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

A multi-target tracking device based on stochastic finite set theory

A multi-target tracking and finite set technology, applied in the field of multi-target tracking, can solve problems such as difficult engineering applications, unresolved target missed detection, and unknown new target strength, so as to improve the effect, improve calculation efficiency, and reduce parameter configuration items Effect

Active Publication Date: 2020-08-21
CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Literature (3) focuses on solving the problem of unknown target intensity, and proposes a double threshold method, but it still cannot solve the problem of missing targets
Moreover, in practical applications, a lot of prior information is unknown, such as models of newborn targets and derived targets, information about newborn target strength, target survival rate, detection probability, etc., so these methods are basically difficult to achieve engineering applications

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 multi-target tracking device based on stochastic finite set theory
  • A multi-target tracking device based on stochastic finite set theory
  • A multi-target tracking device based on stochastic finite set theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The embodiments of the present invention are described in detail below. This embodiment is implemented on the premise of the technical solution of the present invention, and detailed implementation methods and specific operating procedures are provided, but the protection scope of the present invention is not limited to the following implementation example.

[0028] like figure 2 As shown, it is assumed that there are 6 targets moving in a straight line with a uniform speed in a two-dimensional plane (x-y plane), and the state vector is x=[x,v x ,y,v y ] T , x, y represent the positions in the x-direction and y-direction of the x-y plane respectively, v x ,v y respectively represent the speed in the x-direction and y-direction of the x-y plane, and the discrete space motion equation of each target is:

[0029]

[0030] Where F is the state transition matrix, H is the measurement matrix, ω k and υ k are process noise and measurement noise respectively, both of...

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 multi-target tracking device based on random finite set theory. The measurement set generator generates a measurement set according to the received sensor measurement and sends it to a Gaussian component initialization processor; the Gaussian component initialization processor initializes the The Gaussian component set is sent to the Gaussian component set buffer for storage; the Gaussian component matrix generator simultaneously receives the measurement set generated by the measurement set generator and the latest Gaussian component set stored in the Gaussian component set buffer, and is obtained by solving The Gaussian component matrix is ​​sent to the Gaussian component matrix expander; the Gaussian component matrix expander also receives the measurement set generated by the measurement set generator. The present invention adds threshold filtering and generation failure filtering mechanisms to identify the validity of Gaussian components, not only filters and filters the Gaussian component matrix, improves calculation efficiency, but also protects the situation of generation failure, and improves the robustness of the processing process. Stickiness.

Description

technical field [0001] The invention relates to a multi-target tracking technology, in particular to a multi-target tracking device based on random finite set theory. Background technique [0002] Multi-target tracking technology is one of the key technologies in many fields such as radar data processing, image / video processing, and robot navigation. process. Traditional target tracking algorithms are mainly methods based on data association, including track initiation, association, and track termination, among which correct association is a prerequisite for stable target tracking, so the association algorithm has become one of the most complicated processes. One, such as nearest neighbor method, joint probability data association method and multiple hypothesis tracking (MHT) algorithm. [0003] In recent years, the multi-target tracking method based on the random finite set (RFS) theory has become a research hotspot. This method processes the sensor measurement set based ...

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): G06K9/62G06T7/277
CPCG06T7/277G06F18/25
Inventor 武慧勇钮俊清任清安唐匀龙马志娟郭佳意王建富王文洋
Owner CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST