WO2021245858A1 - Information processing device - Google Patents

Information processing device Download PDF

Info

Publication number
WO2021245858A1
WO2021245858A1 PCT/JP2020/022024 JP2020022024W WO2021245858A1 WO 2021245858 A1 WO2021245858 A1 WO 2021245858A1 JP 2020022024 W JP2020022024 W JP 2020022024W WO 2021245858 A1 WO2021245858 A1 WO 2021245858A1
Authority
WO
WIPO (PCT)
Prior art keywords
candidate
drone
foreign body
suspicious
suspicious drone
Prior art date
Application number
PCT/JP2020/022024
Other languages
French (fr)
Japanese (ja)
Inventor
貴宏 渡邉
Original Assignee
株式会社Murakumo
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 株式会社Murakumo filed Critical 株式会社Murakumo
Priority to PCT/JP2020/022024 priority Critical patent/WO2021245858A1/en
Publication of WO2021245858A1 publication Critical patent/WO2021245858A1/en

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64CAEROPLANES; HELICOPTERS
    • B64C39/00Aircraft not otherwise provided for
    • B64C39/02Aircraft not otherwise provided for characterised by special use
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F41WEAPONS
    • F41HARMOUR; ARMOURED TURRETS; ARMOURED OR ARMED VEHICLES; MEANS OF ATTACK OR DEFENCE, e.g. CAMOUFLAGE, IN GENERAL
    • F41H13/00Means of attack or defence not otherwise provided for

Definitions

  • the present invention relates to an information processing device.
  • the present invention has been made in view of such a situation, and it is possible to effectively prevent crimes and accidents caused by the invasion of an object to be captured, and to erroneously capture an object that should not be captured.
  • the purpose is to be able to prevent it.
  • the information processing apparatus is Candidate detection means for detecting candidates for foreign substances that invade the area to be protected, A determination means for determining whether or not the foreign body candidate is a foreign body to be captured based on a predetermined determination method. To prepare for.
  • the information processing apparatus of another aspect of the present invention is When the candidate for the foreign body is determined by the determination means to be the foreign body to be captured, the capture support means for executing the process of supporting the capture of the foreign body and the capture support means. To prepare for.
  • the information processing apparatus of yet another aspect of the present invention is
  • the candidate detecting means is Information on the shape of each of one or more objects included in the protected range is sequentially acquired as object shape information, and the acquired object shape information is sequentially compared with the object shape information in a normal state, and is usually used. A part different from the state is detected as a candidate for a foreign body,
  • the determination means is A first recognition means for recognizing a pattern of change after detection of a first physical quantity for a foreign body candidate, and a first recognition means. Based on the pattern of change after detection of the first physical quantity of the foreign body candidate recognized by the first recognition means, the foreign body candidate may be the foreign body to be captured.
  • the first determination means for making the first determination as to whether or not it is
  • the stimulus giving support for supporting the application of a predetermined stimulus to the foreign body candidate.
  • Means and A second recognition means for recognizing a pattern of change in the second physical quantity of the foreign body candidate after the stimulus is given, and Based on the pattern of change after detection of the second physical quantity of the foreign body candidate recognized by the second recognition means, the foreign body candidate may be the foreign body to be captured.
  • a second determination means for making a second determination as to whether or not it is present, Have The capture support means When the second determination determines that the candidate for the foreign body is likely to be the foreign body to be captured, the execution of a process for supporting the capture of the foreign body to be captured is permitted. The second determination is that the candidate for the foreign body is unlikely to be the foreign body to be captured, or the first determination is that the candidate for the foreign body is the foreign body to be captured. If it is determined that there is no possibility of this, the execution of the process of supporting the capture of the foreign body to be captured is prohibited.
  • FIG. 1 is a diagram relating to an outline of a drone capture system to which a server according to an embodiment of the information processing apparatus of the present invention is applied.
  • the drone capture system is a system that captures suspicious drones that invade buildings and equipment exposed on the surface of the earth.
  • the suspicious object that invades the building or equipment exposed on the surface of the earth is an object that invades from the ground or the surface of the water, such as a person, a car, a bicycle, or a ship, the part is somehow.
  • the method of shielding by the method, it is possible to prevent the invasion of these objects.
  • a method of shielding a part of a building or equipment by surrounding a fence or fence around the building or equipment it is possible to prevent the intrusion of suspicious objects approaching from the ground or the surface of the water. be able to.
  • the suspicious object that invades the building or equipment exposed on the surface of the earth is a drone, the drone approaches the building or equipment from the sky.
  • the method of shielding the parts of buildings and equipment exposed on the ground surface in some way is inappropriate as a method of preventing the invasion of suspicious drones.
  • the suspicious drone can easily be allowed to enter the inside of the building or equipment. Even if it is possible to prevent a suspicious drone from invading the inside of a building or equipment, there is a risk that a suspicious drone will drop a fallen object such as a bomb from the sky above the building or equipment.
  • the drone capture system shown in FIG. 1 can distinguish and capture only suspicious drones.
  • facility B is a protection target, and the facility B invades within the range of a three-dimensional area (hereinafter, referred to as “protection target area W”) to protect the protection target.
  • protection target area W a three-dimensional area
  • the drone capture system shown in FIG. 1 can discriminate between a suspicious drone D and other objects (wild bird P1, manned airplane P2, etc.) and capture them. As a result, it is possible to prevent crimes and accidents committed by the suspicious drone D.
  • the drone capture system shown in FIG. 1 can identify and capture only the suspicious drone D by the method shown in FIG. 2, there is no problem even if the Japanese law at the time of filing the application of the present application is applied. It does not occur and the influence on the surroundings of the facility B is very small.
  • FIG. 2 is a diagram illustrating an example of a method for capturing a drone applied to the drone capture system of FIG.
  • the method shown in FIG. 2 is a method including phases PH0 to PH5.
  • Phase PH0 the system administrator prepares to capture the suspicious drone D.
  • the system administrator first deploys each of the server 1, the reconnaissance device J, the capture device C, and the stimulator S to the monitoring facility K where the monitor A exists.
  • the system administrator deploys the radar L around the center of the facility B to be protected.
  • the server 1 is managed by the system administrator and executes various processes in order to execute the overall control of the drone capture system shown in FIG.
  • the reconnaissance device J scouts the suspicious drone D by acquiring various information such as an image related to the suspicious drone D.
  • the reconnaissance device J is configured as a drone.
  • the reconnaissance device J sets an appropriate flight path toward a suspicious drone D or the like to be reconnaissance, flies and approaches, and acquires various information about the suspicious drone D.
  • the capture device C captures the suspicious drone D.
  • the capture device C is configured as a drone equipped with a capture net.
  • the method of capturing by the capture device C is not particularly limited to the method of mounting the net on the drone, and various other methods such as a method of mounting an electromagnet on the drone and a method of casting a net from the ground with a net gun or the like. Can be adopted.
  • the stimulator S gives a stimulus to the object by physically interfering with the object that has invaded the protected area W.
  • the stimulator S is a device used for determining whether or not the object that has invaded the protected area W is a suspicious drone D.
  • the method of stimulating an object with the stimulator S is not particularly limited, and various methods such as a method of radiating electromagnetic waves from an antenna, a method of radiating sound waves from a speaker or an explosive, and a method of radiating light with a lamp or the like are used. Various methods can be adopted.
  • the monitoring facility K is a facility for monitoring an object invading the protected area W.
  • the radar L emits an electromagnetic wave toward an object that has invaded the protected area W, and measures the reflected wave to measure the distance and direction to the object. For example, since the observation range of the consumer laser radar (LIDAR) as of July 2019 is 1 km, the area within a radius of 1 km from the center of the position where the radar L is installed is set as the protection target area W. Radar.
  • LIDAR consumer laser radar
  • the system designer makes various initial settings in preparation for capturing the suspicious drone D. Specifically, for example, according to the method of capturing a drone shown in FIG. 2, it is first determined whether or not an object invading the protected area W is abnormal (a candidate for a suspicious drone D) (phase described later). PH1).
  • the initial setting for this determination is performed as follows. That is, as a method of detecting a general abnormality, there is a method of detecting an abnormality that is out of the normal state based on the normal state. In the method of capturing the drone shown in FIG. 2, based on the method of detecting this general abnormality, based on the normal state of the protected area W, the one deviating from the normal state is detected as an abnormal state. The method is adopted.
  • the system designer needs to store the normal state of the protected area W in the server 1 as one of the initial settings.
  • the server 1 acquires the information obtained from the radar L in the normal state as the normal state when the suspicious drone candidate X does not exist in the protected area W as the normal object shape information. Then, it is stored in a storage unit (storage unit 18 in FIG. 4 described later).
  • the object shape information refers to information on the shapes of buildings, facilities, plants, etc., and the shapes of the ground and water surface existing in the protected area W, including the facility B to be protected.
  • the server 1 continues to sequentially acquire the information obtained from the radar L as the object shape information in the protection target area W.
  • the server 1 compares the sequentially acquired object shape information with the normal object shape information.
  • the server 1 recognizes the object specified by the recognized difference as the candidate X of the suspicious drone D (hereinafter referred to as "suspicious drone candidate X"), and the suspicious drone.
  • start tracking candidate X The method for tracking the suspicious drone candidate X is not particularly limited, but in the following example, it is assumed that a method for recording the spatial movement history of the suspicious drone candidate X is adopted.
  • the position of the suspicious drone candidate X specified by the information obtained by the radar L in the three-dimensional space (within the protection target area W) changes from moment to moment.
  • the history of each position that changes from moment to moment is recorded as the spatial movement history of the suspicious drone candidate X.
  • the server 1 determines from the spatial movement history of the suspicious drone candidate X that the suspicious drone candidate X approaches the facility B, the server 1 makes a suspicious drone to the reconnaissance device J that exists at the closest distance to the suspicious drone candidate X. Instruct to get information about candidate X.
  • the reconnaissance device J approaches the suspicious drone candidate X and acquires various information such as an image related to the suspicious drone candidate X.
  • the various information is not particularly limited, and for example, here, it is assumed that at least the information of the image obtained as a result of being imaged by an optical camera (in combination with an infrared lamp at night) is acquired. Then, the reconnaissance device J wirelessly transfers the information regarding the suspicious drone candidate X acquired in this way to the server 1.
  • the server 1 collectively refers to various information such as the spatial movement history of the suspicious drone candidate X and the image transferred from the reconnaissance device J (the spatial movement history obtained here and various information such as the image. Recognize the pattern of "first physical quantity").
  • the pattern is a general term for fixed behaviors and forms shown in all situations, although details will be described later.
  • the server 1 determines the possibility that the suspicious drone candidate X is a suspicious drone D based on the pattern indicated by the first physical quantity. How to do it according to this possibility is a design matter of the system designer, but in the method shown in FIG. 2, it is assumed that three stages of processing are executed as follows. That is, in the method shown in FIG.
  • the server 1 determines that the suspicious drone candidate X is unlikely to be a suspicious drone D, the server 1 continues monitoring the suspicious drone candidate X (continues phase PH1) or monitors as the first stage processing. To finish.
  • the server 1 determines that the possibility that the suspicious drone candidate X is the suspicious drone D is moderate, the server 1 shifts from the phase PH2 to the phase PH3 and executes the phase PH3 process as the second stage process.
  • the server 1 determines that the suspicious drone candidate X has a high possibility of being a suspicious drone D, the server 1 shifts from the phase PH2 to the phase PH4 and executes the phase PH4 process as the third stage process.
  • the server 1 instructs the stimulator S to give a stimulus to the suspicious drone candidate X for the purpose of determining in detail whether or not the suspicious drone candidate X is the suspicious drone D.
  • the stimulus given to the suspicious drone candidate X is a plosive sound. That is, here, the stimulator S gives a stimulus to the suspicious drone candidate X by outputting a plosive sound to the suspicious drone candidate X from a speaker or the like.
  • the server 1 As a response to the stimulus to the suspicious drone candidate X, the server 1 has a pattern of various information such as a pattern of the spatial movement history of the suspicious drone candidate X after the burst sound is output and an image transferred from the reconnaissance device J (The spatial movement history obtained here and various information such as images are referred to as "second physical quantities").
  • the server 1 determines the possibility that the suspicious drone candidate X is a suspicious drone D based on the pattern indicated by the second physical quantity. For example, when the suspicious drone candidate X is a wild animal, the suspicious drone candidate X should be surprised at the stimulus given by the stimulator S and show some biological reaction.
  • Some biological reactions here are, for example, the behavior of escaping, the phenomenon of fainting and falling, the behavior of being excited and attacking toward a stimulus, the reaction of being excited and raising the body temperature, and the phenomenon of being excited and alert. There is a reaction to be emitted.
  • the second physical quantity should be different depending on whether or not these biological reactions occur. That is, the server 1 can determine whether or not there is a biological reaction based on the second physical quantity, and can determine the possibility of a suspicious drone D based on the determination result.
  • the possibility of suspicious drone D is a design matter of the system designer, but in the method shown in FIG. 2, two-step processing is executed as follows. And. That is, in the method shown in FIG.
  • the first stage when it is unlikely that the suspicious drone candidate X is a suspicious drone D (when it can be substantially determined that the suspicious drone candidate X is not a suspicious drone D), the first stage. There is a process. Further, there is a second stage process when there is a high possibility that the suspicious drone candidate X is a suspicious drone D (when it can be substantially determined that the suspicious drone candidate X is a suspicious drone D).
  • the server 1 determines that the possibility of the suspicious drone D is low, the server 1 continues the monitoring of the suspicious drone candidate X (returns to the phase PH2) or ends the monitoring as the first stage processing.
  • the server 1 determines that the suspicious drone candidate X has a high possibility of being a suspicious drone D, the server 1 shifts from the phase PH3 to the phase PH4 and executes the phase PH4 process as the second stage process.
  • the server 1 issues a capture instruction to the capture device C for the purpose of capturing the suspicious drone D as a process of the phase PH4. .. Then, the capture device C, which has received the capture instruction, flies toward and approaches the suspicious drone D, and captures the suspicious drone D by casting net.
  • the capture device C stores the captured suspicious drone D in a safe place where, for example, the explosive mounted on the suspicious drone D does not affect the surroundings even if it explodes.
  • the server 1 acquires the information obtained from the radar L in the state where the suspicious drone candidate X does not exist in the protected area W as the normal object shape information.
  • the server 1 continues to sequentially acquire the information obtained from the radar L as the object shape information in the protection target area W.
  • the server 1 compares the sequentially acquired object shape information with the normal object shape information, recognizes the object specified by the recognized difference as the suspicious drone candidate X, and tracks the suspicious drone candidate X.
  • the server 1 acquires various information such as a spatial movement history, which is the first physical quantity of the suspicious drone candidate X, and an image.
  • the server 1 determines the possibility that the suspicious drone candidate X is the suspicious drone D based on the pattern indicated by the first physical quantity.
  • the server 1 instructs the stimulator S to give a stimulus to the suspicious drone candidate X.
  • the server 1 acquires various information such as a spatial movement history, which is a second physical quantity of the suspicious drone candidate X, and an image.
  • the server 1 determines the possibility that the suspicious drone candidate X is the suspicious drone D based on the pattern indicated by the second physical quantity.
  • the server 1 gives a capture instruction to the capture device C for the purpose of capturing the suspicious drone D.
  • FIG. 3 is a block diagram showing an example of the configuration of the drone capture system of FIG. 1 as an information processing system.
  • the information processing system including the server 1 includes the server 1, the capture device C, the reconnaissance device J, and the radar as shown in FIG. It is configured to include L and a stimulator S.
  • the server 1, the capture device C, the reconnaissance device J, the radar L, and the stimulator S are connected to each other via a predetermined network.
  • FIG. 4 is a block diagram showing a hardware configuration of a server among the information processing devices of FIG.
  • the server 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, and an input unit 17. , A storage unit 18, a communication unit 19, and a drive 20.
  • CPU Central Processing Unit
  • ROM Read Only Memory
  • RAM Random Access Memory
  • the CPU 11 executes various processes according to various programs recorded in the ROM 12 or various programs loaded from the storage unit 18 into the RAM 13. Data and the like necessary for the CPU 11 to execute various processes are also appropriately stored in the RAM 13.
  • the CPU 11, ROM 12 and RAM 13 are connected to each other via the bus 14.
  • An input / output interface 15 is also connected to the bus 14.
  • An output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20 are connected to the input / output interface 15.
  • the output unit 16 is composed of various liquid crystal displays and the like, and outputs various information.
  • the input unit 17 is composed of various hardware and the like, and inputs various information.
  • the storage unit 18 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores various data.
  • the communication unit 19 controls communication with other devices (capture device C, reconnaissance device J, radar L, and stimulator S in FIG. 4) via a network N including the Internet.
  • the drive 20 is provided as needed.
  • a removable media 21 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately mounted on the drive 20.
  • the program read from the removable media 21 by the drive 20 is installed in the storage unit 18 as needed. Further, the removable media 21 can also store various data stored in the storage unit 18 in the same manner as the storage unit 18.
  • FIG. 5 is a functional block diagram showing an example of the functional configuration of the server 1 of FIG. 4.
  • the second physical quantity acquisition unit 202 function.
  • the object shape information acquisition unit 101 acquires the information regarding the object shape received by the radar L as the object shape information.
  • the object shape information acquisition unit 101 acquires the object shape information in a state where the suspicious drone candidate X does not exist as the normal time object shape information, and stores it in the storage unit 18.
  • changes in objects that is, expansion / renovation of buildings and facilities, demolition, changes in equipment near facilities, growth and death of plants, etc. may occur.
  • the object shape information at normal times should also be changed. Therefore, the normal object shape information is reacquired at any time and stored (overwritten) in the storage unit 18.
  • the object shape information acquisition unit 101 sequentially acquires the object shape information.
  • the object shape information is acquired at predetermined intervals (each of time t1 to tun) within the time T, the object shape information is acquired at the time tk (k is an integer value of any of 0 to n).
  • the object shape information is particularly referred to as "object shape information L (tk)".
  • the normal time object shape information is acquired at time t0. Therefore, the normal object shape information is particularly referred to as "normal time object shape information L (t0)".
  • the suspicious drone candidate detection unit 102 compares the object shape information L (tk) with the normal object shape information L (t0), and if a difference is obtained as a result of the comparison, the difference is used as the suspicious drone candidate X (. Detect as information).
  • the notification unit 103 controls to notify the observer A of information about the suspicious drone candidate X detected by the suspicious drone candidate detection unit 102. Although not shown here, the notification unit 103 further controls to acquire a response from the observer A.
  • the first physical quantity acquisition instruction unit 104 instructs the radar L and the reconnaissance device J to acquire object shape information, image information, etc., which are the first physical quantities related to the suspicious drone candidate X.
  • the first physical quantity acquisition unit 201 communicates the object shape information which is the first physical quantity regarding the suspicious drone candidate X obtained from the radar L, the image information which is the first physical quantity regarding the suspicious drone candidate X obtained from the reconnaissance device J, and the like. Obtained via unit 19.
  • the image information and the like are image data captured by an optical camera, and for example, information that makes it possible to recognize the size, equipment, specifications that can be estimated from the appearance, etc. by information processing (image processing). Is.
  • the first physical quantity pattern recognition unit 105 is a spatial movement history pattern or image of the suspicious drone candidate X based on the object shape information or image information which is the first physical quantity related to the suspicious drone candidate X acquired by the first physical quantity acquisition unit 201. Recognize pattern information such as information.
  • pattern information such as information.
  • the information of the pattern such as the spatial movement history pattern of the suspicious drone candidate X and the image information is appropriately referred to as "pattern information”.
  • the first determination unit 106 determines the possibility that the suspicious drone candidate X is a suspicious drone D based on the pattern information recognized by the first physical quantity pattern recognition unit 105.
  • the suspicious drone candidate X may be a pedestrian, a car, a ship, an animal having no flight ability, a bicycle, a radio-controlled car, or the like. Is likely to be. That is, the suspicious drone candidate X is unlikely to be a suspicious drone. Further, for example, when the spatial movement history pattern of the suspicious drone candidate X rises from the ground surface, the water surface, or the vicinity of the sea surface and disappears within a few seconds, the suspicious drone candidate X is unlikely to be a suspicious drone.
  • the suspicious drone candidate X is likely to be a short-term flight of birds, a flying fish such as a flying fish or a dolphin, or a whale squirting or a flying squirrel. Is. Further, for example, when the spatial movement history pattern of the suspicious drone candidate X is a pattern of falling from the sky and the falling speed is high, the suspicious drone candidate X may be a suspicious drone. Is low. This is because the suspicious drone candidate X is a meteorite or a fragment of an aircraft that cannot be captured because the falling speed is too fast.
  • the suspicious drone candidate X when the spatial movement history pattern of the suspicious drone candidate X is a pattern that takes a turning trajectory in the sky above the place where the updraft is generated, the suspicious drone candidate X is likely to be a bird of prey. However, if this suspicious drone candidate X comes toward the facility B, the suspicious drone candidate X may be a suspicious drone D. Also, if the spatial movement history pattern of the suspicious drone candidate X is a pattern that rises in a place where an updraft is generated, the suspicious drone candidate X can be a balloon, a plastic bag, or a bird that sails. Highly sex. However, if the suspicious drone candidate X comes toward the facility B, the suspicious drone candidate X may be a suspicious drone D.
  • the suspicious drone candidate X when the spatial movement history pattern of the suspicious drone candidate X is a pattern of flying on the wind, the suspicious drone candidate X is likely to be a balloon, a plastic bag, or the like. However, even in this case, the suspicious drone candidate X may be a suspicious drone.
  • the suspicious drone candidate X is determined. There is a high possibility of a suspicious drone.
  • the suspicious drone candidate X which shows the history of space movement during wavy flight, is highly likely to be a bird.
  • the suspicious drone candidate X may be a suspicious drone.
  • the suspicious drone candidate X may be a suspicious drone.
  • the suspicious drone candidate X may be a suspicious drone D.
  • the first determination unit 106 can also adopt a pattern such as image information of the suspicious drone candidate X as the pattern information to determine the possibility that the suspicious drone candidate X is a suspicious drone D. For example, if the pattern such as the image information of the suspicious drone candidate X is recognized as the pattern of the suspicious drone candidate X such as a known drone, balloon, or plastic bag, the suspicious drone candidate X may be a suspicious drone D. It is determined that there is no sex.
  • the first determination unit 106 may refer to the spatial movement history pattern representing the movement peculiar to the drone in determining the possibility that the suspicious drone candidate X is the suspicious drone D. That is, when the suspicious drone candidate X is a multicopter type drone, the suspicious drone candidate X moves while tilting the traveling direction in a direction corrected by the wind direction, and performs inertial movement due to its own weight. For this reason, turning is generally slow.
  • the suspicious drone candidate X is a fixed-wing drone
  • the suspicious drone candidate X generally has the wing oriented so as not to obstruct the air in the traveling direction, and also performs inertial movement due to its own weight, and the wing is fixed. Therefore, the minimum radius of direction change is considerably large. In response to these drone-specific movements, birds are light in weight and have movable wings, allowing them to make sharp turns.
  • the monitoring of the suspicious drone candidate X may be continued as the first stage processing. That is, the first physical quantity acquisition instruction unit 104 may instruct the radar L and the reconnaissance device J to acquire the first physical quantity, that is, the object shape information, the image information, and the like regarding the suspicious drone candidate X. Alternatively, if the first determination unit 106 determines that the suspicious drone candidate X is unlikely to be a suspicious drone D, the first determination unit 106 may perform an operation to end the monitoring. When the first determination unit 106 determines that the suspicious drone candidate X has a moderate possibility of being a suspicious drone D, as a second stage process, the stimulus application support unit 107 passes through the communication unit 19.
  • the stimulator S is supported to give a stimulus to the suspicious drone candidate X.
  • the capture support unit 111 transfers the capture device via the communication unit 19. Support C to capture the suspicious drone D.
  • the second physical quantity acquisition instruction unit 108 instructs the radar L and the reconnaissance device J to acquire the object shape information, the image information, etc., which are the second physical quantities related to the suspicious drone candidate X.
  • the second physical quantity acquisition unit 202 communicates the object shape information of the suspicious drone candidate X obtained from the radar L, the image information of the second physical quantity of the suspicious drone candidate X obtained from the reconnaissance device J, and the like. Obtained via unit 19.
  • the second physical quantity pattern recognition unit 109 has the spatial movement history pattern and image information of the suspicious drone candidate X based on the object shape information and the image information which are the second physical quantities related to the suspicious drone candidate X acquired by the second physical quantity acquisition unit 202. Recognize pattern information such as.
  • the second determination unit 110 determines the possibility that the suspicious drone candidate X is a suspicious drone D based on the pattern information recognized by the second physical quantity pattern recognition unit 109.
  • the capture support unit 111 supports the capture device C to capture the suspicious drone via the communication unit 19.
  • the capture device C shown in the present embodiment is configured as a drone equipped with a capture net, and this capture drone has a flight plan that balances its speed, sailing time, and takeoff load. It is necessary to stand up and use it. Further, since there is a risk that the drone itself or parts of the drone may fall during the capture operation, the server 1 may specify the area to be captured. Further, in order to increase the possibility of capturing the suspicious drone D, a plurality of capture drones may be coordinated. When capturing multiple capture drones in coordination, a drone that drives in a suspicious drone D, a drone that takes control of a suspicious drone D, a drone that captures a suspicious drone D, and commands and observes it. Each capture drone may have a role, such as a drone to do.
  • the plurality of capture drones may be in contact with each other by wire or wirelessly. Also, since general drones are optimized to generate thrust in the ascending direction for the copter type and in the horizontal direction for the fixed-wing type, the drone can suddenly increase the thrust by being turned over or tilted. Lost to, and control is lost. That is, the capture support unit 111 may control the movement of the capture drone so that the capture drone turns over or tilts the suspicious drone.
  • FIG. 6 is a flowchart illustrating a drone capture process executed by the server of FIG.
  • the object shape information acquisition unit 101 normally acquires the object shape information L (t0) prior to the processing.
  • step S101 the object shape information acquisition unit 101 acquires the object shape information L (tk) at the time tk.
  • step S102 the suspicious drone candidate detection unit 102 compares the object shape information L (tk) with the normal object shape information L (t0), and indicates the existence of the suspicious drone candidate X based on the result of the comparison. Determine if there is a difference. If it is determined in step S102 that there is no difference indicating the existence of the suspicious drone candidate X, the process ends. On the other hand, if it is determined in step S102 that there is a difference indicating the existence of the suspicious drone candidate X, the process proceeds to step S103.
  • step S103 the notification unit 103 notifies the observer A of information regarding the detection of the suspicious drone candidate X.
  • the reason why the notification unit 103 immediately notifies the observer A is to provide information as soon as possible to a person who has an extremely slow processing speed compared to the processing speed of the server 1 and the moving speed of the suspicious drone D. , To ask for judgment.
  • step S104 the notification unit 103 confirms whether or not there is a response from the observer A. If there is no response from the observer A in step S104, the process proceeds to step S107. The processing after step S107 will be described later. On the other hand, if there is a response from the observer A in step S104, the process proceeds to step S105.
  • step S105 the notification unit 103 confirms whether or not there is an instruction to capture the suspicious drone candidate X from the observer A. If the observer A gives an instruction to capture the suspicious drone candidate X in step S105, the process proceeds to step S115. The processing after step 115 will be described later. On the other hand, if there is no instruction to capture the suspicious drone candidate X from the observer A in step S105, the process proceeds to step S106.
  • step S106 the notification unit 103 confirms whether or not there is an instruction from the observer A to ignore the suspicious drone candidate X. If the observer A instructs to ignore in step S106, the process ends. On the other hand, if there is no instruction from the observer A to ignore in step S106, the process proceeds to step S107.
  • step S107 the object shape information acquisition unit 101 of the server 1 measures the size of the suspicious drone candidate X (difference between the object shape information L (tk) and the normal object shape information L (t0)) in real space. do. Then, the object shape information acquisition unit 101 determines whether or not the suspicious drone candidate X is larger than the preset catchable range based on the measurement result. If it is determined in step S107 that the suspicious drone candidate X is larger than the preset catchable range, the process ends. On the other hand, if it is determined in step S107 that the suspicious drone candidate X is not larger than the preset catchable range, the process proceeds to step S108.
  • step S108 the first physical quantity acquisition unit 201 acquires the spatial movement history of the suspicious drone candidate X, the image information obtained from the reconnaissance device J, and the like as the first physical quantity.
  • step S109 the first physical quantity pattern recognition unit 105 recognizes the pattern information of the first physical quantity.
  • step S110 the first determination unit 106 determines the possibility that the suspicious drone candidate X is a suspicious drone D, that is, the possibility that it is a capture target, based on the pattern information recognized by the first physical quantity pattern recognition unit 105. Judgment, the first judgment is performed. If the first determination unit 106 determines in step S110 that the suspicious drone candidate X is not a capture target, the process ends. If the first determination unit 106 does not determine in step S110 that the suspicious drone candidate X is not a capture target, the process proceeds to step S111. In step S111, the stimulus application support unit 107 instructs the stimulus device S to apply a stimulus to the suspicious drone candidate X.
  • the second physical quantity acquisition unit 202 receives the reaction of the suspicious drone candidate X to the stimulus given by the stimulus device S, that is, the spatial movement history of the suspicious drone candidate X, the image information obtained from the reconnaissance device J, and the like. Is acquired as the second physical quantity.
  • the second physical quantity pattern recognition unit 109 recognizes the pattern information of the second physical quantity.
  • the second determination unit 110 determines the possibility that the suspicious drone candidate X is a suspicious drone, that is, the possibility that it is a capture target, based on the pattern information recognized by the second physical quantity pattern recognition unit 109. The second determination is made. If the second determination unit 110 determines in step S114 that the suspicious drone candidate X is not a capture target, the process ends.
  • step S115 the process proceeds to step S115. That is, if it is determined in step S114 that the suspicious drone candidate X is the capture target, or if there is a capture instruction from a human in step S105, the process proceeds to step S115.
  • the fact that the suspicious drone candidate X is determined to be the capture target means that the suspicious drone candidate X is determined to be the suspicious drone D.
  • the capture support unit 111 instructs the capture device C to capture the suspicious drone D.
  • the capture device C instructed to capture the suspicious drone D is a capture drone for convenience in the present embodiment, and captures the suspicious drone D by casting net.
  • the capture drone moves and transports the captured suspicious drone D to a safe place.
  • the suspicious drone D may be put in a shield case or the like by the capture drone, or may be put in the shield case or the like together with the capture drone.
  • the first determination unit 106 has described that if the suspicious drone candidate X is determined to be the capture target, the process proceeds to step S111. However, as described above, the suspicious drone candidate X is here. If it is particularly determined that the target is likely to be captured, the process may proceed to step S115.
  • the object to be captured is described as a suspicious drone D, but the object to be captured is not limited to the suspicious drone D. According to the present invention, it is possible to distinguish a foreign body that poses a threat to the protected target as a capture target from among the candidates for the foreign body that invades the protected target.
  • the predetermined determination method is not limited to the method of the above-described embodiment, and may be arbitrary. In other words, in the above-described embodiment, the following method is adopted as a method for distinguishing the foreign body to be captured. That is, according to the method of the above-described embodiment, the pattern of the first physical quantity such as the object movement history and the image information indicated by the suspicious drone candidate X was recognized.
  • the suspicious drone candidate X is suspicious by combining the so-called passive observation of the pattern recognition of the first physical quantity and the so-called active observation of the pattern recognition of the second physical quantity obtained as a result of active stimulation.
  • the method of distinguishing whether or not it is a drone D (capture target) has been adopted as the method of the above-described embodiment. However, the method for distinguishing is not particularly limited to this method.
  • the suspicious drone candidate X may be distinguished whether or not the suspicious drone candidate X is the suspicious drone D only by the above-mentioned passive observation.
  • information on the temperature of the suspicious drone candidate X, information on electromagnetic waves, and suspicious drone candidate X are emitted as passive observations. It may be determined whether or not the suspicious drone candidate X is a suspicious drone D by obtaining information on a chemical substance or the like.
  • the frequency of the acquired electromagnetic wave and the like are referred to.
  • Living organisms emit almost no electromagnetic waves with frequencies below far infrared rays.
  • drones generally emit electromagnetic waves with frequencies below far infrared rays due to the current flowing through the coil for driving the motor, or electromagnetic waves and electrons with frequencies below far infrared rays for communication with the operator. It emits electromagnetic waves from the circuit. Therefore, if an electromagnetic wave of a specific frequency can be observed, it is almost certain that the suspicious drone candidate X is determined to be a drone.
  • the type of the acquired sound is referred to. If the motor sound and the wind noise of the rotor can be observed from the suspicious drone candidate X, it is almost certain that the suspicious drone candidate X is determined to be a drone.
  • the chemical substances released by the chemical substance sensor are detected. For example, if the machine oil applied to the bearing of the motor is detected, it is almost certain that the suspicious drone candidate X is determined to be a drone. Further, for example, when a suspicious drone uses a motor with a brush, there is a high possibility that ozone is generated by the spark generated in the brush portion reacting with oxygen in the air. If ozone is detected, the suspicious drone candidate X is almost certainly determined to be a suspicious drone.
  • a drone is used as the reconnaissance device J as a means of passive observation, but in addition to this, a drone for meteorological observation, an ocean buoy, a sonde, or the like may be used.
  • information on the suspicious drone candidate X may be acquired with the reconnaissance device J installed in the monitoring facility K.
  • a plurality of drones may be coordinated to collect information.
  • active observation may be used to determine whether the suspicious drone candidate X is a suspicious drone.
  • a bursting sound was used in this embodiment, but in addition to this, a warning sound of other birds and a warning message in a form that can be understood by humans and suspicious drones are read aloud. It may be an example sound, a flash light, a warning message in a form that can be understood by humans or suspicious drones, a visible light such as a mirror, or an unpleasant odor.
  • It may also be a visual stimulus, that is, a stimulus by a rapidly expanding umbrella-shaped object, a stimulus by a shape that expands like a catching net, a stimulus by a drone for reconnaissance, a drone for catching, or a stimulus by the approach of a protrusion such as a stick.
  • it may be stimulated by a strong electromagnetic pulse, an electromagnetic wave for jamming, or an invasive warning means such as a water gun or a blower that is less harmful to the living body.
  • a human is on board the suspicious drone candidate X, or if the operator of the suspicious drone candidate X is in communication, it should respond to the reading and posting of the warning text and evacuate if it intends to obey. be. Further, if the suspicious drone candidate X has a function that can understand the warning, it should be evacuated in response to the warning.
  • the suspicious drone candidate X may be irradiated with an electromagnetic wave, a magnetic field may be generated, or the electromagnetic wave may be shielded.
  • the suspicious drone candidate X is an object equipped with an electronic device such as a drone, the following reactions (1) to (3) can be seen in response to the operation of electromagnetic waves or magnetic fields below far infrared rays.
  • the living body since the living body has extremely low sensitivity to electromagnetic waves lower than far infrared rays and sensitivity to magnetic fields, it is highly possible that the living body does not react to electromagnetic waves lower than far infrared rays.
  • the suspicious drone candidate X may cause an operation abnormality due to an abnormal current flowing through the internal electronic circuit due to a strong electromagnetic pulse.
  • the metal inside may generate heat due to induction heating by electromagnetic waves less than the emitted far infrared rays, which may cause an operation abnormality.
  • due to a strong magnetic field even if an induced current flows in the internal electronic circuit of the suspicious drone candidate X or the ferromagnet causes magnetic saturation, an operation abnormality may occur. In this case, the suspicious drone candidate X stalls and falls.
  • the suspicious drone candidate X is likely to be a suspicious drone.
  • the strong magnetic field may attract the ferromagnetic material inside the suspicious drone candidate X.
  • the suspicious drone candidate X may be captured by this magnetic field.
  • the communication link between the suspicious drone candidate X and the operator of the suspicious drone candidate X may be disconnected, or GNSS information such as GPS may not be obtained. there is a possibility.
  • the suspicious drone candidate X is a drone, it shows a reaction of returning to the home position set in advance for the drone.
  • the suspicious drone candidate X may be a living body, so monitoring is continued.
  • the suspicious drone candidate X takes an escape action, the system administrator can guide the target out of the monitoring range by continuing active observation. And as a result, the monitoring range can be made safe.
  • the suspicious drone candidate X is a suspicious drone. You may. Further, since the suspicious drone candidate X may be a living body here, the strength of the stimulus to be given may be adjusted.
  • a foreign body candidate for example, suspicious drone candidate X
  • a foreign body to be captured for example, a suspicious drone
  • the information processing apparatus to which the present invention is applied can execute a process of supporting the capture of the foreign body when it is determined that the candidate for the foreign body is the foreign body to be captured.
  • the capture method in this case is not limited to the method of the above-described embodiment, and may be arbitrary.
  • the server 1 provides the observer A with information on the suspicious drone candidate X, and the observer A determines whether or not the suspicious drone candidate X is a foreign body to be captured.
  • the method of capture is not limited to this. That is, the observer A may perform all operations from collecting information on the suspicious drone candidate X to determining whether or not the suspicious drone candidate X is a foreign body to be captured. That is, the observer A may monitor the protected area W, and the observer A may discover the suspicious drone candidate X by visual inspection or the like. Then, the observer A may determine whether or not the found suspicious drone candidate X should be captured, and the observer A may capture the suspicious drone candidate X.
  • the observer A can identify the object to be captured by his / her sensory organ without using a computer. In this way, by having the observer A perform all the processing, it is possible to prevent false detections by the computer, and to take measures according to the surrounding situation, such as determining the priority, which cannot be done by the computer. Can be done.
  • the observer A provided with the information regarding the suspicious drone candidate X from the server 1 determines whether or not the suspicious drone candidate X is a foreign body to be captured based on the provided information. ..
  • the suspicious drone D may be captured by assisting the computer with a human.
  • the computer and the observer A can complement each other's roles. That is, when it is difficult for the observer A to handle nighttime, long-time monitoring, long-distance monitoring, etc., it is possible to reduce the human load by automating with a computer.
  • efficient processing can be achieved by using a computer.
  • the timing at which the computer provides the observer A with the information regarding the suspicious drone candidate X is not limited, and the information can be provided at any time.
  • the suspicious drone D that the computer should originally capture may be automatically identified without human intervention. That is, the computer discovers the suspicious drone candidate X by constantly monitoring the protected area W with the radar L or the like, automatically distinguishes whether or not the suspicious drone candidate X is a foreign body to be captured, and captures the suspicious drone candidate X. You may go. At this time, the computer automatically determines whether or not the suspicious drone candidate X is a foreign body to be captured based on the information obtained by the monitoring, and at the same time, the monitor A is notified of the suspicious drone candidate X. Information may be provided. When the observer A gives an instruction to capture the suspicious drone candidate X, the observer A automatically determines whether or not the suspicious drone candidate X is a foreign body to be captured.
  • machine learning by a computer may be used by utilizing the huge accumulated data. That is, the computer is made to machine-learn by accumulating data on a series of responses including detection of a candidate for a foreign body, determination of whether or not the foreign body is a foreign body to be captured, and a series of responses including capture processing. .. As a result, it becomes possible to more accurately and efficiently distinguish whether or not the candidate for the foreign body is the foreign body to be captured, and to perform the capture process.
  • the radar L is installed around the center of the facility B to be protected, and the area within a radius of 1 km from the center of the installed position is set as the protected area W, but the present invention is limited to this. Not done.
  • a monitoring network capable of monitoring a wide range may be created. That is, the longer the time from when the suspicious drone D invades the protected area W to when it reaches the protected facility B, the better so as to secure the time to deal with the suspicious drone D. ..
  • the monitoring distance by the radar L and the operating range of the capture device C and the reconnaissance device J cannot be unnecessarily expanded due to legal reasons and cost reasons. Therefore, by creating a monitoring network capable of monitoring a wide area, it becomes possible to secure a series of response times including the above-mentioned detection of foreign body candidates and capture processing.
  • the object shape information acquisition unit 101 acquires the information obtained from the radar L in the normal state as the normal state when the suspicious drone candidate X does not exist in the protection target area W as the normal time object shape information.
  • the ignore area may be set.
  • the neglected area is an area that is not included in the detection target because it is known that the shape of the object changes frequently. For example, this includes passages where people and cars can normally come and go, and places where splashes are detected at any time on the shoreline.
  • the object shape information acquisition unit 101 may obtain information such as weather information, traffic information, and aircraft operation information at any time, and may add, expand, or reduce the ignored area.
  • the average position of the sea surface and the height of the wave may be determined by the tide information and the wave information, and the height below the height at which the sea surface rises may be set as the neglected region. Further, if the position and time at which the aircraft flies are known in advance, that area may be set as the neglected area.
  • the object shape information acquisition unit 101 may obtain the movement of the wind within the observation range by an appropriate method. Wind movement may be monitored, for example, by a sonde, buoy, or hovering meteorological drone. In this way, by setting an ignoring area for the normal object shape information, it can be confirmed in advance that the building or equipment itself, fixed objects, plants, trees, grass, non-flying objects and non-floating objects are not threatening. It is possible to reduce the possibility of accidentally capturing meteorological solids such as drones, flying or floating objects, leopards, and tornado-wound fish.
  • the suspicious drone candidate detection unit 102 detects the difference between the object shape information L (tk) and the normal object shape information L (t0) in the area excluding the above-mentioned ignored area, but if necessary, a noise filter is used. You may use it. This is because it can be determined that an object smaller than a general suspicious drone will not be captured because it is more likely to be an insect rather than a suspicious drone.
  • the object shape information acquisition unit 101 measures the size of the suspicious drone candidate X in the real space, and here, the range of the size of the suspicious drone candidate X that can be captured by the capture device C may be input in advance. ..
  • the law of Japan at the time of filing of the present application is applied, but the present invention is not limited to this.
  • strict regulations are imposed on the transmission of disturbing radio waves, even for legitimate defense purposes. Therefore, in foreign countries, foreign law may be applied.
  • the information processing apparatus to which the present invention is applied suffices to have the following configuration, and various embodiments can be taken. That is, the information processing apparatus to which the present invention is applied is Candidate detection means (for example, FIG. 5) for detecting a candidate for a foreign body (for example, suspicious drone candidate X in FIGS. 1 and 2) that invades the range of the protection target (for example, the protection target area W in FIGS. 1 and 2). Suspicious drone candidate detection unit 102) and A determination means for determining whether or not the foreign body candidate is a foreign body to be captured (for example, the first determination unit 106 or the second determination unit 110 in FIG. 5) based on a predetermined determination method. To prepare for. This makes it possible to appropriately determine whether or not the candidate for a foreign body that invades the range of the protected object is a foreign body to be captured.
  • Candidate detection means for example, FIG. 5 for detecting a candidate for a foreign body (for example, suspicious drone candidate X in FIGS. 1 and 2) that invades the
  • the information processing apparatus to which the present invention is applied is
  • the capture support means for example, the capture support unit 111 in FIG. 5
  • the capture support unit 111 in FIG. 5 that executes a process of supporting the capture of the foreign body.
  • the information processing apparatus to which the present invention is applied is
  • the candidate detecting means is Information on the shape of each of one or more objects included in the protected range is sequentially acquired as object shape information, and the acquired object shape information is sequentially compared with the object shape information in a normal state, and is usually used. A part different from the state is detected as a candidate for a foreign body,
  • the determination means is A first recognition means (for example, the first physical quantity pattern recognition unit 105 in FIG. 5) for recognizing a pattern of change after detection of the first physical quantity for the foreign body candidate, and Based on the pattern of change after detection of the first physical quantity of the foreign body candidate recognized by the first recognition means, the foreign body candidate may be the foreign body to be captured.
  • a first determination means for example, the first determination unit 106 in FIG. 5 for first determining whether or not to use
  • the stimulus giving support for supporting the application of a predetermined stimulus to the foreign body candidate.
  • Means for example, the stimulus applying support unit 107 in FIG. 5
  • a second recognition means for example, the second physical quantity pattern recognition unit 109 in FIG. 5 for recognizing a pattern of change in the second physical quantity of the foreign body candidate after the stimulus is applied. Based on the pattern of change after detection of the second physical quantity of the foreign body candidate recognized by the second recognition means, the foreign body candidate may be the foreign body to be captured.
  • a second determination means for example, the second determination unit 110 in FIG.
  • the capture support means When the second determination determines that the candidate for the foreign body is likely to be the foreign body to be captured, the execution of a process for supporting the capture of the foreign body to be captured is permitted.
  • the second determination is that the candidate for the foreign body is unlikely to be the foreign body to be captured, or the first determination is that the candidate for the foreign body is the foreign body to be captured. If it is determined that there is no possibility of this, the execution of processing to support the capture of the foreign body to be captured is prohibited. be able to.
  • the foreign body to be captured can be appropriately identified from the candidates for the foreign body invading the range of the protected target, and can be captured as needed.
  • crimes and accidents caused by the invasion of foreign objects to be captured can be effectively prevented, and objects that should not be captured (for example, life forms such as birds) can be prevented from being accidentally captured.

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Engineering & Computer Science (AREA)
  • Alarm Systems (AREA)
  • Burglar Alarm Systems (AREA)

Abstract

The present invention enables effective prevention in advance of crimes or accidents resulting from the entry of an object that should be captured, while preventing mistaken capture of an object that should not be captured. A suspicious drone candidate detection unit 102 detects a foreign object candidate that enters the range of a protection zone. A first determination unit 106, a second determination unit 110, and the like determine whether the foreign object candidate is a foreign object to be captured on the basis of a prescribed determination method. A capture aid unit 111 executes processing for aiding the capture of the foreign object if it is determined that the foreign object candidate is the foreign object to be captured.

Description

情報処理装置Information processing equipment
 本発明は、情報処理装置に関する。 The present invention relates to an information processing device.
 従来、リモートで操作可能な小型無人飛行機(以下「ドローン」と呼ぶ)が普及し、建物や設備への上空からの侵入を容易にしている。そこでテロなどの犯罪や不慮の事故防止のため、脅威となるドローン(以下「不審なドローン」と呼ぶ)などの空中にある物体を捕獲するシステムに関する技術が提案されている(例えば、特許文献1参照)。 Conventionally, small unmanned aerial vehicles that can be operated remotely (hereinafter referred to as "drones") have become widespread, making it easier to invade buildings and equipment from the sky. Therefore, in order to prevent crimes such as terrorism and accidents, a technology related to a system for capturing objects in the air such as a threatening drone (hereinafter referred to as "suspicious drone") has been proposed (for example, Patent Document 1). reference).
特開2017-218141号公報Japanese Unexamined Patent Publication No. 2017-218141
 しかしながら、上述の特許文献1に記載の技術を含む従来の技術では、不審なドローンなどの空中にある物体を闇雲に捕獲するにすぎず、例えば、捕獲すべき物体と捕獲が好ましくない物体を見分けることはできない。そのため、本来捕獲すべき不審なドローンなどの物体だけでなく捕獲すべきでない物体を誤って捕獲してしまう可能性がある。 However, conventional techniques including the technique described in Patent Document 1 described above merely capture an object in the air such as a suspicious drone in a dark cloud, and for example, distinguish between an object to be captured and an object that is not preferable to be captured. It is not possible. Therefore, there is a possibility of accidentally capturing not only suspicious drones and other objects that should be captured, but also objects that should not be captured.
 本発明は、このような状況を鑑みてなされたものであり、捕獲すべき物体の侵入による犯罪や事故を未然に効果的に防止できると共に、捕獲すべきではない物体を誤って捕獲することを防止できるようにすることを目的とする。 The present invention has been made in view of such a situation, and it is possible to effectively prevent crimes and accidents caused by the invasion of an object to be captured, and to erroneously capture an object that should not be captured. The purpose is to be able to prevent it.
 上記目的を達成するため、本発明の一態様の情報処理装置は、
 保護対象の範囲に侵入してくる異物体の候補を検出する候補検出手段と、
 所定の判断手法に基づいて、前記異物体の候補が、捕獲対象の異物体であるか否かを判定する判定手段と、
 を備える。
In order to achieve the above object, the information processing apparatus according to one aspect of the present invention is
Candidate detection means for detecting candidates for foreign substances that invade the area to be protected,
A determination means for determining whether or not the foreign body candidate is a foreign body to be captured based on a predetermined determination method.
To prepare for.
 本発明の別の態様の情報処理装置は、
 前記判定手段により前記異物体の候補が前記捕獲対象の前記異物体であると判定された場合、当該異物体の捕獲を支援する処理を実行する捕獲支援手段と、
 を備える。
The information processing apparatus of another aspect of the present invention is
When the candidate for the foreign body is determined by the determination means to be the foreign body to be captured, the capture support means for executing the process of supporting the capture of the foreign body and the capture support means.
To prepare for.
 本発明のさらに別の態様の情報処理装置は、
 前記候補検出手段は、
  前記保護対象の範囲に含まれる1以上の物体の夫々の形状に関する情報を、物体形状情報として逐次取得して、取得した当該物体形状情報と通常状態の物体形状情報とを逐次比較して、通常状態とは相違する部分を異物体の候補として検出し、
 前記判定手段は、
  前記異物体の候補についての第1物理量の検出後の変化のパターンを認識する第1認識手段と、
  前記第1認識手段により認識された、当該異物体の候補についての前記第1物理量の検出後の変化のパターンに基づいて、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるか否かの第1判定を行う第1判定手段と、
  前記第1判定が、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるという判定の場合、前記異物体の候補に対して所定の刺激を付与することを支援する刺激付与支援手段と、
  当該異物体の候補についての第2物理量の、前記刺激が与えられた後の変化のパターンを認識する第2認識手段と、
  前記第2認識手段により認識された、当該異物体の候補についての前記第2物理量の検出後の変化のパターンに基づいて、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるか否かの第2判定を行う第2判定手段と、
 を有し、
 前記捕獲支援手段は、
  前記第2判定が、前記異物体の候補が前記捕獲対象の前記異物体の可能性が高いという判定の場合、当該捕獲対象の当該異物体の捕獲を支援する処理の実行を許可し、
  前記第2判定が、前記異物体の候補が前記捕獲対象の前記異物体の可能性が低いという判定の場合、若しくは、前記第1判定が、当該異物体の候補が前記捕獲対象の前記異物体の可能性がないという判定の場合、当該捕獲対象の当該異物体の捕獲を支援する処理の実行を禁止する。
The information processing apparatus of yet another aspect of the present invention is
The candidate detecting means is
Information on the shape of each of one or more objects included in the protected range is sequentially acquired as object shape information, and the acquired object shape information is sequentially compared with the object shape information in a normal state, and is usually used. A part different from the state is detected as a candidate for a foreign body,
The determination means is
A first recognition means for recognizing a pattern of change after detection of a first physical quantity for a foreign body candidate, and a first recognition means.
Based on the pattern of change after detection of the first physical quantity of the foreign body candidate recognized by the first recognition means, the foreign body candidate may be the foreign body to be captured. The first determination means for making the first determination as to whether or not it is
When the first determination determines that the foreign body candidate may be the foreign body to be captured, the stimulus giving support for supporting the application of a predetermined stimulus to the foreign body candidate. Means and
A second recognition means for recognizing a pattern of change in the second physical quantity of the foreign body candidate after the stimulus is given, and
Based on the pattern of change after detection of the second physical quantity of the foreign body candidate recognized by the second recognition means, the foreign body candidate may be the foreign body to be captured. A second determination means for making a second determination as to whether or not it is present,
Have,
The capture support means
When the second determination determines that the candidate for the foreign body is likely to be the foreign body to be captured, the execution of a process for supporting the capture of the foreign body to be captured is permitted.
The second determination is that the candidate for the foreign body is unlikely to be the foreign body to be captured, or the first determination is that the candidate for the foreign body is the foreign body to be captured. If it is determined that there is no possibility of this, the execution of the process of supporting the capture of the foreign body to be captured is prohibited.
 本発明によれば、捕獲すべき物体の侵入による犯罪や事故を未然に効果的に防止できると共に、捕獲すべきではない物体を誤って捕獲することを防止できる。 According to the present invention, it is possible to effectively prevent crimes and accidents caused by the intrusion of an object to be captured, and to prevent accidental capture of an object that should not be captured.
本発明の一実施形態に係る情報処理装置が適用されるドローン捕獲システムの概要に関する図である。It is a figure regarding the outline of the drone capture system to which the information processing apparatus which concerns on one Embodiment of this invention is applied. 図1のドローン捕獲システムに適用されるドローンを捕獲する手法の一例の概要を説明する図である。It is a figure explaining the outline of an example of the method of capturing a drone applied to the drone capture system of FIG. 図1のドローン捕獲システムについての情処理システムとしての構成の一例を示すブロック図である。It is a block diagram which shows an example of the structure of the drone capture system of FIG. 1 as an information processing system. 図3の情報処理システムのうちサーバのハードウェア構成を示すブロック図である。It is a block diagram which shows the hardware configuration of the server in the information processing system of FIG. 図4のサーバの機能的構成の一例を示す機能ブロック図である。It is a functional block diagram which shows an example of the functional configuration of the server of FIG. 図5のサーバが実行するドローン捕獲処理を説明するフローチャートである。It is a flowchart explaining the drone capture process executed by the server of FIG.
 本発明の実施形態を説明するに先立ち、図1及び図2を用いて、本発明の情報処理装置の一実施形態に係るサーバが適用されるシステムの一例として、ドローン捕獲システムの概要について説明する。
 図1は、本発明の情報処理装置の一実施形態に係るサーバが適用されるドローン捕獲システムの概要に関する図である。
 ドローン捕獲システムは、地表に露出している建物や設備に対して侵入してくる不審なドローンを捕獲するシステムである。
Prior to explaining the embodiment of the present invention, the outline of the drone capture system will be described as an example of the system to which the server according to the embodiment of the information processing apparatus of the present invention is applied by using FIGS. 1 and 2. ..
FIG. 1 is a diagram relating to an outline of a drone capture system to which a server according to an embodiment of the information processing apparatus of the present invention is applied.
The drone capture system is a system that captures suspicious drones that invade buildings and equipment exposed on the surface of the earth.
 地表に露出している建物や設備に対して侵入してくる不審な物体が、地上や水面上から侵入してくる物体、例えば人物、車、自転車、及び船舶などであれば、その部位を何らかの方法で遮蔽する手法を適用することで、これらの物体の侵入を防ぐことができる。
 例えば、建物や設備の周囲に柵や塀を囲むように設けることで、建物や設備の部位を遮蔽する手法を適用すれば、地上や水面上から接近してくる不審な物体の侵入を防止することができる。
 しかしながら、地表に露出している建物や設備に対して侵入してくる不審な物体が、ドローンである場合、そのドローンは、建物や設備に対して上空から接近してくる。このため、建物や設備の上空に遮蔽物を設置する必要があるが、コストが増大して現実的ではない。
 したがって、地表に露出している建物や設備の部位を何らかの方法で遮蔽する手法は、不審なドローンの侵入を防ぐ手法としては不適切である。しかしながら、不審なドローンに対して何ら措置を施さないと、不審なドローンの建物や設備の内部への侵入を容易に許してしまうことになる。また、不審なドローンの建物や設備の内部への侵入自体を仮に防止できたとしても、その建物や設備の上空から不審なドローンから爆弾などの落下物を投下されるおそれもある。
If the suspicious object that invades the building or equipment exposed on the surface of the earth is an object that invades from the ground or the surface of the water, such as a person, a car, a bicycle, or a ship, the part is somehow. By applying the method of shielding by the method, it is possible to prevent the invasion of these objects.
For example, by applying a method of shielding a part of a building or equipment by surrounding a fence or fence around the building or equipment, it is possible to prevent the intrusion of suspicious objects approaching from the ground or the surface of the water. be able to.
However, if the suspicious object that invades the building or equipment exposed on the surface of the earth is a drone, the drone approaches the building or equipment from the sky. For this reason, it is necessary to install a shield above the building or equipment, but this is not realistic due to the increased cost.
Therefore, the method of shielding the parts of buildings and equipment exposed on the ground surface in some way is inappropriate as a method of preventing the invasion of suspicious drones. However, if no measures are taken against the suspicious drone, the suspicious drone can easily be allowed to enter the inside of the building or equipment. Even if it is possible to prevent a suspicious drone from invading the inside of a building or equipment, there is a risk that a suspicious drone will drop a fallen object such as a bomb from the sky above the building or equipment.
 このような不審なドローンの建物や設備への侵入などによる脅威を排除するために、このようなドローンに対して妨害電波を発信することにより、そのドローンの駆動を制御不能にする技術は、従来から存在し、「アンチドローン技術」と呼ばれている。このようなアンチドローン技術を適用した製品は、海外の企業で販売されている。
 しかしながら、本願の出願時点の日本国では、このアンチドローン技術は、法律や周辺への影響という点で国内民間企業での採用は難しいと考えられている。
 そもそも、従来のアンチドローン技術では、様々な物体の中から不審なドローンのみを見分けて排除することは、非常に困難である。
In order to eliminate the threat caused by the intrusion of such a suspicious drone into a building or equipment, the technology of transmitting an interfering radio wave to such a drone to make the driving of the drone uncontrollable has been conventionally used. It exists from and is called "anti-drone technology". Products to which such anti-drone technology is applied are sold by overseas companies.
However, in Japan at the time of filing the application of this application, it is considered difficult for domestic private companies to adopt this anti-drone technology in terms of the influence on the law and surrounding areas.
In the first place, with conventional anti-drone technology, it is very difficult to distinguish and eliminate only suspicious drones from various objects.
 これに対して、図1に示すドローン捕獲システムは、不審なドローンのみを見分けて捕獲することができる。
 具体的には例えば、図1の例では、施設Bが保護対象とされ、この保護対象を保護すべき3次元の領域(以下、「保護対象領域W」と呼ぶ)の範囲内に侵入してくる物体として、不審なドローンDの他、野鳥P1や有人飛行機P2が存在する。図1に示すドローン捕獲システムは、不審なドローンDと、それ以外の物体(野鳥P1や有人飛行機P2など)を見分けて、捕獲することができる。
 これにより、不審なドローンDにより行われる犯罪や事故を未然に防止することができる。
 さらに、図1に示すドローン捕獲システムは、図2に示す手法により、不審なドローンDのみを見分けて、捕獲することができるので、本願の出願時点の日本国の法律が適用されても問題は生じず、かつ施設Bの周辺への影響が非常に少ないものとなる。
On the other hand, the drone capture system shown in FIG. 1 can distinguish and capture only suspicious drones.
Specifically, for example, in the example of FIG. 1, facility B is a protection target, and the facility B invades within the range of a three-dimensional area (hereinafter, referred to as “protection target area W”) to protect the protection target. In addition to the suspicious drone D, there are wild bird P1 and manned airplane P2 as objects to come. The drone capture system shown in FIG. 1 can discriminate between a suspicious drone D and other objects (wild bird P1, manned airplane P2, etc.) and capture them.
As a result, it is possible to prevent crimes and accidents committed by the suspicious drone D.
Further, since the drone capture system shown in FIG. 1 can identify and capture only the suspicious drone D by the method shown in FIG. 2, there is no problem even if the Japanese law at the time of filing the application of the present application is applied. It does not occur and the influence on the surroundings of the facility B is very small.
 以下、図2を用いて、図1のドローン捕獲システムに適用されるドローンを捕獲する手法の一例について説明する。
 図2は、図1のドローン捕獲システムに適用されるドローンを捕獲する手法の一例を説明する図である。
 図2に示される手法は、フェーズPH0乃至PH5からなる手法である。
Hereinafter, an example of a method for capturing a drone applied to the drone capture system of FIG. 1 will be described with reference to FIG.
FIG. 2 is a diagram illustrating an example of a method for capturing a drone applied to the drone capture system of FIG.
The method shown in FIG. 2 is a method including phases PH0 to PH5.
 フェーズPH0では、システム管理者は、不審なドローンDを捕獲するための準備をする。 In Phase PH0, the system administrator prepares to capture the suspicious drone D.
 システム管理者は、このような準備として先ず、サーバ1、偵察装置J、捕獲装置C、及び刺激装置Sの夫々を、監視者Aが存在する監視施設Kに配備する。また、システム管理者は、レーダLを、保護対象である施設Bの中心周辺に配備する。 As such a preparation, the system administrator first deploys each of the server 1, the reconnaissance device J, the capture device C, and the stimulator S to the monitoring facility K where the monitor A exists. In addition, the system administrator deploys the radar L around the center of the facility B to be protected.
 サーバ1は、システム管理者により管理され、図1のドローン捕獲システムの全体の制御を実行すべく、各種各様な処理を実行する。 The server 1 is managed by the system administrator and executes various processes in order to execute the overall control of the drone capture system shown in FIG.
 偵察装置Jは、不審なドローンDに関する画像などの各種情報を取得することで、当該不審なドローンDを偵察する。
 以下の例では便宜上、偵察装置Jは、ドローンとして構成されるものとする。偵察装置Jは、偵察の対象となる不審なドローンDなどに向かい適切な飛行経路を設定して飛翔して近づき、その不審なドローンDに関する各種情報を取得する。
The reconnaissance device J scouts the suspicious drone D by acquiring various information such as an image related to the suspicious drone D.
In the following example, for convenience, the reconnaissance device J is configured as a drone. The reconnaissance device J sets an appropriate flight path toward a suspicious drone D or the like to be reconnaissance, flies and approaches, and acquires various information about the suspicious drone D.
 捕獲装置Cは、不審なドローンDを捕獲する。
 この例では便宜上、捕獲装置Cは、捕獲用の網を搭載したドローンとして構成されるものとする。
 なお、捕獲装置Cによる捕獲の手法は、網をドローンに搭載する手法に特に限定されず、その他例えば、電磁石をドローンに搭載する手法、地上からネットガンなどで投網する手法など各種各様な手法を採用することができる。
The capture device C captures the suspicious drone D.
In this example, for convenience, the capture device C is configured as a drone equipped with a capture net.
The method of capturing by the capture device C is not particularly limited to the method of mounting the net on the drone, and various other methods such as a method of mounting an electromagnet on the drone and a method of casting a net from the ground with a net gun or the like. Can be adopted.
 刺激装置Sは、保護対象領域Wに侵入してきた物体に対して物理的干渉を行うことで、当該物体に刺激を付与する。
 このようにして刺激が付与された物体が何らかの反応をした場合、その物体は生物などであり不審なドローンDではない。即ち、刺激装置Sは、保護対象領域Wに侵入してきた物体が不審なドローンDであるか否かの見きわめのために用いられる装置である。
 刺激装置Sにより物体へ刺激を与える手法は、特に限定されず、例えば、アンテナから電磁波の放射をする手法、スピーカや爆薬から音波の放射をする手法、ランプなどで光を放射する手法など各種各様な手法を採用することができる。
The stimulator S gives a stimulus to the object by physically interfering with the object that has invaded the protected area W.
When an object to which the stimulus is applied in this way reacts in some way, the object is a living thing or the like and is not a suspicious drone D. That is, the stimulator S is a device used for determining whether or not the object that has invaded the protected area W is a suspicious drone D.
The method of stimulating an object with the stimulator S is not particularly limited, and various methods such as a method of radiating electromagnetic waves from an antenna, a method of radiating sound waves from a speaker or an explosive, and a method of radiating light with a lamp or the like are used. Various methods can be adopted.
 上述のサーバ1、偵察装置J、捕獲装置C、及び刺激装置Sの夫々、及び監視者Aが監視施設Kに配備される。ここで監視施設Kとは保護対象領域Wに侵入してくる物体を監視するための施設である。 Each of the above-mentioned server 1, reconnaissance device J, capture device C, and stimulator S, and observer A are deployed in the monitoring facility K. Here, the monitoring facility K is a facility for monitoring an object invading the protected area W.
 レーダLは、保護対象領域Wに侵入してきた物体に向けて電磁波を発射し、その反射波を測定することにより、当該物体までの距離や方向を測る。
 例えば2019年7月現在の民生用レーザレーダ(LIDAR)の観測範囲は1kmであることから、レーダLが設置された位置を中心としてその中心から半径1km以内のエリアが保護対象領域Wとして設定される。
The radar L emits an electromagnetic wave toward an object that has invaded the protected area W, and measures the reflected wave to measure the distance and direction to the object.
For example, since the observation range of the consumer laser radar (LIDAR) as of July 2019 is 1 km, the area within a radius of 1 km from the center of the position where the radar L is installed is set as the protection target area W. Radar.
 次に、システム設計者は、不審なドローンDを捕獲するための準備として、各種各様な初期設定を行う。
 具体的には例えば、図2に示すドローンを捕獲する手法によれば、保護対象領域Wに侵入した物体が異常(不審なドローンDの候補)か否かの判定が先ず行われる(後述するフェーズPH1)。この判定のための初期設定が次のようにして行われる。
 即ち、一般的な異常を検出する手法として、通常を元にし、その通常から外れたものを異常として検出するという手法が存在する。図2に示すドローンを捕獲する手法では、この一般的な異常を検出する手法に基づいて、保護対象領域Wの通常状態を元にして、その通常状態から外れたものを異常状態として検出するという手法が採用される。このため、システム設計者は、初期設定のひとつとして、保護対象領域Wの通常状態をサーバ1に記憶させる必要がある。
 具体的には例えば、サーバ1は、保護対象領域W内に不審ドローン候補Xが存在しない状態を通常状態として、その通常状態においてレーダLから得られた情報を、通常時物体形状情報として取得して、記憶部(後述の図4の記憶部18)に記憶させる。
 ここで、物体形状情報とは、保護対象の施設Bを含む、保護対象領域W内に存在する、建物、施設、植物などの形状や地面や水面の形状に関する情報をいう。
Next, the system designer makes various initial settings in preparation for capturing the suspicious drone D.
Specifically, for example, according to the method of capturing a drone shown in FIG. 2, it is first determined whether or not an object invading the protected area W is abnormal (a candidate for a suspicious drone D) (phase described later). PH1). The initial setting for this determination is performed as follows.
That is, as a method of detecting a general abnormality, there is a method of detecting an abnormality that is out of the normal state based on the normal state. In the method of capturing the drone shown in FIG. 2, based on the method of detecting this general abnormality, based on the normal state of the protected area W, the one deviating from the normal state is detected as an abnormal state. The method is adopted. Therefore, the system designer needs to store the normal state of the protected area W in the server 1 as one of the initial settings.
Specifically, for example, the server 1 acquires the information obtained from the radar L in the normal state as the normal state when the suspicious drone candidate X does not exist in the protected area W as the normal object shape information. Then, it is stored in a storage unit (storage unit 18 in FIG. 4 described later).
Here, the object shape information refers to information on the shapes of buildings, facilities, plants, etc., and the shapes of the ground and water surface existing in the protected area W, including the facility B to be protected.
 このような準備が完了すると、フェーズPH0からフェーズPH1に移行し、不審なドローンDを捕獲するための処理が開始される。 When such preparations are completed, the process shifts from Phase PH0 to Phase PH1 and the process for capturing the suspicious drone D is started.
 サーバ1は、レーダLから得られる情報を保護対象領域W内の物体形状情報として逐次取得し続ける。
 サーバ1は、この逐次取得される物体形状情報と、通常時物体形状情報とを比較する。
 サーバ1は、その比較により相違が認識された場合、その認識された相違により特定される物体を、不審なドローンDの候補X(以下「不審ドローン候補X」と呼ぶ)として認識し、不審ドローン候補Xの追跡を開始する。
 不審ドローン候補Xの追跡の手法は、特に限定されないが、以下の例では、不審ドローン候補Xの空間移動履歴を記録する手法が採用されているものとする。即ち、レーダLにより得られる情報により特定される不審ドローン候補Xの三次元空間上(保護対象領域W内)の位置は刻々と変化していく。このように刻々と変化していく各位置の履歴が、不審ドローン候補Xの空間移動履歴として記録される。サーバ1は、不審ドローン候補Xが施設Bに近づいてくると不審ドローン候補Xの空間移動履歴より判定した場合、不審ドローン候補Xに対して最も近距離に存在する偵察装置Jに対し、不審ドローン候補Xに関する情報を取得するよう指示する。
 このような指示を受けた偵察装置Jは、不審ドローン候補Xに近づき、その不審ドローン候補Xに関する画像などの各種情報を取得する。
 各種情報は、特に限定されず、例えばここでは光学カメラ(夜間は赤外線灯光器を併用する)により撮像された結果得られる画像の情報が少なくとも取得されるものとする。そして、偵察装置Jは、このようにして取得した不審ドローン候補Xに関する情報を無線によりサーバ1に転送する。
The server 1 continues to sequentially acquire the information obtained from the radar L as the object shape information in the protection target area W.
The server 1 compares the sequentially acquired object shape information with the normal object shape information.
When the difference is recognized by the comparison, the server 1 recognizes the object specified by the recognized difference as the candidate X of the suspicious drone D (hereinafter referred to as "suspicious drone candidate X"), and the suspicious drone. Start tracking candidate X.
The method for tracking the suspicious drone candidate X is not particularly limited, but in the following example, it is assumed that a method for recording the spatial movement history of the suspicious drone candidate X is adopted. That is, the position of the suspicious drone candidate X specified by the information obtained by the radar L in the three-dimensional space (within the protection target area W) changes from moment to moment. The history of each position that changes from moment to moment is recorded as the spatial movement history of the suspicious drone candidate X. When the server 1 determines from the spatial movement history of the suspicious drone candidate X that the suspicious drone candidate X approaches the facility B, the server 1 makes a suspicious drone to the reconnaissance device J that exists at the closest distance to the suspicious drone candidate X. Instruct to get information about candidate X.
Upon receiving such an instruction, the reconnaissance device J approaches the suspicious drone candidate X and acquires various information such as an image related to the suspicious drone candidate X.
The various information is not particularly limited, and for example, here, it is assumed that at least the information of the image obtained as a result of being imaged by an optical camera (in combination with an infrared lamp at night) is acquired. Then, the reconnaissance device J wirelessly transfers the information regarding the suspicious drone candidate X acquired in this way to the server 1.
 フェーズPH2において、サーバ1は、不審ドローン候補Xの空間移動履歴、及び偵察装置Jから転送された画像などの各種情報(ここで得られる空間移動履歴、及び画像などの各種情報を総称して「第1物理量」と呼ぶ)のパターンを認識する。ここでパターンとは、詳細は後述するが、あらゆる状況で示す決まった行動や形態を総称するものである。サーバ1は、第1物理量が示すパターンに基づいて、不審ドローン候補Xが不審なドローンDである可能性を判定する。
 この可能性に応じてどのようにするのかは、システム設計者の設計事項であるが、図2に示す手法では、次のように3段階の処理が実行されるものとする。
 即ち、図2に示す手法では、不審ドローン候補Xが不審なドローンDである可能性が低い場合(不審なドローンDではないと実質的に判定できる場合)の第1段階の処理が存在する。また、不審ドローン候補Xが不審なドローンDである可能性が中程度の場合(不審なドローンDであるか否かを確定できない場合)の第2段階の処理が存在する。また、不審ドローン候補Xが不審なドローンDである可能性が高い場合(不審ドローン候補Xが不審なドローンDであると実質的に判断できる場合)の第3段階の処理が存在する。
In the phase PH2, the server 1 collectively refers to various information such as the spatial movement history of the suspicious drone candidate X and the image transferred from the reconnaissance device J (the spatial movement history obtained here and various information such as the image. Recognize the pattern of "first physical quantity"). Here, the pattern is a general term for fixed behaviors and forms shown in all situations, although details will be described later. The server 1 determines the possibility that the suspicious drone candidate X is a suspicious drone D based on the pattern indicated by the first physical quantity.
How to do it according to this possibility is a design matter of the system designer, but in the method shown in FIG. 2, it is assumed that three stages of processing are executed as follows.
That is, in the method shown in FIG. 2, there is a first stage process when the possibility that the suspicious drone candidate X is a suspicious drone D is low (when it can be substantially determined that the suspicious drone candidate X is not the suspicious drone D). Further, there is a second stage process when the possibility that the suspicious drone candidate X is a suspicious drone D is moderate (when it cannot be determined whether or not the suspicious drone candidate X is a suspicious drone D). Further, there is a third stage process when there is a high possibility that the suspicious drone candidate X is a suspicious drone D (when it can be substantially determined that the suspicious drone candidate X is a suspicious drone D).
 サーバ1は、不審ドローン候補Xが不審なドローンDの可能性が低いと判定し場合、第1段階の処理として、不審ドローン候補Xの監視を続行する(フェーズPH1を継続する)か、あるいは監視を終了する。
 サーバ1は、不審ドローン候補Xが不審なドローンDである可能性が中程度であると判定した場合、フェーズPH2からフェーズPH3へ移行させ、第2段階の処理としてフェーズPH3の処理を実行する。
 サーバ1は、不審ドローン候補Xが不審なドローンDの可能性が高いと判定した場合、フェーズPH2からフェーズPH4へ移行させ、第3段階の処理としてフェーズPH4の処理を実行する。
If the server 1 determines that the suspicious drone candidate X is unlikely to be a suspicious drone D, the server 1 continues monitoring the suspicious drone candidate X (continues phase PH1) or monitors as the first stage processing. To finish.
When the server 1 determines that the possibility that the suspicious drone candidate X is the suspicious drone D is moderate, the server 1 shifts from the phase PH2 to the phase PH3 and executes the phase PH3 process as the second stage process.
When the server 1 determines that the suspicious drone candidate X has a high possibility of being a suspicious drone D, the server 1 shifts from the phase PH2 to the phase PH4 and executes the phase PH4 process as the third stage process.
 フェーズPH3において、サーバ1は、不審ドローン候補Xが不審なドローンDであるか否かを詳細に判定する目的で、刺激装置Sに対し、不審ドローン候補Xに刺激を付与するよう指示を行う。ここでは説明の便宜上、不審ドローン候補Xに対して付与する刺激は破裂音とする。即ち、ここでは、刺激装置Sは、不審ドローン候補Xに対して破裂音をスピーカなどから出力することで、その不審ドローン候補Xに対して刺激を付与する。
 サーバ1は、不審ドローン候補Xへの刺激に対する応答として、例えば破裂音が出力された後の不審ドローン候補Xの空間移動履歴のパターン及び偵察装置Jから転送された画像などの各種情報のパターン(ここで得られる空間移動履歴、及び画像などの各種情報を「第2物理量」と呼ぶ)を認識する。サーバ1は、第2物理量が示すパターンに基づいて、不審ドローン候補Xが不審なドローンDである可能性を判定する。
 例えば、不審ドローン候補Xが野生動物の場合、不審ドローン候補Xは、刺激装置Sにより付与された刺激に驚き、何らかの生体反応を示すはずである。ここでいう何らかの生体反応とは、例えば、逃げる行動、失神して落下する現象、興奮して刺激に向かって攻撃を仕掛けてくる行動、興奮して体温が上昇する反応、興奮して警戒音を発する反応などがある。これらの生体反応があった場合となかった場合とでは、第2物理量が異なるはずである。即ち、サーバ1は、第2物理量に基づいて生体反応があったか否かを判定し、その判定結果に基づいて不審なドローンDの可能性を判定することができる。
 ここで、不審なドローンDの可能性に応じてどのようにするのかは、システム設計者の設計事項であるが、図2に示す手法では、次のように2段階の処理が実行されるものとする。
 即ち、図2に示す手法では、不審ドローン候補Xが不審なドローンDである可能性が低い場合(不審ドローン候補Xが不審なドローンDではないと実質的に判定できる場合)の第1段階の処理が存在する。また、不審ドローン候補Xが不審なドローンDである可能性が高い場合(不審ドローン候補Xが不審なドローンDであると実質的に判断できる場合)の第2段階の処理が存在する。
 サーバ1は、不審なドローンDの可能性が低いと判定し場合、第1段階の処理として、不審ドローン候補Xの監視を続行する(フェーズPH2に戻る)か、あるいは監視を終了する。
 サーバ1は、不審ドローン候補Xが不審なドローンDの可能性が高いと判定した場合、フェーズPH3からフェーズPH4へ移行させ、第2段階の処理としてフェーズPH4の処理を実行する。
In the phase PH3, the server 1 instructs the stimulator S to give a stimulus to the suspicious drone candidate X for the purpose of determining in detail whether or not the suspicious drone candidate X is the suspicious drone D. Here, for convenience of explanation, the stimulus given to the suspicious drone candidate X is a plosive sound. That is, here, the stimulator S gives a stimulus to the suspicious drone candidate X by outputting a plosive sound to the suspicious drone candidate X from a speaker or the like.
As a response to the stimulus to the suspicious drone candidate X, the server 1 has a pattern of various information such as a pattern of the spatial movement history of the suspicious drone candidate X after the burst sound is output and an image transferred from the reconnaissance device J ( The spatial movement history obtained here and various information such as images are referred to as "second physical quantities"). The server 1 determines the possibility that the suspicious drone candidate X is a suspicious drone D based on the pattern indicated by the second physical quantity.
For example, when the suspicious drone candidate X is a wild animal, the suspicious drone candidate X should be surprised at the stimulus given by the stimulator S and show some biological reaction. Some biological reactions here are, for example, the behavior of escaping, the phenomenon of fainting and falling, the behavior of being excited and attacking toward a stimulus, the reaction of being excited and raising the body temperature, and the phenomenon of being excited and alert. There is a reaction to be emitted. The second physical quantity should be different depending on whether or not these biological reactions occur. That is, the server 1 can determine whether or not there is a biological reaction based on the second physical quantity, and can determine the possibility of a suspicious drone D based on the determination result.
Here, what to do according to the possibility of suspicious drone D is a design matter of the system designer, but in the method shown in FIG. 2, two-step processing is executed as follows. And.
That is, in the method shown in FIG. 2, when it is unlikely that the suspicious drone candidate X is a suspicious drone D (when it can be substantially determined that the suspicious drone candidate X is not a suspicious drone D), the first stage. There is a process. Further, there is a second stage process when there is a high possibility that the suspicious drone candidate X is a suspicious drone D (when it can be substantially determined that the suspicious drone candidate X is a suspicious drone D).
When the server 1 determines that the possibility of the suspicious drone D is low, the server 1 continues the monitoring of the suspicious drone candidate X (returns to the phase PH2) or ends the monitoring as the first stage processing.
When the server 1 determines that the suspicious drone candidate X has a high possibility of being a suspicious drone D, the server 1 shifts from the phase PH3 to the phase PH4 and executes the phase PH4 process as the second stage process.
 不審ドローン候補Xが不審なドローンDの可能性が高い判定された場合、サーバ1は、フェーズPH4の処理として、不審なドローンDの捕獲を行う目的で、捕獲装置Cに対し、捕獲指示を行う。そして、捕獲指示を受けた捕獲装置Cは、不審なドローンDに向けて飛翔して近づき、不審なドローンDを投網により捕獲する。 When the suspicious drone candidate X is determined to have a high possibility of being a suspicious drone D, the server 1 issues a capture instruction to the capture device C for the purpose of capturing the suspicious drone D as a process of the phase PH4. .. Then, the capture device C, which has received the capture instruction, flies toward and approaches the suspicious drone D, and captures the suspicious drone D by casting net.
 フェーズPH5において、捕獲装置Cは、捕獲した不審なドローンDを、例えばその不審なドローンDに搭載された爆薬が破裂しても周辺への影響がないような安全な場所に格納する。 In Phase PH5, the capture device C stores the captured suspicious drone D in a safe place where, for example, the explosive mounted on the suspicious drone D does not affect the surroundings even if it explodes.
 このように、フェーズPH0において、サーバ1は、保護対象領域W内に不審ドローン候補Xが存在しない状態においてレーダLから得られた情報を、通常時物体形状情報として取得する。
 フェーズPH1において、サーバ1は、レーダLから得られる情報を保護対象領域W内の物体形状情報として逐次取得し続ける。サーバ1は、この逐次取得される物体形状情報と通常時物体形状情報とを比較して、その認識された相違により特定される物体を不審ドローン候補Xとして認識して、不審ドローン候補Xの追跡を開始する。
 フェーズPH2において、サーバ1は、不審ドローン候補Xの第1物理量たる空間移動履歴、及び画像などの各種情報を取得する。そして、サーバ1は、第1物理量の示すパターンに基づき不審ドローン候補Xが不審なドローンDである可能性を判定する。
 フェーズPH3において、サーバ1は、刺激装置Sに対し、不審ドローン候補Xに刺激を付与するよう指示を行う。そして、サーバ1は、不審ドローン候補Xの第2物理量たる空間移動履歴、及び画像などの各種情報を取得する。そして、サーバ1は、第2物理量の示すパターンに基づき不審ドローン候補Xが不審なドローンDである可能性を判定する。
 フェーズPH4において、サーバ1は、捕獲装置Cに対し、不審なドローンDの捕獲を行う目的で、捕獲指示を行う。
 これにより、施設Bに対して侵入してくる物体の中から本来捕獲すべき不審なドローンのみを見分けて捕獲することにより、不審なドローンによる犯罪や事故を未然に防ぐことが可能になる。
As described above, in the phase PH0, the server 1 acquires the information obtained from the radar L in the state where the suspicious drone candidate X does not exist in the protected area W as the normal object shape information.
In the phase PH1, the server 1 continues to sequentially acquire the information obtained from the radar L as the object shape information in the protection target area W. The server 1 compares the sequentially acquired object shape information with the normal object shape information, recognizes the object specified by the recognized difference as the suspicious drone candidate X, and tracks the suspicious drone candidate X. To start.
In the phase PH2, the server 1 acquires various information such as a spatial movement history, which is the first physical quantity of the suspicious drone candidate X, and an image. Then, the server 1 determines the possibility that the suspicious drone candidate X is the suspicious drone D based on the pattern indicated by the first physical quantity.
In the phase PH3, the server 1 instructs the stimulator S to give a stimulus to the suspicious drone candidate X. Then, the server 1 acquires various information such as a spatial movement history, which is a second physical quantity of the suspicious drone candidate X, and an image. Then, the server 1 determines the possibility that the suspicious drone candidate X is the suspicious drone D based on the pattern indicated by the second physical quantity.
In the phase PH4, the server 1 gives a capture instruction to the capture device C for the purpose of capturing the suspicious drone D.
As a result, it is possible to prevent crimes and accidents caused by suspicious drones by discriminating and capturing only suspicious drones that should be captured from the objects that invade facility B.
 以上、図1及び図2を用いて、本発明の情報処理装置の一実施形態に係るサーバが適用されるシステムの一例として、ドローン捕獲システムの概要について説明した。
 次に、本発明の一実施形態について図3以降を用いて説明する。
The outline of the drone capture system has been described above with reference to FIGS. 1 and 2 as an example of a system to which the server according to the embodiment of the information processing apparatus of the present invention is applied.
Next, an embodiment of the present invention will be described with reference to FIGS. 3 and later.
 図3は、図1のドローン捕獲システムについての情報処理システムとしての構成の一例を示すブロック図である。 FIG. 3 is a block diagram showing an example of the configuration of the drone capture system of FIG. 1 as an information processing system.
 上述のドローン捕獲システムを可能とすべく、本発明の情報処理装置の一実施形態に係るサーバ1を含む情報処理システムは、図3に示すようにサーバ1、捕獲装置C、偵察装置J、レーダL、及び刺激装置Sを含むように構成される。
 サーバ1、捕獲装置C、偵察装置J、レーダL、及び刺激装置Sは、所定のネットワークを介して相互に接続されている。
In order to enable the above-mentioned drone capture system, the information processing system including the server 1 according to the embodiment of the information processing apparatus of the present invention includes the server 1, the capture device C, the reconnaissance device J, and the radar as shown in FIG. It is configured to include L and a stimulator S.
The server 1, the capture device C, the reconnaissance device J, the radar L, and the stimulator S are connected to each other via a predetermined network.
 図4は、図3の情報処理装置のうちサーバのハードウェア構成を示すブロック図である。 FIG. 4 is a block diagram showing a hardware configuration of a server among the information processing devices of FIG.
 サーバ1は、CPU(Central Processing Unit)11と、ROM(Read Only Memory)12と、RAM(Random Access Memory)13と、バス14と、入出力インターフェース15と、出力部16と、入力部17と、記憶部18と、通信部19と、ドライブ20とを備えている。 The server 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, and an input unit 17. , A storage unit 18, a communication unit 19, and a drive 20.
 CPU11は、ROM12に記録されている各種プログラム、または、記憶部18からRAM13にロードされた各種プログラムに従って各種の処理を実行する。
 RAM13には、CPU11が各種の処理を実行する上において必要なデータなども適宜記憶される。
The CPU 11 executes various processes according to various programs recorded in the ROM 12 or various programs loaded from the storage unit 18 into the RAM 13.
Data and the like necessary for the CPU 11 to execute various processes are also appropriately stored in the RAM 13.
 CPU11、ROM12及びRAM13は、バス14を介して相互に接続されている。このバス14にはまた、入出力インターフェース15も接続されている。入出力インターフェース15には、出力部16、入力部17、記憶部18、通信部19及びドライブ20が接続されている。 The CPU 11, ROM 12 and RAM 13 are connected to each other via the bus 14. An input / output interface 15 is also connected to the bus 14. An output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20 are connected to the input / output interface 15.
 出力部16は、各種液晶ディスプレイなどで構成され、各種情報を出力する。
 入力部17は、各種ハードウェアなどで構成され、各種情報を入力する。
 記憶部18は、ハードディスクやDRAM(Dynamic Random Access Memory)などで構成され、各種データを記憶する。
 通信部19は、インターネットを含むネットワークNを介して他の装置(図4の捕獲装置C、偵察装置J、レーダL、及び刺激装置S)との間で行う通信を制御する。
The output unit 16 is composed of various liquid crystal displays and the like, and outputs various information.
The input unit 17 is composed of various hardware and the like, and inputs various information.
The storage unit 18 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores various data.
The communication unit 19 controls communication with other devices (capture device C, reconnaissance device J, radar L, and stimulator S in FIG. 4) via a network N including the Internet.
 ドライブ20は、必要に応じて設けられる。ドライブ20には磁気ディスク、光ディスク、光磁気ディスク、あるいは半導体メモリなどよりなる、リムーバブルメディア21が適宜装着される。ドライブ20によってリムーバブルメディア21から読み出されたプログラムは、必要に応じて記憶部18にインストールされる。またリムーバブルメディア21は、記憶部18に記憶されている各種データも、記憶部18と同様に記憶することができる。 The drive 20 is provided as needed. A removable media 21 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately mounted on the drive 20. The program read from the removable media 21 by the drive 20 is installed in the storage unit 18 as needed. Further, the removable media 21 can also store various data stored in the storage unit 18 in the same manner as the storage unit 18.
 次に図5を参照して、図4に示すサーバ1の機能的構成について説明する。
 図5は、図4のサーバ1の機能的構成の一例を示す機能ブロック図である。
Next, with reference to FIG. 5, the functional configuration of the server 1 shown in FIG. 4 will be described.
FIG. 5 is a functional block diagram showing an example of the functional configuration of the server 1 of FIG.
 図5のサーバ1のCPU11においては、物体形状情報取得部101と、不審ドローン候補検出部102と、通知部103と、第1物理量取得指示部104と、第1物理量パターン認識部105と、第1判定部106と、刺激付与支援部107と、第2物理量取得指示部108と、第2物理量パターン認識部109と、第2判定部110と、捕獲支援部111と、第1物理量取得部201と、第2物理量取得部202とが機能する。 In the CPU 11 of the server 1 of FIG. 5, the object shape information acquisition unit 101, the suspicious drone candidate detection unit 102, the notification unit 103, the first physical quantity acquisition instruction unit 104, the first physical quantity pattern recognition unit 105, and the first 1 determination unit 106, stimulus application support unit 107, second physical quantity acquisition instruction unit 108, second physical quantity pattern recognition unit 109, second determination unit 110, capture support unit 111, and first physical quantity acquisition unit 201. And the second physical quantity acquisition unit 202 function.
 物体形状情報取得部101は、レーダLにおいて受信された物体形状に関する情報を、物体形状情報として取得する。 The object shape information acquisition unit 101 acquires the information regarding the object shape received by the radar L as the object shape information.
 具体的には例えば、先ず、物体形状情報取得部101は、不審ドローン候補Xが存在しない状態における物体形状情報を、通常時物体形状情報として取得して、記憶部18に記憶させる。
 ここで、物体の変化、つまり建物や施設の増改築、取り壊し、施設近隣設備の変更、植物の成長及び枯死などが発生する場合がある。この場合、通常時物体形状情報も合わせて変更されるべきである。そのため、通常時物体形状情報は、随時再取得されて記憶部18に記憶(上書き)される。
 物体形状情報取得部101は、通常時物体形状情報を取得した後には、物体形状情報を逐次取得する。
 ここで、例えば時間T内において所定間隔毎(時刻t1乃至tnの夫々)で物体形状情報が取得されるものとして、時刻tk(kは0乃至nのうちの何れかの整数値)において取得された物体形状情報を、特に「物体形状情報L(tk)」と呼ぶ。ここで、通常時物体形状情報は時刻t0に取得される。そこで、通常時物体形状情報を、特に「通常時物体形状情報L(t0)」と記載する。
Specifically, for example, first, the object shape information acquisition unit 101 acquires the object shape information in a state where the suspicious drone candidate X does not exist as the normal time object shape information, and stores it in the storage unit 18.
Here, changes in objects, that is, expansion / renovation of buildings and facilities, demolition, changes in equipment near facilities, growth and death of plants, etc. may occur. In this case, the object shape information at normal times should also be changed. Therefore, the normal object shape information is reacquired at any time and stored (overwritten) in the storage unit 18.
After acquiring the object shape information at normal times, the object shape information acquisition unit 101 sequentially acquires the object shape information.
Here, for example, assuming that the object shape information is acquired at predetermined intervals (each of time t1 to tun) within the time T, the object shape information is acquired at the time tk (k is an integer value of any of 0 to n). The object shape information is particularly referred to as "object shape information L (tk)". Here, the normal time object shape information is acquired at time t0. Therefore, the normal object shape information is particularly referred to as "normal time object shape information L (t0)".
 不審ドローン候補検出部102は、物体形状情報L(tk)と通常時物体形状情報L(t0)とを比較し、比較の結果として差分が得られた場合、その差分を不審ドローン候補X(を示す情報)として検出する。 The suspicious drone candidate detection unit 102 compares the object shape information L (tk) with the normal object shape information L (t0), and if a difference is obtained as a result of the comparison, the difference is used as the suspicious drone candidate X (. Detect as information).
 通知部103は、不審ドローン候補検出部102で検出された不審ドローン候補Xに関する情報を、監視者Aに通知する制御を行う。ここで図示はしないが、さらに通知部103において、監視者Aからの応答を取得する制御を行う。 The notification unit 103 controls to notify the observer A of information about the suspicious drone candidate X detected by the suspicious drone candidate detection unit 102. Although not shown here, the notification unit 103 further controls to acquire a response from the observer A.
 第1物理量取得指示部104は、レーダL及び偵察装置Jに対し、不審ドローン候補Xに関する第1物理量たる物体形状情報、及び画像情報などを取得するよう指示する。 The first physical quantity acquisition instruction unit 104 instructs the radar L and the reconnaissance device J to acquire object shape information, image information, etc., which are the first physical quantities related to the suspicious drone candidate X.
 第1物理量取得部201は、レーダLから得られた不審ドローン候補Xに関する第1物理量たる物体形状情報や、偵察装置Jから得られた不審ドローン候補Xに関する第1物理量たる画像情報などを、通信部19を介して取得する。ここで、画像情報などとは、光学カメラにより撮像された画像データなどであり、例えば、ドローンの大きさ、装備、外見から推定可能なスペックなどが情報処理(画像処理)により認識可能になる情報である。 The first physical quantity acquisition unit 201 communicates the object shape information which is the first physical quantity regarding the suspicious drone candidate X obtained from the radar L, the image information which is the first physical quantity regarding the suspicious drone candidate X obtained from the reconnaissance device J, and the like. Obtained via unit 19. Here, the image information and the like are image data captured by an optical camera, and for example, information that makes it possible to recognize the size, equipment, specifications that can be estimated from the appearance, etc. by information processing (image processing). Is.
 第1物理量パターン認識部105は、第1物理量取得部201において取得された不審ドローン候補Xに関する第1物理量たる物体形状情報や画像情報などに基づいて、不審ドローン候補Xの空間移動履歴パターンや画像情報などのパターンの情報を認識する。なお、以下、不審ドローン候補Xの空間移動履歴パターンや及び画像情報などのパターンの情報を、「パターン情報」と適宜呼ぶ。 The first physical quantity pattern recognition unit 105 is a spatial movement history pattern or image of the suspicious drone candidate X based on the object shape information or image information which is the first physical quantity related to the suspicious drone candidate X acquired by the first physical quantity acquisition unit 201. Recognize pattern information such as information. Hereinafter, the information of the pattern such as the spatial movement history pattern of the suspicious drone candidate X and the image information is appropriately referred to as "pattern information".
 第1判定部106は、第1物理量パターン認識部105で認識されたパターン情報に基づいて、不審ドローン候補Xが不審なドローンDである可能性を判定する。 The first determination unit 106 determines the possibility that the suspicious drone candidate X is a suspicious drone D based on the pattern information recognized by the first physical quantity pattern recognition unit 105.
 例えば、不審ドローン候補Xの空間移動履歴パターンが、地表や水面の移動を続けているパターンの場合、不審ドローン候補Xは、歩行者、車、船舶、飛翔能力のない動物、自転車、ラジコンカーなどである可能性が高い。つまり不審ドローン候補Xは、不審なドローンである可能性は低い。
 また例えば、不審ドローン候補Xの空間移動履歴パターンが、地表や水面や海面付近から立ち上がり、数秒以内に消えるパターンの場合、不審ドローン候補Xは不審なドローンである可能性は低い。これらのパターンの場合、不審ドローン候補Xは、鳥類の短期間の飛行や、トビウオ、イルカなどを一例とする飛翔する可能性のある生物、またクジラの潮吹きやモモンガなどである可能性が高いためである。
 また例えば、不審ドローン候補Xの空間移動履歴パターンが上空から落下していくパターンの場合であって、その落下の速度が高速の場合には、不審ドローン候補Xは、不審なドローンである可能性は低い。不審ドローン候補Xは、落下速度が速すぎて捕獲できない隕石や航空機の破片などであるからである。
For example, if the spatial movement history pattern of the suspicious drone candidate X is a pattern in which the ground surface or the water surface continues to move, the suspicious drone candidate X may be a pedestrian, a car, a ship, an animal having no flight ability, a bicycle, a radio-controlled car, or the like. Is likely to be. That is, the suspicious drone candidate X is unlikely to be a suspicious drone.
Further, for example, when the spatial movement history pattern of the suspicious drone candidate X rises from the ground surface, the water surface, or the vicinity of the sea surface and disappears within a few seconds, the suspicious drone candidate X is unlikely to be a suspicious drone. In the case of these patterns, the suspicious drone candidate X is likely to be a short-term flight of birds, a flying fish such as a flying fish or a dolphin, or a whale squirting or a flying squirrel. Is.
Further, for example, when the spatial movement history pattern of the suspicious drone candidate X is a pattern of falling from the sky and the falling speed is high, the suspicious drone candidate X may be a suspicious drone. Is low. This is because the suspicious drone candidate X is a meteorite or a fragment of an aircraft that cannot be captured because the falling speed is too fast.
 これに対して、不審ドローン候補Xの空間移動履歴パターンが、上昇気流の発生している場所の上空で旋回軌道を取るパターンの場合、不審ドローン候補Xは、猛禽類である可能性が高い。しかしながら、仮にこの不審ドローン候補Xが施設Bに向かってくるようであれば、不審ドローン候補Xは、不審なドローンDである可能性がある。
 また、不審ドローン候補Xの空間移動履歴パターンが、上昇気流の発生している場所で上昇しているパターンの場合、不審ドローン候補Xは、風船やビニール袋など、あるいは帆翔を行う鳥の可能性が高い。しかしながら、仮に不審ドローン候補Xが施設Bに向かってくるようであれば、不審ドローン候補Xは、不審なドローンDである可能性がある。
 また、不審ドローン候補Xの空間移動履歴パターンが、風に乗って飛行するパターンの場合、不審ドローン候補Xは、風船やビニール袋などの可能性が高い。しかし、この場合も、不審ドローン候補Xが、不審なドローンである可能性はある。
On the other hand, when the spatial movement history pattern of the suspicious drone candidate X is a pattern that takes a turning trajectory in the sky above the place where the updraft is generated, the suspicious drone candidate X is likely to be a bird of prey. However, if this suspicious drone candidate X comes toward the facility B, the suspicious drone candidate X may be a suspicious drone D.
Also, if the spatial movement history pattern of the suspicious drone candidate X is a pattern that rises in a place where an updraft is generated, the suspicious drone candidate X can be a balloon, a plastic bag, or a bird that sails. Highly sex. However, if the suspicious drone candidate X comes toward the facility B, the suspicious drone candidate X may be a suspicious drone D.
Further, when the spatial movement history pattern of the suspicious drone candidate X is a pattern of flying on the wind, the suspicious drone candidate X is likely to be a balloon, a plastic bag, or the like. However, even in this case, the suspicious drone candidate X may be a suspicious drone.
 また、不審ドローン候補Xの空間移動履歴パターンが、風に乗らずに直線的な飛行しているパターン、あるいは風に乗らずに空間上に停止しているパターンの場合、不審ドローン候補Xは、不審なドローンの可能性が高い。
 また、波状飛行をしている空間移動履歴を示す不審ドローン候補Xは、鳥類の可能性が高い。しかし、不審ドローン候補Xが、仮に施設Bに向かってくるようであれば、不審ドローン候補Xは、不審なドローンである可能性がある。
 また、不審ドローン候補Xの空間移動履歴パターンが、一見ランダムに見える飛行経路をたどるパターンの場合、不審ドローン候補Xは、コウモリ類である可能性が高い。しかし、不審ドローン候補Xが、仮に施設Bに向かってくるようであれば、不審ドローン候補Xは、不審なドローンDである可能性がある。
Further, when the spatial movement history pattern of the suspicious drone candidate X is a pattern of flying linearly without riding the wind or a pattern of stopping in the space without riding the wind, the suspicious drone candidate X is determined. There is a high possibility of a suspicious drone.
In addition, the suspicious drone candidate X, which shows the history of space movement during wavy flight, is highly likely to be a bird. However, if the suspicious drone candidate X comes toward the facility B, the suspicious drone candidate X may be a suspicious drone.
Further, when the spatial movement history pattern of the suspicious drone candidate X follows a flight path that seems to be random at first glance, the suspicious drone candidate X is likely to be a bat. However, if the suspicious drone candidate X comes toward the facility B, the suspicious drone candidate X may be a suspicious drone D.
 以上、パターン情報として、不審ドローン候補Xの空間移動履歴パターンが採用された場合における第1判定部106の判定の各種例について説明したが、これは例示である。
 第1判定部106は、パターン情報として、不審ドローン候補Xの画像情報などのパターンを採用して、不審ドローン候補Xが不審なドローンDである可能性を判定することもできる。
 例えば、不審ドローン候補Xの画像情報などのパターンが不審ドローン候補Xが既知のドローンや風船やビニール袋などのパターンであると認識されれば、不審ドローン候補Xは、不審なドローンDである可能性はないと判定される。
As described above, various examples of the determination of the first determination unit 106 when the spatial movement history pattern of the suspicious drone candidate X is adopted as the pattern information have been described, but this is an example.
The first determination unit 106 can also adopt a pattern such as image information of the suspicious drone candidate X as the pattern information to determine the possibility that the suspicious drone candidate X is a suspicious drone D.
For example, if the pattern such as the image information of the suspicious drone candidate X is recognized as the pattern of the suspicious drone candidate X such as a known drone, balloon, or plastic bag, the suspicious drone candidate X may be a suspicious drone D. It is determined that there is no sex.
 さらに、第1判定部106は、不審ドローン候補Xが不審なドローンDである可能性を判断するうえで、ドローン固有の動きを表す空間移動履歴パターンを参考にしてもよい。
 即ち、不審ドローン候補Xがマルチコプタータイプのドローンである場合、不審ドローン候補Xは、進行方向を風向きによって補正した向きに傾きながら移動し、自己重量に起因する慣性移動を行う。このため、方向転換が一般的に緩慢である。
 不審ドローン候補Xが固定翼ドローンである場合、不審ドローン候補Xは、一般的に翼は進行方向の空気を妨げない向きになり、やはり自己重量に起因する慣性移動を行うえ、翼が固定のため方向転換の最小半径はかなり大きくなる。これらのドローン固有の動きに対して、鳥類は自己重量が軽い上に翼が可動なため急激な方向転換が可能である。
Further, the first determination unit 106 may refer to the spatial movement history pattern representing the movement peculiar to the drone in determining the possibility that the suspicious drone candidate X is the suspicious drone D.
That is, when the suspicious drone candidate X is a multicopter type drone, the suspicious drone candidate X moves while tilting the traveling direction in a direction corrected by the wind direction, and performs inertial movement due to its own weight. For this reason, turning is generally slow.
When the suspicious drone candidate X is a fixed-wing drone, the suspicious drone candidate X generally has the wing oriented so as not to obstruct the air in the traveling direction, and also performs inertial movement due to its own weight, and the wing is fixed. Therefore, the minimum radius of direction change is considerably large. In response to these drone-specific movements, birds are light in weight and have movable wings, allowing them to make sharp turns.
 第1判定部106において、不審ドローン候補Xは不審なドローンDである可能性が低いと判定された場合、第1段階の処理として不審ドローン候補Xの監視の続行をしてもよい。即ち、第1物理量取得指示部104は、レーダL及び偵察装置Jに対し、不審ドローン候補Xに関する第1物理量たる、つまり物体形状情報、及び画像情報などを取得するよう指示してもよい。
 あるいは、第1判定部106において、不審ドローン候補Xは不審なドローンDである可能性が低いと判定された場合、第1判定部106は、監視を終了する動作を行ってもよい。
 第1判定部106において、不審ドローン候補Xは不審なドローンDである可能性が中程度であると判定された場合、第2段階の処理として、刺激付与支援部107は、通信部19を介して、刺激装置Sに対し、不審ドローン候補Xへ刺激を付与するための支援を行う。
 第1判定部106において、不審ドローン候補Xは不審なドローンDである可能性が高いと判定された場合、第3段階の処理として、捕獲支援部111は、通信部19を介して、捕獲装置Cに対し、不審なドローンDを捕獲するための支援を行う。
If the first determination unit 106 determines that the suspicious drone candidate X is unlikely to be a suspicious drone D, the monitoring of the suspicious drone candidate X may be continued as the first stage processing. That is, the first physical quantity acquisition instruction unit 104 may instruct the radar L and the reconnaissance device J to acquire the first physical quantity, that is, the object shape information, the image information, and the like regarding the suspicious drone candidate X.
Alternatively, if the first determination unit 106 determines that the suspicious drone candidate X is unlikely to be a suspicious drone D, the first determination unit 106 may perform an operation to end the monitoring.
When the first determination unit 106 determines that the suspicious drone candidate X has a moderate possibility of being a suspicious drone D, as a second stage process, the stimulus application support unit 107 passes through the communication unit 19. Then, the stimulator S is supported to give a stimulus to the suspicious drone candidate X.
When the first determination unit 106 determines that the suspicious drone candidate X is likely to be a suspicious drone D, as a third stage process, the capture support unit 111 transfers the capture device via the communication unit 19. Support C to capture the suspicious drone D.
 第2物理量取得指示部108は、レーダL及び偵察装置Jに対し、不審ドローン候補Xに関する第2物理量たる物体形状情報、及び画像情報などを取得するよう指示する。 The second physical quantity acquisition instruction unit 108 instructs the radar L and the reconnaissance device J to acquire the object shape information, the image information, etc., which are the second physical quantities related to the suspicious drone candidate X.
 第2物理量取得部202は、レーダLから得られた不審ドローン候補Xに関する第2物理量たる物体形状情報や、偵察装置Jから得られた不審ドローン候補Xに関する第2物理量たる画像情報などを、通信部19を介して取得する。 The second physical quantity acquisition unit 202 communicates the object shape information of the suspicious drone candidate X obtained from the radar L, the image information of the second physical quantity of the suspicious drone candidate X obtained from the reconnaissance device J, and the like. Obtained via unit 19.
 第2物理量パターン認識部109は、第2物理量取得部202において取得された不審ドローン候補Xに関する第2物理量たる物体形状情報や画像情報に基づいて、不審ドローン候補Xの空間移動履歴パターンや画像情報などのパターンの情報を認識する。 The second physical quantity pattern recognition unit 109 has the spatial movement history pattern and image information of the suspicious drone candidate X based on the object shape information and the image information which are the second physical quantities related to the suspicious drone candidate X acquired by the second physical quantity acquisition unit 202. Recognize pattern information such as.
 第2判定部110は、第2物理量パターン認識部109で認識されたパターン情報に基づいて、不審ドローン候補Xが不審なドローンDである可能性を判定する。 The second determination unit 110 determines the possibility that the suspicious drone candidate X is a suspicious drone D based on the pattern information recognized by the second physical quantity pattern recognition unit 109.
 例えば、不審ドローン候補Xの空間移動履歴パターンが、生体反応を示唆するような変化を示さない場合、不審ドローン候補Xは不審なドローンDである可能性が高い。
 この場合、捕獲支援部111は、通信部19を介して、捕獲装置Cに対し、不審なドローンの捕獲を実行するための支援を行う。
For example, if the spatial movement history pattern of the suspicious drone candidate X does not show a change suggesting a biological reaction, the suspicious drone candidate X is likely to be a suspicious drone D.
In this case, the capture support unit 111 supports the capture device C to capture the suspicious drone via the communication unit 19.
 ここで本実施形態で示す捕獲装置Cは、捕獲用の網を搭載したドローンとして構成されるが、この捕獲用のドローンは、その速度、航行時間、離陸可能な荷重のバランスをとってフライトプランを立てて用いられる必要がある。また、捕獲作業中にドローン自体、あるいはドローンの部品などが落下する危険があるため、サーバ1により捕獲を試みる区域を指定されてもよい。
 また、不審なドローンDの捕獲の可能性を広げる為に、捕獲用ドローンを複数台協調させてもよい。捕獲用ドローンを複数台協調させて捕獲する場合は、不審なドローンDの追い込みをするドローン、不審なドローンDのコントロールを奪うドローン、不審なドローンDを捕獲するドローン、また、それを指揮、観測するドローン、などのように、夫々の捕獲用ドローンに役割を持たせてもよい。そしてこのとき、複数台の捕獲用ドローン同士は、有線または無線で連絡を取ってもよい。
 また一般的なドローンは、コプター型では上昇方向の、固定翼型では水平方向に推力を発することに最適化されているため、ドローンは、ひっくり返されたりや、傾けられたりすることにより推力を急激に失い、コントロールが効かなくなる。つまり、捕獲支援部111は、捕獲用ドローンが不審なドローンをひっくり返したり、傾けたりするように、捕獲用ドローンの動きを制御してもよい。
Here, the capture device C shown in the present embodiment is configured as a drone equipped with a capture net, and this capture drone has a flight plan that balances its speed, sailing time, and takeoff load. It is necessary to stand up and use it. Further, since there is a risk that the drone itself or parts of the drone may fall during the capture operation, the server 1 may specify the area to be captured.
Further, in order to increase the possibility of capturing the suspicious drone D, a plurality of capture drones may be coordinated. When capturing multiple capture drones in coordination, a drone that drives in a suspicious drone D, a drone that takes control of a suspicious drone D, a drone that captures a suspicious drone D, and commands and observes it. Each capture drone may have a role, such as a drone to do. At this time, the plurality of capture drones may be in contact with each other by wire or wirelessly.
Also, since general drones are optimized to generate thrust in the ascending direction for the copter type and in the horizontal direction for the fixed-wing type, the drone can suddenly increase the thrust by being turned over or tilted. Lost to, and control is lost. That is, the capture support unit 111 may control the movement of the capture drone so that the capture drone turns over or tilts the suspicious drone.
 以上、サーバ1の機能的構成について図5を参照して説明した。 The functional configuration of the server 1 has been described above with reference to FIG.
 次に、図6を参照して、図5の機能的構成を有する、サーバ1、捕獲装置C、偵察装置J、レーダL、及び刺激装置Sが実行する処理の流れについて説明する。
 図6は、図5のサーバが実行するドローン捕獲処理を説明するフローチャートである。
Next, with reference to FIG. 6, the flow of processing executed by the server 1, the capture device C, the reconnaissance device J, the radar L, and the stimulator S, which have the functional configuration of FIG. 5, will be described.
FIG. 6 is a flowchart illustrating a drone capture process executed by the server of FIG.
 上述したように、処理に先立ち、物体形状情報取得部101は通常物体形状情報L(t0)を取得する。 As described above, the object shape information acquisition unit 101 normally acquires the object shape information L (t0) prior to the processing.
 ステップS101において、物体形状情報取得部101は、時刻tkにおける物体形状情報L(tk)を取得する。 In step S101, the object shape information acquisition unit 101 acquires the object shape information L (tk) at the time tk.
 ステップS102において、不審ドローン候補検出部102は、物体形状情報L(tk)と通常時物体形状情報L(t0)とを比較し、その比較の結果に基づいて、不審ドローン候補Xの存在を示す差分があるか否かを判定する。
 ステップS102において、不審ドローン候補Xの存在を示す差分がないと判定された場合、処理は終了する。
 これに対して、ステップS102において、不審ドローン候補Xの存在を示す差分があると判定された場合、処理はステップS103に進む。
In step S102, the suspicious drone candidate detection unit 102 compares the object shape information L (tk) with the normal object shape information L (t0), and indicates the existence of the suspicious drone candidate X based on the result of the comparison. Determine if there is a difference.
If it is determined in step S102 that there is no difference indicating the existence of the suspicious drone candidate X, the process ends.
On the other hand, if it is determined in step S102 that there is a difference indicating the existence of the suspicious drone candidate X, the process proceeds to step S103.
 ステップS103において、通知部103は、不審ドローン候補Xの検出に関する情報を監視者Aに通知する。通知部103が直ちに監視者Aに通知する理由は、サーバ1の処理速度や不審なドローンDの移動速度と比較すると極めて低速な処理速度しか有さない人間に対して、なるべく早く情報を提供し、判断を仰ぐためである。 In step S103, the notification unit 103 notifies the observer A of information regarding the detection of the suspicious drone candidate X. The reason why the notification unit 103 immediately notifies the observer A is to provide information as soon as possible to a person who has an extremely slow processing speed compared to the processing speed of the server 1 and the moving speed of the suspicious drone D. , To ask for judgment.
 ステップS104において、通知部103は、監視者Aからの応答の有無を確認する。
 ステップS104において、監視者Aより応答がなかった場合、処理はステップS107に進む。ステップS107以降の処理については後述する。
 これに対して、ステップS104において、監視者Aより応答があった場合、処理はステップS105に進む。
In step S104, the notification unit 103 confirms whether or not there is a response from the observer A.
If there is no response from the observer A in step S104, the process proceeds to step S107. The processing after step S107 will be described later.
On the other hand, if there is a response from the observer A in step S104, the process proceeds to step S105.
 ステップS105において、通知部103は、監視者Aからの不審ドローン候補Xの捕獲指示の有無を確認する。
 ステップS105において、監視者Aより不審ドローン候補Xの捕獲指示があった場合、処理はステップS115に進む。ステップ115以降の処理については後述する。
 これに対して、ステップS105において、監視者Aより不審ドローン候補Xの捕獲指示がなかった場合、処理はステップS106に進む。
In step S105, the notification unit 103 confirms whether or not there is an instruction to capture the suspicious drone candidate X from the observer A.
If the observer A gives an instruction to capture the suspicious drone candidate X in step S105, the process proceeds to step S115. The processing after step 115 will be described later.
On the other hand, if there is no instruction to capture the suspicious drone candidate X from the observer A in step S105, the process proceeds to step S106.
 ステップS106において、通知部103は、監視者Aから不審ドローン候補Xを無視せよとの指示の有無を確認する。
 ステップS106において、監視者Aから無視せよと指示がある場合、処理は終了する。
 これに対して、ステップS106において監視者Aから無視せよと指示がない場合、処理はステップS107へ進む。
In step S106, the notification unit 103 confirms whether or not there is an instruction from the observer A to ignore the suspicious drone candidate X.
If the observer A instructs to ignore in step S106, the process ends.
On the other hand, if there is no instruction from the observer A to ignore in step S106, the process proceeds to step S107.
 ステップS107において、サーバ1の物体形状情報取得部101は、不審ドローン候補X(物体形状情報L(tk)と通常時物体形状情報L(t0)との差分)の実空間上の大きさを測定する。そして、物体形状情報取得部101は、その測定結果に基づいて、不審ドローン候補Xが事前に設定した捕獲可能な範囲よりも大きいか否かを判定する。
 ステップS107において、不審ドローン候補Xが、事前に設定した捕獲可能な範囲よりも大きいと判定された場合、処理は終了する。
 これに対して、ステップS107において、不審ドローン候補Xが事前に設定した捕獲可能な範囲よりも大きくないと判定された場合は、処理はステップS108に進む。
In step S107, the object shape information acquisition unit 101 of the server 1 measures the size of the suspicious drone candidate X (difference between the object shape information L (tk) and the normal object shape information L (t0)) in real space. do. Then, the object shape information acquisition unit 101 determines whether or not the suspicious drone candidate X is larger than the preset catchable range based on the measurement result.
If it is determined in step S107 that the suspicious drone candidate X is larger than the preset catchable range, the process ends.
On the other hand, if it is determined in step S107 that the suspicious drone candidate X is not larger than the preset catchable range, the process proceeds to step S108.
 ステップS108において、第1物理量取得部201は、不審ドローン候補Xの空間移動履歴、及び偵察装置Jから得られた画像情報などを第1物理量として取得する。
 ステップS109において、第1物理量パターン認識部105は、第1物理量のパターン情報を認識する。
In step S108, the first physical quantity acquisition unit 201 acquires the spatial movement history of the suspicious drone candidate X, the image information obtained from the reconnaissance device J, and the like as the first physical quantity.
In step S109, the first physical quantity pattern recognition unit 105 recognizes the pattern information of the first physical quantity.
 ステップS110において、第1判定部106は、第1物理量パターン認識部105で認識されたパターン情報に基づいて、不審ドローン候補Xが不審なドローンDである可能性、つまり捕獲対象である可能性を判定する、第1判定を行う。
 ステップS110において、第1判定部106が、不審ドローン候補Xは捕獲対象ではないと判定した場合、処理は終了する。
 ステップS110において、第1判定部106が、不審ドローン候補Xは捕獲対象ではないと判定しなかった場合、処理はステップS111に進む。
 ステップS111において、刺激付与支援部107は、不審ドローン候補Xに向けて刺激を付与するよう刺激装置Sに対して指示を行う。
 ステップS112において、第2物理量取得部202は、刺激装置Sにより付与された刺激に対する不審ドローン候補Xの反応、つまり、不審ドローン候補Xの空間移動履歴、及び偵察装置Jから得られた画像情報などを第2物理量として取得する。
 ステップS113において、第2物理量パターン認識部109は、第2物理量のパターン情報を認識する。
 ステップS114において、第2判定部110は、第2物理量パターン認識部109で認識されたパターン情報に基づいて、不審ドローン候補Xが不審なドローンである可能性、つまり捕獲対象である可能性を判定する、第2判定を行う。
 ステップS114において、第2判定部110が、不審ドローン候補Xは捕獲対象ではないと判定した場合、処理は終了する。
 ステップS114において、第2判定部110が、不審ドローン候補Xは捕獲対象であると判定した場合、処理はステップS115に進む。
 即ち、ステップS114において不審ドローン候補Xが捕獲対象であると判定された場合、又は、ステップS105において人間から捕獲指示があった場合、処理はステップS115に進む。ここで、不審ドローン候補Xが捕獲対象であると判定されるということは、つまり、不審ドローン候補Xが不審なドローンDであると判定されたということである。
 ステップS115において、捕獲支援部111は、捕獲装置Cに対し、不審なドローンD捕獲するよう指示する。
 ここで、不審なドローンDを捕獲するよう指示を受けた捕獲装置Cは、本実施形態では便宜上捕獲用のドローンであり、投網により不審なドローンDを捕獲する。捕獲用のドローンは、捕獲した不審なドローンDを、安全な場所に移動運搬する。この際、不審なドローンDは、捕獲用のドローンにより遮蔽ケースなどの中に入れられてもよく、あるいは、捕獲用のドローンと共に遮蔽ケースなどに入れられてもよい。
 なお、ステップS110において、第1判定部106は、不審ドローン候補Xが捕獲対象であると判断した場合、処理はステップS111に進むと記載したが、上述したように、ここで不審ドローン候補Xが捕獲対象である可能性が高いと特に判定した場合は、処理はステップS115に進んでもよい。
In step S110, the first determination unit 106 determines the possibility that the suspicious drone candidate X is a suspicious drone D, that is, the possibility that it is a capture target, based on the pattern information recognized by the first physical quantity pattern recognition unit 105. Judgment, the first judgment is performed.
If the first determination unit 106 determines in step S110 that the suspicious drone candidate X is not a capture target, the process ends.
If the first determination unit 106 does not determine in step S110 that the suspicious drone candidate X is not a capture target, the process proceeds to step S111.
In step S111, the stimulus application support unit 107 instructs the stimulus device S to apply a stimulus to the suspicious drone candidate X.
In step S112, the second physical quantity acquisition unit 202 receives the reaction of the suspicious drone candidate X to the stimulus given by the stimulus device S, that is, the spatial movement history of the suspicious drone candidate X, the image information obtained from the reconnaissance device J, and the like. Is acquired as the second physical quantity.
In step S113, the second physical quantity pattern recognition unit 109 recognizes the pattern information of the second physical quantity.
In step S114, the second determination unit 110 determines the possibility that the suspicious drone candidate X is a suspicious drone, that is, the possibility that it is a capture target, based on the pattern information recognized by the second physical quantity pattern recognition unit 109. The second determination is made.
If the second determination unit 110 determines in step S114 that the suspicious drone candidate X is not a capture target, the process ends.
If the second determination unit 110 determines in step S114 that the suspicious drone candidate X is a capture target, the process proceeds to step S115.
That is, if it is determined in step S114 that the suspicious drone candidate X is the capture target, or if there is a capture instruction from a human in step S105, the process proceeds to step S115. Here, the fact that the suspicious drone candidate X is determined to be the capture target means that the suspicious drone candidate X is determined to be the suspicious drone D.
In step S115, the capture support unit 111 instructs the capture device C to capture the suspicious drone D.
Here, the capture device C instructed to capture the suspicious drone D is a capture drone for convenience in the present embodiment, and captures the suspicious drone D by casting net. The capture drone moves and transports the captured suspicious drone D to a safe place. At this time, the suspicious drone D may be put in a shield case or the like by the capture drone, or may be put in the shield case or the like together with the capture drone.
In step S110, the first determination unit 106 has described that if the suspicious drone candidate X is determined to be the capture target, the process proceeds to step S111. However, as described above, the suspicious drone candidate X is here. If it is particularly determined that the target is likely to be captured, the process may proceed to step S115.
 以上、本発明の実施形態について説明したが、本発明は前述した実施形態に限定されるものではなく、本発明の目的を達成できる範囲での変形、改良は本発明に含まれるものとする。 Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and modifications and improvements within the range in which the object of the present invention can be achieved are included in the present invention.
 上述の実施形態では、本来捕獲すべき物体を不審なドローンDとして説明したが、本来捕獲すべき物体は、不審なドローンDに限定されない。本発明によれば、保護対象に対して侵入してくる異物体の候補の中から、保護対象にとって脅威となる異物体を捕獲対象として見分けることができる。 In the above-described embodiment, the object to be captured is described as a suspicious drone D, but the object to be captured is not limited to the suspicious drone D. According to the present invention, it is possible to distinguish a foreign body that poses a threat to the protected target as a capture target from among the candidates for the foreign body that invades the protected target.
 ここで、所定の判断手法に基づいて、異物体の候補(例えば不審ドローン候補X)が、捕獲対象の異物体(例えば不審なドローンD)であるか否かを判定する(見分ける)場合において、所定の判断手法は、上述の実施形態の手法に限定されず、任意でよい。
 換言すると、上述の実施形態では、捕獲対象の異物体を見分ける手法として、次のような手法が採用された。即ち、上述の実施形態の手法によれば、不審ドローン候補Xの示す物体移動履歴や画像情報などの第1物理量のパターンの認識が行われた。そして、不審ドローン候補Xに付与された刺激に対して、当該不審ドローン候補Xが示す物体移動履歴や画像情報などの第2物理量のパターン認識が行われた。
 このように、第1物理量のパターン認識といういわゆる受動的観察と、能動的に刺激を与えた結果得られる第2物理量のパターン認識といういわゆる能動的観察とが組み合わせることにより、不審ドローン候補Xが不審なドローンD(捕獲対象)か否かを見分ける手法が、上述の実施形態の手法として採用された。しかしながら、見分ける手法としては、特にこの手法に限定されない。
Here, in the case of determining (distinguishing) whether or not the foreign body candidate (for example, suspicious drone candidate X) is the foreign body to be captured (for example, suspicious drone D) based on a predetermined determination method. The predetermined determination method is not limited to the method of the above-described embodiment, and may be arbitrary.
In other words, in the above-described embodiment, the following method is adopted as a method for distinguishing the foreign body to be captured. That is, according to the method of the above-described embodiment, the pattern of the first physical quantity such as the object movement history and the image information indicated by the suspicious drone candidate X was recognized. Then, for the stimulus given to the suspicious drone candidate X, the pattern recognition of the second physical quantity such as the object movement history and the image information indicated by the suspicious drone candidate X was performed.
In this way, the suspicious drone candidate X is suspicious by combining the so-called passive observation of the pattern recognition of the first physical quantity and the so-called active observation of the pattern recognition of the second physical quantity obtained as a result of active stimulation. The method of distinguishing whether or not it is a drone D (capture target) has been adopted as the method of the above-described embodiment. However, the method for distinguishing is not particularly limited to this method.
 即ち、上述した受動的観察のみにより、不審ドローン候補Xが不審なドローンDであるかどうかを見分けてもよい。
 具体的には、上述の実施形態で示した物体移動履歴や画像情報などの他に、受動的観察として、不審ドローン候補Xの温度に関する情報、電磁波に関する情報、不審ドローン候補Xが放出している化学物質に関する情報などを得ることによって不審ドローン候補Xが不審なドローンDであるかどうかを判定してもよい。
That is, it may be possible to distinguish whether or not the suspicious drone candidate X is the suspicious drone D only by the above-mentioned passive observation.
Specifically, in addition to the object movement history and image information shown in the above-described embodiment, information on the temperature of the suspicious drone candidate X, information on electromagnetic waves, and suspicious drone candidate X are emitted as passive observations. It may be determined whether or not the suspicious drone candidate X is a suspicious drone D by obtaining information on a chemical substance or the like.
 ここで、不審ドローン候補Xの電磁波に関する情報を取得する場合、取得される電磁波の周波数などが参照される。生体は遠赤外線未満の周波数の電磁波をほとんど自ら放射しない。これに対して、一般的にドローンは、モーター駆動用のコイルに流れる電流に起因する遠赤外線未満の周波数の電磁波を発し、あるいは操縦者との通信のための遠赤外線未満の周波数の電磁波や電子回路由来の電磁波を放射する。そのため、特定の周波数の電磁波が観測できれば、ほぼ間違いなく不審ドローン候補Xはドローンであると判定される。
 さらに、不審ドローン候補Xの音に関する情報を取得する場合、取得される音の種類が参照される。不審ドローン候補Xからモーター音、ローターの風切り音が観測できれば、ほぼ間違いなく不審ドローン候補Xはドローンであると判定される。
Here, when acquiring information on the electromagnetic wave of the suspicious drone candidate X, the frequency of the acquired electromagnetic wave and the like are referred to. Living organisms emit almost no electromagnetic waves with frequencies below far infrared rays. In contrast, drones generally emit electromagnetic waves with frequencies below far infrared rays due to the current flowing through the coil for driving the motor, or electromagnetic waves and electrons with frequencies below far infrared rays for communication with the operator. It emits electromagnetic waves from the circuit. Therefore, if an electromagnetic wave of a specific frequency can be observed, it is almost certain that the suspicious drone candidate X is determined to be a drone.
Further, when acquiring information about the sound of the suspicious drone candidate X, the type of the acquired sound is referred to. If the motor sound and the wind noise of the rotor can be observed from the suspicious drone candidate X, it is almost certain that the suspicious drone candidate X is determined to be a drone.
 不審ドローン候補Xが放出する化学物質に関する情報を取得する場合、化学物質センサーにより放出される化学物質が検出される。例えばモーターのベアリングに塗布されている機械油が検出されれば、ほぼ間違いなく不審ドローン候補Xはドローンであると判定される。また例えば、不審なドローンがブラシ付きモーターを使用している場合、ブラシ部で発生する火花が空気中の酸素と反応することによりオゾンが発生する可能性が高い。オゾンが検出されれば、ほぼ間違いなく不審ドローン候補Xは不審なドローンであると判定される。 When acquiring information on the chemical substances released by the suspicious drone candidate X, the chemical substances released by the chemical substance sensor are detected. For example, if the machine oil applied to the bearing of the motor is detected, it is almost certain that the suspicious drone candidate X is determined to be a drone. Further, for example, when a suspicious drone uses a motor with a brush, there is a high possibility that ozone is generated by the spark generated in the brush portion reacting with oxygen in the air. If ozone is detected, the suspicious drone candidate X is almost certainly determined to be a suspicious drone.
 また受動的観察の他の具体例として、超小型質量分析器などで不審ドローン候補Xの質量分析を行うことにより、不審ドローン候補Xが、爆発物を一例とする危険物を搭載しているかどうかを判定してもよい。
 さらには不審なドローンと、不審なドローンのオペレータ間でやり取りするラジオ波をpassiveに受信することで、不審ドローン候補Xの製造メーカ、型などを一例とする、不審なドローンを特定する情報を得られるようにしてもよい。
As another specific example of passive observation, whether or not the suspicious drone candidate X is loaded with a dangerous substance such as an explosive by performing mass spectrometry of the suspicious drone candidate X with an ultra-small mass spectrometer or the like. May be determined.
Furthermore, by receiving the suspicious drone and the radio wave exchanged between the suspicious drone operators passively, information for identifying the suspicious drone, such as the manufacturer and model of the suspicious drone candidate X, can be obtained. You may be able to do it.
 さらに本実施形態においては、受動的観察の手段として、偵察装置Jとしてドローンを用いたが、この他に、気象観測用ドローン、海洋ブイ、ゾンデなどを用いてもよい。あるいは、監視施設Kに偵察装置Jが設置された状態で不審ドローン候補Xに関する情報を取得してもよい。また情報収集の精度を上げる為、例えばドローンを複数台協調させて情報収集してもよい。 Further, in the present embodiment, a drone is used as the reconnaissance device J as a means of passive observation, but in addition to this, a drone for meteorological observation, an ocean buoy, a sonde, or the like may be used. Alternatively, information on the suspicious drone candidate X may be acquired with the reconnaissance device J installed in the monitoring facility K. Further, in order to improve the accuracy of information collection, for example, a plurality of drones may be coordinated to collect information.
 以上のように、不審ドローン候補Xの発する様々な物理量を受動的に観察することで、不審ドローン候補Xが不審なドローンであるかどうかを見分けることができる。 As described above, by passively observing various physical quantities emitted by the suspicious drone candidate X, it is possible to distinguish whether the suspicious drone candidate X is a suspicious drone.
 また、能動的観察により不審ドローン候補Xが不審なドローンであるかどうかを見分けてもよい。
 不審ドローン候補Xに対して付与される刺激として、本実施形態では破裂音を用いたが、この他に、他の鳥の警戒音、人間や不審なドローンが理解できる形の警告文の読み上げを一例とする音、フラッシュ光、人間や不審なドローンが理解できる形の警告文の掲示、ミラーなどを一例とする可視光、あるいは不快臭などの匂いでもよい。
 また視覚的な刺激、つまり急激に広がる傘状の物体や、捕獲用網のように広がる形状による刺激、偵察用のドローンや捕獲用のドローン、棒などの突起物の接近による刺激でもよい。さらには強力な電磁パルスやジャミングの為の電磁波や、水鉄砲やブロワーによる送風のような生体に害が少ない侵襲的警告手段などによる刺激でもよい。
 ここで、不審ドローン候補Xに人間が搭乗していたり、不審ドローン候補Xのオペレータと通信がつながっていたりする場合、警告文の読み上げや掲示に反応し、従う意思があるならば退避するはずである。また、不審ドローン候補Xが警告を理解できる機能を有していれば、警告に応じて退避するはずである。
In addition, active observation may be used to determine whether the suspicious drone candidate X is a suspicious drone.
As a stimulus given to the suspicious drone candidate X, a bursting sound was used in this embodiment, but in addition to this, a warning sound of other birds and a warning message in a form that can be understood by humans and suspicious drones are read aloud. It may be an example sound, a flash light, a warning message in a form that can be understood by humans or suspicious drones, a visible light such as a mirror, or an unpleasant odor.
It may also be a visual stimulus, that is, a stimulus by a rapidly expanding umbrella-shaped object, a stimulus by a shape that expands like a catching net, a stimulus by a drone for reconnaissance, a drone for catching, or a stimulus by the approach of a protrusion such as a stick. Furthermore, it may be stimulated by a strong electromagnetic pulse, an electromagnetic wave for jamming, or an invasive warning means such as a water gun or a blower that is less harmful to the living body.
Here, if a human is on board the suspicious drone candidate X, or if the operator of the suspicious drone candidate X is in communication, it should respond to the reading and posting of the warning text and evacuate if it intends to obey. be. Further, if the suspicious drone candidate X has a function that can understand the warning, it should be evacuated in response to the warning.
 また、不審ドローン候補Xに対して与える刺激の他の具体例として、不審ドローン候補Xに対し、電磁波を放射したり、磁場を生成したり、電磁波を遮蔽するなどを行ってもよい。不審ドローン候補Xがドローンのような電子機器を搭載した物体であれば、遠赤外線未満の電磁波や磁場の操作に応じて以下の(1)乃至(3)の反応が見られる。対して生体は、遠赤外線未満の電磁波に対する感受性や磁場に対する感受性が著しく低いため、遠赤外線未満の電磁波には反応しない可能性が高い。但し、遠赤外線未満の電磁波の遮蔽は可視光や音響の遮蔽を伴うことが多いので、これに対して反応する可能性はある。
 (1)不審ドローン候補Xは、強力な電磁パルスにより内部電子回路に異常な電流が流れることで動作異常を来す可能性がある。また、放射した遠赤外線未満の電磁波による誘導加熱により内部の金属が発熱することでも動作異常を来す可能性がある。また、強力な磁場により、不審ドローン候補Xの内部電子回路に誘導電流が流れたり強磁性体が磁気飽和を起こしたりするなどしても動作異常を来す可能性がある。この場合、不審ドローン候補Xは、失速して落下する。このような反応を示した場合、不審ドローン候補Xは不審なドローンである可能性が高いと判定できる。
 (2)強力な磁場により、不審ドローン候補Xの内部にある強磁性体物質が引き寄せられる可能性がある。この場合、不審ドローン候補Xはこの磁場により捕獲される可能性もある。
 (3)電磁波による通信のジャミング、電磁波の遮蔽により、不審ドローン候補Xと、不審ドローン候補Xのオペレータとの通信リンクが切断されたり、GPSなどを一例とするGNSSの情報を得られなくなったりする可能性がある。この場合、不審ドローン候補Xがドローンであれば、事前にそのドローンに設定されたホーム位置に戻るという反応を示す。不審ドローン候補Xが、ホーム位置に戻るという反応を示さない場合は、不審ドローン候補Xは生体である可能性もあるため、監視を継続する。
 ここで、もし不審ドローン候補Xが逃避行動を取るならば、システム管理者は能動的観察を継続することにより対象を監視範囲外にまで誘導することができる。そして結果として、監視範囲内を安全にすることができる。
Further, as another specific example of the stimulus given to the suspicious drone candidate X, the suspicious drone candidate X may be irradiated with an electromagnetic wave, a magnetic field may be generated, or the electromagnetic wave may be shielded. If the suspicious drone candidate X is an object equipped with an electronic device such as a drone, the following reactions (1) to (3) can be seen in response to the operation of electromagnetic waves or magnetic fields below far infrared rays. On the other hand, since the living body has extremely low sensitivity to electromagnetic waves lower than far infrared rays and sensitivity to magnetic fields, it is highly possible that the living body does not react to electromagnetic waves lower than far infrared rays. However, since the shielding of electromagnetic waves less than far infrared rays is often accompanied by the shielding of visible light and sound, there is a possibility of reacting to this.
(1) The suspicious drone candidate X may cause an operation abnormality due to an abnormal current flowing through the internal electronic circuit due to a strong electromagnetic pulse. In addition, the metal inside may generate heat due to induction heating by electromagnetic waves less than the emitted far infrared rays, which may cause an operation abnormality. Further, due to a strong magnetic field, even if an induced current flows in the internal electronic circuit of the suspicious drone candidate X or the ferromagnet causes magnetic saturation, an operation abnormality may occur. In this case, the suspicious drone candidate X stalls and falls. When such a reaction is shown, it can be determined that the suspicious drone candidate X is likely to be a suspicious drone.
(2) The strong magnetic field may attract the ferromagnetic material inside the suspicious drone candidate X. In this case, the suspicious drone candidate X may be captured by this magnetic field.
(3) Due to jamming of communication by electromagnetic waves and shielding of electromagnetic waves, the communication link between the suspicious drone candidate X and the operator of the suspicious drone candidate X may be disconnected, or GNSS information such as GPS may not be obtained. there is a possibility. In this case, if the suspicious drone candidate X is a drone, it shows a reaction of returning to the home position set in advance for the drone. If the suspicious drone candidate X does not respond to return to the home position, the suspicious drone candidate X may be a living body, so monitoring is continued.
Here, if the suspicious drone candidate X takes an escape action, the system administrator can guide the target out of the monitoring range by continuing active observation. And as a result, the monitoring range can be made safe.
 ここで能動的観察を行う場合、刺激の強度には注意が必要である。遠赤外線未満の電磁波でも、誘電加熱により生体に害を及ぼしたり、体内に飲み込んだ針金や胴輪、首輪、識別用タグなどの金属部位が誘導加熱により発熱する可能性がある。
 不審ドローン候補Xが動物である場合、与える刺激が強すぎると失神して落下し、最悪の場合、動物の死を招く。これは望まないため、与える刺激は弱いものから徐々に強くしていってもよい。そして、保護すべき施設から遠ざかる方向に対象物が移動していくならば、刺激をむやみに強くする必要はない。
When making active observations here, attention should be paid to the intensity of the stimulus. Even electromagnetic waves less than far-infrared rays may cause harm to the living body by dielectric heating, or metal parts such as wires, collars, collars, and identification tags swallowed inside the body may generate heat due to induction heating.
When the suspicious drone candidate X is an animal, if the stimulus given is too strong, it faints and falls, and in the worst case, it causes the death of the animal. Since this is not desired, the stimulus given may be gradually increased from weak to strong. And if the object moves away from the facility to be protected, the stimulus does not need to be unnecessarily strong.
 以上のように、不審ドローン候補Xに対して上述に限定されない様々な刺激を付与することにより不審ドローン候補Xが発する物理量を観察することで、不審ドローン候補Xが不審なドローンであるかどうか見極めてもよい。またここで不審ドローン候補Xが生体である場合もあるため、与える刺激の強弱を調節してもよい。 As described above, by observing the physical quantity emitted by the suspicious drone candidate X by giving various stimuli not limited to the above to the suspicious drone candidate X, it is possible to determine whether the suspicious drone candidate X is a suspicious drone. You may. Further, since the suspicious drone candidate X may be a living body here, the strength of the stimulus to be given may be adjusted.
 以上説明したように、本発明が適用される情報処理装置は、各種各様な判断手法に基づいて、異物体の候補(例えば不審ドローン候補X)が、捕獲対象の異物体(例えば不審なドローンD)であるか否かを判定する(見分ける)ことができる。
 さらに、本発明が適用される情報処理装置は、異物体の候補が捕獲対象の異物体であると判定した場合、当該異物体の捕獲を支援する処理を実行することができる。
 この場合の捕獲の手法は、上述の実施形態の手法に限定されず、任意でよい。
As described above, in the information processing apparatus to which the present invention is applied, a foreign body candidate (for example, suspicious drone candidate X) is a foreign body to be captured (for example, a suspicious drone) based on various judgment methods. It is possible to determine (distinguish) whether or not it is D).
Further, the information processing apparatus to which the present invention is applied can execute a process of supporting the capture of the foreign body when it is determined that the candidate for the foreign body is the foreign body to be captured.
The capture method in this case is not limited to the method of the above-described embodiment, and may be arbitrary.
 即ち、上述の実施形態では、サーバ1が、監視者Aに対して不審ドローン候補Xに関する情報を提供し、監視者Aが、不審ドローン候補Xが捕獲対象の異物体であるか否かの判断をしたが、捕獲の手法としてはこれに限定されない。
 即ち、不審ドローン候補Xに関する情報の収集から不審ドローン候補Xが捕獲対象の異物体であるか否かの判断までの全ての作業を監視者Aが行ってもよい。つまり、監視者Aが保護対象領域Wを監視し、監視者Aが目視などにより不審ドローン候補Xを発見してもよい。そして発見された不審ドローン候補Xについて、監視者Aが捕獲すべきか否かの判断を行い、監視者Aが捕獲を行ってもよい。
 これはつまり、コンピュータを用いず、監視者Aが自らの感覚器官により、本来捕獲すべき物体を見分けるということである。このように、全ての処理を監視者Aが行うことにより、コンピュータによる誤検知などを防ぐことができるほか、コンピュータではなし得ない、優先順位を判断など、周囲の状況に応じた対応をとることができる。
That is, in the above-described embodiment, the server 1 provides the observer A with information on the suspicious drone candidate X, and the observer A determines whether or not the suspicious drone candidate X is a foreign body to be captured. However, the method of capture is not limited to this.
That is, the observer A may perform all operations from collecting information on the suspicious drone candidate X to determining whether or not the suspicious drone candidate X is a foreign body to be captured. That is, the observer A may monitor the protected area W, and the observer A may discover the suspicious drone candidate X by visual inspection or the like. Then, the observer A may determine whether or not the found suspicious drone candidate X should be captured, and the observer A may capture the suspicious drone candidate X.
This means that the observer A can identify the object to be captured by his / her sensory organ without using a computer. In this way, by having the observer A perform all the processing, it is possible to prevent false detections by the computer, and to take measures according to the surrounding situation, such as determining the priority, which cannot be done by the computer. Can be done.
 また本実施形態では、不審ドローン候補Xに関する情報をサーバ1から提供された監視者Aが、提供された情報に基づいて不審ドローン候補Xが捕獲対象の異物体であるか否かの判定をした。このように、コンピュータを人間が補助することにより、不審なドローンDを捕獲してもよい。
 このように、コンピュータを監視者Aが補助することにより不審なドローンを捕獲する手法を用いることで、コンピュータと監視者Aが役割を補完し合うすることができるようになる。つまり、夜間や長時間の監視、遠距離の監視など、監視者Aには対応が難しい場合、コンピュータにより自動化することで、人間の負荷を軽減することが可能となる。また、機械的でパターン化された対応が必要な場合も、コンピュータを用いることにより効率的な処理が可能となる。またこの時、コンピュータが監視者Aに不審ドローン候補Xに関する情報を提供するタイミングは限定されず、随時情報提供できるものとする。
Further, in the present embodiment, the observer A provided with the information regarding the suspicious drone candidate X from the server 1 determines whether or not the suspicious drone candidate X is a foreign body to be captured based on the provided information. .. In this way, the suspicious drone D may be captured by assisting the computer with a human.
In this way, by using the method of capturing a suspicious drone by assisting the computer with the observer A, the computer and the observer A can complement each other's roles. That is, when it is difficult for the observer A to handle nighttime, long-time monitoring, long-distance monitoring, etc., it is possible to reduce the human load by automating with a computer. In addition, even when a mechanical and patterned response is required, efficient processing can be achieved by using a computer. Further, at this time, the timing at which the computer provides the observer A with the information regarding the suspicious drone candidate X is not limited, and the information can be provided at any time.
 また人間が介入せず、コンピュータが本来捕獲すべき不審なドローンDを自動的に見分けてもよい。即ち、コンピュータが、レーダLなどで保護対象領域Wを常時監視することにより不審ドローン候補Xを発見し、不審ドローン候補Xが捕獲対象の異物体であるか否かを自動的に見分け、捕獲を行ってもよい。
 またこの際、コンピュータは、監視により得られた情報に基づいて不審ドローン候補Xが捕獲対象の異物体であるか否かを自動的に判断すると同時に、監視者Aに対して不審ドローン候補Xの情報を提供してもよい。そして監視者Aが、不審ドローン候補Xの捕獲の指示を出した場合は、コンピュータ自身が不審ドローン候補Xが捕獲対象の異物体であるか否かを自動的に判定した場合でも、監視者Aが出した指示に従って不審ドローン候補Xを捕獲してもよい。また人間が不審ドローン候補Xの捕獲の指示を出さない場合は、不審ドローン候補Xを捕獲しくてもよい。
 またさらには、コンピュータは、不審なドローンDを捕獲した後、不審なドローンDを継続して捕獲するか否かについて監視者Aに指示を仰ぎ続けてもよい。監視者Aが、不審なドローンXを開放せよという指示をした場合、コンピュータは、不審なドローンDを開放するという構成としてもよい。またさらには、コンピュータは、不審なドローンXを捕獲した後は、不審なドローンXを安全な場所に隔離してもよい。そして、不審なドローンXを継続して捕獲するか否かについて監視者Aに指示を仰ぎ続けてもよい。監視者Aが、不審なドローンを開放せよという指示をした場合、コンピュータは、不審なドローンDを開放するという構成としてもよい。
 このように、人間が介入せず、コンピュータが、本来捕獲すべき不審なドローンDを自動で見分けることにより、異物体の候補の検出、捕獲対象の異物体であるか否かの判定、そして捕獲の処理までを迅速に行うことができるようになる。
Further, the suspicious drone D that the computer should originally capture may be automatically identified without human intervention. That is, the computer discovers the suspicious drone candidate X by constantly monitoring the protected area W with the radar L or the like, automatically distinguishes whether or not the suspicious drone candidate X is a foreign body to be captured, and captures the suspicious drone candidate X. You may go.
At this time, the computer automatically determines whether or not the suspicious drone candidate X is a foreign body to be captured based on the information obtained by the monitoring, and at the same time, the monitor A is notified of the suspicious drone candidate X. Information may be provided. When the observer A gives an instruction to capture the suspicious drone candidate X, the observer A automatically determines whether or not the suspicious drone candidate X is a foreign body to be captured. You may capture the suspicious drone candidate X according to the instructions given by. Further, if a human does not give an instruction to capture the suspicious drone candidate X, the suspicious drone candidate X may be captured.
Furthermore, the computer may continue to ask the observer A whether or not to continuously capture the suspicious drone D after capturing the suspicious drone D. When the observer A instructs to release the suspicious drone X, the computer may be configured to release the suspicious drone D. Furthermore, the computer may isolate the suspicious drone X in a safe place after capturing the suspicious drone X. Then, the observer A may be continuously instructed as to whether or not to continuously capture the suspicious drone X. When the observer A instructs to release the suspicious drone, the computer may be configured to release the suspicious drone D.
In this way, without human intervention, the computer automatically identifies the suspicious drone D that should be captured, so that it can detect foreign body candidates, determine whether it is a foreign body to be captured, and capture it. Will be able to be processed quickly.
 上述のように、本来捕獲すべき不審なドローンDを見分け、その不審なドローンDの捕獲までの処理をさらに迅速かつ効率的に行うためには、巨大なデータを管理し、上述の処理をリアルタイムで行うことが必要となる。このために、例えば蓄積された巨大データを活用してコンピュータによる機械学習を用いてもよい。即ち、異物体の候補の検出、捕獲対象の異物体であるか否かの判定を含む一連の対応の立案、及び捕獲の処理を含む一連の対応に関する夫々のデータを蓄積しコンピュータに機械学習させる。これにより、異物体の候補が捕獲対象の異物体であるか否かをより正確かつ効率的に見分け、捕獲処理を行うことができるようになる。 As mentioned above, in order to identify the suspicious drone D that should be captured and to perform the processing up to the capture of the suspicious drone D more quickly and efficiently, a huge amount of data is managed and the above processing is performed in real time. It is necessary to do it in. For this purpose, for example, machine learning by a computer may be used by utilizing the huge accumulated data. That is, the computer is made to machine-learn by accumulating data on a series of responses including detection of a candidate for a foreign body, determination of whether or not the foreign body is a foreign body to be captured, and a series of responses including capture processing. .. As a result, it becomes possible to more accurately and efficiently distinguish whether or not the candidate for the foreign body is the foreign body to be captured, and to perform the capture process.
 また本実施形態では、保護対象である施設Bの中心周辺にレーダLを設置し、設置された位置を中心としてその中心から半径1km以内のエリアが保護対象領域Wとして設定したが、これに限定されない。レーダLを複数配置することによって、広範囲を監視可能な監視網を作ってもよい。
 即ち、不審なドローンDが保護対象領域Wに侵入してから保護対象の施設Bに到達するまでの時間は、その不審なドローンDに対して対応できる時間を確保すべく、長ければ長いほどよい。しかしながら、一般的にレーダLによる監視距離や、捕獲装置Cや偵察装置Jの稼働範囲は、法規上の理由、及びコスト上の理由によりむやみに広げることはできない。そこで、広範囲を監視可能な監視網を作成することにより上述した異物体の候補の検出から捕獲の処理を含む一連の対応の時間を確保することができるようになる。
Further, in the present embodiment, the radar L is installed around the center of the facility B to be protected, and the area within a radius of 1 km from the center of the installed position is set as the protected area W, but the present invention is limited to this. Not done. By arranging a plurality of radars L, a monitoring network capable of monitoring a wide range may be created.
That is, the longer the time from when the suspicious drone D invades the protected area W to when it reaches the protected facility B, the better so as to secure the time to deal with the suspicious drone D. .. However, in general, the monitoring distance by the radar L and the operating range of the capture device C and the reconnaissance device J cannot be unnecessarily expanded due to legal reasons and cost reasons. Therefore, by creating a monitoring network capable of monitoring a wide area, it becomes possible to secure a series of response times including the above-mentioned detection of foreign body candidates and capture processing.
 また物体形状情報取得部101は、保護対象領域W内に不審ドローン候補Xが存在しない状態を通常状態として、その通常状態においてレーダLから得られた情報を、通常時物体形状情報として取得するが、この際、無視領域を設定などできるようにしてもよい。
 無視領域とは、物体の形状が頻繁に変わることがわかっているために、検出の対象には含めない領域である。例えば、通常人間や車が行き来する可能性のある通路や、海岸の波打ち際で飛沫が随時検知される場所などがこれに該当する。さらに物体形状情報取得部101は、気象情報、交通情報、航空機運行情報などの情報を随時入手し、無視領域を追加、拡張、縮小してよい。例えば、海面の平均位置や波の高さは、潮汐情報、波浪情報により決定し、海面が隆起する高さ以下を無視領域に設定してよい。また、航空機が予め飛行する位置、時間がわかっていれば、その領域を無視領域に設定してよい。また物体形状情報取得部101は、観測範囲内の風の動きを適切な方法で入手していてよい。風の動きは例えば、ゾンデやブイ、ホバリングさせた気象観測用ドローンにより監視させてもよい。
 このように、通常時物体形状情報について無視領域を設定することで、建物や設備そのもの、固定物、植栽、木、草、非飛行物と非浮遊物、事前に脅威ではないと確認できているドローンなどや飛翔物体あるいは浮遊物体、ヒョウ、竜巻で巻き上げられた魚が降ってくるなどの気象的固形物を、誤って捕獲する可能性を低くすることができる。
Further, the object shape information acquisition unit 101 acquires the information obtained from the radar L in the normal state as the normal state when the suspicious drone candidate X does not exist in the protection target area W as the normal time object shape information. At this time, the ignore area may be set.
The neglected area is an area that is not included in the detection target because it is known that the shape of the object changes frequently. For example, this includes passages where people and cars can normally come and go, and places where splashes are detected at any time on the shoreline. Further, the object shape information acquisition unit 101 may obtain information such as weather information, traffic information, and aircraft operation information at any time, and may add, expand, or reduce the ignored area. For example, the average position of the sea surface and the height of the wave may be determined by the tide information and the wave information, and the height below the height at which the sea surface rises may be set as the neglected region. Further, if the position and time at which the aircraft flies are known in advance, that area may be set as the neglected area. Further, the object shape information acquisition unit 101 may obtain the movement of the wind within the observation range by an appropriate method. Wind movement may be monitored, for example, by a sonde, buoy, or hovering meteorological drone.
In this way, by setting an ignoring area for the normal object shape information, it can be confirmed in advance that the building or equipment itself, fixed objects, plants, trees, grass, non-flying objects and non-floating objects are not threatening. It is possible to reduce the possibility of accidentally capturing meteorological solids such as drones, flying or floating objects, leopards, and tornado-wound fish.
 また不審ドローン候補検出部102は、上述の無視領域を除いた領域について、物体形状情報L(tk)と通常時物体形状情報L(t0)の差分を検出するが、必要に応じてノイズフィルターを用いてもよい。これは、一般的な不審なドローンよりも小さい物体は不審なドローンなどではなく昆虫の可能性が高いため、捕獲は行わない、という判断ができるためである。 Further, the suspicious drone candidate detection unit 102 detects the difference between the object shape information L (tk) and the normal object shape information L (t0) in the area excluding the above-mentioned ignored area, but if necessary, a noise filter is used. You may use it. This is because it can be determined that an object smaller than a general suspicious drone will not be captured because it is more likely to be an insect rather than a suspicious drone.
 物体形状情報取得部101は、不審ドローン候補Xの実空間上の大きさを測定するが、ここで事前に捕獲装置Cにより捕獲可能な不審ドローン候補Xの大きさの範囲が入力されていてよい。 The object shape information acquisition unit 101 measures the size of the suspicious drone candidate X in the real space, and here, the range of the size of the suspicious drone candidate X that can be captured by the capture device C may be input in advance. ..
 本実施形態では、本願の出願時点の日本国の法律を適用したが、これに限定されない。いずれの国においても、電波の公平利用のために、たとえ正当な防御目的であっても妨害電波の送出には厳しい規制が行われている。したがって、外国においては、外国の法律が適用されてもよい。 In this embodiment, the law of Japan at the time of filing of the present application is applied, but the present invention is not limited to this. In each country, for the fair use of radio waves, strict regulations are imposed on the transmission of disturbing radio waves, even for legitimate defense purposes. Therefore, in foreign countries, foreign law may be applied.
 以上をまとめると、本発明が適用される情報処理装置は、次のような構成を取れば足り、各種各様な実施形態を取ることが出来る。
 即ち、本発明が適用される情報処理装置は、
 保護対象の範囲(例えば図1や図2の保護対象領域W)に侵入してくる異物体の候補(例えば図1や図2の不審ドローン候補X)を検出する候補検出手段(例えば図5の不審ドローン候補検出部102)と、
 所定の判断手法に基づいて、前記異物体の候補が、捕獲対象の異物体であるか否かを判定する判定手段(例えば図5の第1判定部106や第2判定部110など)と、
 を備える。
 これにより、保護対象の範囲に侵入してくる異物体の候補が、捕獲対象の異物体であるか否かを適切に見分けることが可能になる。
Summarizing the above, the information processing apparatus to which the present invention is applied suffices to have the following configuration, and various embodiments can be taken.
That is, the information processing apparatus to which the present invention is applied is
Candidate detection means (for example, FIG. 5) for detecting a candidate for a foreign body (for example, suspicious drone candidate X in FIGS. 1 and 2) that invades the range of the protection target (for example, the protection target area W in FIGS. 1 and 2). Suspicious drone candidate detection unit 102) and
A determination means for determining whether or not the foreign body candidate is a foreign body to be captured (for example, the first determination unit 106 or the second determination unit 110 in FIG. 5) based on a predetermined determination method.
To prepare for.
This makes it possible to appropriately determine whether or not the candidate for a foreign body that invades the range of the protected object is a foreign body to be captured.
 さらに、本発明が適用される情報処理装置は、
 前記判定手段により前記異物体の候補が前記捕獲対象の前記異物体であると判定された場合、当該異物体の捕獲を支援する処理を実行する捕獲支援手段(例えば図5の捕獲支援部111)、
 を備えることができる。
 これにより、捕獲対象の異物体を適切に捕獲することが可能になる。
Further, the information processing apparatus to which the present invention is applied is
When the candidate for the foreign body is determined by the determination means to be the foreign body to be captured, the capture support means (for example, the capture support unit 111 in FIG. 5) that executes a process of supporting the capture of the foreign body. ,
Can be provided.
This makes it possible to properly capture the foreign body to be captured.
 具体的には例えば、本発明が適用される情報処理装置は、
 前記候補検出手段は、
  前記保護対象の範囲に含まれる1以上の物体の夫々の形状に関する情報を、物体形状情報として逐次取得して、取得した当該物体形状情報と通常状態の物体形状情報とを逐次比較して、通常状態とは相違する部分を異物体の候補として検出し、
 前記判定手段は、
  前記異物体の候補についての第1物理量の検出後の変化のパターンを認識する第1認識手段(例えば図5の第1物理量パターン認識部105)と、
  前記第1認識手段により認識された、当該異物体の候補についての前記第1物理量の検出後の変化のパターンに基づいて、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるか否かの第1判定を行う第1判定手段(例えば図5の第1判定部106)と、
  前記第1判定が、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるという判定の場合、前記異物体の候補に対して所定の刺激を付与することを支援する刺激付与支援手段(例えば図5の刺激付与支援部107)と、
  当該異物体の候補についての第2物理量の、前記刺激が与えられた後の変化のパターンを認識する第2認識手段(例えば図5の第2物理量パターン認識部109)と、
  前記第2認識手段により認識された、当該異物体の候補についての前記第2物理量の検出後の変化のパターンに基づいて、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるか否かの第2判定を行う第2判定手段(例えば図5の第2判定部110)と、
 を有し、
 前記捕獲支援手段は、
  前記第2判定が、前記異物体の候補が前記捕獲対象の前記異物体の可能性が高いという判定の場合、当該捕獲対象の当該異物体の捕獲を支援する処理の実行を許可し、
  前記第2判定が、前記異物体の候補が前記捕獲対象の前記異物体の可能性が低いという判定の場合、若しくは、前記第1判定が、当該異物体の候補が前記捕獲対象の前記異物体の可能性がないという判定の場合、当該捕獲対象の当該異物体の捕獲を支援する処理の実行を禁止する、
 ことができる。
 これにより、保護対象の範囲に対して侵入してくる異物体の候補の中から捕獲対象の異物体を適切に見分け、必要に応じて捕獲することができる。しその結果、捕獲すべき異物体の侵入による犯罪や事故を未然に効果的に防止できると共に、捕獲すべきではない物体(例えば鳥などの生命体)を誤って捕獲することを防止できる。
Specifically, for example, the information processing apparatus to which the present invention is applied is
The candidate detecting means is
Information on the shape of each of one or more objects included in the protected range is sequentially acquired as object shape information, and the acquired object shape information is sequentially compared with the object shape information in a normal state, and is usually used. A part different from the state is detected as a candidate for a foreign body,
The determination means is
A first recognition means (for example, the first physical quantity pattern recognition unit 105 in FIG. 5) for recognizing a pattern of change after detection of the first physical quantity for the foreign body candidate, and
Based on the pattern of change after detection of the first physical quantity of the foreign body candidate recognized by the first recognition means, the foreign body candidate may be the foreign body to be captured. A first determination means (for example, the first determination unit 106 in FIG. 5) for first determining whether or not to use
When the first determination determines that the foreign body candidate may be the foreign body to be captured, the stimulus giving support for supporting the application of a predetermined stimulus to the foreign body candidate. Means (for example, the stimulus applying support unit 107 in FIG. 5) and
A second recognition means (for example, the second physical quantity pattern recognition unit 109 in FIG. 5) for recognizing a pattern of change in the second physical quantity of the foreign body candidate after the stimulus is applied.
Based on the pattern of change after detection of the second physical quantity of the foreign body candidate recognized by the second recognition means, the foreign body candidate may be the foreign body to be captured. A second determination means (for example, the second determination unit 110 in FIG. 5) that makes a second determination as to whether or not the condition is present.
Have,
The capture support means
When the second determination determines that the candidate for the foreign body is likely to be the foreign body to be captured, the execution of a process for supporting the capture of the foreign body to be captured is permitted.
The second determination is that the candidate for the foreign body is unlikely to be the foreign body to be captured, or the first determination is that the candidate for the foreign body is the foreign body to be captured. If it is determined that there is no possibility of this, the execution of processing to support the capture of the foreign body to be captured is prohibited.
be able to.
As a result, the foreign body to be captured can be appropriately identified from the candidates for the foreign body invading the range of the protected target, and can be captured as needed. As a result, crimes and accidents caused by the invasion of foreign objects to be captured can be effectively prevented, and objects that should not be captured (for example, life forms such as birds) can be prevented from being accidentally captured.
 1・・・サーバ、C・・・捕獲装置、L・・・レーダ、S・・・刺激装置S、J・・・偵察装置、101・・・物体形状情報取得部、102・・・不審ドローン候補検出部、103・・・通知部、104・・・第1物理量取得指示部、105・・・第1物理量パターン認識部、106・・・第1判定部、107・・・刺激付与支援部、108・・・第2物理量取得指示部、109・・・第2物理量パターン認識部、110・・・第2判定部、111・・・捕獲支援部、201・・・第1物理量取得部、202・・・第2物理量取得部 1 ... Server, C ... Capture device, L ... Radar, S ... Stimulator S, J ... Reconnaissance device, 101 ... Object shape information acquisition unit, 102 ... Suspicious drone Candidate detection unit, 103 ... Notification unit, 104 ... First physical quantity acquisition instruction unit, 105 ... First physical quantity pattern recognition unit, 106 ... First determination unit, 107 ... Stimulation application support unit , 108 ... second physical quantity acquisition instruction unit, 109 ... second physical quantity pattern recognition unit, 110 ... second determination unit, 111 ... capture support unit, 201 ... first physical quantity acquisition unit, 202 ... Second physical quantity acquisition unit

Claims (3)

  1.  保護対象の範囲に侵入してくる異物体の候補を検出する候補検出手段と、
     所定の判断手法に基づいて、前記異物体の候補が、捕獲対象の異物体であるか否かを判定する判定手段と、
     を備える情報処理装置。
    Candidate detection means for detecting candidates for foreign substances that invade the area to be protected,
    A determination means for determining whether or not the foreign body candidate is a foreign body to be captured based on a predetermined determination method.
    Information processing device equipped with.
  2.  前記判定手段により前記異物体の候補が前記捕獲対象の前記異物体であると判定された場合、当該異物体の捕獲を支援する処理を実行する捕獲支援手段と、
     を備える請求項1に記載の情報処理装置。
    When the candidate for the foreign body is determined by the determination means to be the foreign body to be captured, the capture support means for executing the process of supporting the capture of the foreign body and the capture support means.
    The information processing apparatus according to claim 1.
  3.  前記候補検出手段は、
      前記保護対象の範囲に含まれる1以上の物体の夫々の形状に関する情報を、物体形状情報として逐次取得して、取得した当該物体形状情報と通常状態の物体形状情報とを逐次比較して、通常状態とは相違する部分を異物体の候補として検出し、
     前記判定手段は、
      前記異物体の候補についての第1物理量の検出後の変化のパターンを認識する第1認識手段と、
      前記第1認識手段により認識された、当該異物体の候補についての前記第1物理量の検出後の変化のパターンに基づいて、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるか否かの第1判定を行う第1判定手段と、
      前記第1判定が、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるという判定の場合、前記異物体の候補に対して所定の刺激を付与することを支援する刺激付与支援手段と、
      当該異物体の候補についての第2物理量の、前記刺激が与えられた後の変化のパターンを認識する第2認識手段と、
      前記第2認識手段により認識された、当該異物体の候補についての前記第2物理量の検出後の変化のパターンに基づいて、当該異物体の候補が前記捕獲対象の前記異物体の可能性があるか否かの第2判定を行う第2判定手段と、
     を有し、
     前記捕獲支援手段は、
      前記第2判定が、前記異物体の候補が前記捕獲対象の前記異物体の可能性が高いという判定の場合、当該捕獲対象の当該異物体の捕獲を支援する処理の実行を許可し、
      前記第2判定が、前記異物体の候補が前記捕獲対象の前記異物体の可能性が低いという判定の場合、若しくは、前記第1判定が、当該異物体の候補が前記捕獲対象の前記異物体の可能性がないという判定の場合、当該捕獲対象の当該異物体の捕獲を支援する処理の実行を禁止する、
     請求項2に記載の情報処理装置。
    The candidate detecting means is
    Information on the shape of each of one or more objects included in the protected range is sequentially acquired as object shape information, and the acquired object shape information is sequentially compared with the object shape information in a normal state, and is usually used. A part different from the state is detected as a candidate for a foreign body,
    The determination means is
    A first recognition means for recognizing a pattern of change after detection of a first physical quantity for a foreign body candidate, and a first recognition means.
    Based on the pattern of change after detection of the first physical quantity of the foreign body candidate recognized by the first recognition means, the foreign body candidate may be the foreign body to be captured. The first determination means for making the first determination as to whether or not it is
    When the first determination determines that the foreign body candidate may be the foreign body to be captured, the stimulus giving support for supporting the application of a predetermined stimulus to the foreign body candidate. Means and
    A second recognition means for recognizing a pattern of change in the second physical quantity of the foreign body candidate after the stimulus is given, and
    Based on the pattern of change after detection of the second physical quantity of the foreign body candidate recognized by the second recognition means, the foreign body candidate may be the foreign body to be captured. A second determination means for making a second determination as to whether or not it is present,
    Have,
    The capture support means
    When the second determination determines that the candidate for the foreign body is likely to be the foreign body to be captured, the execution of a process for supporting the capture of the foreign body to be captured is permitted.
    The second determination is that the candidate for the foreign body is unlikely to be the foreign body to be captured, or the first determination is that the candidate for the foreign body is the foreign body to be captured. If it is determined that there is no possibility of this, the execution of processing to support the capture of the foreign body to be captured is prohibited.
    The information processing apparatus according to claim 2.
PCT/JP2020/022024 2020-06-03 2020-06-03 Information processing device WO2021245858A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/022024 WO2021245858A1 (en) 2020-06-03 2020-06-03 Information processing device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/022024 WO2021245858A1 (en) 2020-06-03 2020-06-03 Information processing device

Publications (1)

Publication Number Publication Date
WO2021245858A1 true WO2021245858A1 (en) 2021-12-09

Family

ID=78830194

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/022024 WO2021245858A1 (en) 2020-06-03 2020-06-03 Information processing device

Country Status (1)

Country Link
WO (1) WO2021245858A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105759834A (en) * 2016-03-09 2016-07-13 中国科学院上海微系统与信息技术研究所 System and method of actively capturing low altitude small unmanned aerial vehicle
JP2017009244A (en) * 2015-06-25 2017-01-12 株式会社ディスコ Small-sized unmanned aircraft repulsion device
JP2017167870A (en) * 2016-03-17 2017-09-21 セコム株式会社 Flying object monitoring system, and flying object monitoring apparatus
JP2019040321A (en) * 2017-08-23 2019-03-14 有限会社アイ・アール・ティー Drone monitoring system and drone monitoring method
US20190180632A1 (en) * 2016-08-14 2019-06-13 Iron Drone Ltd. Flight planning system and method for interception vehicles

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017009244A (en) * 2015-06-25 2017-01-12 株式会社ディスコ Small-sized unmanned aircraft repulsion device
CN105759834A (en) * 2016-03-09 2016-07-13 中国科学院上海微系统与信息技术研究所 System and method of actively capturing low altitude small unmanned aerial vehicle
JP2017167870A (en) * 2016-03-17 2017-09-21 セコム株式会社 Flying object monitoring system, and flying object monitoring apparatus
US20190180632A1 (en) * 2016-08-14 2019-06-13 Iron Drone Ltd. Flight planning system and method for interception vehicles
JP2019040321A (en) * 2017-08-23 2019-03-14 有限会社アイ・アール・ティー Drone monitoring system and drone monitoring method

Similar Documents

Publication Publication Date Title
RU2615470C2 (en) System to avoid collision with animals
US10026165B1 (en) Object image recognition and instant active response
US9474265B2 (en) Methods and systems for directing birds away from equipment
EP3537875B1 (en) System and method for detecting flying animals
US10846572B2 (en) Induction system for product authentication
US10650284B2 (en) Induction system for product authentication
US11636745B2 (en) Detection of animal intrusions and control of a repellent mechanism for detected animal intrusions
US20190235494A1 (en) System and method for defending an unmanned aerial vehicle from ground threats
CN111664752A (en) Unmanned aerial vehicle counter-braking system
US10339426B2 (en) Induction system for crowd monitoring
US10425996B1 (en) Induction heating systems
JP2018050503A (en) System and method for repelling or exterminating harmful animal
WO2014085328A1 (en) Methods and systems for directing birds away from equipment
US10956794B2 (en) Induction heating systems
US10694588B2 (en) Induction heating systems
Kovács et al. Landmine detection with drones
WO2021245858A1 (en) Information processing device
JP2004355551A (en) Protection system
EP3608746A1 (en) Wildlife intercept system and method of operating
AU2020202481B2 (en) Pest control assembly, system and method
CN110874847A (en) System and method for countering aerial moving target
KR20190141941A (en) Detecting and neutralizing apparatus of flight vehicle capable of flying underground and method thereof
CN107943101B (en) Method for unmanned aerial vehicle to fly by selecting interference background
Feltynowski et al. Zagrożenia związane z wykorzystaniem bezzałogowych platform w służbach ratunkowo-porządkowych
Luňáček Analysis of UAV usage in the physical security area

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20939052

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20939052

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP