Vegetation management system and vegetation management method

Abstract

To precisely analyze the risk that vegetation gets in contact with a facility and also suppress increase of cost at the same time.SOLUTION: A vegetation management system 1 includes: a data acquisition unit 11 for acquiring input data including remote sensing data formed by taking images of an analysis target facility and vegetation by remote sensing; a vegetation classification unit 13 for classifying the vegetation taken in the remote sensing data; a wide area growth prediction unit 14 for predicting a time-series change of the range of growth of the vegetation taken in the remote sensing data; a vegetation amount simulation unit 15 for predicting a change in the growth amount of each vegetation by a simulation; a three-dimension constructing unit 16 for constructing the facility and a three-dimensional model showing vegetation; and a risk determination unit 17 for determining a contact risk showing the possibility that the facility and the vegetation get in contact with each other.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a vegetation management system and a vegetation management method, and is suitable for application to a vegetation management system and a vegetation management method that assist maintenance work of power facilities against vegetation contact using measurement information of remote sensing.

Background Art

[0002] In conventional power facility maintenance work, regularly, the routes where power facilities such as distribution lines and transmission lines are arranged are manually surveyed, and for places where there is a risk of problems such as trees coming into contact with power facilities, operations such as removing tree branches and using herbicides were carried out. In recent years, however, efforts have been made to automate the survey work due to reasons such as a shortage of manpower.

[0003] In the effort to automate this survey work, considering that many power facilities such as distribution lines and transmission lines are installed in inaccessible places such as mountainous areas, remote sensing technology that can remotely monitor power facilities and trees (vegetation) has attracted attention. Representative means of remote sensing technology include the use of artificial satellites, aircraft, drones, etc. Furthermore, as a method for determining contact between vegetation and facilities, research and development of vegetation contact determination by three-dimensional measurement using a LiDAR (Light Detection and Ranging) sensor has been progressing.

[0004] For example, Patent Document 1 discloses a system for analyzing plant growth based on a remote sensing image taken by remote sensing technology.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, in the prior art, when analyzing the contact between a facility and vegetation by utilizing remote sensing data, it is necessary to perform vegetation contact determination by three-dimensional measurement using a remote sensing sensor such as a LiDAR sensor. In order to make an accurate determination, there has been a problem that the cost becomes extremely high due to the wide shooting range or frequent shooting times. In addition, in order to support visualization for users and intuitive operation, three-dimensionalization of the facility and vegetation is an indispensable process, and for this purpose, the need for a large amount of heterogeneous and time-series geographical information has also been a factor contributing to cost increase.

[0007] The present invention has been made in consideration of the above points, and aims to propose a vegetation management system and a vegetation management method that can suppress an increase in cost and accurately analyze the risk of contact between vegetation and a facility.

Means for Solving the Problems

[0008] In order to solve such problems, in the present invention, there is provided the following vegetation management system that analyzes the contact of the vegetation with respect to the facility by using remote sensing data obtained by photographing the facility and vegetation to be analyzed by remote sensing. This vegetation management system includes a data acquisition unit that acquires input data including at least the remote sensing data, the geographical data of the facility, and environmental data related to the growth of the vegetation; a vegetation classification unit that classifies the vegetation photographed in the remote sensing data; a wide-area growth prediction unit that predicts the time-series change of the growth range of the vegetation photographed in the remote sensing data; a vegetation amount simulation unit that predicts the variation of the growth amount of each vegetation classified by the vegetation classification unit by simulation; a three-dimensional construction unit that constructs a three-dimensional model representing the facility and the vegetation based on the remote sensing data and the geographical data; and a risk determination unit that determines a contact risk indicating the possibility of contact between the facility and the vegetation based on the processing results of the wide-area growth prediction unit, the vegetation amount simulation unit, and the three-dimensional construction unit.

[0009] In addition, in order to solve such problems, the present invention provides the following vegetation management method by a vegetation management system that analyzes the contact between the vegetation and the facility using remote sensing data obtained by photographing the facility and vegetation to be analyzed by remote sensing. This vegetation management method includes a data acquisition step of acquiring input data including at least the remote sensing data, geographical data of the facility, and environmental data related to the growth of the vegetation, a vegetation classification step of classifying the vegetation photographed in the remote sensing data, a wide-area growth prediction step of predicting the temporal change in the growth range of the vegetation photographed in the remote sensing data, a vegetation amount simulation step of predicting the variation in the growth amount of each vegetation classified in the vegetation classification step by simulation, a three-dimensional construction step of constructing a three-dimensional model representing the facility and the vegetation based on the remote sensing data and the geographical data, and a risk determination step of determining a contact risk indicating the possibility of contact between the facility and the vegetation based on the processing results of the wide-area growth prediction step, the vegetation amount simulation step, and the three-dimensional construction step.

Advantages of the Invention

[0010] According to the present invention, an increase in cost can be suppressed, and the risk of contact between the vegetation and the facility can be accurately analyzed.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Embodiments for Carrying Out the Invention

[0012] Hereinafter, with reference to the drawings, one embodiment of the present invention will be described in detail.

[0013] FIG. 1 is a block diagram showing a configuration example of a vegetation management system 1 according to an embodiment of the present invention. The vegetation management system 1 according to the present embodiment is a system that analyzes the contact risk between vegetation and power facilities using remote sensing data for a region to be analyzed (target region) specified by a user. As shown in FIG. 1, it is a system into which a plurality of different input data 10 (specifically, remote sensing image data 10a, spectral library data 10b, geographical information data 10c, environmental information data 10d, management information data 10e) are input, and includes a data acquisition unit 11 (individually, a remote sensing image data acquisition unit 11a, a geographical information data acquisition unit 11b, an environmental information data acquisition unit 11c, a management information data acquisition unit 11d), a database generation unit 12, a vegetation classification unit 13, a wide-area growth prediction unit 14, a vegetation amount simulation unit 15, a three-dimensional construction unit 16, a risk determination unit 17, a visualization unit 18, a maintenance instruction unit 19, and a database 20. Details of each unit will be appropriately shown in the following description. In FIG. 1, the movement of data and the transition of processing are represented by solid lines with arrows, but since access is performed from almost all configurations to the database 20, the display of arrows is omitted.

[0014] The individual data constituting the input data 10 will be described.

[0015] The remote sensing image data 10a is time-series image data obtained by a remote sensing sensor observing the ground surface, and specifically, for example, satellite photos or aerial photos by RapidEye, LANDSAT, Sentinel, etc. For the remote sensing image data 10a, for example, time-series low-resolution remote sensing images and high-resolution remote sensing images can be used, but the type of data of the remote sensing image data 10a in the present embodiment is not limited to these, and for example, time-series images in the same remote sensing image may be used. In this description, the high or low resolution is not based on an absolute standard but on a relative comparison.

[0016] Spectral library data 10b is data of a spectral library obtained by an optical sensor (especially a passive sensor that obtains information from light from an object (in this example, vegetation)) observing vegetation. A passive sensor basically has the same structure and function as the eye (naked eye). Specifically, an optical system such as a lens (corresponding to the lens of the eye) collects light from the object and forms an image on the detection system (corresponding to the retina of the eye) to obtain spectral and spatial information (for example, color and shape). In particular, regarding the spectrum (color), while the eye can only capture visible light, an optical sensor can detect over a wide wavelength range from visible light to infrared light. As a result, it is possible to obtain a number of useful information such as the identification of minerals, rocks, and vegetation that cannot be interpreted by the eye, the temperature of the ground surface, the land use situation, water resources and plankton resources in the sea and lakes, etc. Furthermore, an optical sensor can also obtain these useful information as a two-dimensional image over a wide range.

[0017] Geographic information data 10c is data of geographic information provided by a Geographic Information System (GIS), and includes information on the location and shape (for example, polygon) of power facilities (distribution lines, transmission lines, etc.) and vegetation. Geographic information data 10c is essential data when sharing data obtained locally and data obtained from satellites, aircraft, etc. in the vegetation management system 1.

[0018] Environmental information data 10d is data on the local environment, for example, data on soil, biosphere, temperature, weather, etc. in the value range of the analysis target. Specific weather data includes, for example, data from AMeDAS, land surface temperature data from MODIS (Moderate Resolution Imaging Spectroradiometer), meteorological agency data, etc.

[0019] The management information data 10e is data necessary for determining the content of the maintenance instruction by the maintenance instruction unit 19, and can include, for example, the history of maintenance work (maintenance history), the location where the maintenance work was carried out (maintenance location), the personnel and equipment required for the maintenance work (personnel and equipment), etc. Also, the location of the office and equipment warehouse, the information of personnel and equipment, etc., which are referred to when determining the maintenance instruction content in the maintenance instruction process described later, are also included in the management information data 10e. The provider of the management information data 10e is, for example, an electric power company, and operation data such as operation and maintenance memos, logs, and histories can be used.

[0020] Figure 2 is a block diagram showing an example of the hardware configuration of the vegetation management system 1. Figure 2 shows the state in which the remote sensing image data 10a provided from the remote sensing observation device 2 is input into the vegetation management system 1.

[0021] In Figure 2, the remote sensing observation device 2 is an observation satellite, aircraft, etc. equipped with a remote sensing sensor (such as LiDAR), and its type is not limited. The remote sensing observation device 2 periodically provides the remote sensing image data 10a as the observation result by the remote sensing sensor. Then, the vegetation management system 1 acquires this remote sensing image data 10a as one of the input data 10.

[0022] The vegetation management system 1 can be realized by a general computer system (PC) having a computing function, and is configured to include, for example, a CPU (Central Processing Unit) 1a, a RAM (Random Access Memory) 1b, and a storage device 1c as shown in Figure 2. Note that the vegetation management system 1 may have a configuration other than that shown in Figure 2. For example, it is conceivable to include an output device such as a display as the output destination of the maintenance instruction.

[0023] In the vegetation management system 1, each functional unit (data acquisition unit 11, database generation unit 12, vegetation classification unit 13, wide-area growth prediction unit 14, vegetation amount simulation unit 15, three-dimensional construction unit 16, risk determination unit 17, visualization unit 18, maintenance instruction unit 19) shown in FIG. 1 performs arithmetic processing, and thus is implemented as a combination of a plurality of CPUs 1a and RAMs 1b divided according to roles. Each of these functional units can read / write data by accessing the storage device 1c. Also, the database 20 of the vegetation management system 1 shown in FIG. 1 is implemented by the storage device 1c. Specifically, the storage device 1c can include not only storage media such as HDD (Hard Disk Drive) and SSD (Solid State Drive) built into a PC, but also storage media such as USB (Universal Serial Bus) memory externally connected to the PC. Further, storage means such as a database communicably connected to the PC via a network may also be included as a form of the storage device 1c.

[0024] FIG. 3 is a flowchart showing the processing procedure of the overall processing in the vegetation management system 1. Prior to the start of the processing shown in FIG. 3, a region to be analyzed (target region) is specified by the user for the vegetation management system 1.

[0025] First, in step S1, the input data 10 is input to the vegetation management system 1 by the data acquisition unit 11. Describing the individual configuration of the data acquisition unit 11, the remote sensing image data acquisition unit 11a acquires the remote sensing image data 10a and the spectral library data 10b, the geographic information data acquisition unit 11b acquires the geographic information data 10c, the environmental information data acquisition unit 11c acquires the environmental information data 10d, and the management information data acquisition unit 11d acquires the management information data 10e. The input data 10 acquired by the data acquisition unit 11 in step S1 is transmitted to the database generation unit 12.

[0026] In the next step S2, the database generation unit 12 stores the input data 10 transmitted from the data acquisition unit 11 in step S1 in the database 20, performs a predetermined data generation process, and stores the processed data in the database 20.

[0027] The above data generation process is mainly a process for preparing intermediate data necessary for the processes performed by each unit described later. Specifically, the following processes are performed. In the data generation process, the database generation unit 12 first masks the past time-series remote sensing image data 10a (for example, satellite images) using the position and shape information included in the geographic information data 10c for the target area specified by the user. Further, the database generation unit 12 combines the "remote sensing data" obtained by extracting the target area, which is the masked part, from the remote sensing image data 10a and the "geographic data" obtained by extracting information on the target area from the geographic information data 10c to generate "mapping data" for the target area. In addition, the database generation unit 12 also masks the spectral library data 10b and the environmental information data 10d, and generates a "spectral library" and "environmental data" obtained by extracting information on the target area. Further, the database generation unit 12 may also mask the management information data 10e and extract "management data" obtained by extracting information on the target area. Then, the database generation unit 12 stores the generated remote sensing data, geographic data, mapping data, spectral library, environmental data, and management data in the database 20.

[0028] In the next step S3, the vegetation classification unit 13 discriminates the type of vegetation based on the remote sensing data and geographic data (or mapping data combined therefrom) generated in step S2 and the spectral library, and generates a "vegetation classification map" in which the discriminated vegetation type is reflected in the mapping data and stores it in the database 20 (vegetation classification process). The details of the vegetation classification process will be described later with reference to FIG. 5 and the like.

[0029] In the next step S4, the wide-area growth prediction unit 14 uses the vegetation classification map generated in step S3 and the past time-series remote sensing data stored in the database 20 to predict the time-series wide-area range variation (wide-area vegetation growth) for the vegetation classified in step S3, and stores the prediction result in the database 20 (wide-area growth prediction process). The details of the wide-area growth prediction process will be described later with reference to FIG. 7 and the like.

[0030] In the next step S5, the vegetation amount simulation unit 15 uses the vegetation classification map stored in the database 20, the environmental data, and the biological growth model (growth model) of the classified vegetation to simulate the variation of the vegetation amount of the corresponding vegetation for each vegetation, and stores the simulation result in the database 20 (vegetation amount prediction process). Note that the growth model of the vegetation is stored in the database 20 in advance. The details of the vegetation amount prediction process will be described later with reference to FIG. 9 and the like.

[0031] In the next step S6, the three-dimensional construction unit 16 generates a three-dimensional model including power facilities (such as distribution lines and transmission lines) and vegetation, and stores the generated three-dimensional model in the database 20 (three-dimensional model construction process). The details of the three-dimensional model construction process will be described later with reference to FIG. 11 and the like.

[0032] In the next step S7, the risk determination unit 17 determines (calculates) the contact risk between the vegetation and the power facilities in consideration of the time-series variation of the vegetation in the wide-area range and the positional relationship between the vegetation and the power facilities based on the prediction result of the wide-area vegetation growth by the wide-area growth prediction unit 14 stored in the database 20 and the prediction result of the vegetation amount prediction process by the vegetation amount simulation unit 15, and stores the determination result (risk determination result) in the database 20 (risk determination process). The details of the risk determination process will be described later with reference to FIG. 13 and the like.

[0033] In the next step S8, the visualization unit 18 performs two-dimensional or three-dimensional visualization at time intervals of a specific time (or a time specified by the user) based on the prediction results of the wide-area vegetation growth by the wide-area growth prediction unit 14 stored in the database 20, the prediction results of the vegetation amount prediction process by the vegetation amount simulation unit 15, the determination results of the risk determination process by the risk determination unit 17, etc. (visualization process). The visualization process is divided into a two-dimensional visualization process and a three-dimensional visualization process, and the details of these processes will be described later with reference to FIGS. 15 to 18.

[0034] And in the last step S9, the maintenance instruction unit 19 selects necessary maintenance work based on the determination result of the risk determination process by the risk determination unit 17 and the management information data 10e (or management data) stored in the database 20, and presents a maintenance instruction to the user by outputting the selection result (maintenance instruction process). In the selection of the maintenance work by the maintenance instruction unit 19, for example, in addition to specifying the maintenance location, a personnel dispatch plan, a vehicle allocation plan, a determination of the transport route of equipment, etc. are performed. The details of the maintenance instruction process will be described later with reference to FIG. 19 and the like.

[0035] By performing the processes of steps S1 to S9 above, in the vegetation management system 1, for the target area designated by the user, using remote sensing data, even if the target area is wide, it can accurately analyze the contact risk between the power facility and the vegetation at low cost, and based on the analysis result, accurately instruct the user to perform maintenance work. Also, in the vegetation management system 1, since various types of data (input data, intermediate data, output data) input or generated in the above series of analyses are stored in the database 20, these data can also be used for subsequent analyses or other analyses.

[0036] FIG. 4 is a diagram for explaining an image of the data stored in the database 20. In FIG. 4, as an example of the data used as intermediate data, images of the remote sensing data 201, the spectral library 202, the geographical data 203, the environmental data 204, and the management data 205 are visually shown respectively.

[0037] As described above in step S2, the remote sensing data 201 is an example of the time-series remote sensing image data 10a from which the target area has been extracted by the database generation unit 12. Similarly, the spectral library 202 is an example of the spectral library data 10b from which information about the target area has been extracted, the geographical data 203 is an example of the geographical information data 10c from which information about the target area has been extracted, the environmental data 204 is an example of the environmental information data 10d from which information about the target area has been extracted, and the management data 205 is an example of the management information data 10e from which information about the target area has been extracted. However, in FIG. 4, for the sake of simplicity, the illustration of the detailed content of each piece of information is omitted.

[0038] FIG. 5 is a flowchart showing an example of the processing procedure of the vegetation classification process. As described above, the vegetation classification process corresponds to the process of step S3 in FIG. 3 and is executed by the vegetation classification unit 13.

[0039] According to FIG. 5, first, the vegetation classification unit 13 acquires the mapping data of the target area generated by combining the remote sensing data and the geographical data by the database generation unit 12 in step S2 of FIG. 3 (step S11). Next, the vegetation classification unit 13 acquires the spectral library generated in step S2 of FIG. 3 (step S12).

[0040] In steps S11 and S12, the vegetation classification unit 13 may directly acquire the target data from the database generation unit 12, or may acquire the target data stored in the database 20. This is because in the vegetation management system 1 according to the present embodiment, basically all data including intermediate data is stored in the database 20. Similarly, in the processing by other functional units described later, the desired data may be acquired from the functional unit that is the source of generation, or may be acquired from the database 20.

[0041] Next, the vegetation classification unit 13 discriminates the type of vegetation in the mapping data (in other words, the remote sensing image data 10a in the mapped range) by using the mapping data obtained in steps S11 to S12 and the spectral library (step S13). As a specific method of "vegetation classification" for discriminating the type of vegetation, for example, a machine learning method can be used. In this case, the vegetation classification unit 13 can estimate the type of vegetation from the spectral features of the vegetation by learning the spectral library. Note that the method of vegetation classification is not limited to the above example, and other known methods may be used.

[0042] Next, for each type of vegetation classified in step S13, the vegetation classification unit 13 generates a vegetation classification map by recording geographical data and provides it to the database 20 (step S14).

[0043] Note that the processes in steps S11 to S14 may be repeatedly executed for time-series past mapping data. As a result, the vegetation classification unit 13 can generate time-series past vegetation classification maps.

[0044] FIG. 6 is a diagram for explaining an example of a vegetation classification map. In FIG. 6(A), as an example of the mapping data before the vegetation classification in step S13 of FIG. 5, a pre-classification map image 211 is shown. In FIG. 6(B), as an example of the mapping data (vegetation classification map) after the vegetation classification generated in step S14 of FIG. 5, a vegetation classification map image 212 is shown. As shown in FIG. 6(A), the pre-classification map image 211 is a normal satellite image. In contrast, the vegetation classification map image 212 shown in FIG. 6(B) is an image obtained by generating a mapping image colored for each type of vegetation through vegetation classification on the pre-classification map image 211. Also, in the vegetation classification map image 212, the geographical information included in the mapping data before vegetation classification may also be color-coded by range and shape.

[0045] FIG. 7 is a flowchart showing an example of the processing procedure of the wide-area growth prediction process. As described above, the wide-area growth prediction process corresponds to the process of step S4 in FIG. 3 and is executed by the wide-area growth prediction unit 14.

[0046] According to FIG. 7, first, the wide-area growth prediction unit 14 acquires the past time-series remote sensing data (satellite images in this example) stored in the database 20 (step S21). The remote sensing data acquired in step S21 is a satellite image obtained by extracting the target area from the past time-series remote sensing image data 10a (satellite image).

[0047] Next, the wide-area growth prediction unit 14 acquires the time-series past vegetation classification maps generated by the vegetation classification process in FIG. 5 (step S22).

[0048] Next, based on the data acquired in steps S21 and S22, the wide-area growth prediction unit 14 predicts the time-series variation (wide-area vegetation growth) of the vegetation classified by the vegetation classification process in a wide area (step S23). As a method for predicting wide-area vegetation growth, for example, a method of predicting time-series variation using a regression-type neural network (RNN: Recurrent Neural Network) can be mentioned, but other methods may also be used. Then, the wide-area growth prediction unit 14 stores the prediction result of the wide-area vegetation growth in the database 20.

[0049] FIG. 8 is a diagram for explaining an image of the process of predicting wide-area vegetation growth. In FIG. 8, two-dimensional maps 220 at respective times of past times t1 and t2 and future time t3 are shown, and a vegetation range 221 is shown as an image of the wide-area vegetation range in each two-dimensional map 220. The vegetation ranges 221 at past times t1 and t2 are derived from the remote sensing data (e.g., satellite images) and the vegetation classification maps at each time, and the vegetation range 221 at future time t3 is predicted from the time-series variation of the vegetation ranges 221 at past times t1 and t2. In the case of FIG. 8, it is predicted that the vegetation range 221 will expand from past times t1 and t2 to future time t3.

[0050] FIG. 9 is a flowchart showing an example of a processing procedure for vegetation amount prediction processing. As described above, the vegetation amount prediction processing corresponds to the processing of step S5 in FIG. 3 and is executed by the vegetation amount simulation unit 15. Specifically, the vegetation amount simulated in the vegetation amount prediction processing includes, for example, the size of the tree crown, the weight of the leaves, the length of the stems, the number of branches, the amount of biomass, and the like.

[0051] According to FIG. 9, first, the vegetation amount simulation unit 15 acquires the result of vegetation classification (vegetation classification map) by the vegetation classification processing in FIG. 5 (step S31).

[0052] Next, the vegetation amount simulation unit 15 acquires the growth model of the corresponding vegetation from the database 20 for the vegetation shown in the vegetation classification map acquired in step S31 (step S32). It is assumed that the growth model of the vegetation is stored in the database 20 in advance for each type of vegetation.

[0053] Here, a supplementary explanation will be given for the growth model of the vegetation. In the fields of forestry and agriculture, research has been conducted on the growth models of plants, and in many studies, the following (1) to (4) have been pointed out as factors affecting tree growth.

[0054] (1) Environmental factors. Specifically, for example, light (e.g., heliotropism growing in the direction of strong light), wind conditions, latitude and longitude, temperature, geology, water, region, site, etc. can be mentioned. For example, even for the same tree species, the growth rate is different between cold regions and warm regions.

[0055] (2) Genetic factors. The main genetic factor is the difference in growth depending on the tree species. For example, depending on the tree species, there are various branching patterns (forked branching, sympodial branching, monopodial branching), and even for the same tree species, some produce two types of branches called long branches and short branches. It is considered that long branches have an extension orientation that grows towards new space, and short branches have a leaf area expansion orientation that increases the light received in place.

[0056] (3) Influence of neighboring individuals. The above environmental factors and genetic factors affect the growth rate of each individual. However, when multiple trees are grouped together, the interaction between the trees also affects their growth. Therefore, the situation of neighboring individuals is also a factor to be considered in constructing a growth model.

[0057] (4) Temporal factors. Specifically, for example, seasons and tree ages can be cited. Trees have periods of active growth and periods of non-active growth throughout the year, and factors affecting tree growth are diverse, such as differences in growth rates and tree heights depending on the tree age.

[0058] And research has been conducted on modeling the growth of trees through computer simulation considering various factors as described above.

[0059] For example, regarding the branching model, there is one that generates small branches with an extension direction in an inverted T shape with respect to the axis of the parent branch and generates small branches with a leaf area expansion direction in a Y shape on the plane of the maximum inclination of the parent branch. Also, regarding the light environment model, there is a model that approximates the leaf group at the branch tip with a sphere called a leaf ball. With this light environment model, the amount of light received by the leaf ball and the direction (light vector) where light most commonly reaches on average can be calculated, and heliotropism can be realized by rotating the branch tip at a certain ratio in the direction of the light vector.

[0060] Regarding the relationship between tree age and tree height, an exponential function model is widely used. In this exponential function model, the tree height H can be expressed, for example, by the following Equation 1 using a coefficient k that depends on the type and size of the tree and the tree age t.

Equation

[0061] Also, the tree height H may be expressed by the following Equation 2, which is a more generalized form of Equation 1.

Equation

[0062] In addition, research on forest growth prediction using the Mitscherlich equation shown in the following Equation 3 has also been conducted.

Equation

[0063] As described above in detail for several vegetation growth models, the growth models that can be used in the vegetation amount prediction process according to the present embodiment are not limited to these.

[0064] Returning to the description of FIG. 9. The vegetation amount simulation unit 15 acquires environmental data corresponding to the growth model acquired in step S32 from the database 20 (step S33), and performs a simulation of vegetation growth using the growth model (step S34).

[0065] FIG. 10 is a diagram for explaining an image of vegetation growth simulation. FIG. 10 shows a tree crown 231 representing the growth image of the tree crown at each of the past times t1, t2 and the future time t3. The times t1 to t3 shown in FIG. 10 correspond to the times t1 to t3 shown in FIG. 8. By performing a vegetation growth simulation on the tree crown by the vegetation amount simulation unit 15, as shown in FIG. 10, the variation in the size of the tree crown 231 at each time t1 to t3 can be predicted.

[0066] In FIG. 10, as an example of the vegetation growth simulation, the prediction of the variation in the size of the tree crown is given. However, in the vegetation growth simulation in step S34 of FIG. 9, it may be considered that simulations are similarly performed for other vegetation amounts.

[0067] Return to the description of FIG. 9. After performing the vegetation growth simulation in step S34, the vegetation amount simulation unit 15 generates a time-series vegetation amount variation curve (time-series vegetation amount) as a simulation result and stores it in the database 20 (step S35).

[0068] FIG. 11 is a flowchart showing an example of the processing procedure of the three-dimensional model construction process. As described above, the three-dimensional model construction process corresponds to the process of step S6 in FIG. 3 and is executed by the three-dimensional construction unit 16.

[0069] According to FIG. 11, first, the three-dimensional construction unit 16 acquires a plurality of remote sensing data taken at a specified time (step S41). The specified time may be, for example, the above-mentioned time t1 or time t2. The plurality of remote sensing data is remote sensing data taken from a plurality of viewpoints necessary for generating a three-dimensional model, and the imaging subject may be the same type of remote sensing sensor or different types of remote sensing sensors.

[0070] Next, the three-dimensional construction unit 16 performs three-dimensional restoration using the remote sensing data acquired in step S41 to generate a three-dimensional model of the target area at the specified time (step S42). Then, the three-dimensional construction unit 16 stores the generated three-dimensional model in the database 20.

[0071] As a method for generating a three-dimensional model of the specified object (target area) at the specified time in step S42, for example, a method of performing three-dimensional restoration from the imaging data (LiDAR data) of the power facility and vegetation taken by LiDAR (an example of a remote sensing sensor) mounted on a drone (an example of the remote sensing observation device 2) can be mentioned. Note that various methods of three-dimensional restoration are widely known, and for example, a three-dimensional model can also be generated by SFM (Structure From Motion) using a plurality of images.

[0072] FIG. 12 is a diagram showing an example of a three-dimensional model. According to the three-dimensional model 240 illustrated in FIG. 12, it is shown that in the target area, a power facility (in this example, a transmission line 241) exists near the vegetation 242.

[0073] FIG. 13 is a flowchart showing an example of the processing procedure of the risk determination process. As described above, the risk determination process corresponds to the process of step S7 in FIG. 3 and is executed by the risk determination unit 17. In FIG. 13, the series of processes of steps S51 to S53 and the series of processes of steps S54 to S56 may be executed in a swapped order or may be executed in parallel.

[0074] First, the processes of steps S51 to S53 in FIG. 13 will be described.

[0075] In step S51, the risk determination unit 17 acquires and inputs the geographical data related to the power facility and the vegetation classification map generated in the vegetation classification process of FIG. 5. The geographical data related to the power facility may be data including the geographical information of the distribution lines and transmission lines in the target area. For example, other data having the position and shape information of the power facility may be substituted. Then, in step S52, the risk determination unit 17 acquires and inputs the prediction result of the wide-area vegetation growth by the wide-area growth prediction process of FIG. 7.

[0076] Then, in step S53, based on the data input in steps S51 and S52, the risk determination unit 17 maps the prediction result of the wide-area vegetation growth to the remote sensing data (two-dimensional mapping data) having the information of the power facility, for example, to calculate in the target area the range in which a specific vegetation is distributed at a specified specific time (for example, time t3), and stores the calculation result (wide-area vegetation distribution at the specific time) in the database 20.

[0077] Next, the processes of steps S54 to S56 in FIG. 13 will be described.

[0078] In step S54, the risk determination unit 17 acquires and inputs the three-dimensional model of the power facility and vegetation generated in the three-dimensional model construction process of FIG. 11. Then, in step S55, the risk determination unit 17 acquires and inputs the simulation result (time-series vegetation amount) of the vegetation amount generated in the vegetation amount prediction process of FIG. 9.

[0079] Then, in step S56, based on the data input in steps S54 and S55, the risk determination unit 17 estimates how the vegetation amount changes in the three-dimensional model at a specified specific time (for example, time t3) in the target area, and stores the estimation result (the vegetation amount estimation three-dimensional model at the specific time) in the database 20.

[0080] After the processing of steps S51 to S53 and steps S54 to S56 above is completed, in step S57, the risk determination unit 17 constructs a model (risk determination model) for determining the contact risk with the power facility (for example, transmission lines and distribution lines). Specifically, for example, the risk determination unit 17 constructs a risk determination model for "wide-area judgment" that determines the contact risk in the wide-area range between the power facility and the vegetation using the wide-area vegetation distribution at the specific time calculated in step S53, and constructs a risk determination model for "detailed judgment" that determines the detailed contact risk between the power facility and the vegetation using the vegetation amount three-dimensional estimation model at the specific time estimated in step S56. Various methods can be adopted for the model construction method of the risk determination model. An example image of the risk determination model is shown in FIG. 14 described later.

[0081] In step S58, the risk determination unit 17 calculates the contact risk between the vegetation and the power facility at a specific time using the risk determination model constructed in step S57, and stores the determination result (risk determination result) in the database 20. In step S58, the risk determination unit 17 first performs a wide-area contact risk determination using the risk determination model for wide-area determination. For a location (risk location) where it is estimated that the vegetation and the power facility are likely to come into contact in this determination, a more detailed contact risk determination is performed using the risk determination model for detailed determination (see FIG. 14). In this way, the risk determination unit 17 can accurately determine (calculate) the contact risk between the vegetation and the power facility by considering the evaluation results of both wide-area determination and detailed determination.

[0082] FIG. 14 is a diagram showing an example of the risk determination model. FIG. 14(A) shows an image diagram of the risk determination model 250 for wide-area determination, and FIG. 14(B) shows an image diagram of the risk determination model 260 for detailed determination.

[0083] The risk determination model 250 for wide-area determination in FIG. 14(A) is constructed based on the wide-area vegetation distribution at a specific time calculated in step S53. Specifically, it has a vegetation range 251 based on the prediction result of wide-area vegetation growth (see FIG. 8) and a transmission line 252 based on the geographical information of the power facility included in the remote sensing data (mapping data). And when performing the wide-area contact risk determination, the risk determination unit 17 uses the above risk determination model 250 to estimate a location (risk location 253) where the vegetation and the power facility are likely to come into contact.

[0084] The risk determination model 260 for detailed determination in FIG. 14(B) is constructed based on the vegetation amount estimation three-dimensional model at a specific time calculated in step S56. Specifically, it has a power facility 261 and vegetation 262 based on the time-series vegetation amount by vegetation growth simulation included in the estimated three-dimensional model. In FIG. 14(B), the simulation result of the tree crown (see FIG. 10) is reflected as the vegetation 262 based on the time-series vegetation amount. However, other elements (for example, tree height, wind speed, lodging, etc.) can also be reflected in the risk determination model 260. Then, when performing the contact risk determination for detailed determination, the risk determination unit 17 uses the risk determination model 260 corresponding to the location of the risk location 253 estimated to have a high contact risk in the wide-area determination, and estimates in detail the situation where the vegetation and the power facility may come into contact at the risk location 253. For example, in the case of FIG. 14(B), it can be estimated that there is a possibility of contact with the utility pole due to the lodging of the vegetation, or there is a possibility of contact with the distribution line due to the influence of the wind. Note that the determination method of the contact risk determination is not limited to the above example, and other widely known methods may be used.

[0085] FIG. 15 is a flowchart showing an example of the processing procedure of the two-dimensional visualization process. As described above, the two-dimensional visualization process is one of the visualization processes in step S8 of FIG. 3 and is mainly executed by the visualization unit 18. However, as will be described later in the description of each process, it is not necessarily required that the visualization unit 18 execute all the processes, and the processes by other functional units may be used as appropriate. This is the same for the three-dimensional visualization process described in FIG. 17.

[0086] According to FIG. 15, first, the visualization unit 18 acquires and inputs mapping data including the geographical information of the power facility, the vegetation classification map, and the prediction result of the wide-area vegetation growth from the database 20 (step S61).

[0087] Next, the visualization unit 18 generates a wide-area vegetation distribution at a specified time (or a specified time interval) using the prediction result of the wide-area vegetation growth acquired in step S61 (step S62).

[0088] Next, based on the wide-area vegetation distribution generated in step S62, the visualization unit 18 performs a contact risk determination to evaluate the contact risk between the vegetation in the target area and the power facilities at a specified time (or specified time interval), and generates the risk determination result (step S63). Note that for the processing of steps S61 to S63, after giving the specified time, the risk determination unit 17 may be made to calculate the wide-area vegetation distribution at a specific time and perform the contact risk determination for the wide-area judgment, and the visualization unit 18 may acquire the determination result.

[0089] Finally, the visualization unit 18 displays the risk determination result obtained in step S63 on a two-dimensional map representing the target area at the specified time (step S64). More specifically, for example, it displays a highlight of the contact situation and contact locations (risk locations) where the vegetation and the power facilities are likely to come into contact at the specified time on the two-dimensional map. Also, when a time interval is specified as the specified time by the user, it displays, as a moving image, how the contact situation and risk locations change over time at the specified time interval.

[0090] FIG. 16 is a diagram for explaining the image of two-dimensional visualization. In FIG. 16, when the specific times (specified times) specified by the user are t1, t2, and t3, two-dimensional maps 270 at each time displayed by the two-dimensional visualization process are illustrated. Each two-dimensional map 270 shows the vegetation range 271 and the transmission line 272 (an example of a power facility) at each specified time. Among these, in the case where it is determined by the contact risk determination that there is a possibility that the vegetation range 271 and the transmission line 272 come into contact at time t3, as an example, a risk location 273 is displayed, so that the contact situation and contact location are clearly shown. Note that when the time interval from t1 to t3 is specified by the user, a moving image showing the change in the contact situation and risk locations at the specified time interval (time resolution) may be displayed.

[0091] By performing the two-dimensional visualization process in this way, the visualization unit 18 can display the determination result of the contact risk determination for the wide-area judgment at the specified time in an easy-to-understand manner to the user.

[0092] FIG. 17 is a flowchart showing an example of a processing procedure for three-dimensional visualization processing. As described above, the three-dimensional visualization processing is one of the visualization processes in step S8 of FIG. 3 and is mainly executed by the visualization unit 18.

[0093] According to FIG. 15, first, the visualization unit 18 acquires and inputs a three-dimensional model of the power facility and vegetation from the database 20 (step S71).

[0094] Next, the visualization unit 18 uses the time-series vegetation amount, which is the simulation result of the vegetation amount by the vegetation amount prediction process, to estimate how the vegetation amount changes in the target area at a specified time (or specified time interval) in the three-dimensional model acquired in step S71 (step S72). By the process of step S72, a three-dimensional model for estimating the vegetation amount at a specific time is generated.

[0095] Next, the visualization unit 18 performs a contact risk determination to evaluate the contact risk between the vegetation and the power facility at a specified time (or specified time interval) based on the three-dimensional model generated in step S72, and generates the risk determination result (step S73). Note that the processes of steps S71 to S63 may be performed by causing the risk determination unit 17 to estimate the three-dimensional model for estimating the vegetation amount at a specific time and perform a detailed contact risk determination after giving a specified time, and the visualization unit 18 may acquire the determination result.

[0096] Finally, the visualization unit 18 displays the risk determination result obtained in step S73 on a three-dimensional model representing the target area at the specified time (step S74). More specifically, for example, a highlight of a contact situation and a contact location (risk location) where the vegetation and the power facility are likely to come into contact at the specified time is displayed on the three-dimensional model. Also, when a time interval is specified as the specified time by the user, a moving image is displayed showing how the contact situation and the risk location change with the passage of time at the specified time interval.

[0097] FIG. 18 is a diagram for explaining an image of three-dimensional visualization. In FIG. 18, when the specific times (designated times) specified by the user are times t1, t2, and t3, three-dimensional models 280 at each time displayed by three-dimensional visualization processing are collectively illustrated. Specifically, in the three-dimensional model 280, a tree crown 281 is shown as an example of the simulation result of vegetation at each designated time, and a transmission line 282 and a utility pole 283 are shown as examples of power facilities. Among these, at time t3, as an example when it is determined by contact risk determination that there is a possibility of contact between the tree crown 281 and the transmission line 282, a risk location 284 is displayed, so that the contact situation and the contact location are clearly shown. Note that when the time intervals from t1 to t3 are specified by the user, a moving image showing the variation of the contact situation and the risk location may be displayed at the specified time interval (time resolution).

[0098] By performing the three-dimensional visualization processing in this way, the visualization unit 18 can clearly display the determination result of the contact risk determination for detailed determination at the designated time to the user. As a derivative example in the present embodiment, the display of the determination result of the contact risk determination for wide-area determination at the designated time may also be performed by the three-dimensional visualization processing in FIG. 17 instead of the two-dimensional visualization processing in FIG. 15. However, when processing a three-dimensional model, the processing load increases compared to when processing a two-dimensional map, so the analysis cost increases.

[0099] FIG. 19 is a flowchart showing an example of the processing procedure of the maintenance instruction processing. As described above, the maintenance instruction processing corresponds to the processing in step S9 of FIG. 3 and is executed by the maintenance instruction unit 19.

[0100] According to FIG. 19, first, the maintenance instruction unit 19 acquires and inputs remote sensing data from the database 20 (step S81). Examples of the remote sensing data acquired in step S81 include satellite images, drone images, in-vehicle camera images, etc., but other data may also be used.

[0101] Next, the maintenance instruction unit 19 checks the determination result of the contact risk determination using the remote sensing data acquired in step S81 (steps S82, S83).

[0102] Specifically, in step S82, the maintenance instruction unit 19 checks the wide-area contact risk. Specifically, the maintenance instruction unit 19 checks the wide-area risk location calculated by the wide-area determination contact risk determination in the risk determination process (see FIG. 13) (for example, the risk location 253 in FIG. 14(A)), and the wide-area risk situation visualized by the two-dimensional visualization process (see FIG. 15) (for example, the situation around the risk location 273 at time t3 in FIG. 16), and selects an area of interest where a wide-area contact risk is predicted between the power facility and the vegetation. The selection of the area of interest may be made using a threshold based on the quantification of the risk value, but other methods may also be used.

[0103] Then, in step S83, the maintenance instruction unit 19 checks the detailed contact risk for the area of interest selected in step S82. Specifically, the maintenance instruction unit 19 checks the detailed risk location calculated by the detailed determination contact risk determination in the risk determination process (see FIG. 13) (for example, the contact location on the utility pole due to toppling in FIG. 14(B)), and the detailed risk situation visualized by the three-dimensional visualization process (see FIG. 17) (for example, the situation around the risk location 284 at time t3 in FIG. 18), and identifies a detailed area where a contact risk is predicted between the power facility and the vegetation. The identification of the detailed area may be determined using a threshold based on the quantification of the risk value, but other methods may also be used.

[0104] After the processes of steps S82 and S83, the maintenance instruction unit 19 obtains the management data corresponding thereto from the database 20 based on the risk determination results confirmed in steps S82 and S83 and the detailed areas specified in step S83, and determines the instruction content of the necessary maintenance work (step S84). The instruction content of the maintenance work determined in step S84 can include, for example, identification of the maintenance location, optimization of vehicle allocation, business trip plans for personnel, transportation of equipment, etc. Also, the method for determining the instruction content of the maintenance work is not limited to a specific method. For example, the identified risk locations (detailed areas) can be listed, and the routes and times for personnel dispatch and equipment transportation associated with the maintenance work can be optimized from the registered content of the list. Then, in step S84, the maintenance instruction unit 19 outputs the determined instruction content of the maintenance work from a predetermined output device (such as a liquid crystal display or a printer). A specific image of the maintenance work instruction is illustrated in FIG. 20.

[0105] FIG. 20 is a diagram showing an example of the display output of the maintenance instruction. The maintenance instruction screen 290 shown in FIG. 20 is an output example of the instruction content of the maintenance work output in step S84 of FIG. 19, and is a display screen displayed on the display device (not shown) of the vegetation management system 1.

[0106] The maintenance instruction screen 290 in FIG. 20 shows an office, two equipment warehouses (Equipment Warehouse 1-2), and four risk locations (Risk Location 1-4). When determining the instruction content of the maintenance work (step S84 in FIG. 19), the maintenance instruction unit 19 searches for the optimal routes for personnel dispatch and equipment transportation with reference to the positions of the office and the equipment warehouses for each risk location. Further, the maintenance instruction unit 19 estimates the maintenance time at each risk location by performing calculations considering the travel time and the maintenance work time, and displays the instructions for the route and time together on the maintenance instruction screen 290. Specifically, in the case of FIG. 20 and the maintenance instruction screen 290, the schedules for the movement to and the implementation of the maintenance work at each risk location are scheduled for April 12th or April 13th, and the routes for personnel dispatch and equipment transportation are represented by lines with arrows. Note that such instruction content of the maintenance work varies depending on the number and positions of the risk locations, the positions of the office and the warehouses, etc.

[0107] In addition, in the output of the maintenance work instruction content, the visualization display of the risk location and the contact status may be performed for each risk location by using the processing results of two-dimensional visualization processing or three-dimensional visualization processing.

[0108] As described above with reference to the respective drawings, according to the vegetation management system 1 according to the present embodiment, by utilizing remote sensing data that can photograph a wide area from a distance, discrimination of vegetation types (vegetation classification), prediction of vegetation growth in a wide area (wide-area vegetation growth prediction), prediction of temporal variation of vegetation growth for each vegetation by growth simulation (temporal series vegetation amount prediction), generation of a three-dimensional model of vegetation and facilities (three-dimensional model construction), etc. can be executed. Furthermore, based on these execution results, it is possible to determine the risk of contact between vegetation and facilities (for example, power facilities). Therefore, even when facilities are installed in places where it is difficult for people to enter, such as mountainous areas, an effect of accurately and inexpensively realizing the analysis of contact risks for a wide area can be obtained. In particular, when generating a three-dimensional model of the vegetation amount, by performing growth simulation and making predictions, it is possible to expect an effect of suppressing costs at each stage compared to the case of generating a three-dimensional model using remote sensing data obtained by actually photographing the vegetation.

[0109] In addition, according to the vegetation management system 1 according to the present embodiment, in the determination of the contact risk between vegetation and facilities, after specifying a wide-area risk location by wide-area judgment, detailed judgment is performed on the risk location. Therefore, a more accurate evaluation can be performed on the location where the contact risk exists and its contact status. Furthermore, the wide-area judgment can suppress the overall cost by using a relatively low-cost two-dimensional model (two-dimensional map) without using a relatively high-cost three-dimensional model.

[0110] In addition, according to the vegetation management system 1 according to the present embodiment, since the determination result of the contact risk by wide-area judgment and detailed judgment can be visualized in two dimensions or three dimensions, it is possible to easily visually judge the contact status of the location where there is a contact risk.

[0111] Further, according to the vegetation management system 1 according to the present embodiment, based on the determination result of the contact risk by the wide-area determination and the detailed determination, the work content of the necessary maintenance work can be determined, and an instruction for the maintenance work can be output, so that a low-cost and accurate instruction for the maintenance work can be realized. Furthermore, when determining the work content of the maintenance work, by integrating and comprehensively judging the information on a plurality of risk locations, the introduction routes of personnel and equipment can be optimized, and a more efficient instruction for the maintenance work can be realized.

[0112] Note that the present invention is not limited to the above-described embodiments, and various modifications are included. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described. Also, a part of the configuration of one embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of one embodiment. Also, for a part of the configuration of an embodiment, addition, deletion, or replacement with other configurations is possible.

[0113] In addition, each of the above configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them, for example, by an integrated circuit. Also, each of the above configurations, functions, etc. may be realized in software by a processor interpreting and executing a program for realizing each function. Information such as a program, table, and file for realizing each function can be placed in a memory, a recording device such as a hard disk or an SSD (Solid State Drive), or a recording medium such as an IC (Integrated Circuit) card, an SD card, or a DVD (Digital Versatile Disc).

[0114] Also, in the drawings, control lines and information lines show those considered necessary for explanation, and not necessarily all control lines and information lines on the product are shown. In reality, it may be considered that almost all configurations are interconnected.

Description of Symbols

[0115] 1 Vegetation Management System 1a CPU 1b RAM 1c Storage Device 2 Remote Sensing Observation Device 10 Input Data 10a Remote Sensing Image Data 10b Spectrum Library Data 10c Geographic Information Data 10d Environmental Information Data 10e Management Information Data 11 Data Acquisition Unit 11a Remote Sensing Image Data Acquisition Unit 11b Geographic Information Data Acquisition Unit 11c Environmental Information Data Acquisition Unit 11d Management Information Data Acquisition Unit 12 Database Generation Unit 13 Vegetation Classification Unit 14 Wide Area Growth Prediction Unit 15 Vegetation Quantity Simulation Unit 16 Three-Dimensional Construction Unit 17 Risk Judgment Unit 18 Visualization Unit 19 Maintenance Instruction Unit 20 Database 201 Remote Sensing Data 202 Spectrum Library 203 Geographic Data 204 Environmental Data 205 Management Data 211 Pre-Classification Map Image 212 Vegetation Classification Map Image 220, 270 Two-Dimensional Map 221, 251, 271 Vegetation Range 231, 281 Tree Canopy 240, 280 Three-Dimensional Model 241, 252, 272, 282 Transmission Line 242, 262 Vegetation 250,260 Risk Judgment Model 253,273,284 Risk Location 261 Power Facility 283 Utility Pole 290 Maintenance Instruction Screen

Claims

1. A vegetation management system that analyzes the contact between the vegetation and the facility using remote sensing data obtained by remotely sensing the facility and vegetation to be analyzed, comprising: a data acquisition unit that acquires input data including at least the remote sensing data, geographical data of the facility, and environmental data related to the growth of the vegetation; a vegetation classification unit that classifies the vegetation captured in the remote sensing data; a wide-area growth prediction unit that predicts the temporal change in the growth range of the vegetation captured in the remote sensing data based on the vegetation classified by the vegetation classification unit; a vegetation amount simulation unit that predicts the variation in the growth amount of each vegetation classified by the vegetation classification unit by simulation; a three-dimensional construction unit that constructs a three-dimensional model representing the facility and the vegetation based on the remote sensing data and the geographical data; a risk determination unit that determines a contact risk indicating the possibility of contact between the facility and the vegetation based on the processing results of the wide-area growth prediction unit, the vegetation amount simulation unit, and the three-dimensional construction unit; and the vegetation classification unit estimates the type of vegetation from the spectral features of the vegetation by machine learning of a spectral library associated with the target area. The vegetation management system is characterized by this.

2. a visualization unit that generates a visualization model for visualizing the positional relationship and contact risk between the facility and the vegetation; a maintenance instruction unit that determines the maintenance work necessary to eliminate the contact risk based on the determination result of the contact risk by the risk determination unit and the visualization model generated by the visualization unit, and outputs the content of the determined maintenance work. The vegetation management system according to claim 1, further comprising: This is the feature.

3. The risk determination unit a wide-area judgment that evaluates the contact risk between the facility and the vegetation in a relative wide area using the prediction result of the temporal change in the growth range of the vegetation by the wide-area growth prediction unit; a detailed judgment that evaluates the contact risk between the facility and the vegetation at the location where the contact risk is evaluated to exist in the wide-area judgment using the prediction result of the variation in the growth amount of each vegetation by the vegetation amount simulation unit; is executed step by step The vegetation management system according to claim 1, characterized by this.

4. In the wide-area determination, a two-dimensional risk determination model that reflects the prediction results of the time-series changes in the growth range of vegetation by the wide-area growth prediction unit is used for the two-dimensional map obtained by incorporating the geographical data of the facility into the remote sensing data. The vegetation management system according to claim 3, characterized in that.

5. In the detailed determination, a three-dimensional risk determination model that reflects the prediction results of the fluctuations in the growth amount of each vegetation by the vegetation amount simulation unit is used for the three-dimensional model constructed by the three-dimensional construction unit. The vegetation management system according to claim 3, characterized in that.

6. The vegetation amount simulation unit uses the environmental data, the growth model for each vegetation held in advance, and the classification result of the vegetation by the vegetation classification unit to simulate the fluctuations in the growth amount of each vegetation. The vegetation management system according to claim 1, characterized in that.

7. The vegetation management system further includes a database for storing various input data, intermediate data, and output data input or generated in the vegetation management system. The vegetation management system according to claim 2, characterized in that.

8. A vegetation management method by a vegetation management system that analyzes the contact of the vegetation with respect to a facility using remote sensing data obtained by photographing the facility and vegetation to be analyzed by remote sensing, A data acquisition step of acquiring input data including at least the remote sensing data, the geographical data of the facility, and environmental data related to the growth of the vegetation; A vegetation classification step of classifying the vegetation photographed in the remote sensing data; A wide-area growth prediction step of predicting the time-series changes in the growth range of the vegetation photographed in the remote sensing data based on the vegetation classified in the vegetation classification step; A vegetation amount simulation step of predicting the fluctuations in the growth amount of each vegetation classified in the vegetation classification step by simulation; A three-dimensional construction step of constructing a three-dimensional model representing the facility and the vegetation based on the remote sensing data and the geographical data; A risk determination step of determining a contact risk indicating the contact possibility between the facility and the vegetation based on the processing results of the wide-area growth prediction step, the vegetation amount simulation step, and the three-dimensional construction step; Comprising The vegetation classification step includes a step of estimating the type of vegetation from the spectral features of the vegetation by machine learning of a spectral library associated with the target area, and is characterized as a vegetation management method.

9. A visualization step of generating a visualization model for visualizing the positional relationship between the facility and the vegetation and the contact risk; Based on the determination result of the contact risk by the risk determination step and the visualization model generated in the visualization step, determining the maintenance work necessary to eliminate the contact risk and outputting the content of the determined maintenance work, further comprising a maintenance instruction step. The vegetation management method according to claim 8, characterized in that.

10. In the risk determination step, A wide-area determination for evaluating the contact risk between the facility and the vegetation in a relative wide-area range using the prediction result of the time-series change of the growth range of the vegetation by the wide-area growth prediction step; A detailed determination for evaluating the contact risk between the facility and the vegetation at a location where the contact risk is evaluated in the wide-area determination using the prediction result of the variation in the growth amount of each vegetation by the vegetation amount simulation step; Is executed step by step The vegetation management method according to claim 8, characterized in that.

11. In the wide-area determination, a two-dimensional risk determination model reflecting the prediction result of the time-series change of the growth range of the vegetation by the wide-area growth prediction step is used in a two-dimensional map obtained by incorporating the geographical data of the facility into the remote sensing data. The vegetation management method according to claim 10, characterized in that.

12. In the detailed determination, a three-dimensional risk determination model reflecting the prediction result of the variation in the growth amount of each vegetation by the vegetation amount simulation step is used in the three-dimensional model constructed in the three-dimensional construction step. The vegetation management method according to claim 10, characterized in that.

13. In the vegetation amount simulation step, the variation in the growth amount of each vegetation is simulated using the environmental data, a growth model for each vegetation held in advance, and the classification result of the vegetation by the vegetation classification step. The vegetation management method according to claim 8, characterized in that.

14. A storage step of storing various input data, intermediate data, and output data input or generated in the vegetation management system in a database of the vegetation management system, further comprising. The vegetation management method according to claim 9, characterized in that.

Images