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

Particle Filtering Algorithm for Centralized Multi-Sensor Formation Target Based on Shape and Orientation Descriptor

A technology of descriptors and targets, applied in the field of multi-sensor and multi-target information fusion, can solve the problems of no research on multi-sensor situations, and achieve the effects of effective interconnection and fusion, small time-consuming increase, and high target tracking rate

Active Publication Date: 2016-09-21
NAVAL AERONAUTICAL & ASTRONAUTICAL UNIV PLA
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of algorithm reduces the probability of tracking confusion and calculation explosion to a certain extent, improves the stability of the entire tracking system, and saves a lot of radar resources. However, with the improvement of sensor resolution, it gradually shows the following shortcomings: First, the derivation environment of the algorithm is mostly relatively simple, and it is usually assumed that the individual targets in the formation are completely identifiable. However, in reality, due to factors such as mutual occlusion of targets and environmental interference, the formation targets are usually partially identifiable; second, in In some practical engineering applications, while tracking the entire formation, individual targets in the formation need to be tracked individually; third, in order to effectively improve the precise tracking effect of targets in the formation, it is necessary to use multiple sensors in engineering to observe from different directions Formation targets, however, the existing algorithms only consider the single-sensor situation, and there is no research on the complex multi-sensor situation

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
  • Particle Filtering Algorithm for Centralized Multi-Sensor Formation Target Based on Shape and Orientation Descriptor
  • Particle Filtering Algorithm for Centralized Multi-Sensor Formation Target Based on Shape and Orientation Descriptor
  • Particle Filtering Algorithm for Centralized Multi-Sensor Formation Target Based on Shape and Orientation Descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] combine figure 1 As shown in the algorithm flow chart, the specific implementation of the centralized multi-sensor formation target particle filter algorithm based on shape and orientation descriptors is as follows:

[0017] (1) Establishment of formation target shape vector

[0018] The shape orientation descriptor is a common method for describing spatial graphics in digital image processing. It consists of the height, width, area, and ratio of the image orientation box, the height, width, area, ratio, minimum radius, maximum radius, and The minimum radius angle and the maximum radius angle are composed of 12 components.

[0019] Assume figure 2 The polygon A in is the target G of a certain formation at a certain moment t Planar shape graph of (k-1), t 1 , t 2 , t 3 , t 4 is the position of each target in the formation. Create the shape vector of A using the shape orientation descriptor

[0020] Ω t (k-1)={ω 1 , ω 2 , ω 3 , ω 4 , ω 5 , ω 6 , ω 7 , ω ...

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

In order to meet the engineering needs of using multiple sensors to achieve accurate tracking of targets in the formation under complex backgrounds such as cloud and rain clutter and ribbon interference, it is difficult to achieve ideal tracking results for traditional multi-sensor multi-target tracking algorithms and existing formation target tracking algorithms. Insufficient, based on the fact that the real echo space structure of the target in the same non-maneuvering formation is relatively fixed at adjacent times, a centralized multi-sensor formation target particle filter algorithm based on shape and orientation descriptors is proposed. The invention eliminates redundant traces in state prediction based on graphic similarity, realizes state update of multi-dimensional traces of formation targets based on particle filter, and completes precise tracking of targets in centralized multi-sensor formations.

Description

1. Technical field [0001] The invention belongs to the technical field of multi-sensor multi-target information fusion and provides a centralized multi-sensor formation target tracking algorithm under complex background. 2. Background technology [0002] The traditional multi-sensor multi-target tracking algorithm has very limited tracking effect on formation targets. This type of algorithm is usually based on the measurement and directly builds the navigation of the targets in the formation. However, due to the small distance between the targets in the formation, the tracking gates of each target will overlap seriously, and the difficulty of data interconnection is greatly increased; and because the behavior patterns of the targets in the formation are similar, False track initiation and maintenance can accumulate over time and cause serious confusion in the overall situation. [0003] In recent years, scholars at home and abroad have proposed a series of formation target ...

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): G06T5/00
Inventor 王海鹏齐林熊伟潘丽娜董凯刘瑜
Owner NAVAL AERONAUTICAL & ASTRONAUTICAL UNIV PLA
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