JP2023041994A - Outdoor lamp monitoring system and outdoor lamp monitoring program - Google Patents

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

The present invention relates to an outdoor light monitoring system and an outdoor light monitoring program for monitoring lighting states of outdoor lights.

For example, street lights (outside lights) installed on utility poles are usually managed and operated by the local residents' association, etc., and are replaced by the residents' association, etc. when they become unlit due to aging or the like. However, if a resident or a nearby worker who discovers that the lamp is not lit does not have a contact address, there is a risk that the lamp will be left unlit for a long period of time.

On the other hand, there is known a lighting fixture failure detection system that can detect failures of lighting fixtures such as street lights easily and inexpensively using existing devices and facilities (see, for example, Patent Document 1). .). This system consists of a smart meter that measures the amount of electricity used by lighting fixtures and transmits the data at predetermined time intervals, and a predetermined data calculated using the amount of electricity used from the smart meter that is compared with a threshold to and a failure detection device that detects a failure.

JP 2020-77584 A

By the way, many outdoor lights are installed over a wide area. will not be contacted. On the other hand, the system described in Patent Document 1 is effective for lighting fixtures with smart meters installed, but cannot be applied to lighting fixtures without smart meters installed.

SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide an outdoor light monitoring system and an outdoor light monitoring program that enable proper and reliable monitoring of the lighting state of an outdoor light and appropriate notification when an abnormality is detected. .

In order to solve the above-mentioned problems, the invention of claim 1 provides a photographing means mounted on a flying drone, and an image of the outdoor light photographed by the photographing means. and monitoring means for determining whether or not there is an abnormality, and reporting to a pre-stored destination when it is determined that there is an abnormality.

According to a second aspect of the invention, in the outdoor light monitoring system according to the first aspect, the monitoring means stores identification information and an installation position for each outdoor light, and based on the position information when the outdoor light is photographed by the photographing means. and determining the identification information of the outdoor lamp judged to have the abnormality, and notifying the notification destination of the identification information.

According to a third aspect of the invention, there is provided an outdoor light monitoring system according to the second aspect, wherein the monitoring means stores a report destination corresponding to the identification information of the outdoor light, and reports to the report destination according to the determined identification information. characterized in that

According to a fourth aspect of the present invention, in the outdoor light monitoring system according to the first to third aspects, the photographing means and the monitoring means are provided in a portable communication terminal.

The invention according to claim 5 is characterized in that, in the outdoor light monitoring system according to claims 1 to 4, the drone automatically flies along a predetermined route.

According to a sixth aspect of the present invention, in the outdoor light monitoring system according to any one of claims 1 to 5, when the image of the outdoor lamp is input, the monitoring means outputs whether or not there is an abnormality in the lighting state of the outdoor lamp. It is characterized by using a learning model for outdoor light monitoring that is machine-learned based on past performance data.

According to the seventh aspect of the invention, the computer determines whether or not there is an abnormality in the lighting state of the outdoor light based on an image of the outdoor light captured by a photographing means mounted on a flying drone. The outdoor light monitoring program is characterized by functioning as monitoring means for reporting to a pre-stored reporting destination when determined.

According to an eighth aspect of the invention, there is provided an outdoor light monitoring program according to the seventh aspect, wherein when the image of the outdoor lamp is input, the monitoring means outputs whether or not there is an abnormality in the lighting state of the outdoor lamp. Secondly, it is characterized by using a learning model for outdoor light monitoring that is machine-learned based on past performance data.

According to the inventions of claims 1 and 7, when the drone flies and the outdoor light is photographed by the photographing means, whether or not there is an abnormality in the lighting state of the outdoor light is automatically determined based on the image. If it is determined that there is an abnormality, the information is automatically notified to a pre-stored notification destination. In other words, the presence or absence of abnormalities in the outdoor lights is automatically determined based on the images taken by the drone, without the need for visual inspection by humans. Also, it is possible to properly and reliably monitor the lighting state of the outdoor lamp. In addition, when it is determined that there is an abnormality, it is automatically notified to the destination, so that it is possible to properly and reliably notify that the abnormality has been discovered. As a result, it becomes possible to properly manage the outdoor lights and ensure the safety of the area.

According to the invention of claim 2, since the identification information of the outdoor light determined to be abnormal is notified to the reporting destination, the outdoor light determined to be abnormal can be specified properly and quickly at the reporting destination. It is possible to respond appropriately and quickly to outdoor lights.

According to the third aspect of the present invention, a report is sent to an appropriate report destination according to the identification information of the outdoor light determined to be abnormal. In other words, if the report destination and administrator are different depending on the outdoor light, the report is sent to the appropriate report destination that manages the outdoor light determined to be abnormal, so that the outdoor light can be dealt with appropriately and promptly. It becomes possible.

According to the fourth aspect of the invention, since the photographing means and the monitoring means are provided in the portable communication terminal, it is possible to construct the outdoor light monitoring system easily and at low cost. In other words, it is possible to construct a main outdoor light monitoring system simply by providing a photographing means and a monitoring means in a mobile communication terminal such as a smartphone (multifunctional mobile terminal) and mounting it on a drone. Moreover, since a smartphone or the like is generally equipped with a photographing means, that is, a camera, it is sufficient to simply provide the smartphone with a monitoring means.

According to the fifth aspect of the invention, since the drone automatically flies along a predetermined route, it is possible not only to reduce labor and costs due to human operation, but also to set the predetermined route appropriately, thereby reducing the number of drones. Therefore, it is possible to reliably and properly photograph the outdoor lights. As a result, it becomes possible to monitor many outdoor lights more reliably and appropriately.

According to the sixth and eighth aspects of the present invention, whether or not there is an abnormality in the lighting state of the outdoor light is output using the machine-learned outdoor light monitoring learning model. can be determined. As a result, it becomes possible to monitor the lighting state of the outdoor lamp more appropriately and reliably.

1 is a schematic configuration diagram showing an outdoor light monitoring system according to Embodiment 1 of the present invention; FIG. It is the front view (a) and top view (b) which show the drone of the outdoor light monitoring system of FIG. 2 is a schematic configuration block diagram showing a monitoring server of the outdoor light monitoring system of FIG. 1; FIG. FIG. 2 is a plan view showing an example of a flight route of a drone in the outdoor light monitoring system of FIG. 1; 4 is a data configuration diagram of an outdoor light database of the monitoring server of FIG. 3; FIG. FIG. 2 is a diagram showing a healthy lighting state of an outdoor light photographed by a camera of the outdoor light monitoring system of FIG. 1; 2 is a diagram showing a lighting state of a deteriorated outdoor light photographed by a camera of the outdoor light monitoring system of FIG. 1; FIG. FIG. 4 is a functional block diagram showing a schematic configuration of an outdoor light monitoring learning model of the monitoring server of FIG. 3 ; It is a side view which shows the drone and smart phone in the outdoor light monitoring system which concerns on Embodiment 2 of this invention.

BEST MODE FOR CARRYING OUT THE INVENTION The present invention will be described below based on the illustrated embodiments.

(Embodiment 1)
FIG. 1 is a schematic configuration diagram showing 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 an outdoor light (street light) L, and mainly includes a drone 2, a camera (photographing means) 3, and a monitoring server (monitoring means) 4. , the drone 2 and the monitoring server 4 are communicatively connected to each other. Here, in this embodiment, the case where the outdoor light L is installed on the utility pole P will be described, but the outdoor light may be installed on a structure other than the utility pole P or may be installed independently. . In addition, many outdoor lights L installed over a wide area are monitored, and these outdoor lights L are managed and operated by a plurality of neighborhood associations, residents' associations, and the like.

The drone 2 is a flying unmanned aerial vehicle, and in this embodiment, automatically flies along a predetermined flight route/course. That is, it is equipped with a GPS (Global Positioning System), for example, for a flight route set by a monitoring server 4 described later and stored in the drone 2, autonomous control along the flight route while checking its own position with GPS to fly. At this time, an obstacle avoidance function may be provided according to the flight environment or the like. 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 to simultaneously fly different flight routes.

The camera 3 is a photographing device for photographing the outdoor lamp L, etc., and photographs at least the lighting state of the outdoor lamp L, and as shown in FIG. This camera 3 is controlled by the drone 2, and in this embodiment, when the drone 2 flies and hovers to a predetermined hovering position on the flight route, that is, the shooting position of the outdoor light L, the outdoor light L is automatically photographed. . Then, every time the outdoor light L is photographed, photographing information including the photographed image, the position information (latitude and longitude) at the time of photographing, and the identification information of the drone 2 is transmitted from the drone 2 to the monitoring server 4. there is Thus, as will be described later, the monitoring server 4 can know which outdoor lamp L is captured in which image.

On the other hand, while the flight position of the drone 2 is always memorized over time, the camera 3 constantly captures the outdoor lights L and the like, and the flight position of the drone 2 at each time and the captured animation/video are transmitted to the monitoring server 4. . Then, by comparing the flight position of the drone 2 with the image at the same time in the monitoring server 4, it may be possible to know which outdoor light L is being photographed.

The monitoring server 4 is a server/computer for judging the quality of each outdoor light L based on the image of each outdoor light L photographed by the camera 3 and for monitoring. As shown in FIG. 3, the monitoring server 4 mainly includes an input unit 41, a display unit 42, a communication unit 43, a storage unit 44, a monitoring task (monitoring means) 45, a learning task 46, and these and a central processing unit 47 that controls the .

The input unit 41 is an interface for inputting various types of information and commands, and specifically inputs the flight route of the drone 2 and the like. That is, a flight route is input by designating a route for the drone 2 to fly on a map that stores the positions (latitude and longitude) of each outdoor light L and buildings, the position and width of roads, and the like. For example, as shown by the arrows in FIG. 4, a flight route is input while photographing each outdoor light L. At this time, the flight route is set so that more outdoor lights L can be photographed reliably and efficiently without omission in a predetermined time. In this flight route, the latitude, longitude, traveling direction, traveling distance, hovering position, shooting position, etc. of each point on the flight route are stored. A plurality of such flight routes can be set and stored, and by transmitting and storing different flight routes to the drone 2 according to the flight date and time, the drone 2, etc., the drone 2 can be flown on a desired flight route. can be done.

The display unit 42 is a display for displaying various data, information, etc. Specifically, it displays the above-described map, flight route, determination results described later, and the like. The communication unit 43 is an interface for communicating with the outside via an Internet network, a telephone communication network, or the like, and communicates with each drone 2, each reporting destination 5, and the like.

The storage unit 44 mainly includes an outdoor light database (outdoor light information storage means) 441 , an outdoor light monitoring learning model 442 , and an outdoor light monitoring performance database 443 . Here, the exterior light database 441 will be described, and the exterior light monitoring learning model 442 and the exterior light monitoring result database 443 will be described later.

The outdoor lamp database 441 is a database that stores information about each outdoor lamp L, and as shown in FIG. remembered.

The outdoor lamp ID 441a stores identification information of the outdoor lamp L, specifically, the outdoor lamp number, the name of the community association that manages and operates the outdoor lamp L, and the like. The type 441b stores the type and model of the outdoor light L, and the installation position 441c stores information on the location where the outdoor light L is installed (latitude, longitude, etc.). In the report destination 441d, the report destination 5 to be notified when there is an abnormality in the outdoor light L, for example, the e-mail address or telephone number of the residents' association or the neighborhood association, the representative thereof, or the inspection and replacement of the outdoor light L. Company contact information and the like are stored. The standard lifespan 441e stores the standard lifespan of the outdoor light L of the same type and model as the outdoor light L, and the image 441f contains images of the outdoor light L photographed in a normal state at the beginning of monitoring and when the product is new, Images taken after that, determination results to be described later, and the like are stored in chronological order. In addition, the date of installation, the date of replacement of the outdoor light L, and the like are stored in the other 441g.

The monitoring task 45 determines whether or not there is an abnormality in the lighting state (brightness state) of the outdoor light L based on the image of the outdoor light L captured by the camera 3, and if it is determined that there is an abnormality, the communication unit It is a program task for reporting to a preset/stored reporting destination 5 via 43 . The monitoring task 45 is activated when imaging information is received from the drone 2, or when an activation command is input with an image and position information at the time of imaging specified by the input unit 41, or the like.

First, based on the image taken by the camera 3, it is determined whether or not the outdoor light L to be photographed has an abnormality based on the image in the normal state. That is, based on the image of the outdoor lamp L stored in the outdoor lamp database 441 when it is in a normal state and the image to be determined that is currently photographed, it is determined whether the lighting condition of the outdoor lamp L is normal compared to the normal state. Image analysis is performed to determine whether. Alternatively, it is determined by image analysis whether the lighting state of the outdoor light L is abnormal based on the normal lighting state of the outdoor light L (such as stable lighting with a predetermined brightness). . For example, as shown in FIG. 6, if it is normal, it is lit stably with a predetermined brightness and magnitude, but as shown in FIG. If it is lit or if it is not lit at all, it is judged to be abnormal. In this way, since the presence or absence of an abnormality is determined based on the lighting state (brightness, size, stability, etc.) of the outdoor light L, the appearance of the outdoor light L does not necessarily have to be clear in the image. In other words, the image captured by the camera 3 should only show the lighting state of the outdoor lamp L clearly.

The standard life stored in the standard life 441e may be used as a reference when determining the presence or absence of an abnormality in this way. For example, when the standard life has passed and the outdoor light L is lit with a predetermined brightness but is occasionally turned off, it may be determined as abnormal.

Here, as described above, based on the position information at the time of shooting included in the shooting information and the installation position 441c of the outdoor light database 441, the outdoor lamp L that has been photographed, that is, the outdoor lamp ID 441a is identified, and from the image 441f of this outdoor lamp ID 441a, Acquire normal images. Alternatively, the image 441f of the outdoor light database 441 may be searched for an image equivalent to the image to be determined (such as the background except for the lighting state) included in the photographing information, and the photographed outdoor light L, that is, the outdoor light ID 441a may be specified.

Next, when it is determined that there is an abnormality, the identification information of the outdoor lamp L is determined. That is, the identification information of the outdoor lamp L is acquired by specifying the outdoor lamp ID 441a as described above. Then, in the notification destination 5 stored in the notification destination 441d of this outdoor lamp ID 441a, the identification information of this outdoor lamp L, the fact that it is abnormal, the image determined as abnormal, the type stored in the type 441b, and the abnormal information/judgment including the model Send and report the results. In this way, by including the type and model of the outdoor light L in the abnormality information, the reporting destination 5 can easily and quickly prepare the outdoor light L for replacement.

Such a monitoring task 45 performs outdoor lamp monitoring through machine learning based on past performance data so that when an image of the outdoor lamp L is input, whether or not there is an abnormality in the lighting state of the outdoor lamp L is output. A learning model 442 is used. This outdoor light monitoring learning model 442 is created by the learning task 46 .

That is, the learning task 46 uses past performance data recorded and accumulated in the outdoor light monitoring performance database 443 to create the outdoor light monitoring learning model 442 by a known machine learning algorithm such as a neural network. In this outdoor light monitoring result database 443, an expert/experienced person (executive of a community association, etc.) in outdoor light management determines whether or not an abnormality has occurred in the outdoor light L, based on a photographed image of the outdoor light L as input information. It is a database that records and accumulates performance data including judgment results. Past performance data includes data created based on actual images and actual judgment results by experts and experienced people in outdoor lighting management, as well as data created during pre-training.

As shown in FIG. 8, this learning task 46 uses machine learning and deep learning using a neural network, and based on the performance data recorded in the outdoor light monitoring performance database 443, for example, the outdoor light L is photographed. A neural network is created with an image as an input layer, an abnormality determination result 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 outdoor light monitoring learning model 442 as learning data to learn various parameters in the intermediate layer. That is, the learning task 46 learns various parameters in the intermediate layer so that the presence/absence of an abnormality is appropriately determined and output based on the image of the outdoor light L that has been photographed.

As described above, according to the outdoor light monitoring system 1, when a flight route is set and input to the drone 2 and the drone 2 is automatically flown, the drone 2 flies along the flight route and hovers at predetermined positions sequentially. Then, the outdoor light L is photographed by the camera 3 . Photographing information including the photographed image, the position information at the time of photographing, and the identification information of the drone 2 is sequentially transmitted from the drone 2 to the monitoring server 4 .

In response to this, the monitoring server 4 automatically determines whether or not there is an abnormality in the lighting state of the outdoor lamp L based on the image, and if it is determined that there is an abnormality, it is sent to the pre-stored notification destination 5. automatically notified. That is, the presence or absence of an abnormality in the outdoor lights L is automatically determined based on the images captured by the drone 2 in flight without relying on visual inspection by a person. Even so, the lighting state of the outdoor lamp L can be properly and reliably monitored. In addition, when it is determined that there is an abnormality, it is automatically notified to the notification destination 5, so that it is possible to properly and reliably notify that the abnormality has been found.

In addition, since the identification information of the outdoor light L determined to be abnormal is notified to the reporting destination 5, the outdoor light L determined to be abnormal can be specified appropriately and quickly at the reporting destination 5, and the outdoor light L It is possible to respond appropriately and quickly.

In addition, the notification is sent to the proper notification destination 5 according to the identification information of the outdoor lamp L determined to be abnormal. That is, when the notification destination 5, the administrator, etc. are different depending on the outdoor light L, the proper notification destination 5 that manages the outdoor light L determined to be abnormal is notified. It is possible to respond quickly.

In addition, since the drone 2 automatically flies along a predetermined route/flight route, it is possible not only to reduce the labor and cost required for human operation, but also to ensure that many outdoor lights L are provided by appropriately setting the predetermined route. And it becomes possible to shoot properly. As a result, it becomes possible to monitor many outdoor lights L more reliably and appropriately.

Furthermore, since whether or not there is an abnormality in the lighting state of the outdoor lamp L is output using the machine-learned outdoor lamp monitoring learning model 442, it is possible to determine the presence or absence of an abnormality more appropriately. As a result, it becomes possible to monitor the lighting state of the outdoor lamp L more appropriately and reliably.

As described above, it is possible to appropriately and quickly manage the outdoor lights L to ensure the safety of the area.

(Embodiment 2)
FIG. 9 is a side view showing the drone 2 and the smartphone (mobile communication terminal) 6 in the outdoor light monitoring system according to this embodiment. In this embodiment, the configuration differs from that of the first embodiment in that the photographing means and the monitoring means are provided in the smartphone 6, and the same components as in the first embodiment are denoted by the same reference numerals. omitted.

That is, the camera generally provided in the smartphone 6 constitutes the camera 3 of Embodiment 1, the touch panel of the smartphone 6 constitutes the input unit 41 and the display unit 42 of Embodiment 1, and the communication interface of the smartphone 6 configures the communication unit 43 of the first embodiment. The outdoor light database 441 , the outdoor light monitoring learning model 442 , and the outdoor light monitoring result database 443 as described above are stored in the memory of the smartphone 6 . Furthermore, since the monitoring task 45 and the learning task 46 of the first embodiment are installed on the smartphone 6, the smartphone 6 constitutes the camera 3 and the monitoring server 4 of the first embodiment.

Such a smartphone 6 is attached substantially horizontally to the bottom of the drone 2 with a band 21 . In addition, the camera of the smartphone 6 can photograph the front side through the lens 22 provided on the bottom of the drone 2 . That is, light is refracted by the mirrors and prisms in the lens 22 so that the camera can photograph the front side of the drone 2 even when the smartphone 6 is lying on its side.

Then, when the drone 2 equipped with the smartphone 6 starts automatic flight, each outdoor light L is sequentially photographed by the smartphone 6 while flying along the flight route. Then, based on the photographed image, the smartphone 6 determines whether or not there is an abnormality in the lighting state of the outdoor light L, and when it is determined that there is an abnormality, the smartphone 6 notifies the reporting destination 5.例文帳に追加

According to such an embodiment, since the smartphone 6 is provided with the photographing means and the monitoring means, it is possible to construct the outdoor lamp monitoring system easily and at low cost. That is, it is only necessary to provide the photographing means and the monitoring means in the smartphone 6 and mount them on the drone 2, and the monitoring server 4 is not required, making it possible to easily construct the main outdoor light monitoring system. Moreover, since the smartphone 6 or the like is generally equipped with a photographing means, that is, a camera or the like, it is sufficient to simply install the monitoring task 45 (application) or the like on the smartphone 6 or the like. Of course, a mobile communication terminal other than the smart phone 6 may be used.

Although the embodiment of the present invention has been described in detail above, the specific configuration is not limited to this embodiment. Included in the invention. For example, in the above embodiment, the case where the drone 2 automatically flies along a predetermined flight route has been described, but the drone 2 may be flown by manipulating the controller. In this case, the camera 3 may constantly shoot a moving image, shoot at a time and position operated by a person using a controller, or the drone 2 may automatically shoot at a predetermined position. In addition, only when the outdoor light L is determined to be abnormal, the notification destination 5 is notified. can be

On the other hand, the monitoring server 4 as described above may be configured by installing the following outdoor light monitoring program in a general-purpose computer. That is, when the computer determines whether or not there is an abnormality in the lighting state of the outdoor light L based on the image of the outdoor light L photographed by the camera 3 mounted on the flying drone 2, and determines that there is an abnormality function as a monitoring means (monitoring task 45) for reporting to the notification destination 5 pre-stored in , and when the image of the outdoor light L is input, the monitoring means outputs whether or not there is an abnormality in the lighting state of the outdoor light L. As described above, a learning model 442 for monitoring outdoor lamps, which is machine-learned based on past performance data, is used.

1 outdoor light monitoring system 2 drone 3 camera (shooting means)
4 Monitoring server (monitoring means)
441 outdoor light database (outdoor light information storage means)
442 Learning model for outdoor light monitoring 443 Actual database for outdoor light monitoring 45 Monitoring task (monitoring means)
46 learning task 5 destination 6 smartphone (mobile communication terminal)
L Outside light P Telephone pole

Claims (8)

A shooting means mounted on a flying drone,
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 notifying a pre-stored reporting destination when it is determined that there is an abnormality. and,
An outdoor light monitoring system comprising: The monitoring means stores identification information and an installation position for each outdoor lamp, and based on the position information when the outdoor lamp is photographed by the imaging means, determines the identification information of the outdoor lamp determined to be abnormal, and identifies the outdoor lamp. reporting the information to said contact;
The outdoor light monitoring system according to claim 1, characterized in that: The monitoring means stores a report destination corresponding to the identification information of the outdoor light, and reports to the report destination according to the determined identification information.
The outdoor light monitoring system according to claim 2, characterized in that: The photographing means and the monitoring means are provided in a mobile communication terminal,
The outdoor light monitoring system according to any one of claims 1 to 3, characterized in that: The drone automatically flies along a predetermined route,
The outdoor light monitoring system according to any one of claims 1 to 4, characterized in that: The monitoring means has a learning model for monitoring outdoor lights that is machine-learned based on past performance data so that when an image of the outdoor lights is input, whether or not there is an abnormality in the lighting state of the outdoor lights is output. using
The outdoor light monitoring system according to any one of claims 1 to 5, characterized in that: the computer,
Based on the image of the outdoor light captured by the imaging means mounted on the flying drone, it is determined whether or not there is an abnormality in the lighting state of the outdoor light, and if it is determined that there is an abnormality, a pre-stored notification destination monitoring means reporting to
An outdoor light monitoring program characterized by functioning as a The monitoring means has a learning model for monitoring outdoor lights that is machine-learned based on past performance data so that when an image of the outdoor lights is input, whether or not there is an abnormality in the lighting state of the outdoor lights is output. using
The outdoor light monitoring program according to claim 7, characterized in that:

Images