Outdoor light monitoring system and outdoor light monitoring program

Abstract

To properly and surely monitor a lighting state of an outdoor lamp and properly perform a notification in a case where abnormality is found.SOLUTION: An outdoor lamp monitoring system comprises: a camera 3 which is mounted on a flying drone 2; and a monitoring server 4 which determines the presence / absence of abnormality in a lighting state of an outdoor lamp L based on an image of the outdoor lamp L captured by the camera 3 and, when the presence of abnormality is determined, performs a notification to a previously stored notification destination 5.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an outdoor light monitoring system and an outdoor light monitoring program for monitoring the lighting state of outdoor lights. [Background technology]

[0002] For example, streetlights (outdoor lights) installed on utility poles are usually managed and operated by local residents' associations, etc., and when they stop working due to aging or other reasons, they are replaced by the residents' association, etc. However, if residents or people working nearby who notice that the lights are not working do not know how to contact them, there is a risk that the lights will remain off for a long period of time.

[0003] Meanwhile, a lighting fixture failure detection system is known that can inexpensively and easily detect failures in lighting fixtures such as streetlights by utilizing existing devices and facilities (see, for example, Patent Document 1). This system comprises a smart meter that measures the amount of power used by a lighting fixture and transmits that data at predetermined time intervals, and a failure detection device that compares predetermined data calculated using the amount of power used from the smart meter with a threshold value to detect a failure in the lighting fixture. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-77584 Summary of the Invention [Problem to be solved by the invention]

[0005] However, outdoor lights are installed in large numbers over a wide area, and not only is it difficult for people to monitor and inspect each and every one of them without exception, but even if an abnormality is discovered, it is not necessarily communicated to the appropriate contact point. On the other hand, the system described in Patent Document 1 is effective for lighting fixtures equipped with smart meters, but cannot be applied to lighting fixtures that do not have smart meters installed.

[0006] Therefore, an object of the present invention is to provide an outdoor light monitoring system and an outdoor light monitoring program that can properly and reliably monitor the lighting status of outdoor lights and properly report any abnormalities that are discovered. [Means for solving the problem]

[0007] In order to solve the above problem, the invention of claim 1 is as follows: Along the flight route The drone is equipped with a photographing means mounted on the drone in flight, and a monitoring means for determining whether or not there is an abnormality in the lighting state of the street light based on an image of the street light photographed by the photographing means, and for reporting the abnormality to a pre-stored reporting destination when it is determined that there is an abnormality. The flight route is set so that as many street lights as possible can be photographed efficiently and without omission in a given time. The monitoring means is configured to detect the identification information of each outdoor light and 、 Installation location and 、 Type, model and , and reporting points including neighborhood associations and town associations. and based on the position information when the outdoor light is photographed by the photographing means, determining the identification information of the outdoor light that is determined to have an abnormality, and storing the identification information, the type, and the model. According to the identified information This is an outdoor light monitoring system characterized by sending a report to the reporting destination.

[0008] The invention of claim 2 is the outdoor light monitoring system according to claim 1, The monitoring means is characterized in that it uses the general lighting state of the outdoor light under normal conditions as a standard, and determines that there is an abnormality if the outdoor light is dimly lit, flickers, or is not lit at all, whereas if it is normal, it is lit stably at a predetermined brightness and size.

[0010] Claim 3 The invention is 1 or 2 In the outdoor light monitoring system described above, the photographing means and the monitoring means are provided in a mobile communication terminal.

[0011] Claim 4The invention is as follows: 3 In the outdoor light monitoring system described above, the drone is characterized by automatically flying along a predetermined route.

[0012] Claim 5 The invention is as follows: 4 In the outdoor light monitoring system described above, the monitoring means uses a learning model for outdoor light monitoring that is machine-learned based on past performance data so that when an image of the outdoor light is input, it outputs whether or not there is an abnormality in the lighting status of the outdoor light.

[0013] Claim 6 The invention of Along the flight route A street light monitoring program for functioning as a monitoring means for determining whether or not there is an abnormality in the lighting state of a street light based on an image of the street light captured by a photographing means mounted on a flying drone, and for reporting to a pre-stored reporting destination when it is determined that there is an abnormality, The flight route is set so that as many street lights as possible can be photographed efficiently and without omission in a given time. The monitoring means is configured to detect the identification information of each outdoor light and 、 Installation location, type, model, and , and reporting points including neighborhood associations and town associations. and based on the position information when the outdoor light is photographed by the photographing means, determining the identification information of the outdoor light that is determined to have an abnormality, and storing the identification information, the type, and the model. According to the identified information This is a program for monitoring outdoor lights, characterized in that it notifies the reporting destination.

[0014] Claim 7 The invention is 6 In the described outdoor light monitoring program, the monitoring means uses a learning model for outdoor light monitoring that has been machine-learned based on past performance data so that when an image of the outdoor light is input, it outputs whether or not there is an abnormality in the lighting status of the outdoor light. [Effects of the Invention]

[0015] Claim 1 and Claim 6According to the invention described in the above, when a drone flies and photographs a street light with a photographing means, it is automatically determined whether or not there is an abnormality in the lighting condition of the street light based on the image, and if it is determined that there is an abnormality, a report is automatically sent to a pre-stored reporting destination. In other words, since the presence or absence of an abnormality in the street light is automatically determined based on the image taken by the drone while flying, without relying on a human visual inspection, it is possible to properly and reliably monitor the lighting condition of street lights even when many street lights are installed over a wide area. Furthermore, since a report is automatically sent to a reporting destination when it is determined that there is an abnormality, it is possible to properly and reliably notify the reporting destination that an abnormality has been found. As a result, it becomes possible to properly manage outdoor lights and ensure the safety of the area.

[0016] Claim 1 and Claim 6 According to the invention described above, the identification information of an outdoor light that has been determined to have an abnormality is reported to the reporting destination, so that the reporting destination can properly and quickly identify the outdoor light that has been determined to have an abnormality and respond to the outdoor light properly and quickly.

[0017] Claim 1 and claim 6 According to the invention described in the above, a report is sent to an appropriate reporting destination according to the identification information of the outdoor light that has been determined to have an abnormality. In other words, even if the reporting destination and manager vary depending on the outdoor light, a report is sent to the appropriate reporting destination that manages the outdoor light that has been determined to have an abnormality, making it possible to respond to the outdoor light appropriately and quickly.

[0018] Claim 3 According to the invention described in the above, since the photographing means and monitoring means are provided in the mobile communication terminal, it is possible to construct this outdoor light monitoring system easily and at low cost. In other words, this outdoor light monitoring system can be constructed simply by providing the photographing means and monitoring means in a mobile communication terminal such as a smartphone (multi-function mobile terminal) and mounting it on a drone. Moreover, since smartphones and the like generally come standard with a photographing means, i.e., a camera, it is only necessary to provide the monitoring means in the smartphone or the like.

[0019] Claim4 According to the invention described in the above, the drone automatically flies along a predetermined route, which not only reduces the labor and costs involved in manual operation, but also makes it possible to photograph many street lights reliably and appropriately by properly setting the predetermined route. As a result, it becomes possible to monitor many street lights more reliably and appropriately.

[0020] Claim 5 and claims 7 According to the invention described in the above, a learning model for monitoring outdoor lights that has been machine-learned is Since the presence or absence of an abnormality in the lighting state of the outdoor light is output using the above, it is possible to more accurately determine whether or not there is an abnormality. As a result, it is possible to more accurately and reliably monitor the lighting state of the outdoor light. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a schematic configuration diagram showing an outdoor light monitoring system in accordance with Embodiment 1 of the present invention. [Figure 2] 2A and 2B are a front view and a plan view, respectively, showing the drone of the outdoor light monitoring system of FIG. 1. [Figure 3] 2 is a schematic block diagram showing the configuration of a monitoring server of the outdoor light monitoring system of FIG. 1. FIG. [Figure 4] FIG. 2 is a plan view showing an example of a flight route of a drone in the streetlight monitoring system of FIG. 1. [Figure 5] FIG. 4 is a data configuration diagram of an outdoor light database of the monitoring server of FIG. 3. [Figure 6] 2 is a diagram showing the lighting state of a normal outdoor light photographed by a camera of the outdoor light monitoring system of FIG. 1. FIG. [Figure 7] 2 is a diagram showing the lighting state of a deteriorated outdoor light photographed by a camera of the outdoor light monitoring system of FIG. 1. FIG. [Figure 8] 4 is a functional block diagram showing a schematic configuration of a learning model for monitoring outdoor lights in the monitoring server of FIG. 3. FIG. [Figure 9]FIG. 10 is a side view showing a drone and a smartphone in an outdoor light monitoring system according to a second embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0022] The present invention will be described below based on the illustrated embodiments.

[0023] (Embodiment 1) FIG. 1 is a schematic diagram showing the configuration of an outdoor light monitoring system 1 according to this embodiment. This outdoor light monitoring system 1 is a system for monitoring the lighting state of outdoor lights (street lights) L, and mainly comprises a drone 2, a camera (imaging means) 3, and a monitoring server (monitoring means) 4, with the drone 2 and monitoring server 4 connected to each other so as to be able to communicate freely. Here, in this embodiment, a case will be described in which the outdoor light L is installed on a utility pole P, but the outdoor light may also be installed on a structure other than a utility pole P or installed freestanding. Furthermore, the monitoring target is many outdoor lights L installed over a wide area, and these outdoor lights L are managed and operated by multiple neighborhood associations or local community associations.

[0024] The drone 2 is an unmanned aerial vehicle that flies, and in this embodiment, it is configured to automatically fly along a predetermined flight route / flight path. That is, it is equipped with a GPS (Global Positioning System), and flies autonomously along a flight route set by a monitoring server 4 (described later) and stored in the drone 2, while confirming its own position using the GPS. At this time, the drone 2 may be equipped with an obstacle avoidance function according to the flight environment, etc. The drone 2 also has an automatic hovering function that hovers at a predetermined hovering position. A plurality of such drones 2 may be provided, and they may fly different flight routes simultaneously.

[0025] The camera 3 is an imaging device that captures images of streetlights L and the like, and captures at least images of the streetlights L when they are lit. As shown in FIG. 2, the camera 3 is mounted on the drone 2 with its lens facing forward. The camera 3 is controlled by the drone 2, and in this embodiment, when the drone 2 flies to a predetermined hovering position on its flight route, i.e., the position where the streetlights L are to be captured, and hovers there, the camera automatically captures the streetlights L. Each time the streetlights L are captured, the drone 2 transmits the captured image, location information (latitude and longitude) at the time of capture, and imaging information including the drone 2's identification information to the monitoring server 4. This allows the monitoring server 4 to determine which streetlights L are captured in which images, as will be described later.

[0026] In response to this, the camera 3 constantly photographs street lights L and the like while constantly recording the flight position of the drone 2 over time, and the flight position of the drone 2 at each time and the captured moving images and videos are sent to the monitoring server 4. Then, by comparing the flight position of the drone 2 and the images at the same time in the monitoring server 4, it may be possible to determine which street lights L are being photographed.

[0027] The monitoring server 4 is a server computer for monitoring and determining whether each outdoor light L is in good condition based on images of each outdoor light L captured by the camera 3. As shown in Fig. 3, the monitoring server 4 mainly comprises an input unit 41, a display unit 42, a communication unit 43, a memory unit 44, a monitoring task (monitoring means) 45, a learning task 46, and a central processing unit 47 that controls these components.

[0028] The input unit 41 is an interface for inputting various information and commands, such as the flight route of the drone 2. Specifically, the flight route is input by specifying the route the drone 2 should fly on a map that stores the locations (latitude and longitude) of each street light L and building, the location and width of roads, and so on. For example, as shown by the arrows in FIG. 4, a flight route is input along which the drone 2 will fly while photographing each street light L. In this case, the flight route is set so that as many street lights L as possible can be photographed reliably and efficiently within a given time period. The latitude, longitude, direction of travel, and distance traveled of each point on the route, as well as the latitude and longitude of the hovering position and photographing position, are stored in this flight route. Multiple such flight routes can be set and stored, and different flight routes can be transmitted to the drone 2 and stored according to the flight date and time, the drone 2, and so on, allowing the drone 2 to fly along a desired flight route.

[0029] The display unit 42 is a display that displays various data and information, and specifically displays the above-mentioned map and flight route, the determination results described below, etc. The communication unit 43 is an interface for communicating with the outside via the Internet network, telephone communication network, etc., and communicates with each drone 2, each reporting destination 5, etc.

[0030] The storage unit 44 mainly includes an outdoor light database (street light information storage means) 441, an outdoor light monitoring learning model 442, and an outdoor light monitoring performance database 443. Here, the outdoor light database 441 will be explained, and the outdoor light monitoring learning model 442 and the outdoor light monitoring performance database 443 will be explained later.

[0031] The outdoor light database 441 is a database that stores information about each outdoor light L, and as shown in Figure 5, for each outdoor light ID 441a, a type 441b, an installation location 441c, a reporting destination 441d, a standard lifespan 441e, an image 441f, and other information 441g are stored.

[0032] The outdoor light ID 441a stores the identification information of the outdoor light L, specifically the outdoor light number and the name of the neighborhood association or other organization that manages and operates the outdoor light L. The type 441b stores the type and model of the outdoor light L, and the installation location 441c stores information about the location (latitude, longitude, etc.) where the outdoor light L is installed. The report destination 441d stores the report destination 5 to which a report should be sent if there is an abnormality in the outdoor light L, such as a neighborhood association or a town association, the email address or telephone number of its representative, or contact information for a construction company that inspects or replaces the outdoor light L. The standard lifespan 441e stores the standard lifespan of outdoor lights L of the same type and model as the outdoor light L. The image 441f chronologically stores images of the outdoor light L taken in a normal state at the beginning of monitoring or when it was new, images taken thereafter, and the results of the evaluation (described later). The other 441g stores the installation date and replacement date of the outdoor light L, etc.

[0033] The monitoring task 45 is a program task that determines whether there is an abnormality in the lighting state (brightness state) of the street light L based on an image of the street light L captured by the camera 3, and if it determines that there is an abnormality, reports it to a pre-set and stored reporting destination 5 via the communication unit 43. This monitoring task 45 is activated when it receives shooting information from the drone 2, or when an activation command is input via the input unit 41 specifying an image and location information at the time of shooting.

[0034] First, based on the image captured by camera 3, whether or not an abnormality has occurred in the street light L being photographed is determined based on, for example, an image taken under normal conditions. That is, based on images of the street light L in a normal state stored in the street light database 441 and the image currently being photographed, image analysis is performed to determine whether or not there is an abnormality in the lighting state of the street light L compared to normal conditions. Alternatively, image analysis is performed to determine whether or not there is an abnormality in the lighting state of the street light L, using the general lighting state of the street light L under normal conditions (e.g., stable lighting at a predetermined brightness) as a reference. For example, as shown in FIG. 6, if the street light L is normally lit stably at a predetermined brightness and size, whereas as shown in FIG. 7, if the street light is dimly lit, flickering, or not lit at all, an abnormality is determined. In this way, because the presence or absence of an abnormality is determined based on the lighting state of the street light L (brightness, size, stability, etc.), the appearance of the street light L does not necessarily need to be clearly visible in the image. In other words, the image captured by camera 3 only needs to clearly show the lighting state of the street light L.

[0035] When determining whether or not there is an abnormality in this way, the standard lifespan stored in standard lifespan 441e may be used as a reference. For example, if the standard lifespan has expired and outdoor light L is on at a predetermined brightness but occasionally goes out, it may be determined that there is an abnormality.

[0036] Here, as described above, the photographed street light L, i.e., street light ID 441a, is identified based on the location information at the time of photography included in the photography information and the installation position 441c in the street light database 441, and an image in normal condition, etc. is acquired from the image 441f of this street light ID 441a. Alternatively, the photographed street light L, i.e., street light ID 441a may be identified by searching the images 441f of the street light database 441 for an image equivalent to the image to be determined included in the photography information (such as the background excluding the lit state).

[0037] Next, if it is determined that there is an abnormality, the identification information of that street light L is determined. That is, the street light ID 441a is specified as described above and the identification information of the street light L is obtained. Then, the abnormality information and determination result, including the identification information of this street light L, a fact that there is an abnormality, an image of the determined abnormality, and the type and model stored in type 441b, are transmitted and reported to the reporting destination 5 stored in the reporting destination 441d of this street light ID 441a. In this way, by including the type and model of the street light L in the abnormality information, a replacement street light L can be easily and quickly prepared at the reporting destination 5.

[0038] Such a monitoring task 45 uses a learning model 442 for monitoring outdoor lights that has been machine-learned based on past performance data so that, when an image of an outdoor light L is input, it outputs whether or not there is an abnormality in the lighting state of the outdoor light L. This learning model 442 for monitoring outdoor lights is created by the learning task 46.

[0039] That is, the learning task 46 uses past performance data recorded and accumulated in a street light monitoring performance database 443 to create a street light monitoring learning model 442 using a known machine learning algorithm such as a neural network. This street light monitoring performance database 443 is a database in which performance data is recorded and accumulated, including the results of judgments made by experts and experienced persons in street light management (such as residents' association officials) as to whether or not an abnormality has occurred in street light L, based on photographed images of the street light L as input information. The past performance data includes data created based on actual images and the results of actual judgments made by experts and experienced persons in street light management, as well as data created through prior training, etc.

[0040] As shown in Fig. 8, this learning task 46 uses machine learning and deep learning using a neural network to create a neural network based on performance data recorded in a street light monitoring performance database 443, with, for example, a photographed image of a street light L as an input layer, a determination result of the presence or absence of an abnormality as an output layer, and an analysis process from the input layer to the output layer as an intermediate layer. Then, the learning task 46 uses the performance data of the street light monitoring learning model 442 as learning data to learn various parameters in the intermediate layer. In other words, the learning task 46 learns various parameters in the intermediate layer so that the presence or absence of an abnormality can be appropriately determined and output based on the photographed image of the street light L.

[0041] As described above, according to this street light monitoring system 1, when a flight route is set and input for the drone 2 and the drone 2 is made to fly automatically, the drone 2 flies along the flight route, successively hovering at predetermined positions, and photographs of the street lights L are taken by the camera 3. Then, the photographed images, position information at the time of photographing, and photographing information including the identification information of the drone 2 are sequentially transmitted from the drone 2 to the monitoring server 4.

[0042] In response to this, the monitoring server 4 automatically determines whether or not there is an abnormality in the lighting state of the street light L based on the image, and if it determines that there is an abnormality, it automatically reports it to the pre-stored reporting destination 5. In other words, since the presence or absence of an abnormality in the street light L is automatically determined based on images taken by the drone 2 while flying, without relying on visual inspection by a person, it becomes possible to properly and reliably monitor the lighting state of the street light L even if many street lights L are installed over a wide area. Furthermore, if it is determined that there is an abnormality, it is automatically reported to the reporting destination 5, making it possible to properly and reliably report that an abnormality has been discovered.

[0043] In addition, since the identification information of the outdoor light L that has been determined to have an abnormality is reported to the reporting destination 5, the outdoor light L that has been determined to have an abnormality can be properly and quickly identified at the reporting destination 5, and appropriate and quick response can be made to that outdoor light L.

[0044] Furthermore, a report is sent to the appropriate report destination 5 according to the identification information of the outdoor light L that has been determined to have an abnormality. In other words, even if the report destination 5, manager, etc. differs depending on the outdoor light L, a report is sent to the appropriate report destination 5 that manages the outdoor light L that has been determined to have an abnormality, making it possible to respond to the outdoor light L appropriately and quickly.

[0045] Furthermore, because drone 2 automatically flies a predetermined route and flight path, not only can the labor and costs associated with manual operation be reduced, but by properly setting the predetermined route, it becomes possible to reliably and properly photograph many street lights L. As a result, it becomes possible to more reliably and properly monitor many street lights L.

[0046] Furthermore, whether or not there is an abnormality in the lighting state of the outdoor light L is output using the machine-learned outdoor light monitoring learning model 442, making it possible to more accurately determine whether or not there is an abnormality. As a result, it becomes possible to more accurately and reliably monitor the lighting state of the outdoor light L.

[0047] In this way, it is possible to properly and quickly manage the outdoor lights L and ensure the safety of the area.

[0048] (Embodiment 2) 9 is a side view showing the drone 2 and smartphone (mobile communication terminal) 6 in the outdoor light monitoring system according to this embodiment. This embodiment differs from the first embodiment in that the imaging means and monitoring means are provided in the smartphone 6. Components equivalent to those in the first embodiment are assigned the same reference numerals and will not be described further.

[0049] That is, a camera that is generally provided on a smartphone 6 constitutes the camera 3 of the first embodiment, a touch panel of the smartphone 6 constitutes the input unit 41 and display unit 42 of the first embodiment, and a communication interface of the smartphone 6 constitutes the communication unit 43 of the first embodiment. Also, the above-described outdoor light database 441, outdoor light monitoring learning model 442, and outdoor light monitoring performance database 443 are stored in the memory of the smartphone 6. Furthermore, by installing the monitoring task 45 and learning task 46 of the first embodiment in the smartphone 6, the smartphone 6 constitutes the camera 3 and monitoring server 4 of the first embodiment.

[0050] Such a smartphone 6 is attached approximately horizontally to the bottom of the drone 2 by a band 21. The camera of the smartphone 6 is also able to capture images of the front side through a lens 22 provided on the bottom of the drone 2. That is, light is refracted by the mirror and prism within the lens 22, so that the camera can capture images of the front side of the drone 2 even when the smartphone 6 is lying on its side.

[0051] Then, when the drone 2 equipped with the smartphone 6 starts automatic flight, the smartphone 6 sequentially photographs each street light L while flying along the flight route. The smartphone 6 then determines whether there is an abnormality in the lighting state of the street light L based on the photographed images, and if it determines that there is an abnormality, the smartphone 6 reports it to the reporting destination 5.

[0052] According to this embodiment, since the photographing means and monitoring means are provided in the smartphone 6, it is possible to easily and inexpensively construct this street light monitoring system. In other words, it is only necessary to provide the photographing means and monitoring means in the smartphone 6 and mount them on the drone 2, and it is possible to easily construct this street light monitoring system without the need for a monitoring server 4. Moreover, since the smartphone 6 and the like generally come standard with a photographing means, i.e., a camera, it is only necessary to install a monitoring task 45 (application) on the smartphone 6 and the like. It goes without saying that a mobile communication terminal other than the smartphone 6 may also be used.

[0053] Although the embodiments of the present invention have been described in detail above, the specific configuration is not limited to these embodiments, and design changes within the scope of the present invention are also included within the scope of the present invention. For example, while the above embodiments describe a case in which the drone 2 automatically flies a predetermined flight route, the drone 2 may also be flown by a human operating a controller. In this case, video may be continuously captured by the camera 3, or the drone 2 may capture video at a time and position determined by a human operating the controller, or the drone 2 may automatically capture video at a predetermined position. Furthermore, although a notification is sent to the notification destination 5 only when an abnormality is determined in a street light L, the determination results for all street lights L photographed and monitored may also be reported or notified, regardless of whether an abnormality is present.

[0054] On the other hand, the above-described monitoring server 4 may be configured by installing the following street light monitoring program on a general-purpose computer. That is, the computer is made to function as monitoring means (monitoring task 45) that determines whether or not there is an abnormality in the lighting state of the street light L based on an image of the street light L taken by a camera 3 mounted on a flying drone 2, and reports the abnormality to a pre-stored reporting destination 5 if it determines that there is an abnormality. The monitoring means uses a street light monitoring learning model 442 that has been machine-learned based on past performance data so that, when an image of the street light L is input, whether or not there is an abnormality in the lighting state of the street light L is output. [Explanation of symbols]

[0055] 1. Outdoor lighting monitoring system 2. Drone 3. Camera (photography means) 4 Monitoring server (monitoring method) 441 Outdoor light database (street light information storage means) 442 Learning Model for Outdoor Light Monitoring 443 Outdoor Light Monitoring Performance Database 45 Monitoring Tasks (Monitoring Methods) 46 Learning Tasks 5. Where to report 6. Smartphones (mobile communication devices) L Outdoor Light P utility pole

Claims

1. A photographing means mounted on a drone flying along a flight route; a monitoring means for determining whether or not there is an abnormality in the lighting state of the outdoor light based on the image of the outdoor light photographed by the photographing means, and for reporting the abnormality to a pre-stored reporting destination when it is determined that there is an abnormality; The flight route is set so that as many street lights as possible can be photographed efficiently and without omission in a given time. The monitoring means stores the identification information, installation location, type, model, and reporting destinations including neighborhood associations and town associations for each outdoor light, and determines the identification information of the outdoor light determined to have an abnormality based on the location information when the outdoor light is photographed by the photographing means, and reports the identification information and the type and model to the reporting destinations corresponding to the determined identification information. An outdoor light monitoring system.

2. The monitoring means uses the general lighting state of the outdoor light under normal conditions as a standard, and determines that an abnormality has occurred if the outdoor light is dimly lit, flickers, or is not lit at all, whereas if the outdoor light is normally lit stably at a predetermined brightness and size, it is determined to be abnormal.

2. The outdoor light monitoring system according to claim 1.

3. The photographing means and the monitoring means are provided in a mobile communication terminal.

3. The outdoor light monitoring system according to claim 1 or 2.

4. The drone automatically flies a predetermined route.

4. The outdoor light monitoring system according to claim 1, wherein the outdoor light monitoring system is a monitoring system for monitoring an outdoor light.

5. the monitoring means uses a learning model for monitoring outdoor lights that has been machine-learned based on past performance data so that, when an image of the outdoor light is input, whether or not there is an abnormality in the lighting state of the outdoor light is output.

5. The outdoor light monitoring system according to claim 1, wherein the outdoor light monitoring system is a monitoring system for monitoring an outdoor light.

6. Computer, A monitoring means for determining whether or not there is an abnormality in the lighting state of the outdoor light based on an image of the outdoor light photographed by a photographing means mounted on the drone flying along the flight route, and for reporting the abnormality to a pre-stored reporting destination when it is determined that there is an abnormality; An outdoor light monitoring program for causing the outdoor light monitoring program to function as The flight route is set so that as many street lights as possible can be photographed efficiently and without omission in a given time. The monitoring means stores the identification information, installation location, type, model, and reporting destinations including neighborhood associations and town associations for each outdoor light, and determines the identification information of the outdoor light determined to have an abnormality based on the location information when the outdoor light is photographed by the photographing means, and reports the identification information and the type and model to the reporting destinations corresponding to the determined identification information. An outdoor light monitoring program.

7. the monitoring means uses a learning model for monitoring outdoor lights that has been machine-learned based on past performance data so that, when an image of the outdoor light is input, whether or not there is an abnormality in the lighting state of the outdoor light is output.

7. The outdoor light monitoring program according to claim 6.

Images