking algorithm. The method comprises the steps of 1, predicting a target state value variance at a next moment at a(k-1) th moment; 2, calculating a target extinction probability according to the predicted target state value variance and a uniform distribution probability termination model; and 3, performing MonteCarlo sampling on the particles according to the target extinction probability, and determining a target state. According to the method, the predicted target state value variance is used as a judgment basis, so that the relation between the parameters of the target extinction probability model and the measurement noise and the state transfer noise is established, the parameters of the target extinction model do not need to be adjusted additionally, and the system has better robustness.

Description

technical field [0001] The invention belongs to the technical field of multi-target tracking, and in particular relates to a target demise judgment method applied to an RBMCDA tracking algorithm. Background technique [0002] R-B Monte Carlo data association tracking algorithm (RBMCDA, Rao-Blackwellized Monte Carlo DataAssociation) is an improved multi-target tracking algorithm based on multi-hypothesis tracking, which achieves the goal by combining Rao-Blackwellized particle filter (RBPF) and multi-hypothesis data association Tracking and trajectory generation, this method uses a mixture of particle filter and Kalman filter methods, and uses the posterior distribution of data association as the optimal importance density function for particle sampling, which has good robustness and high Tracking accuracy is one of the most effective ways to solve the multi-sensor MTT problem in the complex environment of the real world. [0003] The target disappearance problem refers to w...

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): G06F17/18G06F30/20G06F111/08
CPCG06F17/18
Inventor 齐滨付进王燕梁国龙卢鹏博樊姜华王逸林张光普孙思博邹男王晋晋
Owner HARBIN ENG UNIV