KR102159197B1 - Radar sensor payload for small uav, remote processing device, detection system and method of detecting target using the same - Google Patents

Abstract

Disclosed are a radar sensor payload for a small unmanned aerial vehicle, a remote processing unit, a detection system, and a detection method of a target using the same, capable of realizing a distributed cooperative radar sensor by multi-operation of a plurality of small unmanned aerial vehicles. According to one embodiment of the present invention, the detection system comprises: a radar reception data acquisition unit which includes a plurality of small unmanned aerial vehicles and acquires radar reception data for a target through the plurality of small unmanned aerial vehicles; and a remote processing unit which is connected to the plurality of small unmanned aerial vehicles through a network, generates a control signal for controlling at least one of a formation and a beam waveform for the plurality of small unmanned aerial vehicles to transmit the control signal to the plurality of small unmanned aerial vehicles, receives the radar reception data from the plurality of small unmanned aerial vehicles, and generates an image for the target based on the radar reception data.

Description

Radar sensor payload for small unmanned aerial vehicles, remote processing unit, detection system, and object detection method using the same {RADAR SENSOR PAYLOAD FOR SMALL UAV, REMOTE PROCESSING DEVICE, DETECTION SYSTEM AND METHOD OF DETECTING TARGET USING THE SAME}

The present invention relates to a radar sensor loading body for a small unmanned aerial vehicle, a remote processing unit, a detection system, and a method of detecting an object using the same.

In general, a drone is a generic term for an unmanned aerial vehicle (UAV) or an uninhabited aerial vehicle (UAV) that can fly and manipulate by induction of radio waves. Drones are for military use and are used as targets for practice shooting or for reconnaissance, surveillance and anti-submarine attacks.

Military drones have partially replaced the mission area of manned aircraft by increasing their size and performance, and each country is currently researching a combat system capable of simultaneous operation of manned and unmanned fighters based on network-centric warfare. Drones are equipped with network-based real-time big data collection, hyper-connectivity for use, artificial intelligence-based autonomous flight, super-functionality such as the emergence of future drones through operational management, and convergence and complex features such as sensors and mission equipment that respond to various demands. Have.

In order to detect an object (eg, a person, a building, an aircraft, etc.), equipment such as a camera, a thermal imager, an infrared camera, etc. is installed on the drone. In addition, mine detection equipment is mounted on the drone to detect objects such as land mines. In this way, according to the target of the object to be detected, a corresponding device may be mounted on the drone.

However, according to the target of the object (target) to be detected, equipment corresponding thereto must be mounted on the drone, so there is an inconvenience in that the equipment mounted on the drone must be changed whenever the target of the object is changed. In addition, since one or a small-scale drone is used to detect an object, there are many restrictions on the operation method, and thus, there is a problem in that the utility and versatility are poor. Moreover, since imaging equipment such as a camera is used to detect an object, there is a limit to visually confirming the object, and in the case of a radar sensor that can detect and acquire images even in a non-visible area, there is a limit to mounting on a small drone. There is a problem.

The present invention is equipped with a radar sensor for each of a plurality of small unmanned aerial vehicles (e.g., drones, etc.), and a radar sensor loading body for a small unmanned aerial vehicle capable of implementing a distributed cooperative radar sensor by multi-operation of a plurality of small unmanned aerial vehicles, a remote processing unit , A detection system and a method for detecting an object using the same can be provided.

In addition, the present invention acquires radar data for an object using radar sensors mounted on each of a plurality of small unmanned aerial vehicles, and uses the obtained radar data to detect an object, a radar sensor payload for a small unmanned aerial vehicle, a remote processing unit, a detection system, and A method of detecting an object using this can be provided.

According to an embodiment of the present invention, a detection system may be disclosed. A detection system according to an embodiment includes: a radar reception data acquisition unit including a plurality of small UAVs and acquiring radar reception data for an object through the plurality of UAVs; And generating a control signal for controlling at least one of a large or beam waveform for the plurality of small UAVs connected to the plurality of small UAVs through a network, and transmitting them to the plurality of small UAVs, and the plurality of small UAVs. And a remote processing unit configured to receive the radar reception data from and to generate an image of the object based on the radar reception data.

In an embodiment, the plurality of small UAVs includes a plurality of drones, and each of the plurality of drones radiates a beam to the object and receives a beam reflected from the object to obtain radar reception data for the object. can do.

In one embodiment, the radar reception data acquisition unit includes a distributed cooperative radar sensor implemented by multi-operating a plurality of drones, and a radar signal transmitted from the distributed cooperative radar sensor to an object and reflected from the object is distributed cooperative type. It can be received by all radar sensors included in the radar sensor.

In an embodiment, the plurality of drones may determine a location corresponding to the formation based on the control signal.

In an embodiment, the plurality of drones may generate the beams corresponding to the beam waveforms based on the control signal.

In an embodiment, the plurality of drones may communicate with each other to change the beam waveform according to the position and characteristic of each of the plurality of drones.

In an embodiment, the control signal may further include a signal for moving the plurality of small UAVs to a location where the object is located.

In an embodiment, the control signal may further include a signal for changing at least one of the large size or the beam waveform for the plurality of small UAVs.

In an embodiment, the remote processor may process the radar received data to identify the object and the clutter, and classify the object and the clutter to generate an image of the object.

In an embodiment, the remote processing unit may apply the radar received data to an artificial intelligence algorithm for classifying the object and the clutter.

In one embodiment, the detection system is connected to the remote processing unit through the network, and updates the artificial intelligence algorithm by using the radar received data provided from the remote processing unit for artificial intelligence learning, and the updated It may further include an artificial intelligence server that provides the artificial intelligence algorithm to the remote processing unit.

According to an embodiment of the present invention, a remote processing unit connected to a plurality of small UAVs through a network may be disclosed. According to an embodiment, the remote processing unit includes: a control signal generator for generating a control signal for controlling at least one of a large or beam waveform for the plurality of small UAVs; A communication module for transmitting the control signal to the plurality of small unmanned aerial vehicles and receiving radar reception data for an object from the plurality of small unmanned aerial vehicles; And a data processing unit that generates an image of the object based on the radar received data.

In an embodiment, the data processor may process the radar received data to identify the object and the clutter, and classify the object and the clutter to generate the image of the object.

In an embodiment, the data processor may apply the radar received data to an artificial intelligence algorithm for classifying the object and the clutter.

In an embodiment, the control signal may further include a signal for moving the plurality of small UAVs to a location where the object is located.

In an embodiment, the control signal may further include a signal for changing at least one of the large size or the beam waveform for the plurality of small UAVs.

According to an embodiment of the present invention, as a radar sensor mount for a small UAV, a plurality of small UAVs equipped with a radar sensor mount are multi-operated, and a distributed cooperative radar sensor is implemented using a plurality of small UAVs that are multi-operated. However, the radar signal radiated to the object and reflected from the object from any radar sensor included in the distributed cooperative radar sensor is received as detection data from another radar sensor included in the distributed cooperative radar sensor, and the distributed cooperative radar sensor It is possible to share information on acquired data by performing communication with other small UAVs within the multi-operated range.

According to an embodiment of the present invention, a method of detecting an object in a detection system including a plurality of small UAVs and a remote processing unit may be disclosed. A method according to an embodiment includes the steps of: generating a control signal for controlling at least one of a large size or a beam waveform for the plurality of small UAVs, in the remote processing unit; Receiving the control signal from the remote processing unit in the plurality of small UAVs; Obtaining, from the plurality of small UAVs, radar reception data for the object based on the control signal; Receiving, at the remote processing unit, the radar reception data from the plurality of small unmanned aerial vehicles; And generating, at the remote processing unit, an image of the object based on the radar received data.

In an embodiment, the obtaining of radar reception data for the object comprises: transmitting a beam to the object based on the control signal; And receiving the beam reflected from the object to obtain the radar reception data for the object.

In an embodiment, acquiring radar reception data for the object may include determining a location corresponding to the formation based on the control signal.

In an embodiment, obtaining radar reception data for the object may include generating the beam corresponding to the beam waveform based on the control signal.

In one embodiment, the step of obtaining radar reception data for the object further comprises performing communication between the plurality of small UAVs and varying the beam waveform according to the positions and characteristics of each of the plurality of small UAVs. can do.

In an embodiment, the generating of the image of the object comprises: identifying the object and the clutter by processing the radar received data; And generating an image of the object by classifying the object and the clutter.

In an embodiment, the step of processing the radar received data to identify the object and the clutter may include applying the radar received data to an artificial intelligence algorithm for classifying the object and the clutter. have.

In an embodiment, the method includes: updating the artificial intelligence algorithm by using the radar received data for artificial intelligence learning, in an artificial intelligence server of the detection system; And providing, in the artificial intelligence server, the updated artificial intelligence algorithm to the remote processing unit.

According to various embodiments of the present invention, a radar sensor is mounted on each of a plurality of small unmanned aerial vehicles (e.g., drones, etc.), and a distributed cooperative radar sensor is implemented by multi-operation of a plurality of small unmanned aerial vehicles. For example, compared to a camera, a thermal imaging camera, an infrared camera, etc.), an invisible area that cannot be visually identified by a human may be detected.

In addition, by configuring a distributed cooperative radar sensor using a plurality of small unmanned aerial vehicles, not only the detection distance is improved compared to individual radar sensors, but also images with improved quality are displayed using the radar reception data acquired through the distributed cooperative radar sensor. Can provide.

In addition, by using a plurality of small UAVs, in situations such as power shortage and errors (for example, errors) of some small UAVs, a continuous detection mission may be performed using an alternative small UAV.

In addition, since the order of a plurality of small UAVs can be changed, various antenna beamforming is possible, and an object to be detected can be checked at various times, so that various information of the object can be obtained, as well as Since the waveform can be set differently for each radar sensor, the detection rate of the object can be increased.

In addition, since various information of an object can be used as data for artificial intelligence learning that requires a lot of data, the performance of the artificial intelligence can be improved, and the detection rate of the object can be increased through this.

Moreover, it can be used to detect areas and objects that are difficult to identify by humans, such as mobile surveillance and reconnaissance, inaccessible area detection, hazardous area detection, and land mine detection.

1 is a schematic diagram of a detection system according to an embodiment of the present invention.
2A to 2C are exemplary views showing the large size of a plurality of drones according to an embodiment of the present invention.
3A to 3C are exemplary views showing beam waveforms of a plurality of drones according to an embodiment of the present invention.
4 is a flowchart illustrating a method of detecting an object according to an embodiment of the present invention.
5 is an exemplary view showing an example of obtaining radar reception data for an object from a plurality of drones according to an embodiment of the present invention.
6 is an exemplary view showing composite data obtained by synthesizing radar reception data obtained from a plurality of drones according to an embodiment of the present invention.
7 is an exemplary view showing an image of an object according to an embodiment of the present invention.

Embodiments of the present invention are illustrated for the purpose of describing the technical idea of the present invention. The scope of the rights according to the present invention is not limited to the embodiments presented below or the detailed description of these embodiments.

All technical terms and scientific terms used in the present invention have meanings generally understood by those of ordinary skill in the art, unless otherwise defined. All terms used in the present invention are selected for the purpose of describing the present invention more clearly, and are not selected to limit the scope of the present invention.

Expressions such as "comprising", "having", "having" and the like used in the present invention are open terms that imply the possibility of including other embodiments unless otherwise stated in the phrase or sentence in which the expression is included. It should be understood as (open-ended terms).

The expression of the singular form described in the present invention may include the meaning of the plural, unless otherwise stated, and this applies equally to the expression of the singular form described in the claims.

Expressions such as "first" and "second" used in the present invention are used to distinguish a plurality of elements from each other, and do not limit the order or importance of the elements.

The term "unit" used in the present invention refers to software or hardware components such as field-programmable gate array (FPGA) and application specific integrated circuit (ASIC). However, "unit" is not limited to hardware and software. The “unit” may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors. Thus, as an example, "unit" refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, Includes segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. Components and functions provided within "units" may be combined into a smaller number of components and "units" or separated into additional components and "units".

The expression "based on" as used in the present invention is used to describe one or more factors that influence the act or action of a decision judgment, which is described in a phrase or sentence in which the expression is included, and this expression However, additional factors that influence the behavior or behavior of judgment are not excluded.

In the present invention, when a component is referred to as being "connected" or "connected" to another component, a component can be directly connected to or can be connected to another component, or a new other component It is to be understood that it may or may be connected via an element.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, the same or corresponding elements are assigned the same reference numerals. In addition, in the description of the following embodiments, overlapping descriptions of the same or corresponding components may be omitted. However, even if description of a component is omitted, it is not intended that such component is not included in any embodiment.

1 is a schematic diagram of a detection system according to an embodiment of the present invention. Referring to FIG. 1, the detection system 100 may include a radar reception data acquisition unit 110 and a remote processing unit 120. In addition, the detection system 100 may include an artificial intelligence server 130. In one embodiment, the radar reception data acquisition unit 110 may be connected to the remote processing unit 120 through the network 140. In addition, the remote processing unit 120 may connect the network 140 to the artificial intelligence server 130.

The radar reception data acquisition unit 110 may acquire radar reception data for an object to be detected. For example, the object may include terrain, people, buildings, aircraft, land mines, etc., but is not limited thereto. In an embodiment, the radar reception data acquisition unit 110 may obtain radar reception data for the object by emitting a radar signal (ie, a radar beam) to the object and receiving a radar signal reflected from the object. In an embodiment, the radar reception data acquisition unit 110 may include a plurality of small UAVs. For example, a plurality of small UAVs may include a plurality of drones 112.

The plurality of drones 112 may set at least one of a large size or a beam waveform based on a control signal provided from the remote processing unit 120 and obtain radar reception data for an object. In one embodiment, the large size may mean a form in which a plurality of drones 112 are disposed on an object. For example, the large size may include a circular large size as shown in Fig. 2A, an elliptical large size as shown in Fig. 2B, and a rectangular large size as shown in Fig. 2C. However, the large size is not limited to a circular large size, an elliptical large size, and a rectangular large size, and may include various types of large sizes depending on the object.

In an embodiment, the plurality of drones 112 may communicate with each other based on a control signal provided from the remote processing unit 120 to determine a location corresponding to a large size.

In one embodiment, the beam waveform may be variously set for antenna beamforming for the plurality of drones 112 according to the object. As an example, the plurality of drones 112 may have a beam waveform (beam waveform 1 to beam waveform 9) as shown in FIG. 3A. As another example, the plurality of drones 112 may have a beam waveform (beam waveform A to beam waveform I) as shown in FIG. 3B. As another example, the plurality of drones 112 may have a beam waveform (beam waveform a to beam waveform i) as shown in FIG. 3C.

In one embodiment, the plurality of drones 112 may communicate with each other to change a beam waveform according to the location and characteristics of the drone. Accordingly, the detection rate of the object can be improved.

In one embodiment, the plurality of drones 112 may communicate with each other to transmit and receive information on the acquired radar reception data. That is, the plurality of drones 112 may share information on the acquired radar reception data.

In one embodiment, each of the plurality of drones 112 includes: a radar sensor mount (not shown) that transmits and receives radar signals and digitizes them and performs signal processing of the radar signals; A wireless communication payload (not shown) for performing wireless communication with the remote processing unit 120 through the network 140 and performing wireless communication between drones; An antenna mount (not shown) capable of emitting and receiving a radio signal (ie, a beam) carrying a radar waveform and a radio signal for radio communication; An auxiliary function loading body (not shown) capable of mounting a navigation device for identifying the location of the drone 112, an auxiliary sensor, and the like; And a payload fixing mechanism (not shown) for fixing a radar sensor payload, a wireless communication payload, an antenna payload, and an auxiliary function payload to the drone 112.

In one embodiment, a distributed cooperative radar sensor may be implemented by multi-operating a plurality of drones 112 on which a radar sensor mount is mounted. For example, the distributed cooperative radar sensor not only receives the radar signal reflected from the object by being radiated from the radar sensor of the corresponding drone 112, but also the radar signal reflected from the object by being emitted from the radar sensor of the other drone 112. Can receive. In this process, the radar reception data obtained from each of the plurality of drones 112 are synthesized to generate synthetic data, the object and the clutter are identified from the generated synthetic data, and the object is determined based on the identified object and the clutter. You can create an image.

In this process, multiple drones are multi-operated, and radar signals radiated from radar sensors mounted on each drone are received as detection data from each of the multiple drones that are multi-operated. Data information about the object is shared through communication at.

The remote processing unit 120 may generate a control signal for controlling the radar reception data acquisition unit 110. In an embodiment, the control signal may include a first control signal for moving the plurality of drones 112 to a location where an object to be detected is located. In one embodiment, the control signal is a second control signal for setting the size of the plurality of drones 112 moved to the place where the object is located or a third control for setting the beam waveforms of the plurality of drones 112 It may include at least one of the signals. For example, the third control signal may be a control signal for reconfiguring the antennas 310 (refer to FIG. 4) of each of the plurality of drones 112 for beamforming and beam transmission according to the size. In one embodiment, the control signal may include at least one of a fourth control signal for changing the formation of the plurality of drones 112 or a fifth control signal for changing the beam waveform of the plurality of drones 112. have.

The remote processing unit 120 transmits the generated control signal to the radar reception data acquisition unit 110 through the network 140, receives radar reception data from the radar reception data acquisition unit 110 through the network 140, and , By processing the received radar reception data, an image of the object may be generated.

In one embodiment, the remote processing unit 120 processes the received radar reception data to identify the object and the clutter to identify the object and the clutter, and classifies the identified object and the clutter to generate an image of the object. can do.

In an embodiment, the remote processing unit 120 may classify the object and the clutter by applying the radar received data to an artificial intelligence algorithm for classifying the object and the clutter. For example, the artificial intelligence algorithm may be an algorithm updated by the artificial intelligence server 130.

In one embodiment, the remote processing unit 120 generates a control signal generation unit (not shown) for generating a control signal for controlling at least one of a large or beam waveform for the plurality of drones 112, a plurality of control signals. A communication module (not shown) that transmits to the drone 112 of, and receives radar reception data for the object from the plurality of drones 112, and a data processing unit (shown) that generates an image of the object based on the radar received data. Not).

The artificial intelligence server 130 may be connected to the remote processing unit 120 through the network 140. The artificial intelligence server 130 may receive radar reception data from the remote processing unit 120, and update the artificial intelligence algorithm by using the received radar reception data for artificial intelligence learning. In one embodiment, the artificial intelligence server 130 performs singular point identification and comparison on the processing result of the radar received data using a singular point identification and comparison algorithm, and applies the singular point identification and comparison result to a learning algorithm. Algorithm can be updated. The artificial intelligence server 130 may transmit the updated artificial intelligence algorithm to the remote processing unit 120 through the network 140.

In one embodiment, the artificial intelligence server 130 stores a storage unit (not shown) that stores a beamforming condition and a processing result of radar reception data for each object, a singular point identification and comparison algorithm, and performs a singular point identification and comparison algorithm. A singular point identification and comparison algorithm processing unit (not shown) that performs singularity identification and comparison on the processing result of the radar received data, and the learning algorithm, and applies the singular point identification and comparison result to the learning algorithm to apply the artificial intelligence algorithm. It may include a learning algorithm processing unit (not shown) to update.

4 is a flowchart illustrating a method of detecting an object according to an embodiment of the present invention. Although process steps, method steps, algorithms, and the like have been described in a sequential order in the flowchart shown in FIG. 4, such processes, methods, and algorithms may be configured to operate in any suitable order. In other words, the steps of the processes, methods and algorithms described in various embodiments of the present invention need not be performed in the order described in the present invention. Further, although some steps are described as being performed asynchronously, in other embodiments, some of these steps may be performed simultaneously. Further, the illustration of the process by depiction in the drawings does not imply that the illustrated process excludes other changes and modifications thereto, and the illustrated process or any of its steps are among the various embodiments of the present disclosure. It does not imply that it is essential for one or more, and does not imply that the illustrated process is desirable.

Referring to FIG. 4, in step S402, the remote processing unit 120 may generate a control signal for controlling at least one of large or beam waveforms for the plurality of drones 112. In an embodiment, the remote processing unit 120 may generate a control signal including a first control signal for moving the plurality of drones 112 to a location where an object to be detected is located. In one embodiment, the remote processing unit 120 is a second control signal for setting the size of the plurality of drones 112 moved to the location where the object is located, or for setting the beam waveforms of the plurality of drones 112 A control signal including at least one of the third control signals may be generated.

In step S404, the plurality of drones 112 may receive control signals from the remote processing unit 120 through the network 140. In an embodiment, the plurality of drones 112 may receive a control signal including a first control signal from the remote processing unit 120. In one embodiment, the plurality of drones 112 transmit a control signal including at least one of a second control signal from the remote processing unit 120 or a third control signal for setting a beam waveform of the plurality of drones 112. Can receive.

In step S406, the plurality of drones 112 may acquire radar reception data for the object based on the control signal. In an embodiment, the plurality of drones 112 may move to a location where an object to be detected is located based on a control signal (ie, a first control signal). In an embodiment, the plurality of drones 112 may determine a location corresponding to a large size based on a control signal (ie, a second control signal). In one embodiment, the plurality of drones 112 determine a waveform of a radar signal (ie, a radar beam) to be transmitted to the object based on a control signal (ie, a third control signal), and the radar signal of the determined waveform is Can be generated. In addition, each of the plurality of drones 112 may radiate the generated radar signal to the object and receive radar signals reflected from the object to obtain radar reception data for the object.

For example, a plurality of drones 112 radiate a radar signal (ie, a radar beam) at a position corresponding to a large size on the object 500, as shown in FIG. 5, and the radar reflected from the object 500 By receiving a signal, radar reception data for the object 500 may be obtained.

Optionally, the plurality of drones 112 may perform wireless communication with each other to vary the beam waveform according to the positions and characteristics of each of the plurality of drones 112.

In step S408, the remote processing unit 120 may receive radar reception data from the plurality of drones 112. For example, as shown in FIG. 6, the remote processing unit 120 may receive radar reception data obtained from each of the plurality of drones 112.

In step S410, the remote processing unit 120 may generate an image of the object based on the radar received data. In an embodiment, the remote processor 120 may process radar received data to identify an object and a clutter, and classify the object and the clutter to generate an image of the object. In an embodiment, the remote processing unit 120 may generate an image of an object by applying the radar received data to an artificial intelligence algorithm for classifying the object and the clutter.

For example, as shown in FIG. 7, the remote processing unit 120 generates composite data by synthesizing radar reception data obtained from each of the plurality of drones 112, and generates composite data from the generated composite data. It is identified, and an image of the object may be generated based on the identified object and clutter.

Optionally, the remote processing unit 120 controls at least one of a fourth control signal for changing the size of the plurality of drones 112 or a fifth control signal for changing the beam waveform of the plurality of drones 112 A signal may be generated and the generated control signal may be transmitted to the plurality of drones 112. Accordingly, the plurality of drones 112 may change a large size or beam waveform based on the control signal, and obtain radar reception data for an object according to the changed large size or beam waveform. The remote processing unit 120 may generate an image of an object based on newly acquired radar reception data. In this way, the detection rate for the object may be improved by acquiring radar data for the object by changing a large size or a beam waveform.

Also, optionally, the remote processing unit 120 may transmit radar reception data obtained from the plurality of drones 112 to the artificial intelligence server 130. The artificial intelligence server 130 may update the artificial intelligence algorithm by using radar reception data provided from the remote processing unit 120 for artificial intelligence learning, and transmit the updated artificial intelligence algorithm to the remote processing unit 120.

Although the above method has been described through specific embodiments, the above method may also be implemented as computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. In addition, the computer-readable recording medium is distributed over a computer system connected through a network, so that computer-readable codes can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the above embodiments can be easily inferred by programmers in the technical field to which the present invention belongs.

Although the technical idea of the present invention has been described with reference to some embodiments and examples shown in the accompanying drawings above, it does not depart from the technical idea and scope of the present invention that can be understood by those of ordinary skill in the art to which the present invention belongs. It will be appreciated that various substitutions, modifications and changes may be made in the range. In addition, such substitutions, modifications and alterations should be considered to fall within the scope of the appended claims.

100: detection system 110: radar data acquisition unit
112: drone 120: remote processing unit
130: artificial intelligence server 140: network
500: object

Claims (25)

As a detection system,
A radar reception data acquisition unit including a plurality of small UAVs and acquiring radar reception data for an object through the plurality of small UAVs; And
It is connected to the plurality of small UAVs through a network, generates a control signal for controlling at least one of a large size or a beam waveform for the plurality of small UAVs and transmits it to the plurality of small UAVs, from the plurality of small UAVs A remote processing unit that receives the radar reception data and generates an image of the object based on the radar reception data
Including,
The remote processing unit sets the beam waveform for beamforming of radar beams emitted from the plurality of small UAVs according to the size of the plurality of small UAVs. The method of claim 1, wherein the plurality of small UAVs comprises a plurality of drones,
Each of the plurality of drones radiates a beam to the object and receives a beam reflected from the object to obtain radar reception data for the object. delete The detection system of claim 2, wherein the plurality of drones determine a location corresponding to the formation based on the control signal. The detection system of claim 2, wherein the plurality of drones generate the beams corresponding to the beam waveforms based on the control signals. The detection system of claim 5, wherein the plurality of drones communicate with each other to vary the beam waveform according to the positions and characteristics of each of the plurality of drones. The detection system of claim 1, wherein the control signal further comprises a signal for moving the plurality of small UAVs to a location where the object is located. The detection system of claim 1, wherein the control signal further comprises a signal for changing at least one of the large size or the beam waveform for the plurality of small UAVs. The detection system of claim 1, wherein the remote processor processes the radar received data to identify the object and the clutter, and classifies the object and the clutter to generate an image of the object. The method of claim 9, wherein the remote processing unit applies the radar received data to an artificial intelligence algorithm for classifying the object and the clutter, performs singular point identification and comparison on the radar received data, and identifies the singular point and A detection system for classifying the object and the clutter based on a result of performing the comparison. The method of claim 10,
An artificial intelligence that is connected to the remote processing unit through the network, updates the artificial intelligence algorithm by using the radar received data provided from the remote processing unit for artificial intelligence learning, and provides the updated artificial intelligence algorithm to the remote processing unit. Intelligent server
Including more,
The artificial intelligence algorithm performs the singular point identification and comparison on the radar received data using a singular point identification and comparison algorithm, and is updated by applying a result of the singular point identification and comparison to a learning algorithm. As a remote processing unit connected to a plurality of small UAVs through a network,
A control signal generator for generating a control signal for controlling at least one of large or beam waveforms for the plurality of small UAVs;
A communication module for transmitting the control signal to the plurality of small UAVs and receiving radar reception data for an object from the plurality of small UAVs; And
A data processing unit that generates an image of the object based on the radar received data
Including,
The control signal generator sets the beam waveform for beamforming of radar beams radiated from the plurality of small UAVs according to the size of the plurality of small UAVs. The remote processing unit of claim 12, wherein the data processing unit processes the radar reception data to identify the object and the clutter, and classifies the object and the clutter to generate the image of the object. The method of claim 13, wherein the data processing unit applies the radar received data to an artificial intelligence algorithm for classifying the object and the clutter to identify and compare singular points on the radar received data, and identify and compare the singular points. A remote processing unit that classifies the object and the clutter based on a result of performing the comparison. The remote processing unit of claim 12, wherein the control signal further comprises a signal for moving the plurality of small UAVs to a location where the object is located. The remote processing unit of claim 12, wherein the control signal further comprises a signal for changing at least one of the large size or the beam waveform for the plurality of small UAVs. delete A method of detecting an object in a detection system including a plurality of small unmanned aerial vehicles and a remote processing unit,
Generating, at the remote processing unit, a control signal for controlling at least one of a large size or a beam waveform for the plurality of small UAVs;
Receiving the control signal from the remote processing unit in the plurality of small UAVs;
Obtaining, from the plurality of small UAVs, radar reception data for the object based on the control signal;
Receiving, at the remote processing unit, the radar reception data from the plurality of small unmanned aerial vehicles; And
Generating, by the remote processing unit, an image of the object based on the radar received data
Including,
An object detection method in which the beam waveform for beamforming of radar beams radiated from the plurality of small UAVs is set for the plurality of small UAVs according to the size of the plurality of small UAVs. The method of claim 18, wherein obtaining radar reception data for the object comprises:
Transmitting a beam to the object based on the control signal; And
Receiving the beam reflected from the object and obtaining the radar reception data for the object
Object detection method comprising a. The method of claim 19, wherein obtaining radar reception data for the object
Determining a position corresponding to the formation based on the control signal
Object detection method comprising a. The method of claim 20, wherein obtaining radar reception data for the object
Generating the beam corresponding to the beam waveform based on the control signal
Object detection method comprising a. The method of claim 20, wherein obtaining radar reception data for the object
Performing communication between the plurality of small UAVs and varying the beam waveform according to the positions and characteristics of each of the plurality of small UAVs
Object detection method further comprising a. The method of claim 18, wherein generating an image of the object comprises:
Processing the radar received data to identify the object and the clutter; And
Classifying the object and the clutter to generate an image of the object
Object detection method comprising a. The method of claim 23, wherein the step of identifying the object and the clutter by processing the radar received data comprises:
Applying the radar received data to an artificial intelligence algorithm for classifying the object and the clutter, performing singular point identification and comparison on the radar received data, and based on the result of performing the singular point identification and comparison, the object and Classifying the clutter
Object detection method comprising a. The method of claim 24,
Updating the artificial intelligence algorithm by using the radar received data for artificial intelligence learning in the artificial intelligence server of the detection system; And
In the artificial intelligence server, providing the updated artificial intelligence algorithm to the remote processing unit
Including more,
The artificial intelligence algorithm performs the singular point identification and comparison of the radar received data using a singular point identification and comparison algorithm, and is updated by applying a result of the singular point identification and comparison to a learning algorithm.

Images