CN114067224A - Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion - Google Patents

Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion Download PDF

Info

Publication number
CN114067224A
CN114067224A CN202111209459.9A CN202111209459A CN114067224A CN 114067224 A CN114067224 A CN 114067224A CN 202111209459 A CN202111209459 A CN 202111209459A CN 114067224 A CN114067224 A CN 114067224A
Authority
CN
China
Prior art keywords
radar
unmanned aerial
aerial vehicle
com
vehicle cluster
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111209459.9A
Other languages
Chinese (zh)
Inventor
闫川
甄子洋
江驹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN202111209459.9A priority Critical patent/CN114067224A/en
Publication of CN114067224A publication Critical patent/CN114067224A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/251—Fusion techniques of input or preprocessed data

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Aiming, Guidance, Guns With A Light Source, Armor, Camouflage, And Targets (AREA)

Abstract

The invention belongs to the technical field of information processing, and discloses an unmanned aerial vehicle cluster target quantity detection method based on multi-sensor data fusion, which comprises the following steps that 1, two sensors, namely a radar sensor and a communication signal receiver, respectively obtain unmanned aerial vehicle cluster target quantity values to obtain basic probability assignment of detection data; step 2, fusing the basic probability assignments in the step 1 by applying a D-S evidence theory fusion rule, and outputting the fused basic probability assignments; and 3, judging and deciding the fused basic probability assignment, and outputting the detection result of the number of the unmanned aerial vehicle cluster targets. The unmanned aerial vehicle cluster target number detection method based on the D-S evidence theory effectively solves the problem of low reliability of detecting the unmanned aerial vehicle cluster number by a single sensor, can provide more accurate data support for unmanned aerial vehicle cluster detection and defense, and improves the accuracy of cluster defense effect evaluation so as to carry out more reasonable defense decision.

Description

Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion
Technical Field
The invention belongs to the technical field of information processing, and particularly relates to an unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion.
Background
With the rapid development of leading-edge technologies such as multi-agent and communication, the research on unmanned aerial vehicle cluster defense has gradually become the focus of attention of all countries. The individual existence signal characteristics of the unmanned aerial vehicle cluster target are weak, the cluster form is complex, the change is multi-end-to-end, and the like, so that the difficulty is brought to the detection of the number of the unmanned aerial vehicle cluster targets, and the selection of the defense strategy and the evaluation of the defense effect are influenced.
In the actual unmanned aerial vehicle cluster combat environment, data acquired by single detection sensors such as radars often have certain uncertainty, so that the data acquired by the sensors of different types need to be fused to eliminate redundant and contradictory information possibly existing in multi-sensor information, the reliability of the data is improved, and more accurate data support is provided for unmanned aerial vehicle cluster combat and defense.
In a data fusion algorithm, a D-S (Dempster-Shafer) evidence theory is often used for processing uncertainty problems, and the evidence theory is a set of probability theory-based mathematical theory and has wide application in the fields of expert systems, pattern recognition and information fusion.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides the unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion, and the unmanned aerial vehicle cluster target number information acquired by a radar and a communication signal receiver is synthesized, so that a more accurate unmanned aerial vehicle cluster target number identification result is obtained.
The invention discloses an unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion, which is characterized by comprising the following steps of:
step 1, two sensors, namely a radar sensor and a communication signal receiver, respectively acquire a target quantity value of an unmanned aerial vehicle cluster to obtain basic probability assignment of detection data;
step 2, fusing the basic probability assignments in the step 1 by applying a D-S evidence theory fusion rule, and outputting the fused basic probability assignments;
and 3, judging and deciding the fused basic probability assignment, and outputting the detection result of the number of the unmanned aerial vehicle cluster targets.
Further, in step 1, setting the identification frame Θ as { θ ═ formed by the detection results of the number of the unmanned aerial vehicle cluster targets1,θ2,…,θnN is the maximum number of possible unmanned plane clusters; then the basic probability assignment of the number of drones obtained by the radar is represented as:
Mradar:{mradar(θ1),mradar(θ2),…,mradar(θn) And (1) basic probability assignment of the number of the unmanned aerial vehicles acquired by the communication reconnaissance machine is represented as:
Mcom:{mcom(θ1),mcom(θ2),…,mcom(θn)}。 (2)
further, the calculation process of the fused basic probability assignment in step 2 is as follows:
the calculation formula of the reliability function is as follows:
Figure BDA0003308335940000021
wherein m (B) represents the base probability assignment for event B;
calculating a normalization constant K:
Figure BDA0003308335940000022
wherein m is1，m2Respectively as the metric function Bel in the recognition frame thetaradarAnd BelcomCorresponding basic probability assignment function, BelradarAnd BelcomRespectively corresponding reliability functions of the radar and the communication sensor;
calculating a fused basic probability assignment function m by using Dempster evidence synthesis ruleradar-comThe concrete formula is as follows:
Figure BDA0003308335940000023
further, the decision rule in step 3 is as follows:
Figure BDA0003308335940000024
among them, Max1{mradar-com(θi)}，Max2{mradar-com(θi) Respectively representing the first two largest basic probability assignments, epsilon1，ε2Is a set threshold; if Max1{mradar-com(θi) If the formula is satisfied, the identification result is judged to be Max1{mradar-com(θi) Theta corresponding toiOtherwise, the judgment fails and the judgment is identified as uncertain.
The invention has the beneficial effects that: the unmanned aerial vehicle cluster target number detection method based on the D-S evidence theory effectively solves the problem of low reliability of detecting the unmanned aerial vehicle cluster number by a single sensor, can provide more accurate data support for unmanned aerial vehicle cluster detection and defense, and improves the accuracy of cluster defense effect evaluation so as to carry out more reasonable defense decision.
The method provided by the invention is used for processing uncertain information, can fully utilize the information, reduces the uncertainty and reduces the decision risk.
The method has the advantages of concise algorithm and strong compatibility and operability.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flow chart of detecting the number of targets in a cluster of unmanned planes.
Detailed Description
In order that those skilled in the art will better understand the technical solutions of the present invention, the present invention will be further described in detail with reference to the following detailed description.
The embodiment of the invention provides an unmanned aerial vehicle cluster target quantity detection method based on multi-sensor data fusion, wherein a sensor comprises a radar and a communication signal receiver, the flow chart of the method is shown in figure 1, and the method mainly relates to the steps of utilizing basic probability assignment of the unmanned aerial vehicle cluster target quantity given by the radar and the communication signal receiver, and outputting the unmanned aerial vehicle cluster target quantity detection result through a D-S data fusion algorithm and a judgment algorithm.
Step 1, taking the detection of unmanned aerial vehicle clusters with a certain number as an example, two sensors, namely a radar sensor and a communication signal receiver, respectively acquire the target number values of the unmanned aerial vehicle clusters to obtain basic probability assignment of detection data.
The detection results of the number of unmanned aerial vehicle cluster targets form an identification frame theta ═ theta1,θ2,…,θnN is the maximum number of individuals that a cluster of drones may appear. Then the basic probability assignment of the number of drones obtained by the radar is represented as:
Mradar:{mradar(θ1),mradar(θ2),…,mradar(θn)} (1)
the basic probability assignment of the number of the unmanned aerial vehicles acquired by the communication reconnaissance machine is represented as follows:
Mcom:{mcom(θ1),mcom(θ2),…,mcom(θn)} (2)
and 2, fusing the basic probability assignments by applying a D-S evidence theory fusion rule, and outputting the fused basic probability assignments.
The fusion process comprises the following calculation methods:
the calculation formula of the reliability function is as follows:
Figure BDA0003308335940000041
where Θ is the recognition framework, representing the set of all possible events, i.e. the number of all possible detected drone cluster targets, θ represents the events, i.e. the number of drone targets, B is a subset of θ, and m (B) represents the fundamental probability assignment for event B.
Calculating a normalization constant K:
Figure BDA0003308335940000042
wherein m is1，m2Respectively as the metric function Bel in the recognition frame thetaradarAnd BelcomCorresponding basic probability assignment function, BelradarAnd BelcomAnd respectively, corresponding reliability functions of the radar and the communication sensor.
Wherein:
Figure BDA0003308335940000043
Figure BDA0003308335940000044
calculating a fused basic probability assignment function m by using Dempster evidence synthesis ruleradar-comThe concrete formula is as follows:
Figure BDA0003308335940000051
and 3, judging and deciding the fused basic probability assignment, and outputting the detection result of the number of the unmanned aerial vehicle cluster targets.
The decision rule is as follows:
Figure BDA0003308335940000052
among them, Max1{mradar-com(θi)}，Max2{mradar-com(θi) Respectively representing the first two largest basic probability assignments, Max, in the fused basic probability assignments1{mradar-com(θi) Denotes the largest of the fused elementary probability assignments, ε1，ε2Is a set threshold. If Max1{mradar-com(θi) If the formula is satisfied, the identification result is judged to be Max1{mradar-com(θi) Theta corresponding toiOtherwise, the judgment fails and the judgment is identified as uncertain.
The numerical simulation of this embodiment verifies that, assuming that the maximum number of individuals of a certain unmanned aerial vehicle cluster is 15, two sensors, namely an active radar sensor and a communication signal receiver, respectively detect the number of the individual clusters, wherein the basic probability assignment of the number of the unmanned aerial vehicle cluster targets detected by the radar is shown in table 1.
TABLE 1 Radar detection unmanned aerial vehicle Cluster target number BAF
Figure BDA0003308335940000053
Figure BDA0003308335940000061
The basic probability assignment of the number of the unmanned aerial vehicle cluster targets acquired by the communication signal receiver is shown in table 2.
Table 2 communication signal detecting machine for detecting unmanned aerial vehicle cluster target number BAF
mcom(θ1) mcom(θ2) mcom(θ3) mcom(θ4) mcom(θ5)
0.01 0.00 0.03 0.03 0.05
mcom(θ6) mcom(θ7) mcom(θ8) mcom(θ9) mcom(θ10)
0.05 0.07 0.06 0.10 0.46
mcom(θ11) mcom(θ12) mcom(θ13) mcom(θ14) mcom(θ15)
0.11 0.02 0.01 0.01 0.00
And performing data fusion on the two groups of basic probability assignments by applying a D-S evidence theory to obtain fused basic probability assignments, as shown in Table 3.
TABLE 3 fused UAV Cluster target number BAF
mradar-com(θ1) mradar-com(θ2) mradar-com(θ3) mradar-com(θ4) mradar-com(θ5)
0.0000 0.0000 0.000 0.0013 0.0019
mradar-com(θ6) mradar-com(θ7) mradar-com(θ8) mradar-com(θ9) mradar-com(θ10)
0.0038 0.0051 0.0111 0.0593 0.8800
mradar-com(θ11) mradar-com(θ12) mradar-com(θ13) mradar-com(θ14) mradar-com(θ15)
0.0349 0.0019 0.0006 0.0000 0.0000
After the fused basic probability assignment is obtained, judging the number of the unmanned aerial vehicle cluster targets by applying a discrimination algorithm, and setting epsilon1Is 0.3,. epsilon2Is 0.6, then the judgment result can be output: the detection result of the number of unmanned aerial vehicle cluster targets is 10.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (4)

1. A method for detecting the number of unmanned aerial vehicle cluster targets based on multi-sensor data fusion is characterized by comprising the following steps:
step 1, two sensors, namely a radar sensor and a communication signal receiver, respectively acquire a target quantity value of an unmanned aerial vehicle cluster to obtain basic probability assignment of detection data;
step 2, fusing the basic probability assignments in the step 1 by applying a D-S evidence theory fusion rule, and outputting the fused basic probability assignments;
and 3, judging and deciding the fused basic probability assignment, and outputting the detection result of the number of the unmanned aerial vehicle cluster targets.
2. The method for detecting the number of the unmanned aerial vehicle cluster targets based on the multi-sensor data fusion as claimed in claim 1, wherein in step 1, the detection result of the number of the unmanned aerial vehicle cluster targets is set to form an identification frame Θ ═ θ1,θ2,…,θnN is the maximum number of possible unmanned plane clusters; then the basic probability assignment of the number of drones obtained by the radar is represented as:
Mradar:{mradar(θ1),mradar(θ2),…,mradar(θn)} (1)
the basic probability assignment of the number of the unmanned aerial vehicles acquired by the communication reconnaissance machine is represented as follows:
Mcom:{mcom(θ1),mcom(θ2),…,mcom(θn)}。 (2) 。
3. the method for detecting the number of the unmanned aerial vehicle cluster targets based on the multi-sensor data fusion as claimed in claim 2, wherein the calculation process of the fused basic probability assignment in step 2 is as follows:
the calculation formula of the reliability function is as follows:
Figure FDA0003308335930000011
wherein m (B) represents the base probability assignment for event B;
calculating a normalization constant K:
Figure FDA0003308335930000012
wherein m is1，m2Respectively as the metric function Bel in the recognition frame thetaradarAnd BelcomCorresponding basic probability assignment function, BelradarAnd BelcomRespectively corresponding reliability functions of the radar and the communication sensor;
calculating a fused basic probability assignment function m by using Dempster evidence synthesis ruleradar-comThe concrete formula is as follows:
Figure FDA0003308335930000021
4. the method for detecting the number of unmanned aerial vehicle cluster targets based on multi-sensor data fusion as claimed in claim 3,
the decision rule in step 3 is as follows:
Figure FDA0003308335930000022
among them, Max1{mradar-com(θi)}，Max2{mradar-com(θi) Respectively representing the first two largest basic probability assignments, epsilon1，ε2Is a set threshold; if Max1{mradar-com(θi) If the formula is satisfied, the identification result is judged to be Max1{mradar-com(θi) Theta corresponding toiOtherwise, the judgment fails and the judgment is identified as uncertain.
CN202111209459.9A 2021-10-18 2021-10-18 Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion Pending CN114067224A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111209459.9A CN114067224A (en) 2021-10-18 2021-10-18 Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111209459.9A CN114067224A (en) 2021-10-18 2021-10-18 Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion

Publications (1)

Publication Number Publication Date
CN114067224A true CN114067224A (en) 2022-02-18

Family

ID=80234813

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111209459.9A Pending CN114067224A (en) 2021-10-18 2021-10-18 Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion

Country Status (1)

Country Link
CN (1) CN114067224A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114510068A (en) * 2022-02-24 2022-05-17 北京航空航天大学 Multi-unmanned aerial vehicle collaborative situation perception method and system based on information fusion
CN115457351A (en) * 2022-07-22 2022-12-09 中国人民解放军战略支援部队航天工程大学 Multi-source information fusion uncertainty judgment method

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114510068A (en) * 2022-02-24 2022-05-17 北京航空航天大学 Multi-unmanned aerial vehicle collaborative situation perception method and system based on information fusion
CN115457351A (en) * 2022-07-22 2022-12-09 中国人民解放军战略支援部队航天工程大学 Multi-source information fusion uncertainty judgment method
CN115457351B (en) * 2022-07-22 2023-10-20 中国人民解放军战略支援部队航天工程大学 Multi-source information fusion uncertainty judging method

Similar Documents

Publication Publication Date Title
CN107230218B (en) Method and apparatus for generating confidence measures for estimates derived from images captured by vehicle-mounted cameras
CN108932736B (en) Two-dimensional laser radar point cloud data processing method and dynamic robot pose calibration method
CN112526513B (en) Millimeter wave radar environment map construction method and device based on clustering algorithm
CN113412505B (en) Processing unit and method for ordered representation and feature extraction of a point cloud obtained by a detection and ranging sensor
CN114067224A (en) Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion
CN111340855A (en) Road moving target detection method based on track prediction
US20210166085A1 (en) Object Classification Method, Object Classification Circuit, Motor Vehicle
CN111353450A (en) Target identification system and method based on heterogeneous electromagnetic perception information fusion
CN111126504A (en) Multi-source incomplete information fusion image target classification method
CN117495891B (en) Point cloud edge detection method and device and electronic equipment
CN112198878A (en) Instant map construction method and device, robot and storage medium
CN114973195A (en) Vehicle tracking method, device and system based on multi-information fusion
CN111007871A (en) Unmanned aerial vehicle dynamic feature identification method, medium, equipment and device
CN107273914B (en) Efficient fusion identification method based on information source self-adaptive dynamic selection
CN117456480A (en) Light vehicle re-identification method based on multi-source information fusion
CN113065395A (en) Radar target new class detection method based on generation countermeasure network
CN109977763B (en) Aerial small target identification method based on improved evidence trust
CN113065604B (en) Air target grouping method based on DTW-DBSCAN algorithm
CN111858816B (en) Method and system for improving track association efficiency of single monitoring source and multiple monitoring sources
CN110488259B (en) Radar target classification method and device based on GDBSCAN
CN116194803A (en) Method for fusing environment-related parameters
CN113673105A (en) Design method of true value comparison strategy
CN113837270B (en) Target identification method, device, equipment and storage medium
CN112257750B (en) Distributed fusion system for composite detection node
CN116168543B (en) Vehicle track correction method and device based on millimeter wave radar and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination