Bird damage control support device and bird damage control support method

Abstract

To support a rapid specification of the content of measures to take to cope with bird damages for a power facility.SOLUTION: A bird damage coping support device 1 includes: an image acquisition unit 11 having a processor and a memory, the image acquisition unit acquiring an image including a power facility and information of a region in the image suffering from bird damages in the image; a measures determination unit 17 for outputting information of the range of attaching a bird damage coping tool in the power facility in the acquired image by inputting the acquired image including the power facility and information of the region in the image suffering from bird damages into a learned model in which an image including a region that can suffer from bird damages and a power facility around the region is input and information of the range of a power facility to which a bird damage coping tool is to be equipped for coping with bird damages is output.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a bird damage countermeasure support device and a bird damage countermeasure support method. [Background technology]

[0002] Electric power companies receive reports from residents about bird damage, such as bird droppings, caused by birds flying onto power lines, and depending on the report, they install countermeasures (bird pest prevention devices) to prevent birds from flying onto power lines.

[0003] Various types of bird pest control devices have been developed. For example, Patent Document 1 discloses a bird and animal repellent device that includes a discharger that has a plurality of thin conductive material pieces arranged thereon and that can discharge in all directions or in a fixed direction, and a discharge control means that discharges the discharger at regular or irregular timing, and that stimulates birds and animals that have a sense of electrical charge, including crows, by discharging the discharger. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-92629 Summary of the Invention [Problem to be solved by the invention]

[0005] Electric power companies interview residents about the bird damage they are experiencing in order to determine the scope and type of bird prevention equipment to be installed. However, residents who are not bird experts may find it difficult to accurately communicate the details of the bird damage they are experiencing. If there is a misunderstanding between the two parties on this point and the electric power company continues its countermeasure work, the construction work will have to be redone midway, which will result in burdens for both the electric power company and the residents.

[0006] The present invention has been made in consideration of this current situation, and its purpose is to provide a bird damage control support device and a bird damage control support method that can assist in quickly identifying the bird damage control measures that should be taken for power equipment. [Means for solving the problem]

[0007] One aspect of the present invention for achieving the above-mentioned object is a bird damage control support device that includes an image acquisition unit having a processor and memory, and that acquires information about an image including power equipment and areas in the image that are affected by bird damage; and a countermeasure determination unit that inputs the acquired image including power equipment and information about areas in the image that are affected by bird damage into a trained model that receives input of an image including areas that may be affected by bird damage and power equipment around those areas, and outputs information about the range of the power equipment where bird damage control devices should be installed to prevent the bird damage, and outputs information about the range of the power equipment in the acquired image where bird damage control devices should be installed.

[0008] In this way, the bird damage control support device of the present invention acquires site images and information on bird-damaged areas, and inputs these into a trained model (bird damage control determination model) that receives images of the bird-damaged area and the surrounding power equipment and outputs information on the installation range of bird damage control devices on the power equipment, thereby outputting information on the installation range of bird damage control devices on the power equipment in the site image.This allows users such as residents suffering from bird damage or workers in charge of bird damage control to know the range of bird damage prevention devices that should be installed on the power equipment (e.g., power lines) at that site simply by preparing an image of the site suffering from bird damage.In other words, the bird damage control support device of the present invention can support the rapid identification of bird damage control measures that should be taken for power equipment.

[0009] Furthermore, one aspect of the present invention for achieving the above-mentioned object is a bird damage control support device that includes a type acquisition unit that acquires information on the type of bird damage prevention equipment, and the trained model is a model into which an image including the area that may be affected by bird damage and power equipment around that area, and information on the type of bird damage prevention equipment that can be used against the bird damage are input, and the countermeasure determination unit inputs the acquired image including the power equipment and information on the area that is affected by bird damage in the image, and the acquired information on the type of bird damage prevention equipment into the trained model, and outputs information on the range in which bird damage control equipment should be installed on the power equipment in the acquired image.

[0010] In this way, the bird pest control support device of the present invention acquires information on the types of bird pest control equipment, and then inputs the site image and the above-mentioned types of information into a trained model (bird pest control judgment model) that uses information on the types of bird pest control equipment that can be used against bird pests as input values, thereby outputting information on the range in which bird pest control devices should be installed in the power equipment in the site image, so that users such as residents who are suffering from bird pest damage or workers in charge of bird pest control can know the installation range of bird pest control equipment that is suitable for each type of bird pest control equipment.

[0011] In addition, one aspect of the present invention for achieving the above-mentioned object is a bird pest control support device that includes an information display unit that displays on a screen information on the range in which the bird pest control device is to be installed, output by the trained model, superimposed on the acquired image.

[0012] In this way, the bird pest control support device according to the present invention displays information on the range in which bird pest control devices should be installed, which is output by the trained model (bird pest control determination model), superimposed on the site image, allowing users such as residents affected by bird pests or workers in charge of bird pest control measures to easily check the range in which bird pest control devices should be installed at the site.

[0013] Furthermore, one aspect of the present invention for achieving the aforementioned object is a bird damage control support device, wherein the trained model is a model that outputs information on the range in which the bird damage control devices are to be installed and information on the accuracy of that range, and the countermeasure determination unit inputs the acquired image including the power equipment and information on the area in the image that is suffering from bird damage into the trained model, and outputs one or more pieces of information on the range in which the bird damage control devices are to be installed and information on the accuracy of that range for the power equipment in the acquired image.

[0014] In this way, the bird damage control support device according to the present invention outputs one or more pieces of information about the range and accuracy of installing bird damage control devices in electric power facilities in the site image by inputting a site image and a bird damage area into a trained model that outputs information about the range for installing bird damage control devices and information about the accuracy of that range. This allows users such as residents suffering from bird damage or workers in charge of bird damage control to prioritize and implement multiple bird damage countermeasures.

[0015] Furthermore, one aspect of the present invention for achieving the above-mentioned object is a bird damage control support device, in which the control determination unit inputs the acquired image into a first trained model, which receives an image including an area that may be damaged by birds and power equipment around that area and outputs information about the area of ​​the power equipment in the image, and outputs information about the area of ​​the power equipment in the acquired image; and inputs information about the area of ​​the power equipment and an image including an area that may be damaged by birds into a second trained model, which receives an image including an area that may be damaged by birds and outputs information about the range of the power equipment where bird damage control devices are to be installed to prevent the bird damage, and outputs information about the range of the power equipment in the acquired image where bird damage control devices are to be installed.

[0016] In this way, the bird damage control support device according to the present invention uses a trained model (bird damage control determination model) consisting of a first trained model and a second trained model to output information on the range in which bird damage control devices should be installed. That is, the bird damage control support device inputs an image of a bird-damaged area and its surrounding power equipment into the first trained model, which outputs information on the area of ​​the power equipment in the image, thereby outputting information on the area of ​​the power equipment in the site image. Next, the information on the area of ​​the power equipment and an image of the bird-damaged area are input into the second trained model, which outputs information on the area of ​​the power equipment in which bird damage control devices should be installed to prevent bird damage. By inputting the information on the area of ​​the power equipment output by the first trained model and the information on the bird-damaged area, the device outputs information on the range in which bird damage control devices should be installed on the power equipment in the site image. In this way, by using the second trained model with information on the area of ​​the power equipment accurately recognized by the first trained model as an input value, the range in which bird damage control devices should be installed can be accurately identified.

[0017] Furthermore, one aspect of the present invention for achieving the above-mentioned object is a bird damage control support method in which an information processing device executes an image acquisition process in which an image including power equipment and information about areas in the image that are affected by bird damage are acquired, and a bird damage control determination process in which an image including areas that may be affected by bird damage and power equipment around those areas is input into a trained model that outputs information about the range of the power equipment in which bird damage control devices should be installed to prevent bird damage, by inputting the acquired image including power equipment and information about the areas in the image that are affected by bird damage into a trained model that outputs information about the range of the power equipment in which bird damage control devices should be installed to prevent bird damage. [Effects of the Invention]

[0018] According to the present invention, it is possible to assist in quickly identifying the details of bird damage countermeasures that should be taken for electric power facilities. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 10 is a diagram illustrating an example of a performance image. [Figure 2] FIG. 10 is a diagram illustrating another example of the performance image. [Figure 3] FIG. 2 is a diagram illustrating an example of functions provided in the bird damage countermeasure support device. [Figure 4] FIG. 10 is a diagram illustrating an example of a teacher data DB. [Figure 5] FIG. 2 is a diagram illustrating an example of hardware of a bird damage control support device. [Figure 6] FIG. 10 is a flow diagram illustrating an example of a model learning process. [Figure 7] FIG. 10 is a flow diagram illustrating an example of bird damage countermeasure determination processing. [Figure 8] FIG. 10 is a diagram showing an example of a bird damage countermeasure proposal screen. [Figure 9] FIG. 10 is a diagram showing another example of the bird damage countermeasure proposal screen. DETAILED DESCRIPTION OF THE INVENTION

[0020] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A bird damage prevention support device according to an embodiment of the present invention will be described below with reference to the drawings.

[0021] The bird damage control support device of this embodiment provides bird damage control measures that should be taken against the droppings, noise, or other bird damage (droppings in this embodiment) caused by birds such as crows and sparrows flying into power equipment such as electric wires, specifically information on the range of bird damage prevention devices that should be installed.

[0022] That is, the bird pest control support device creates a predetermined trained model (hereinafter referred to as a bird pest control determination model) by performing machine learning using as training data images (hereinafter referred to as actual images) of a site where a worker or the like has previously implemented bird pest control measures (for example, an area affected by bird damage, electric wires to which bird pest control devices have been attached as a countermeasure, and the area surrounding them).The bird pest control support device then inputs images (hereinafter referred to as site images) of a location where new bird damage has been reported into the bird pest control determination model, and displays on the screen information such as the range and type of bird pest control devices that should be attached at that location.

[0023] (Actual image) 1 is a diagram showing an example of an actual image. This actual image 50 is an image captured of an electric wire 53 installed by a utility pole 55, a bird-damaged area 57 (cars in this case) that is an area or range that is damaged by birds that fly onto the electric wire 53, and a bird-damage prevention device 51 (fishing line in this case) attached to a portion of the electric wire 53 as a measure against bird damage in the bird-damaged area 57. The bird-damaged area 57 may include, for example, a building such as a house, an automobile, a road, a site, or a person.

[0024] Here, the installation range of the bird damage prevention device 51 correlates with the position of the bird damage area 57. For example, the installation range of the bird damage prevention device 51 is the power equipment located above the bird damage area 57.

[0025] 2 is a diagram showing another example of an actual image 70. This actual image 70 is an image captured of a utility pole 75 on which an electric wire 73 is installed, a bird-damaged area (not shown, e.g., a road) that is an area or range that is damaged by birds that fly onto the electric wire 73, and a bird-damage prevention device 71 attached to a portion of the electric wire 73.

[0026] Bird pest prevention device 71 (here, a pincushion) is easier to install than bird pest prevention device 51 (fishing line) in FIG. 1, and is therefore more suitable for installation on a tall utility pole 75 (than utility pole 55 in FIG. 1).

[0027] In other words, the range of bird deterrents that can be attached to electric wires, etc. correlates with the type of bird deterrent. In the example shown in the figure, bird deterrent 71 is attached particularly high from the ground surface, so a pincushion or the like, which is easier to attach, is preferable to fishing line.

[0028] From the above, it is thought that the installation range (position) of bird pest control devices is correlated with the bird pest area, the location of power equipment such as electric wires around the bird pest area, and the type of bird pest control device. Therefore, the bird pest control support device of this embodiment uses such correlation to generate a bird pest control determination model.

[0029] The bird damage prevention support device will be described in detail below. --Bird damage prevention support device-- 3 is a diagram illustrating an example of functions of the bird damage control support device 1 according to this embodiment. The bird damage control support device 1 is an information processing device (computer) including an image acquisition unit 11, a type acquisition unit 12, a preprocessing unit 13, a learning unit 15, a countermeasure determination unit 17, and an information display unit 19.

[0030] The bird damage control support device 1 also includes a teacher data DB 200 that stores data on feature amounts and correct labels of actual images, and an image DB 300 that stores actual images and on-site images.

[0031] The image acquisition unit 11 acquires images (actual images and on-site images) by reading them from a recording medium or receiving them via a communication network.

[0032] The type acquiring unit 12 acquires information on the type of bird damage prevention equipment. For example, the type acquiring unit 12 receives input of information on the type of bird damage prevention equipment from a worker or the like in charge of bird damage prevention measures.

[0033] Based on the teacher data DB200, the learning unit 15 inputs an image (site image) including an area that may be subject to bird damage (bird damage area) and the power equipment around that area, and creates a trained model (bird damage control judgment model) that outputs information on the range of the power equipment where bird damage control devices should be installed (hereinafter referred to as the installation range) to prevent bird damage.

[0034] The trained model may be a model to which, in addition to the site image, information on the type of bird pest control equipment that can be used against bird pests is input. The bird pest control measure determination model of this embodiment is a model to which information on the type of bird pest control equipment is input.

[0035] The trained model of this embodiment is constructed by machine learning the features of site images using deep learning. In this embodiment, this trained model is a neural network that has an input layer to which pixel information of the image (pixel content and coordinates) and the type of bird pest control device are input, one or more intermediate layers (hidden layers) that extract and output image features from the pixel information, and an output layer that outputs information on the installation range based on the image features and the type of bird pest control device.

[0036] As the neural network in the trained model of this embodiment, for example, a convolution neural network (CNN), a support vector machine (SVM), a Bayesian network, or a regression tree can be applied, but this embodiment is based on CNN, which is a method suitable for image recognition.

[0037] The countermeasure determination unit 17 inputs information about bird-damaged areas and site images acquired by the image acquisition unit 11 into the bird-damage countermeasure determination model, and outputs information about the range in which bird-damage prevention devices should be installed in the power equipment in the site image.

[0038] The information display unit 19 displays on a screen information on the range in which bird damage control devices should be installed, which information is output by the bird damage control determination model in the countermeasure determination unit 17.

[0039] (Teacher data DB) 4 is a diagram showing an example of the training data DB 200. The training data DB 200 stores actual images and related information. The training data DB 200 has the following data items: a shooting date and time 201 for each image; image data 202, which is information about the data file recording each image; a bird damage area 203, in which information about the bird damage area in each image (information about the content and position of each pixel in the image) is set; a device type 204, in which information about the type of bird damage prevention device to be installed is set; a power equipment area 205, in which area information about the power equipment (such as electric wires) to which the bird damage prevention device is to be installed in each image (information about the content and position of each pixel in the image) is set; and an installation range 206, in which information about the installation range of the bird damage prevention device in the power equipment related to the power equipment area 205 (information about the range in the image) is set.

[0040] For example, information on the type of tool, such as a pincushion, net, fishing line, or pinwheel, may be set in the tool type 204, or information on the product model number may be set.

[0041] In the power equipment area 205, information on the range in the image of power equipment to which bird damage prevention devices are attached, such as electric wires, utility poles, transformers, and switches, is set.

[0042] The contents of these data items in the training data DB 200 are set by, for example, a worker involved in installing the bird pest prevention device while referring to the actual image. Note that the photographing date and time 201 may be extracted from the metadata of the actual image, or may be set by the worker who photographed the actual image.

[0043] 4 are merely examples. In addition to these data items, information that affects the installation range of bird pest control devices (for example, information about surrounding buildings, area or location information, and the type and location of each device installed on a utility pole) may also be set as a feature of the bird pest control determination model.

[0044] 5 is a diagram showing an example of hardware of the bird damage control support device 1. The bird damage control support device 1 includes a processor 31, a main memory device 32, an auxiliary memory device 33, an input device 34, an output device 35, and a communication device 36.

[0045] The processor 31 is configured using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), an AI (Artificial Intelligence) chip, etc.

[0046] The main memory device 32 is a device that stores programs and data, and is, for example, a read-only memory (ROM), a random access memory (RAM), or a non-volatile memory (NVRAM (Non-Volatile RAM)).

[0047] The auxiliary storage device 33 is, for example, an SSD (Solid State Drive), a hard disk drive, an optical storage device (CD (Compact Disc), DVD (Digital Versatile Disc), etc.), a storage system, a read / write device for a recording medium such as an IC card, an SD card or an optical recording medium, a storage area of ​​a cloud server, etc. Programs and data can be read into the auxiliary storage device 33 via a recording medium reader or a communication device 36. The programs and data stored (memorized) in the auxiliary storage device 33 are read into the main storage device 32 as needed.

[0048] The input device 34 is an interface that accepts input from the outside, and is, for example, a keyboard, a mouse, a touch panel, a card reader, a pen-input tablet, a voice input device, or the like.

[0049] The output device 35 is an interface that outputs various information such as the progress of processing and the results of processing. The output device 35 is, for example, a display device (liquid crystal monitor, LCD (Liquid Crystal Display), graphic card, etc.) that visualizes the various information described above, a device that converts the various information described above into audio (audio output device (speaker, etc.)), or a device that converts the various information described above into text (printer, etc.). Note that, for example, the bird damage control support device 1 may be configured to input and output information to and from other devices via the communication device 36.

[0050] The input device 34 and the output device 35 constitute a user interface that receives and presents information.

[0051] The communication device 36 is a device that realizes communication with other devices. The communication device 36 is a wired or wireless communication interface that realizes communication with other devices via a communication network such as the Internet, and is, for example, a NIC (Network Interface Card), a wireless communication module, a USB module, or the like.

[0052] All or part of the bird damage control support device 1 may be realized using virtual information processing resources provided using virtualization technology, process space separation technology, or the like, such as a virtual server provided by a cloud system. All or part of the functions provided by the bird damage control support device 1 may be realized by a service provided by the cloud system via an API (Application Programming Interface), for example. The bird damage control support device 1 may also be configured as a system including multiple information processing devices connected to each other so that they can communicate with each other.

[0053] The above-mentioned functions of the bird damage control support device 1 are realized by the processor 31 of the bird damage control support device 1 reading and executing a program stored in the main memory device 32, or by the hardware (FPGA, ASIC, AI chip, etc.) that constitutes the bird damage control support device 1. The bird damage control support device 1 stores the above-mentioned various information (data), for example, as a database table or a file managed by a file system. Next, the processing performed by the bird damage control support device 1 will be described.

[0054] --Model learning process-- 6 is a flow diagram illustrating an example of a model learning process performed by the bird damage control support device 1. The model learning process is started, for example, when a predetermined input is made to the bird damage control support device 1 by a worker or the like, or at a predetermined timing (a predetermined time or a predetermined time interval).

[0055] First, the learning unit 15 acquires information on the performance image and the corresponding correct label. Specifically, the learning unit 15 acquires data of each record in the training data DB 200 (s11).

[0056] Here, the learning unit 15 may perform pre-processing on the data acquired in s11 to generate feature quantities for a bird damage countermeasure determination model (s13).

[0057] For example, the learning unit 15 may enlarge or reduce each actual image so that the same object in all actual images is composed of the same number of image elements, or may adjust each actual image by performing a projective transformation or the like so that the actual image is an image taken from a predetermined direction, or may correct the color tone, etc. of each actual image.

[0058] The learning unit 15 performs machine learning on the record images acquired in s11 and their corresponding correct labels to create a bird damage countermeasure determination model (s15).

[0059] For example, the learning unit 15 inputs the image data 202, bird damage area 203, and tool type 204 data in the teacher data DB 200 acquired in s11 into the bird damage countermeasure determination model, thereby acquiring output values ​​corresponding to the actual image. When this process is executed for the first time, initial values ​​are set in advance for the hyperparameters (described next) of the bird damage countermeasure determination model.

[0060] The learning unit 15 optimizes the hyperparameters in the bird damage countermeasure determination model so that each acquired output value approaches the power equipment area 205 and the installation range 206 in the teacher data DB 200 (s17). For example, the learning unit 15 adjusts hyperparameters such as weights between units (neurons) or coefficients in activation functions using a learning method such as backpropagation. This completes the model creation process.

[0061] The output value of the bird damage control determination model may include information on the accuracy of the installation range as well as the installation range information. In this case, the bird damage control determination model can output one or more combinations of the installation range information and the accuracy information.

[0062] The learning unit 15 may configure the bird damage countermeasure determination model using two trained models. For example, first, the learning unit 15 generates a first trained model that receives an actual image and outputs information about the area of ​​the power equipment in the actual image. That is, the learning unit 15 inputs the image data 202 in the training data DB 200 acquired in s11 into the first trained model, thereby acquiring each output value corresponding to the actual image. The learning unit 15 optimizes the hyperparameters in the bird damage countermeasure determination model so that each acquired output value approaches the power equipment area 205 in the training data DB 200.

[0063] Second, the learning unit 15 receives the area of ​​the power equipment, the bird damage area, and the type of bird damage prevention equipment as input, and generates a second trained model that outputs information on the range of the power equipment to which the bird damage prevention equipment is to be attached. That is, the learning unit 15 inputs the information on the area of ​​the power equipment output by the first trained model and the bird damage area 203 and the equipment type 204 in the teacher data DB 200 acquired in s11 into the second trained model, thereby acquiring each output value. The learning unit 15 optimizes the hyperparameters in the second trained model so that each acquired output value approaches the installation range 206 in the teacher data DB 200.

[0064] In this way, by configuring the bird damage prevention control judgment model with two trained models, it is possible to accurately recognize the area of ​​each power facility and estimate the installation range of bird damage prevention devices, thereby making it possible to accurately determine the installation range of bird damage prevention devices.

[0065] - Bird damage prevention judgment processing - 7 is a flow diagram illustrating an example of the bird damage countermeasure determination process. The bird damage countermeasure determination process is started, for example, when a predetermined input is made to the bird damage countermeasure support device 1 by a worker or the like, or at a predetermined timing (a predetermined time or a predetermined time interval).

[0066] The image acquisition unit 11 acquires site images (s31). For example, the image acquisition unit 11 acquires site images taken by a camera or terminal held by a resident who needs bird damage control measures or a worker in charge of bird damage control measures, via a recording medium or a communication network such as the Internet or a LAN (Local Area Network). The image acquisition unit 11 may also receive images taken by a monitoring camera installed in a power facility or the like.

[0067] Next, the countermeasure determination unit 17 receives input of the bird-damaged area (s33). For example, the countermeasure determination unit 17 receives input of the bird-damaged area from a worker, a resident, or the like while displaying the site image acquired in s31 on a screen.

[0068] The countermeasure determination unit 17 also receives an input of the type of bird damage prevention equipment to be used (s35). For example, the countermeasure determination unit 17 receives an input of the selection of the type of bird damage prevention equipment from a worker, a resident, or the like while displaying the site image acquired in s31 on the screen.

[0069] The countermeasure determination unit 17 inputs the site image acquired in s31, the information on the bird damage area input in s33, and the information on the type of bird damage prevention device acquired in s35 into the bird damage prevention control model, thereby acquiring information on the range for installing the bird damage prevention devices output from the bird damage prevention control model (s37).The countermeasure determination unit 17 then displays this information on a bird damage prevention control proposal screen (s39), which will be described next.This completes the bird damage prevention control determination process.

[0070] <Bird damage countermeasure proposal screen> 8 is a diagram showing an example of a bird damage countermeasure proposal screen 500. The bird damage countermeasure proposal screen 500 has an equipment display field 510 that displays the type of bird damage prevention equipment selected in advance by residents or workers, etc., and a display field 520 for an image of the site.

[0071] In the site image display field 520, information on the bird damage area 522 specified in the bird damage countermeasure determination process and the attachment range 524 of the bird damage prevention equipment of the type related to the equipment display field 510 is displayed superimposed on the site image.

[0072] By checking the bird damage prevention measures proposal screen 500, residents or workers in bird-damaged areas can easily find out information about the range of power equipment on which bird damage prevention devices they should install if they use the type of bird damage prevention device they have selected as a measure against the bird-damaged area.

[0073] 9 is a diagram showing another example of the bird damage countermeasure proposal screen 600. This bird damage countermeasure proposal screen 600 has an appliance display field 610 and a site image display field 620, similar to FIG.

[0074] However, information on a plurality of attachment ranges 624 of bird pest control devices is displayed superimposed on the site image in display area 620 of this site image. Also, information 630 of the accuracy output from the bird pest control determination model corresponding to each of the plurality of attachment ranges 624 is displayed on bird pest control proposal screen 600.

[0075] Residents or workers in bird-damaged areas can check the accuracy information 630 on the bird damage countermeasure proposal screen 600 to confirm the priority of the installation range 624 displayed in the display area 620 of the site image.

[0076] As described above, the bird pest control support device 1 of this embodiment acquires site images and information on bird-damaged areas, and inputs these into a trained model (bird pest control determination model) that receives images of the bird-damaged area and the surrounding power equipment and outputs information on the installation range of bird pest control devices on the power equipment, thereby outputting information on the installation range of bird pest control devices on the power equipment in the site image.This allows users such as residents suffering from bird damage or workers in charge of bird pest control measures to know the range of bird pest control devices that should be installed on the power equipment (e.g., power lines) at that site simply by preparing an image of the site suffering from bird damage.In other words, the bird pest control support device 1 of this embodiment can support the rapid identification of bird pest control measures that should be taken for power equipment.

[0077] Furthermore, the bird pest control support device 1 of this embodiment acquires information on the types of bird pest control equipment, and then inputs the site image and the above-mentioned type information into a trained model (bird pest control judgment model) that uses information on the types of bird pest control equipment that can be used against bird pests as input values, thereby outputting information on the range in which bird pest control devices should be installed in the power equipment in the site image, so that users such as residents who are suffering from bird pests or workers in charge of bird pest control can know the installation range of bird pest control equipment that is suitable for each type of bird pest control equipment.

[0078] Furthermore, the bird damage control support device 1 of this embodiment displays information on the range in which bird damage control devices should be installed, which information is output by the trained model (bird damage control determination model), superimposed on the site image, allowing users such as residents affected by bird damage or workers in charge of bird damage control measures to easily check the range in which bird damage control devices should be installed at the site.

[0079] Furthermore, the bird damage control support device 1 of this embodiment inputs a site image and a bird damage area into a trained model that outputs information on the range for installing bird damage control devices and information on the accuracy of that range, and outputs one or more pieces of information on the range for installing bird damage control devices in power equipment in the site image and information on the accuracy. This allows users such as residents suffering from bird damage or workers in charge of bird damage control to prioritize and implement multiple bird damage countermeasures.

[0080] Furthermore, the bird damage control support device 1 of this embodiment outputs information on the range in which bird damage control devices should be installed using a trained model (bird damage control determination model) consisting of a first trained model and a second trained model. That is, the bird damage control support device 1 receives an image including a bird-damaged area and surrounding power equipment, and outputs information on the area of ​​the power equipment in the image. The first trained model receives the site image and outputs information on the area of ​​the power equipment in the site image. The second trained model receives the information on the area of ​​the power equipment and the image of the bird-damaged area, and outputs information on the area of ​​the power equipment where bird damage control devices should be installed. The second trained model then receives the information on the area of ​​the power equipment output by the first trained model and the information on the bird-damaged area, and outputs information on the area of ​​the power equipment in the site image where bird damage control devices should be installed. In this way, by using the second trained model with the information on the area of ​​the power equipment accurately recognized by the first trained model as an input value, the range in which bird damage control devices should be installed can be accurately identified.

[0081] The above description of the embodiments is intended to facilitate understanding of the present invention, and is not intended to limit the present invention. The present invention may be modified or improved without departing from the spirit thereof, and the present invention includes equivalents thereof.

[0082] For example, the combination of each functional unit of the bird damage control support device 1 described in this embodiment is just one example, and for example, some of the functional units may be provided in other functional units, or multiple functional units may be combined into one functional unit.

[0083] Furthermore, in this embodiment, the bird damage control judgment model was created based on the assumption that bird damage is caused by bird droppings, utilizing the characteristic that the installation range of bird damage prevention devices is above the location of the bird damage area. However, the bird damage control judgment model can also be applied to other types of bird damage. For example, if the bird damage is the presence of birds themselves or noise, power equipment within a predetermined distance from the bird damage area is subject to installation of bird damage prevention devices, so there is a correlation between the installation range of bird damage prevention devices and the bird damage area. Therefore, a new bird damage control judgment model for when the presence of birds themselves or noise is considered to be bird damage can be created using a method similar to that described in this embodiment.

[0084] Furthermore, the bird pest control determination model of this embodiment may be configured to output the area of ​​the power equipment to which the bird pest prevention device is to be attached based on the feature quantities of the area of ​​the power equipment other than the power equipment to which the bird pest prevention device is to be attached, which is included in the image. This allows, for example, to identify the electric wire based on the configuration of the utility pole and various electric power equipment attached thereto, thereby more accurately identifying the electric wire to which the bird pest prevention device is to be attached.

[0085] In addition, in this embodiment, the type of bird damage prevention device is an input value of the bird damage prevention measure determination model, but it may also be an output value of the bird damage prevention measure determination model. For example, the bird damage prevention measure determination model may be a model that uses the bird damage area and the area of ​​each power facility in the image as input values ​​and the type of bird damage prevention device and its installation range as output values. [Explanation of symbols]

[0086] 1 Bird damage countermeasure support device, 11 Image acquisition unit, 12 Type acquisition unit, 13 Preprocessing unit, 15 Learning unit, 17 Countermeasure determination unit, 19 Information display unit

Claims

1. a processor and a memory; an image acquisition unit that acquires an image including the power facility and information about an area in the image that is affected by bird damage; a countermeasure determination unit that inputs the acquired image including the power equipment and information about the area that is damaged by birds in the image into a trained model that receives input of an image including an area that may be damaged by birds and power equipment around the area, and outputs information about the area of ​​the power equipment where bird damage prevention devices should be installed to prevent the bird damage; and A bird damage prevention support device equipped with:

2. A type acquisition unit is provided for acquiring information on the type of bird damage prevention device, The trained model is a model into which an image including an area susceptible to bird damage and power facilities around the area, and information on the type of bird damage prevention equipment that can be used against the bird damage are input, The countermeasure determination unit inputs the acquired image including the power facility, information on the area in the image that is affected by bird damage, and information on the acquired type of bird damage prevention equipment into the trained model, and outputs information on the range in which bird damage prevention devices should be installed in the power facility in the acquired image. The bird damage control support device according to claim 1.

3. An information display unit is provided that displays information on the range in which the bird damage control device is to be installed, which is output by the trained model, on a screen by superimposing it on the acquired image. The bird damage control support device according to claim 1.

4. The trained model is a model that outputs information on the range in which the bird damage control device is to be installed and information on the accuracy of the range, The countermeasure determination unit inputs the acquired image including the power equipment and information on the area affected by bird damage in the image into the trained model, and outputs one or more pieces of information on the range in which bird damage control devices should be installed in the power equipment in the acquired image and information on accuracy. The bird damage control support device according to claim 1.

5. The countermeasure determination unit An image including an area susceptible to bird damage and power equipment around the area is input, and information about the area of ​​the power equipment in the image is output by inputting the acquired image into a first trained model. Information on the area of ​​the power equipment and an image including an area that may be damaged by birds are input, and information on the area of ​​the power equipment where bird damage prevention devices are to be installed to prevent the bird damage is output to a second trained model, by inputting information on the area of ​​the power equipment that is damaged by birds in the acquired image and information on the area of ​​the output power equipment. Information on the area of ​​the power equipment that is damaged by birds in the acquired image and information on the area of ​​the output power equipment is output. The bird damage control support device according to claim 1.

6. The information processing device an image acquisition process for acquiring an image including the power facility and information on areas in the image that are affected by bird damage; a bird damage control determination process that inputs the acquired image including the power equipment and information about the area affected by bird damage in the image into a trained model that receives input of an image including an area that may be damaged by birds and the power equipment around that area, and outputs information about the area of ​​the power equipment where bird damage control devices should be installed to prevent the bird damage; and A bird damage prevention support method that implements the following.

Images