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

A Radar Network Target Recognition Method

A technology of target recognition and radar networking, applied in the field of target recognition

Inactive Publication Date: 2018-08-31
PEOPLES LIBERATION ARMY ORDNANCE ENG COLLEGE
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, in the existing technology, the technology related to target recognition using feature layer fusion is still in a blank state

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 Radar Network Target Recognition Method
  • A Radar Network Target Recognition Method
  • A Radar Network Target Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Assume that three radars in the existing radar network detect and identify an air target. Three target classes are known A 1 、A 2 、A 3 . Select four attribute variables c for identification 1 、c 2 、c 3 and c 4 , and the standard values ​​are θ 1 , θ 2 , θ 3 and θ 4 , and the standard deviations are δ 1 ,δ 2 ,δ 3 and δ 4 , the parameter templates of the three target categories are given by the prior knowledge, as shown in Table 1.

[0065] Table 1 Standard value and standard deviation of target category

[0066]

[0067] The measurement data records of each radar after space-time registration and correlation processing are shown in Table 2. Try to determine the category of the air target.

[0068] Table 2 Radar measurement data

[0069]

[0070] First, the leaf nodes of the class decision tree are formed from the prior information in Table 1.

[0071] Second, create the first node. Obtained from formula (2), the information entropy required for ...

Embodiment 2

[0079] The prior knowledge of the three object categories is shown in Table 1. Assuming that there are some blank values ​​in the measurement data of the radar network, the blank values ​​are arbitrarily set in the original measurement data to obtain Table 3. Try to determine the category of the air target.

[0080] Table 3 Radar measurement data (including blank values)

[0081]

[0082] The identification method is similar to that in Embodiment 1, and the same parts will not be described again. At the first node, the information gain of each attribute variable is calculated. Due to the presence of vacant values, only the information entropy required for the classification of non-null attribute values ​​is calculated. will have the maximum information gain property c 3 As a classification attribute, classify the current node data set. get the degree of membership

[0083]

[0084] It can be seen from the degree of membership that the second group and the third gro...

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 radar network target recognition method, which belongs to the technical field of radar data processing. In the method, s radars respectively measure n attributes of detection targets to form s groups of radar measurement data, and attribute the detection targets to m One of the possible targets, where each property of each possible target has a specific range of values. This method improves the anti-interference ability of the identification system, the identification difficulty is small, the identification accuracy is high, and the identification and classification process is carried out from top to bottom. Compared with the identification method in the prior art, it has the characteristics of a simpler and more reliable identification process, and has a good promotion and application prospects.

Description

technical field [0001] The invention relates to the technical field of target recognition, in particular to a radar network target recognition method. Background technique [0002] The modern battlefield environment is becoming more and more complex. In the presence of various interferences, the target measurement information obtained by radar echo has great uncertainty, which makes it difficult to meet the needs of combat system target recognition. For this reason, a target fusion recognition method based on radar networking has appeared in the prior art. This method uses multiple radars to detect a target at the same time and fuses the detection results to obtain a measurement result that is more accurate than a single radar. This radar network helps to enhance the system's anti-jamming capability and environmental adaptability, improves the credibility and accuracy of target recognition, and provides an important basis for combat command auxiliary decision-making. [00...

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): G01S7/41
Inventor 尚朝轩韩壮志王品王雪飞胡文华解辉刘利民
Owner PEOPLES LIBERATION ARMY ORDNANCE ENG COLLEGE