CN111679257A - Light and small unmanned aerial vehicle target identification method and device based on radar detection data - Google Patents

Light and small unmanned aerial vehicle target identification method and device based on radar detection data Download PDF

Info

Publication number
CN111679257A
CN111679257A CN201911394547.3A CN201911394547A CN111679257A CN 111679257 A CN111679257 A CN 111679257A CN 201911394547 A CN201911394547 A CN 201911394547A CN 111679257 A CN111679257 A CN 111679257A
Authority
CN
China
Prior art keywords
target
unmanned aerial
aerial vehicle
light
detection data
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.)
Granted
Application number
CN201911394547.3A
Other languages
Chinese (zh)
Other versions
CN111679257B (en
Inventor
夏鹏辉
何志峰
周自立
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.)
709th Research Institute of CSIC
China State Shipbuilding Corp Ltd
Original Assignee
709th Research Institute of CSIC
China State Shipbuilding Corp Ltd
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 709th Research Institute of CSIC, China State Shipbuilding Corp Ltd filed Critical 709th Research Institute of CSIC
Priority to CN201911394547.3A priority Critical patent/CN111679257B/en
Publication of CN111679257A publication Critical patent/CN111679257A/en
Application granted granted Critical
Publication of CN111679257B publication Critical patent/CN111679257B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/211—Selection of the most significant subset of features
    • G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses a method and a device for identifying a target of a small light unmanned aerial vehicle based on radar detection data, wherein the method comprises the following steps: establishing a database of the small and light unmanned aerial vehicle, and discretizing the flight speed range and the height range information in a table form; acquiring detection data of two adjacent periods of a radar, preliminarily screening detected targets according to a database of the light and small unmanned aerial vehicle, formulating a fuzzy rule according to experience, quantifying the possibility of the light and small unmanned aerial vehicle targets in each grid interval, generating corresponding confidence factors for the screened targets, and then taking the confidence factors and the state information of the targets as the characteristics of the targets; and classifying through a classifier based on a BP neural network, and finally realizing the identification of the light and small unmanned aerial vehicle target based on radar detection data. In the unmanned aerial vehicle prevention and control system based on radar detection, the detection recognition rate of the light and small unmanned aerial vehicle can be improved, and the false alarm rate of the system can be reduced.

Description

Light and small unmanned aerial vehicle target identification method and device based on radar detection data
Technical Field
The invention belongs to the field of radar target detection and classification, and relates to a method and a device for identifying a light and small unmanned aerial vehicle target based on radar detection data, which improve the detection identification rate of the light and small unmanned aerial vehicle.
Background
Light unmanned aerial vehicle belongs to a typical "low slow little" target, and traditional radar detection equipment is difficult to deal with. With the rise of the consumer-grade unmanned aerial vehicle industry, various unmanned aerial vehicle ' black flight ' events emerge endlessly, great hidden dangers are caused to air transportation and social public safety, and therefore the unmanned aerial vehicle's detection and identification method has great significance for effective detection and identification of light and small unmanned aerial vehicles.
Under the continuous efforts of researchers of all parties, some radar manufacturers and research institutions realize the successful detection of the low-slow small type target, but the problem of how to effectively distinguish the type of the target according to limited data to extract the light and small unmanned aerial vehicle target still exists universally. The specific difficulties are as follows:
1) objects such as birds, kites, balloons and the like possibly existing in the air also have the characteristic of low-slow small targets, and the objects are easily confused with light and small unmanned planes for radars;
2) the target data detected by radar is very limited and difficult to exploit to characterize different target types.
Disclosure of Invention
In order to solve the problem of high false alarm rate of radar detection, the invention provides a method for identifying a target of a small-sized light unmanned aerial vehicle based on radar detection data.
In a first aspect of the invention, a method for identifying a target of a small light unmanned aerial vehicle based on radar detection data is disclosed, and the method comprises the following steps:
s1, establishing a motion characteristic library of the small light unmanned aerial vehicle, and discretizing motion characteristic data in a table form;
s2, acquiring detection data of two adjacent periods of the radar, and primarily screening the radar detection data according to the data of the motion characteristic library of the small and light unmanned aerial vehicle;
s3, acquiring target states according to the detection data of two adjacent periods, formulating a fuzzy rule according to experience, quantifying the possibility of the light and small unmanned aerial vehicle target in each grid interval, and generating a confidence factor for the screened target according to the fuzzy rule based on the target states;
s4, taking the target state and the confidence factor corresponding to the target state as the input of a classifier of the BP neural network, and outputting the judgment result of whether the target is the small unmanned aerial vehicle;
s5, if the type of the target output by the classifier is a light small unmanned aerial vehicle, reporting the target to the system; and if the classification result output by the classifier is not the light small unmanned aerial vehicle, acquiring the detection data of the current target in two subsequent periods again, repeating the steps S3-S4, and if the judgment of the target of the non-light small unmanned aerial vehicle is still obtained, rejecting the target.
Preferably, in step S1, the motion characteristics in the motion characteristic library of the light and small unmanned aerial vehicle specifically include flight speed range and altitude range information.
Preferably, in step S2, the radar detection result is expressed by: distance s, azimuth of target detected by radar
Figure BDA0002345931800000021
The height h is the basic data, and the feature vector is formed
Figure BDA0002345931800000022
To indicate radar detection results at any one time.
Preferably, the step S2 is specifically: acquiring detection results P of the radar at the t moment and the t +1 momenttAnd Pt+1According to the high or speed range in the light small unmanned aerial vehicle motion characteristic library, the detection result is preliminarily screened, and the rule is as follows:
1) entering the next processing step for the target within the range;
2) if the target is not in the range, acquiring detection data of two subsequent periods again, and if the target is not in the range for a plurality of periods, rejecting the target;
preferably, in step S3, the obtaining of the target state according to the detection data of two adjacent cycles specifically includes:
according to the detection data of two adjacent periods, the horizontal speed v of the target is obtainedhAnd a vertical velocity vvThe formula is as follows:
Figure BDA0002345931800000031
wherein s ist、st+1The distances of the targets at the time t and t +1, ht、ht+1The heights of the targets at the moments T and T +1, T is the radar detection period, and v is considered to behAnd vvState information for the target at time t +1, and forming the target state
Figure BDA0002345931800000032
In a second aspect of the present invention, a device for identifying a target of a small light unmanned aerial vehicle based on radar detection data is disclosed, the device comprising:
the characteristic library module: establishing a motion characteristic library of the small and light unmanned aerial vehicle, and discretizing motion characteristic data in a table form;
a screening module: acquiring detection data of two adjacent periods of a radar, and screening the radar detection data according to the data of the motion characteristic library of the small and light unmanned aerial vehicle to acquire a target state;
a quantization module: formulating a fuzzy rule according to experience, quantifying the possibility of the light and small unmanned aerial vehicle target in each table interval, and generating a confidence factor for the screened target according to the fuzzy rule based on the target state;
a classification module: constructing a classifier based on a BP neural network, taking the target state and a confidence factor corresponding to the target state as the input of the neural network, and outputting a judgment result of whether the target is the small unmanned aerial vehicle;
a reclassification module: if the type of the target output by the classifier in the classification module is a light small unmanned aerial vehicle, reporting the target to the system; and if the classification result output by the classifier is not the light small unmanned aerial vehicle, acquiring the detection data of the current target in a plurality of subsequent periods again, recalculating the target state, generating a confidence factor and inputting the confidence factor into the classifier, and if the judgment of the target of the non-light small unmanned aerial vehicle is still obtained, rejecting the target.
Preferably, in the feature library module, the motion features in the motion feature library of the light and small unmanned aerial vehicle specifically include flight speed range and altitude range information.
Preferably, in the screening module, the radar detection result is expressed in the following manner: distance s, azimuth of target detected by radar
Figure BDA0002345931800000033
The height h is the basic data, and the feature vector is formed
Figure BDA0002345931800000034
To indicate radar detection results at any one time.
Preferably, the screening module specifically includes:
target preliminary screening unit: acquiring detection results P of the radar at the t moment and the t +1 momenttAnd Pt+1According to the high or speed range in the light small unmanned aerial vehicle motion characteristic library, the detection result is preliminarily screened, and the rule is as follows:
1) entering the next processing step for the target within the range;
2) if the target is not in the range, acquiring detection data of two subsequent periods again, and if the target is not in the range for a plurality of periods, rejecting the target;
a target state calculation unit: for the target which is screened by the primary screening unit and meets the condition of entering the next processing step, the horizontal velocity v of the target is calculatedhAnd a vertical velocity vvThe formula is as follows:
Figure BDA0002345931800000041
wherein s ist、st+1The distances of the targets at the time t and t +1, ht、ht+1The heights of the targets at the moments T and T +1, T is the radar detection period, and v is considered to behAnd vvState information for the target at time t +1, and forming the target state
Figure BDA0002345931800000042
A confidence factor generation unit: and generating a confidence factor for the target according to the fuzzy rule based on the target state.
The invention provides a method and a device for identifying a target of a light and small unmanned aerial vehicle based on radar detection data, wherein a motion characteristic library of the light and small unmanned aerial vehicle is established, the detection data of two adjacent periods are preliminarily screened through the motion characteristic library of the light and small unmanned aerial vehicle, the target speed range and height range information of the light and small unmanned aerial vehicle are discretized in a table form, a confidence factor is generated for the screened target according to a fuzzy rule, the obtained confidence factor is used as a part of target characteristics, and finally the target of the light and small unmanned aerial vehicle is correctly identified through the processing of a BP neural network classifier. In the unmanned aerial vehicle prevention and control system based on radar detection, the detection recognition rate of the light and small unmanned aerial vehicle can be improved, and the false alarm rate of the system can be reduced.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the technical description of the present invention will be briefly introduced below, and it is apparent 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 inventive labor.
Fig. 1 is a schematic flow chart of a method for identifying a target of a small-sized light unmanned aerial vehicle based on radar detection data according to an embodiment of the present invention;
fig. 2 is a schematic diagram of discretizing a target speed range and a height range in a table form and generating a confidence factor for each interval according to a fuzzy rule according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a light and small unmanned aerial vehicle target recognition device based on radar detection data according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a method for identifying a target of a small-sized light unmanned aerial vehicle based on radar detection data, where the method includes:
s1, establishing a motion characteristic library of the small light unmanned aerial vehicle, and discretizing motion characteristic data in a table form;
further, the motion characteristics in the motion characteristic library of the light and small unmanned aerial vehicles specifically comprise flight speed range [ v [ ]min,vmax]Height range information [ h ]min,hmax]And then discretizing the data of the two dimensions of speed and height in a table form to form closed grid intervals.
Fig. 1 is a schematic diagram of a method for identifying a target of a small and light unmanned aerial vehicle based on radar detection data, which corresponds to the following steps S2-S5.
S2, acquiring detection data of two adjacent periods of the radar, and screening the detection data of the radar according to the data of the motion characteristic library of the small and light unmanned aerial vehicle;
further, the radar detection result is represented by: distance s, azimuth of target detected by radar
Figure BDA0002345931800000061
The height h is the basic data, and the feature vector is formed
Figure BDA0002345931800000062
To indicate radar detection results at any one time.
Further, the step S2 is specifically:
acquiring detection results P of the radar at the t moment and the t +1 momenttAnd Pt+1According to the high or speed range in the light small unmanned aerial vehicle motion characteristic library, the detection result is preliminarily screened, and the rule is as follows:
1) entering the next processing step for the target within the range;
2) if the target is not in the range, acquiring detection data of two subsequent periods again, and if the target is not in the range for a plurality of periods, rejecting the target;
s3, acquiring a target state according to the detection data of two adjacent periods, formulating a fuzzy rule according to experience, quantifying the possibility of the light and small unmanned aerial vehicle target in each grid interval, and generating a confidence factor for the screened target;
further, in step S3, the obtaining of the target state according to the detection data of two adjacent cycles specifically includes:
according to the detection data of two adjacent periods, the horizontal velocity v of the screened target is obtainedhAnd a vertical velocity vvThe formula is as follows:
Figure BDA0002345931800000063
wherein s ist、st+1The distances of the targets at the time t and t +1, ht、ht+1Are respectively provided withThe height of the target at T and T +1, T is radar detection period, consider vhAnd vvState information for the target at time t +1, and forming the target state
Figure BDA0002345931800000064
Specifically, a fuzzy rule is formulated according to experience, the probability of the target of the small unmanned aerial vehicle in each grid interval is quantified, a confidence factor theta is recorded, the range is [0,1 ], and the definition of the theta value follows the fuzzy rule: the target flies at a general speed, altitude, the larger θ and vice versa. Referring to fig. 2, fig. 2 is a schematic diagram illustrating discretization of target speed ranges and altitude ranges in a table form, and generating a confidence factor for each interval according to a fuzzy rule, where θ ═ f (h, v), where f (·) represents a fuzzy rule, and roughly determines the possibility of belonging to the unmanned aerial vehicle target according to target flight altitude information h and speed information v.
S4, setting the target state
Figure BDA0002345931800000071
The confidence factor theta corresponding to the confidence factor theta is used as the input of a classifier of the BP neural network, and the judgment result of whether the target is the light small unmanned aerial vehicle or not is output;
specifically, a classifier based on the BP neural network is constructed, and the classifier does not need strong generalization capability in design. The target state
Figure BDA0002345931800000072
And the confidence factor theta corresponding to the unmanned aerial vehicle target is used as the characteristic of the unmanned aerial vehicle target, the characteristic is input into the classifier, and the light and small unmanned aerial vehicle target is identified through the classifier.
S5, if the classifier outputs that the target type is the light and small unmanned aerial vehicle in the step S4, reporting the target to the system; and if the classification result output by the classifier is not the light small unmanned aerial vehicle, acquiring the detection data of the current target in two subsequent periods again, repeating the steps S3-S4, and if the judgment of the target of the non-light small unmanned aerial vehicle is still obtained, rejecting the target.
Referring to fig. 3, the present invention provides a target identification apparatus for a small and light unmanned aerial vehicle based on radar detection data, the apparatus includes:
feature library module 310: establishing a motion characteristic library of the small and light unmanned aerial vehicle, and discretizing motion characteristic data in a table form;
further, in the feature library module 310, the motion features in the motion feature library of the light small unmanned aerial vehicle specifically include flight speed range and altitude range information.
The screening module 320: acquiring detection data of two adjacent periods of a radar, and primarily screening the radar detection data according to the data of the motion characteristic library of the small and light unmanned aerial vehicle to acquire the target state of a screened target;
further, in the screening module 320, the radar detection result is represented by: distance s, azimuth of target detected by radar
Figure BDA0002345931800000073
The height h is the basic data, and the feature vector is formed
Figure BDA0002345931800000074
To indicate radar detection results at any one time.
Further, the screening module 320 specifically includes:
target preliminary screening unit 3201: acquiring detection results P of the radar at the t moment and the t +1 momenttAnd Pt+1According to the high or speed range in the light small unmanned aerial vehicle motion characteristic library, the detection result is preliminarily screened, and the rule is as follows:
1) entering the next processing step for the target within the range;
2) if the target is not in the range, acquiring detection data of two subsequent periods again, and if the target is not in the range for a plurality of periods, rejecting the target;
target state calculation unit 3202: according to the detection data of two adjacent periods, the horizontal speed v of the target is obtainedhAnd a vertical velocity vvThe formula is as follows:
Figure BDA0002345931800000081
wherein s ist、st+1The distances of the targets at the time t and t +1, ht、ht+1The heights of the targets at the moments T and T +1, T is the radar detection period, and v is considered to behAnd vvState information for the target at time t +1, and forming the target state
Figure BDA0002345931800000082
The quantization module 330: formulating a fuzzy rule according to experience, quantifying the possibility of the light and small unmanned aerial vehicle target in each table interval, and generating a confidence factor for the screened target according to the fuzzy rule based on the target state;
the classification module 340: constructing a classifier based on a BP neural network, taking the target state and a confidence factor corresponding to the target state as the input of the neural network, and outputting a judgment result of whether the target is the small unmanned aerial vehicle;
the reclassification module 350: if the type of the target output by the classifier in the classification module is a light small unmanned aerial vehicle, reporting the target to the system; and if the classification result output by the classifier is not the light small unmanned aerial vehicle, acquiring the detection data of the current target in a plurality of subsequent periods again, recalculating the target state, generating a confidence factor and inputting the confidence factor into the classifier, and if the judgment of the target of the non-light small unmanned aerial vehicle is still obtained, rejecting the target.
The above apparatus embodiments and method embodiments are in one-to-one correspondence, and reference may be made to the method embodiments for a brief point of the apparatus embodiments. The method can be used in the process of detecting and discovering the light and small unmanned aerial vehicle by the radar, not only can provide a design idea for radar detection data processing software from an equipment level, but also can help improve the identification efficiency of the unmanned aerial vehicle, reduce resource waste and the like in a system level (such as an unmanned aerial vehicle prevention and control system containing radar equipment).
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in random access memory, read only memory, electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (9)

1. A target identification method of a light and small unmanned aerial vehicle based on radar detection data is characterized by comprising the following steps:
s1, establishing a motion characteristic library of the small light unmanned aerial vehicle, and discretizing motion characteristic data in a table form;
s2, acquiring detection data of two adjacent periods of the radar, and primarily screening the radar detection data according to the data of the motion characteristic library of the small and light unmanned aerial vehicle;
s3, acquiring target states according to the detection data of two adjacent periods, formulating a fuzzy rule according to experience, quantifying the possibility of the light and small unmanned aerial vehicle target in each grid interval, and generating a confidence factor for the screened target according to the fuzzy rule based on the target states;
s4, taking the target state and the confidence factor corresponding to the target state as the input of a classifier of the BP neural network, and outputting the judgment result of whether the target is the small unmanned aerial vehicle;
s5, if the type of the target output by the classifier is a light small unmanned aerial vehicle, reporting the target to the system; and if the classification result output by the classifier is not the light small unmanned aerial vehicle, acquiring the detection data of the current target in two subsequent periods again, repeating the steps S3-S4, and if the judgment of the target of the non-light small unmanned aerial vehicle is still obtained, rejecting the target.
2. The method for light drone target identification based on radar detection data of claim 1, wherein in step S1, the motion features in the light drone motion feature library specifically include flight speed range and altitude range information.
3. The method for identifying the target of the small and light unmanned aerial vehicle based on the radar detection data as claimed in claim 1, wherein in the step S2, the radar detection result is represented by: distance s, azimuth of target detected by radar
Figure FDA0002345931790000011
The height h is the basic data, and the feature vector is formed
Figure FDA0002345931790000012
To express asRadar detection results at a time.
4. The method for identifying the target of the small and light unmanned aerial vehicle based on the radar detection data as claimed in claim 3, wherein the step S2 is specifically as follows:
acquiring detection results P of the radar at the t moment and the t +1 momenttAnd Pt+1According to the high or speed range in the light small unmanned aerial vehicle motion characteristic library, the detection result is preliminarily screened, and the rule is as follows:
1) entering the next processing step for the target within the range;
2) and if the target is not in the range, acquiring the detection data of the two subsequent periods again, and if the target is not in the range for a plurality of periods, rejecting the target.
5. The method for identifying the target of the small and light unmanned aerial vehicle based on the radar detection data as claimed in claim 4, wherein in the step S3, the obtaining the target state according to the detection data of two adjacent cycles specifically includes:
according to the detection data of two adjacent periods, the horizontal velocity v of the screened target is obtainedhAnd a vertical velocity vvThe formula is as follows:
Figure FDA0002345931790000021
wherein s ist、st+1The distances of the targets at the time t and t +1, ht、ht+1The heights of the targets at the moments T and T +1, T is the radar detection period, and v is considered to behAnd vvIs the state information of the target at the time t +1 and constitutes the target state
Figure FDA0002345931790000022
6. A light unmanned aerial vehicle target identification device based on radar detection data, its characterized in that, the device includes:
the characteristic library module: establishing a motion characteristic library of the small and light unmanned aerial vehicle, and discretizing motion characteristic data in a table form;
a screening module: acquiring detection data of two adjacent periods of a radar, and screening the radar detection data according to the data of the motion characteristic library of the small and light unmanned aerial vehicle to acquire a target state;
a quantization module: formulating a fuzzy rule according to experience, quantifying the possibility of the target of the small-sized light unmanned aerial vehicle in each grid interval, and generating a confidence factor for the screened target according to the fuzzy rule based on the target state;
a classification module: constructing a classifier based on a BP neural network, taking the target state and a confidence factor corresponding to the target state as the input of the neural network, and outputting a judgment result of whether the target is the small unmanned aerial vehicle;
a reclassification module: if the type of the target output by the classifier in the classification module is a light small unmanned aerial vehicle, reporting the target to the system; and if the classification result output by the classifier is not the light small unmanned aerial vehicle, acquiring the detection data of the current target in a plurality of subsequent periods again, recalculating the target state, generating a confidence factor and inputting the confidence factor into the classifier, and if the judgment of the target of the non-light small unmanned aerial vehicle is still obtained, rejecting the target.
7. The device for light unmanned aerial vehicle target recognition based on radar detection data as claimed in claim 6, wherein in the feature library module, the motion features in the motion feature library of the light unmanned aerial vehicle specifically include flight speed range and altitude range information.
8. The device for identifying the target of the unmanned aerial vehicle based on the radar detection data as claimed in claim 6, wherein in the screening module, the radar detection result is expressed by: distance s, azimuth of target detected by radar
Figure FDA0002345931790000031
The height h is the basic data, and the feature vector is formed
Figure FDA0002345931790000032
To indicate radar detection results at any one time.
9. The device for identifying the target of the small and light unmanned aerial vehicle based on the radar detection data as claimed in claim 8, wherein the screening module specifically comprises:
target preliminary screening unit: acquiring detection results P of the radar at the t moment and the t +1 momenttAnd Pt+1According to the high or speed range in the light small unmanned aerial vehicle motion characteristic library, the detection result is preliminarily screened, and the rule is as follows:
1) entering the next processing step for the target within the range;
2) if the target is not in the range, acquiring detection data of two subsequent periods again, and if the target is not in the range for a plurality of periods, rejecting the target;
a target state calculation unit: according to the detection data of two adjacent periods, the horizontal speed v of the target is obtainedhAnd a vertical velocity vvThe formula is as follows:
Figure FDA0002345931790000033
wherein s ist、st+1The distances of the targets at the time t and t +1, ht、ht+1The heights of the targets at the moments T and T +1, T is the radar detection period, and v is considered to behAnd vvState information for the target at time t +1, and forming the target state
Figure FDA0002345931790000034
CN201911394547.3A 2019-12-30 2019-12-30 Target recognition method and device for light unmanned aerial vehicle based on radar detection data Active CN111679257B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911394547.3A CN111679257B (en) 2019-12-30 2019-12-30 Target recognition method and device for light unmanned aerial vehicle based on radar detection data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911394547.3A CN111679257B (en) 2019-12-30 2019-12-30 Target recognition method and device for light unmanned aerial vehicle based on radar detection data

Publications (2)

Publication Number Publication Date
CN111679257A true CN111679257A (en) 2020-09-18
CN111679257B CN111679257B (en) 2023-05-23

Family

ID=72451244

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911394547.3A Active CN111679257B (en) 2019-12-30 2019-12-30 Target recognition method and device for light unmanned aerial vehicle based on radar detection data

Country Status (1)

Country Link
CN (1) CN111679257B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106546975A (en) * 2016-10-14 2017-03-29 中国民航科学技术研究院 A kind of small-sized unmanned plane based on radar data and flying bird classifying identification method
JP2017159750A (en) * 2016-03-08 2017-09-14 国立大学法人京都大学 Unmanned aircraft position estimation method and system
WO2018237204A1 (en) * 2017-06-21 2018-12-27 Airspace Systems Inc. System and method for broadcasting the location of low altitude objects
CN109815773A (en) * 2017-11-21 2019-05-28 北京航空航天大学 A kind of low slow small aircraft detection method of view-based access control model
GB201905256D0 (en) * 2019-04-12 2019-05-29 Rinicom Ltd Object classificaytion
CN110398720A (en) * 2019-08-21 2019-11-01 深圳耐杰电子技术有限公司 A kind of anti-unmanned plane detection tracking interference system and photoelectric follow-up working method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017159750A (en) * 2016-03-08 2017-09-14 国立大学法人京都大学 Unmanned aircraft position estimation method and system
CN106546975A (en) * 2016-10-14 2017-03-29 中国民航科学技术研究院 A kind of small-sized unmanned plane based on radar data and flying bird classifying identification method
WO2018237204A1 (en) * 2017-06-21 2018-12-27 Airspace Systems Inc. System and method for broadcasting the location of low altitude objects
CN109815773A (en) * 2017-11-21 2019-05-28 北京航空航天大学 A kind of low slow small aircraft detection method of view-based access control model
GB201905256D0 (en) * 2019-04-12 2019-05-29 Rinicom Ltd Object classificaytion
CN110398720A (en) * 2019-08-21 2019-11-01 深圳耐杰电子技术有限公司 A kind of anti-unmanned plane detection tracking interference system and photoelectric follow-up working method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
YANG F等: "DDMA MIMO radar system for low, slow, and small target detection", 《THE JOURNAL OF ENGINEERING》 *
王伟等: "基于形状特征辅助的低慢小目标检测与跟踪算法", 《第十二届全国信号和智能信息处理与应用学术会议论文集》 *
程士广: "无人机自动起飞/着陆的控制技术研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 *

Also Published As

Publication number Publication date
CN111679257B (en) 2023-05-23

Similar Documents

Publication Publication Date Title
Li et al. Adaptively constrained dynamic time warping for time series classification and clustering
Xiao et al. A target detection model based on improved tiny-yolov3 under the environment of mining truck
Huttunen et al. Car type recognition with deep neural networks
Wan et al. UAV swarm based radar signal sorting via multi-source data fusion: A deep transfer learning framework
CN105447459A (en) Unmanned plane automation detection target and tracking method
CN108710114B (en) Turbulent target detection method based on BP neural network multi-class classification
Park et al. Wildfire smoke detection using spatiotemporal bag-of-features of smoke
Huang et al. Ship target detection based on improved YOLO network
Mozaffari et al. Convergent heterogeneous particle swarm optimisation algorithm for multilevel image thresholding segmentation
Park et al. Smoke detection in ship engine rooms based on video images
Pullakandam et al. Weapon object detection using quantized yolov8
Mou et al. Structured behaviour prediction of on‐road vehicles via deep forest
Valaboju et al. Drone detection and classification using computer vision
Lim et al. Practically classifying unmanned aerial vehicles sound Using convolutional neural networks
CN111679257A (en) Light and small unmanned aerial vehicle target identification method and device based on radar detection data
Tsetsos et al. A forest fire detection system: The Meleager approach
Lim et al. Detection of salient regions in crowded scenes
CN117152486A (en) Image countermeasure sample detection method based on interpretability
Siddiqui et al. Towards efficient vehicle classification in intelligent transportation systems
Tiwari et al. Detection of Camouflaged Drones using Computer Vision and Deep Learning Techniques
Wu et al. Research on asphalt pavement disease detection based on improved YOLOv5s
Hu et al. Statistical analysis of massive AIS trajectories using Gaussian mixture models
CN113466798B (en) Sea surface small target detection method based on polarized signal multi-scale entropy characteristics
CN115457414A (en) Unmanned aerial vehicle abnormal behavior identification method based on improved residual error network
Khan et al. Translearn-yolox: Improved-yolo with transfer learning for fast and accurate multiclass uav detection

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
GR01 Patent grant
GR01 Patent grant