Monitoring system, monitoring device, monitoring method, and program

Abstract

To detect a state of a monitoring object using no special structure for detecting the same.SOLUTION: A monitoring system according to the present disclosure includes: optical fiber; a reception unit (31) configured to receive, from the optical fiber, backscattered light including a pattern that dynamically varies according to a state of a monitoring target (10) to detect the pattern from the received backscattered light; and a control unit (32) for detecting the state of the monitoring object (10) based on dynamic changes of the pattern and a learning model learned about the monitoring object (10).SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a monitoring system, a monitoring device, a monitoring method, and a computer-readable medium. [Background technology]

[0002] Traditionally, detecting abnormalities in monitored objects such as fences is often done by a monitor in a monitoring room monitoring images from multiple cameras. For example, if a monitor determines that there is something suspicious about the monitored object, he or she will point the camera at the monitored object and zoom in to detect the abnormality. However, manually detecting abnormalities in monitored objects is very costly and time-consuming, and may result in delays in discovering and dealing with the abnormality. For this reason, recently, systems have been proposed that use optical fibers to monitor abnormalities in monitored objects (for example, Patent Documents 1 to 3).

[0003] In the technologies described in Patent Documents 1 and 2, FBG (Fiber Bragg Grating) type optical fibers are laid on the fence, and OTDR (Optical Time-Domain Reflectometry) type optical fibers are laid on the fence, and intruders attempting to climb over the fence are detected by an FBG type intrusion detector, while intruders attempting to destroy the fence are detected by an OTDR type intrusion detector. An ITV (Industrial Television) monitoring system installed in a monitoring room directs the shooting direction of an ITV camera to the detection position based on detection position information included in the intrusion detection signal from the intrusion detector.

[0004] In the technology described in Patent Document 3, multiple FBG optical fibers are laid on a fence, and a pulse signal is output when the reflected wave shift amount of the reflected wave generated in the optical fiber exceeds a certain threshold. In addition, events occurring on the fence are classified according to the frequency and amount of fluctuation of the fence, and a table is prepared in which the events occurring on the fence correspond to the generation time delay and occurrence frequency of the pulse signal in each of the multiple optical fibers. Then, the generation time delay and occurrence frequency of the pulse signal in each of the multiple optical fibers are compared with the above table to detect the event occurring on the fence. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2005-032224 A [Patent Document 2] JP 2006-172339 A [Patent Document 3] JP 2006-208061 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, the techniques described in Patent Documents 1 to 3 have a problem in that they require the use of a special optical fiber called an FBG optical fiber. Also, the techniques described in Patent Documents 1 and 2 have a problem in that they require the use of an OTDR optical fiber together with an FBG optical fiber. Also, the technique described in Patent Document 3 has a problem in that it requires the installation of multiple optical fibers and the reception of reflected waves from the multiple optical fibers.

[0007] Therefore, an object of the present disclosure is to solve the above-mentioned problems and provide a monitoring system, a monitoring device, a monitoring method, and a computer-readable medium that can detect the status of an object to be monitored without using a special structure for detecting the status of the object to be monitored. [Means for solving the problem]

[0008] According to one aspect, a monitoring system includes: a cable including an optical fiber; a receiving unit that receives an optical signal including a pattern corresponding to a state of an object to be monitored from at least one optical fiber included in the cable and detects the pattern from the received optical signal; A control unit that detects a state of the monitoring target based on the pattern; Equipped with.

[0009] A monitoring device according to one aspect includes: a receiving unit that receives an optical signal including a pattern corresponding to a state of an object to be monitored from at least one optical fiber included in the cable and detects the pattern from the received optical signal; A control unit that detects a state of the monitoring target based on the pattern; Equipped with.

[0010] A monitoring method according to one aspect includes: A monitoring method using a monitoring device, comprising: receiving an optical signal including a pattern corresponding to a state of an object to be monitored from at least one optical fiber included in the cable, and detecting the pattern from the received optical signal; A state of the monitored object is detected based on the pattern.

[0011] According to one aspect, a non-transitory computer readable medium includes: On the computer, receiving an optical signal including a pattern corresponding to a state of an object to be monitored from at least one optical fiber included in the cable, and detecting the pattern from the received optical signal; detecting a state of the monitored object based on the pattern; The program for executing the above is stored. Effect of the Invention

[0012] According to the above-mentioned aspect, the above-mentioned problem is solved, and an effect is obtained in that the state of the monitored object can be detected without using a special structure for detecting the state of the monitored object. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 illustrates an example of a configuration of a monitoring system according to an embodiment. [Diagram 2] FIG. 11 is a diagram showing an example of fence position information in the embodiment. [Diagram 3] 5A and 5B are diagrams illustrating an example of vibration data generated by an optical fiber detector according to the embodiment. [Figure 4] FIG. 13 is a diagram illustrating an example of machine learning by a control unit according to an embodiment. [Diagram 5] FIG. 11 is a diagram showing an example of fence event information according to the embodiment. [Figure 6] FIG. 13 is a diagram illustrating an example of a configuration of a monitoring system according to a modified example of an embodiment. [Figure 7] FIG. 4 is a diagram showing an example of camera information in the embodiment. [Figure 8] FIG. 13 is a diagram illustrating another example of the configuration of a monitoring system according to a modified example of the embodiment. [Figure 9] FIG. 2 is a block diagram showing an example of a hardware configuration of a computer that realizes the monitoring device according to the embodiment. [Figure 10] FIG. 4 is a flow diagram showing an example of an operation flow of the monitoring system according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. Note that in the embodiment described below, a monitoring target to be monitored is a fence as an example, but the monitoring target is not limited to a fence.

[0015] <Embodiment Mode> <Configuration of the embodiment> First, with reference to FIG. 1, the configuration of a monitoring system according to the present embodiment will be described. As shown in Fig. 1, the monitoring system according to this embodiment monitors a fence 10 and its surroundings, and includes an optical fiber cable 20, a monitoring device 30, and a camera 40. The monitoring device 30 includes an optical fiber detection unit 31 and a control unit 32. Although the fence 10 may be made up of a single fence 10, in this embodiment, it is configured by connecting a plurality of fences 10. The optical fiber detection unit 31 is an example of a receiving unit.

[0016] The optical fiber cable 20 is a cable configured by covering one or more optical fibers, and is laid on the fence 10 and buried in the ground along the fence 10. In detail, the optical fiber cable 20 extends from the optical fiber detection unit 31 along the fence 10, turns back at a turning point, and returns to the optical fiber detection unit 31. Of these, one of the portions between the optical fiber detection unit 31 and the turning point is laid on the fence 10, and the other is buried in the ground along the fence 10. However, the laying and burying method of the optical fiber cable 20 shown in Fig. 1 is one example, and is not limited to this.

[0017] The camera 40 is a camera that photographs the area in which the fence 10 is installed, and is realized by, for example, a fixed camera, a PTZ (Pan Tilt Zoom) camera, or the like.

[0018] The monitoring system according to the present embodiment utilizes optical fiber sensing technology that uses optical fibers as sensors to monitor the fence 10 and its surroundings. Specifically, the optical fiber detection unit 31 inputs a pulsed light into at least one optical fiber included in the optical fiber cable 20. Then, as the pulsed light is transmitted through the optical fiber in the direction of the fence 10, backscattered light is generated for each transmission distance. This backscattered light returns to the optical fiber detection unit 31 via the same optical fiber.

[0019] At this time, the optical fiber detection unit 31 inputs a pulsed light in a clockwise direction and receives backscattered light corresponding to the pulsed light from the clockwise direction, and also inputs a pulsed light in a counterclockwise direction and receives backscattered light corresponding to the pulsed light from the counterclockwise direction. Therefore, the optical fiber detection unit 31 receives backscattered light from two directions.

[0020] Here, when an event occurs, such as a person grabbing and shaking the fence 10, the fence 10 vibrates, and the vibration of the fence 10 is transmitted to the optical fiber. The vibration pattern of the vibration of the fence 10 transmitted to the optical fiber is a dynamically changing fluctuation pattern, and differs depending on the type of event occurring on the fence 10 and its surroundings. In the first embodiment, the following events, for example, are assumed as predetermined events occurring on the fence 10 and its surroundings. (1) A person grabs and shakes fence 10 (2) A person hits fence 10 (3) A person climbs fence 10 (4) A person hangs a ladder on fence 10 and climbs the ladder. (5) People and animals wander around fence 10. (6) A person digs around fence 10

[0021] Therefore, the backscattered light received from the optical fiber by the optical fiber detection unit 31 contains a pattern corresponding to the state of the fence 10 and its surroundings, i.e., a pattern corresponding to an event occurring on the fence 10 and its surroundings. Therefore, in this embodiment, the state of the fence 10 and its surroundings is detected by the method described below, utilizing the fact that the backscattered light contains a pattern corresponding to the state of the fence 10 and its surroundings. Specifically, it is detected whether a predetermined event is occurring on the fence 10 and its surroundings.

[0022] The optical fiber detection unit 31 can identify the position of the fence 10 from which the backscattered light has been generated, based on the time difference between the time when the pulsed light is incident on the optical fiber and the time when the backscattered light is received from the same optical fiber. In the present embodiment, as described above, the fence 10 is configured by connecting a plurality of fences 10. Therefore, as shown in FIG. 2, the optical fiber detection unit 31 can identify the fence 10 from which the backscattered light has been generated, from among the plurality of fences 10, by retaining position information indicating the installation position (here, the distance from the optical fiber detection unit 31) and the installation area of ​​each of the plurality of fences 10. In addition, the optical fiber detection unit 31 can detect the intensity of vibration of the identified fence 10 by detecting the received backscattered light with a distributed vibration sensor.

[0023] Therefore, the optical fiber detector 31 can generate, as sensing data, vibration data such as that shown in Fig. 3. In Fig. 3, the horizontal axis indicates position (distance from the optical fiber detector 31), and the vertical axis indicates the passage of time. In the example shown in Fig. 3, vibration occurs at a position approximately 400 m away from the optical fiber detection unit 31. The optical fiber detection unit 31 detects the strength of this vibration, the vibration position, the transition of the vibration frequency fluctuation, etc., thereby making it possible to define the dynamic unique pattern of this vibration. Furthermore, the optical fiber detection unit 31 also detects dynamic fluctuation patterns of sound and temperature, thereby making it possible to detect complex unique patterns of the fence 10 and its surroundings, and to detect complex movements and conditions with even higher sensitivity.

[0024] Therefore, in this embodiment, the control unit 32 performs machine learning (e.g., deep learning, etc.) on the vibration pattern when a specified event occurs on the fence 10 and its surroundings, and uses the learning results of the machine learning (initial learning model) to detect whether a specified event is occurring on the fence 10 and its surroundings.

[0025] First, the machine learning method will be described with reference to FIG. As shown in Fig. 4, a plurality of vibration patterns are prepared for when a predetermined event occurs on the fence 10 and its surroundings. The control unit 32 inputs the plurality of vibration patterns and teacher data that is fence event information that indicates a predetermined event that occurs on the fence 10 and its surroundings when the vibration pattern is present (steps S1 and S2). Fig. 5 shows an example of the fence event information that serves as the teacher data. The fence event information is held by the control unit 32.

[0026] Next, the control unit 32 performs matching and classification between the two (step S3) and performs supervised learning (step S4). As a result, an initial learning model is obtained (step S5). When a vibration pattern corresponding to an event occurring on the fence 10 and its surroundings is input, this initial learning model is a model that outputs the predetermined event that may possibly correspond if the event is likely to correspond to one of the predetermined events. Alternatively, this initial learning model may be a model that outputs the predetermined event that may possibly correspond together with the confidence that the predetermined event has occurred.

[0027] Next, a method for detecting whether a predetermined event has occurred on the fence 10 or in its surroundings will be described. In this case, the control unit 32 first obtains a vibration pattern corresponding to an event occurring on the fence 10 and its surroundings from the optical fiber detection unit 31. Next, the control unit 32 inputs the vibration pattern into the initial learning model. As a result, the control unit 32 detects that the predetermined event has occurred because a possibly applicable predetermined event is obtained as the output result of the initial learning model. Furthermore, when the control unit 32 obtains a reliability together with the possibly applicable predetermined event as the output result of the initial learning model, it may detect that the predetermined event has occurred if the reliability is equal to or greater than a threshold value.

[0028] As described above, in this embodiment, the vibration pattern when a specified event occurs on the fence 10 and its surroundings is learned by machine learning, and the results of the machine learning are used to detect the specified event occurring on the fence 10 and its surroundings. It may be difficult for a human to extract features from data to detect events occurring on or around the fence 10. In this embodiment, by constructing a learning model from a large number of patterns, it is possible to detect a specific event occurring on or around the fence 10 with high accuracy, even in cases where human analysis would be difficult.

[0029] In the machine learning according to the present embodiment, a learning model may be generated based on two or more pieces of teacher data in the initial state. A newly detected pattern may be newly learned in the learning model. In this case, the detailed conditions for detecting a predetermined event occurring on the fence 10 and its surroundings may be adjusted from the new learning model.

[0030] 6, the surveillance system according to this embodiment may include a plurality of cameras 40 (three cameras 40A-40C in FIG. 6), and may also include a display unit 50 installed in a surveillance room or the like for monitoring the entire area in which the fence 10 is installed. Note that it is sufficient to install a plurality of cameras 40 so as to be able to capture the entire area in which the fence 10 is installed, and there are no particular limitations on the number of cameras installed or the intervals between installations. For example, when using high-performance cameras 40 with a long maximum shooting distance, the number of cameras installed can be reduced and the intervals between installations can be increased.

[0031] As shown in FIG. 7, the control unit 32 holds camera information indicating the installation position (distance from the optical fiber detection unit 31) of each of the multiple cameras 40, the area where the camera can capture images, and the like. The control unit 32 can also obtain position information of each of the multiple fences 10 as shown in FIG. 2 from the optical fiber detection unit 31. Therefore, when the control unit 32 detects a predetermined event occurring on the fence 10 and its periphery as described above, the control unit 32 identifies, among the multiple cameras 40, a camera 40 that captures an area including the fence 10 where the predetermined event is detected, based on the camera information and the position information of the fence 10 described above, and controls the identified camera 40. For example, the control unit 32 controls the angle (azimuth angle, elevation angle), zoom magnification, and the like of the camera 40. The control unit 32 may also change the control of the camera 40 according to the pattern of the detected state. For example, the control unit 32 may track actions with a higher degree of urgency (for example, digging around, climbing over, and the like) with multiple cameras 40, or control the camera 40 by zooming, etc., to identify a face or person in more detail.

[0032] Furthermore, the control unit 32 may control two or more cameras 40 among the multiple cameras 40 to capture an area including the fence 10 where a predetermined event has been detected. In this case, the functions may be divided for each camera 40. For example, at least one camera 40 among the two or more cameras 40 may capture the face of a person present in the above-mentioned area, and the captured face image may be utilized for face recognition, and at least one camera 40 among the two or more cameras 40 may capture the entire above-mentioned area, and the captured image may be utilized for monitoring the behavior of people and animals present in the above-mentioned area. Furthermore, the two or more cameras 40 may capture the area from different angles. Furthermore, at least one camera 40 among the two or more cameras 40 may capture an image to complement the image captured by another camera 40. For example, when there is a blind spot in the above-mentioned area that cannot be captured by another camera 40, the camera 40 may capture the blind spot. Furthermore, when there is a dark area at night, the control unit 32 may additionally control a camera 40 with a night vision function such as an infrared camera, instead of the camera 40 that captures the area, or may switch the camera 40 to a night vision mode. Furthermore, as shown in Fig. 8, the control unit 32 may control a spotlight 70, and for example, when a predetermined event is detected in an area captured by the camera 40A, control the spotlight 70 to shine its light on the area.

[0033] Furthermore, the control unit 32 may cause the display unit 50 to display a sensing data image showing the sensing data generated by the optical fiber detection unit 31, a camera image of the camera 40 capturing an image of an area including the fence 10 where a predetermined event has been detected based on the sensing data, etc. However, there is no limitation on the display content.

[0034] Next, the hardware configuration of the computer 60 that realizes the monitoring device 30 will be described with reference to FIG. 9, the computer 60 includes a processor 601, a memory 602, a storage 603, an input / output interface (input / output I / F) 604, and a communication interface (communication I / F) 605. The processor 601, the memory 602, the storage 603, the input / output interface 604, and the communication interface 605 are connected by a data transmission path for transmitting and receiving data to and from each other.

[0035] The processor 601 is an arithmetic processing device such as a central processing unit (CPU) or a graphics processing unit (GPU). The memory 602 is a memory such as a random access memory (RAM) or a read only memory (ROM). The storage 603 is a storage device such as a hard disk drive (HDD), a solid state drive (SSD), or a memory card. The storage 603 may also be a memory such as a RAM or a ROM.

[0036] The storage 603 stores programs for realizing the functions of the optical fiber detection unit 31 and the control unit 32 included in the monitoring device 30. The processor 601 executes each of these programs to respectively realize the functions of the optical fiber detection unit 31 and the control unit 32. Here, when executing each of the above programs, the processor 601 may read these programs onto the memory 602 before executing them, or may execute them without reading them onto the memory 602. In addition, the memory 602 and the storage 603 also serve to store information and data held by the optical fiber detection unit 31 and the control unit 32.

[0037] The above-mentioned program can be stored and provided to a computer (including the computer 60) using various types of non-transitory computer readable media. The non-transitory computer readable medium includes various types of tangible storage media. Examples of the non-transitory computer readable medium include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Compact Disc-Read Only Memory), CD-Rs (CD-Recordable), CD-R / Ws (CD-ReWritable), and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program can also be provided to a computer by various types of transitory computer readable media. Examples of the transitory computer readable medium include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0038] The input / output interface 604 is connected to a display device 6041, an input device 6042, and the like. The display device 6041 is a device that displays a screen corresponding to drawing data processed by the processor 601, such as an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube) display. The input device 6042 is a device that accepts an operation input by an operator, and is, for example, a keyboard, a mouse, and a touch sensor. The display device 6041 and the input device 6042 may be integrated and realized as a touch panel. The computer 60 may also include sensors (not shown) including a distributed vibration sensor, and may be configured to connect this sensor to the input / output interface 604. The display unit 50 may be connected to the input / output interface 604.

[0039] The communication interface 605 transmits and receives data to and from an external device. For example, the communication interface 605 communicates with the external device via a wired communication path or a wireless communication path.

[0040] <Operation of the embodiment> The operation of the monitoring system according to the present embodiment will be described below. Here, the operation flow of the monitoring system according to the present embodiment will be described with reference to FIG.

[0041] As shown in FIG. 10, first, the optical fiber detector 31 inputs pulsed light into at least one optical fiber included in the optical fiber cable 20 (step S11). Next, the optical fiber detection unit 31 receives backscattered light including a pattern corresponding to the state of the fence 10 and its surroundings from the same optical fiber as the optical fiber into which the pulsed light is incident, and detects a pattern corresponding to the state of the fence 10 and its surroundings from the received backscattered light (step S12). Specifically, a pattern corresponding to an event occurring on the fence 10 and its surroundings is detected. At this time, the optical fiber detection unit 31 detects the dynamic fluctuation pattern of the fence 10 and its surroundings by detecting the strength and weakness of vibrations caused by an event occurring on the fence 10 and its surroundings, the vibration position, the transition of the fluctuation of the vibration frequency, etc., as described above. Alternatively, the optical fiber detection unit 31 may detect a complex unique pattern of the fence 10 and its surroundings by further detecting the dynamic fluctuation patterns of sound and temperature.

[0042] Thereafter, the control unit 32 detects the state of the fence 10 and its surroundings based on the pattern detected by the optical fiber detection unit 31 (step S13). Specifically, it detects whether a predetermined event has occurred on the fence 10 and its surroundings. At this time, the control unit 32 may detect whether a predetermined event has occurred on the fence 10 and its surroundings by the above-mentioned machine learning method.

[0043] <Effects of the embodiment> As described above, according to the present embodiment, backscattered light (optical signal) including a pattern corresponding to the state of the fence 10 and its surroundings is received from at least one optical fiber included in the optical fiber cable 20, a pattern is detected from the received backscattered light, and the state of the fence 10 and its surroundings is detected based on the detected pattern. In this way, since the state of the fence 10 and its surroundings is detected based on the pattern included in the backscattered light, it is not necessary to use a special optical fiber called an FBG type optical fiber as in Patent Documents 1 to 3, to use an OTDR type optical fiber together with an FBG type optical fiber as in Patent Documents 1 to 2, or to lay a plurality of optical fibers as in Patent Document 3. Therefore, it is possible to detect the state of the fence 10 and its surroundings without using a special structure for detecting the state of the fence 10 and its surroundings. In addition, since no special structure is required, the monitoring system can be constructed at low cost.

[0044] Furthermore, according to this embodiment, the state of the fence 10 and its surroundings is detected based on a pattern contained in the backscattered light that corresponds to the state of the fence 10 and its surroundings. That is, in this embodiment, unlike, for example, cited reference 3, the state is not distinguished by the strength of vibration or the magnitude of vibration frequency (for example, the state is specified by vibration being large and vibration frequency being high), but the state of the fence 10 and its surroundings is detected by dynamically analyzing the pattern of these changes (for example, the transition of changes in the strength of vibration, etc.). Therefore, it is possible to detect the state of the fence 10 and its surroundings with high accuracy.

[0045] Furthermore, according to this embodiment, the condition of the fence 10 and its surroundings is detected based on a pattern contained in the backscattered light that corresponds to the condition of the fence 10 and its surroundings. Therefore, even for weak changes, such as events around the fence 10 that do not involve contact with the fence 10, it is possible to clearly separate these from other noise components such as wind by detecting dynamic pattern fluctuations, and to detect the condition in which the event is occurring with high accuracy.

[0046] Moreover, the FBG type optical fiber used in Patent Documents 1 to 3 has a structure in which grating sections are provided at regular intervals, and intruders are detected at the "points" where the grating sections are provided. In contrast, the present embodiment detects the state of the fence 10 by capturing a dynamic fluctuation pattern such as the vibration pattern in Fig. 4 as a "line", resulting in higher resolution and sensitivity and higher detection accuracy compared to Patent Documents 1 to 3.

[0047] Furthermore, according to the present embodiment, optical fiber sensing technology is used, which uses optical fiber as a sensor, and therefore has the advantages of being immune to electromagnetic noise, not requiring power supply to the sensor, excellent environmental resistance, and easy maintenance.

[0048] <Other embodiments> In the above embodiment, an example in which the monitored object is the fence 10 (and its surroundings) has been described, but the monitored object is not limited to the fence 10 (and its surroundings). First, the location of the monitored object may be an airport, a port, a plant, a nursing facility, a company building, a border, a nursery school, a home, etc. In addition, the monitored object may be a wall, a pipeline, a utility pole, a civil engineering structure, etc., other than a fence. In addition, the optical fiber cable 20 may be laid or buried in a wall, a pipeline, a utility pole, a civil engineering structure, a floor, etc., other than a fence or underground, when monitoring the monitored object. For example, when monitoring a fence 10 installed in a nursing facility, a predetermined event that occurs on the fence 10 may be a person hitting the fence 10, a person leaning on the fence 10 due to injury, a person climbing the fence 10 to escape, etc.

[0049] In the above embodiment, the fence 10 is described as vibrating when a predetermined event occurs. When these events occur, changes in sound, temperature, strain, stress, etc. also occur in the fence 10, and these changes are also transmitted to the optical fiber. The patterns of sound, temperature, strain, stress, etc. also vary dynamically and differ depending on the type of event occurring in the fence 10. Therefore, the optical fiber detection unit 31 may detect changes in vibration, sound, temperature, strain, stress, etc. using a distributed acoustic sensor and a distributed temperature sensor in addition to a distributed vibration sensor, generate sensing data, and the control unit 32 may detect an event occurring in the fence 10 based on the sensing data reflecting the changes in vibration, sound, temperature, strain, stress, etc. This can further improve the detection accuracy.

[0050] In the above embodiment, when a predetermined event occurs on the fence 10, the control unit 32 controls the angle, zoom magnification, etc. of the camera 40 that captures the area including the fence 10, but the control may continue even after the predetermined event occurs. For example, the control unit 32 may control the camera 40 to track people, animals, cars, etc. that are present in the above-mentioned area. In addition, when a person who has been wandering around the fence 10 leaves a suspicious object or the like and leaves, the control unit 32 may control a certain camera 40 to capture the object and control the other cameras 40 to track the person.

[0051] In addition, the optical fiber detection unit 31 and the control unit 32 of the monitoring device 30 may be provided separately from each other. For example, the optical fiber detection unit 31 may be provided in a telecommunications carrier station, and the monitoring device 30 including the control unit 32 may be provided outside the telecommunications carrier station.

[0052] Further, in the above embodiment, only one optical fiber detector 31 is provided and occupies the optical fiber cable 20, but the present invention is not limited to this. For example, the optical fiber detector 31 may be provided in a telecommunications carrier building, and the optical fiber cable 20 may be shared between the optical fiber detector 31 and existing communication equipment provided inside the telecommunications carrier building.

[0053] Also, one optical fiber detector 31 may be provided in each of a plurality of communication carrier offices, and the optical fiber cable 20 may be shared among the plurality of optical fiber detectors 31 provided in each of the plurality of communication carrier offices. Furthermore, a plurality of optical fiber detectors 31 may be provided in one communications carrier station, and the optical fiber cable 20 may be shared among the plurality of optical fiber detectors 31.

[0054] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

[0055] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes. (Appendix 1) a cable including an optical fiber; a receiving unit that receives an optical signal including a pattern corresponding to a state of an object to be monitored from at least one optical fiber included in the cable and detects the pattern from the received optical signal; A control unit that detects a state of the monitoring target based on the pattern; A surveillance system comprising: (Appendix 2) The control unit is learning a pattern according to a state of the monitored object, and detecting the state of the monitored object based on a learning result and the pattern included in the optical signal received by the receiving unit; 2. A monitoring system as described in claim 1. (Appendix 3) Further equipped with multiple cameras, The control unit is Controlling a camera among the plurality of cameras that captures an area including the monitoring target; 3. The surveillance system according to claim 1 or 2. (Appendix 4) The control unit is Controlling two or more cameras among the plurality of cameras that capture an area including the monitoring target; 4. A monitoring system as described in appended claim 3. (Appendix 5) The control unit is At least one of the two or more cameras is controlled to capture a face of a person present in the area, and at least one of the two or more cameras is controlled to capture an image of the entire area. 6. A monitoring system as described in claim 4. (Appendix 6) The pattern is a dynamically changing fluctuation pattern. 6. The monitoring system according to claim 1 , (Appendix 7) a receiving unit that receives an optical signal including a pattern corresponding to a state of an object to be monitored from at least one optical fiber included in the cable and detects the pattern from the received optical signal; A control unit that detects a state of the monitoring target based on the pattern; A monitoring device comprising: (Appendix 8) The control unit is learning a pattern according to a state of the monitored object, and detecting the state of the monitored object based on a learning result and the pattern included in the optical signal received by the receiving unit; 8. The monitoring device according to claim 7. (Appendix 9) The control unit is Controlling a camera among the plurality of cameras that captures an area including the monitoring target; 9. The monitoring device according to claim 7 or 8. (Appendix 10) The control unit is Controlling two or more cameras among the plurality of cameras that capture an area including the monitoring target; 10. The monitoring device according to claim 9. (Appendix 11) The control unit is At least one of the two or more cameras is controlled to capture a face of a person present in the area, and at least one of the two or more cameras is controlled to capture an image of the entire area. 11. The monitoring device of claim 10. (Appendix 12) The pattern is a dynamically changing fluctuation pattern. 12. The monitoring device according to any one of claims 7 to 11. (Appendix 13) A monitoring method using a monitoring device, comprising: receiving an optical signal including a pattern corresponding to a state of an object to be monitored from at least one optical fiber included in the cable, and detecting the pattern from the received optical signal; Detecting a state of the monitored object based on the pattern; Monitoring method. (Appendix 14) On the computer, receiving an optical signal including a pattern corresponding to a state of an object to be monitored from at least one optical fiber included in the cable, and detecting the pattern from the received optical signal; detecting a state of the monitored object based on the pattern; A non-transitory computer-readable medium having stored thereon a program for executing the program. [Explanation of symbols]

[0056] 10. Fence 20 Optical fiber cable 30 Monitoring equipment 31 Optical fiber detector 32 Control section 40,40A~40C Camera 50 Display 60 Computer 601 Processor 602 Memory 603 Storage 604 Input / Output Interface 6041 Display device 6042 Input Device 605 Communication Interface 70 Spotlight

Claims

1. an optical fiber laid in contact with the fence; a receiving means for receiving backscattered light including a pattern corresponding to an event occurring around the fence from the optical fiber; An identification means for identifying an event occurring around the fence based on the pattern and a learning model that has been previously learned; Equipped with The learning model learns in advance, for each of the events, a vibration pattern corresponding to the event and one of a sound fluctuation pattern and a temperature fluctuation pattern corresponding to the event; the identification means identifies an event that has occurred around the fence based on a vibration pattern included in the pattern, any one of a sound fluctuation pattern and a temperature fluctuation pattern included in the pattern, and the learning model. Surveillance system.

2. The events include at least one of the following: (1) a person grabbing and shaking the fence; (2) a person hitting the fence; (3) a person climbing the fence; (4) a person using a ladder to climb the fence; (5) a person or animal wandering around the fence; and (6) a person digging around the fence. The monitoring system of claim 1 .

3. The optical fiber is laid around the fence. The monitoring system of claim 1 .

4. The receiving means detects the pattern from the backscattered light. The monitoring system of claim 1 .

5. a receiving means for receiving backscattered light including a pattern corresponding to an event occurring around the fence from an optical fiber laid in contact with the fence; An identification means for identifying an event occurring around the fence based on the pattern and a learning model that has been previously learned; Equipped with The learning model learns in advance, for each of the events, a vibration pattern corresponding to the event and one of a sound fluctuation pattern and a temperature fluctuation pattern corresponding to the event; the identification means identifies an event that has occurred around the fence based on a vibration pattern included in the pattern, any one of a sound fluctuation pattern and a temperature fluctuation pattern included in the pattern, and the learning model. Monitoring equipment.

6. A monitoring method using a monitoring device, comprising: receiving backscattered light including a pattern corresponding to an event occurring around the fence from an optical fiber laid in contact with the fence; and identifying an event occurring around the fence based on the pattern and a previously learned learning model, The learning model learns in advance, for each of the events, a vibration pattern corresponding to the event and one of a sound fluctuation pattern and a temperature fluctuation pattern corresponding to the event; In the identifying step, an event occurring around the fence is identified based on a vibration pattern included in the pattern, any one of a sound fluctuation pattern and a temperature fluctuation pattern included in the pattern, and the learning model. Monitoring method.

7. On the computer, receiving backscattered light including a pattern corresponding to an event occurring around the fence from an optical fiber laid in contact with the fence; an identification step of identifying an event occurring around the fence based on the pattern and a learning model that has been previously trained; A program for executing The learning model learns in advance, for each of the events, a vibration pattern corresponding to the event and one of a sound fluctuation pattern and a temperature fluctuation pattern corresponding to the event; In the identification step, an event occurring around the fence is identified based on a vibration pattern included in the pattern, any one of a sound fluctuation pattern and a temperature fluctuation pattern included in the pattern, and the learning model. program.

Images