Vegetation management system and vegetation management method

Abstract

[Problem to be solved] To predict the influence of vegetation on features with high accuracy. [Solution] A vegetation management system that manages the influence of vegetation on predetermined features, the vegetation management system comprising: an acquisition unit that acquires remote sensing image data of vegetation; the classification unit is used for classifying trees included in vegetation according to the growth vitality representing the future growth potential on the basis of the remote sensing image data; a growth prediction unit that predicts the growth of the tree on the basis of the classification result obtained by the classification unit; a risk determination unit that determines a risk of contact with the predetermined feature; and a visualization unit that outputs and visualizes the determination result obtained by the risk determination unit.

Description

Technical Field

[0001] The invention relates to a vegetation management system and a vegetation management method. Background Art

[0002] Traditional vegetation management systems used to maintain power facilities predict vegetation growth to prevent contact with power lines. In vegetation growth prediction, detailed tree species are essential basic information.

[0003] Regarding the estimation of detailed tree species, a technique is described in Japanese Patent Laid-Open No. 2019-144607 (Patent Document 1). The patent document includes the following description, for example: "Capturing an image of the ground to be analyzed via a satellite; generating a panchromatic image including trees; automatically extracting trees from the generated panchromatic image according to image features; encircling the trees with circles; calculating a co-occurrence matrix in the inner area of ​​the extracted circles; obtaining multispectral normalized data at the center of the circles; performing normalization processing; comparing the extracted trees with teacher data; creating a tree species estimation model using a multivariate analysis model; and estimating the species of trees extracted from the panchromatic image of the ground to be analyzed using the analysis model."

[0004] Recently, efforts are being made to automate survey work due to a shortage of manpower. Many power lines are installed in places that are difficult for people to reach, such as mountainous areas. Therefore, the focus is on remote sensing technology to remotely monitor the contact between trees and distribution lines or power lines. Typical remote sensing means are satellites or drones. In addition, research and development work is also underway to determine vegetation contact through three-dimensional measurement using LIDAR sensors.

[0005] Japanese Patent Laid-Open No. 2016-123369 (Patent Document 1) describes a technique related to determining vegetation growth using remote sensing image data. Patent Document 2 includes, for example, the following description: "A plant growth analysis system for analyzing plant growth based on remote sensing images, the plant growth analysis system comprising: a feature value calculation unit that calculates feature values ​​of plant growth based on a plant growth model, wherein changes in the recorded feature values ​​correspond to time information indicating the time elapsed from a predetermined time period for the plant, and an image corresponds to a plurality of growth positions of the plant, the image being a part of the remote sensing image; a growth difference correction unit that refers to the plant growth model and corrects the feature values ​​of the plurality of growth positions to feature values ​​corresponding to the reference time information; and an image generation unit that generates a new image so that the image corresponding to the plurality of growth positions that are a part of the remote sensing image shows the corrected feature values".

[0006] Reference List

[0007] [Patent Document 1] Japanese Patent Laid-Open No. 2019-144607

[0008] [Patent Document 2] Japanese Patent Laid-Open No. 2016-123369 Summary of the invention

[0009] Problems to be solved by the present invention

[0010] In traditional power facility maintenance work, workers regularly conduct field surveys along power facilities (e.g., distribution lines or transmission lines) and perform work such as branch removal or herbicide application in areas where problems may occur. In tree surveys, workers with tree expertise go to the site to inspect trees one by one to identify tree species and predict future growth risks. If a tree is found that is considered risky, the worker notifies the logging company. However, tree species identification is extremely difficult, and even experts often have difficulty determining it.

[0011] Methods using drones and helicopters are also beginning to be introduced. In these methods, a platform is developed for processing a large amount of geographic information data of different types and time series, and operation support is provided through operation and visualization. However, if the shooting area becomes wider or the shooting frequency increases, the cost will increase significantly.

[0012] There is also a method of generating a 3D tree map by 3D restoration of data obtained by LiDAR sensors. In this vegetation analysis using 3D maps, it is difficult to perform high-precision vegetation classification analysis and growth prediction due to the characteristics of the data. In addition, vegetation classification modeling itself is difficult because it is difficult to distinguish vegetation and the reliability of the calibration data is not high.

[0013] In view of the above, an important purpose is how to predict the impact of vegetation on power facilities with high accuracy. This purpose not only appears in power facilities, but also appears in another feature in the same way. Therefore, the purpose of the present invention is to predict the impact of vegetation on features with high accuracy.

[0014] Means of solving the problem

[0015] In order to achieve the above-mentioned purpose, one of the representative vegetation management systems of the present invention is a vegetation management system for managing the impact of vegetation on predetermined features, the vegetation management system comprising: an acquisition unit, which acquires remote sensing image data of the vegetation; a classification unit, which classifies trees included in the vegetation according to growth vitality representing future growth potential based on the remote sensing image data; a growth prediction unit, which predicts the growth of the trees based on the classification results obtained by the classification unit; a risk determination unit, which determines the risk of contact with the predetermined features; and a visualization unit, which outputs the determination results obtained by the risk determination unit and visualizes them.

[0016] Furthermore, one of the representative vegetation management methods of the present invention is a vegetation management method performed by a vegetation management system that manages the impact of vegetation on predetermined characteristics, the method comprising: obtaining, by the vegetation management system, remote sensing image data of the vegetation; based on the remote sensing image data, classifying the trees included in the vegetation according to growth vitality representing future growth potential; predicting the growth of the trees based on the classification results obtained by the classification; determining the risk of contact with the predetermined characteristics; and outputting the determination results obtained by determining the risk and visualizing them.

[0017] Advantageous Effects of the Invention

[0018] According to the present invention, the influence of vegetation on features can be predicted with high accuracy.In addition to the problems, configurations and effects described above, other problems, configurations and effects will become apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic diagram illustrating an example of the configuration of a vegetation management system for power facility maintenance in the first embodiment of the present invention.

[0020] Figure 2 is a configuration diagram illustrating the hardware configuration of the vegetation management system in the first embodiment.

[0021] Figure 3 is a flowchart for explaining the processing of the entire system 100 in the first embodiment.

[0022] Figure 4 is a flowchart for explaining the processing of the dead tree extraction unit in the first embodiment.

[0023] Figure 5 is a flowchart for explaining the processing of the tree height estimation unit in the first embodiment.

[0024] Figure 6is a flowchart for explaining the processing of the tree crown extraction unit in the first embodiment.

[0025] Figure 7 is a flowchart for explaining the processing of the time series analysis unit in the first embodiment.

[0026] Figure 8 It is a flowchart for explaining the processing of the vegetation classification unit in the first embodiment.

[0027] Fig. 9 is a flowchart for explaining the processing of the growth prediction unit in the first embodiment.

[0028] Fig.10 is a flowchart for explaining the processing of the risk determination unit in the first embodiment.

[0029] Fig.11 is a schematic diagram illustrating the processing of the dead tree extraction unit in the first embodiment.

[0030] Fig.12 is a schematic diagram illustrating the processing of the tree height estimation unit in the first embodiment.

[0031] Fig.13 2 is a schematic diagram illustrating the processing of the tree crown extraction unit in the first embodiment.

[0032] Fig.14 is a schematic diagram illustrating the processing of the vegetation classification unit in the first embodiment.

[0033] Fig.15 is a schematic diagram illustrating an intrusion risk process of the risk determination unit in the first embodiment.

[0034] Fig.16 2 is a schematic diagram illustrating a lodging risk process of the risk determination unit in the first embodiment.

[0035] Fig.17 is a schematic diagram illustrating a fly-out risk process of the risk determination unit in the first embodiment.

[0036] Fig.18 is a schematic diagram illustrating a database in the first embodiment.

[0037] Fig.19 is an example of a GUI schematic diagram illustrating visualization and maintenance instructions in the first embodiment.

[0038] Fig. 20 is an example of a schematic diagram illustrating a maintenance instruction in the first embodiment.

[0039] Fig.21is a flowchart for explaining the processing of the maintenance instructing unit in the first embodiment. DETAILED DESCRIPTION

[0040] Hereinafter, embodiments will be described with reference to the accompanying drawings.

[0041] First embodiment

[0042] Hereinafter, a first embodiment of a vegetation management system and method for power facility maintenance to which the present invention is applied will be described.

[0043] First, an overview will be given. The vegetation management system disclosed in the embodiments uses measurement information such as remote sensing information, geographic information, and environmental information to generate a height map of a vegetation area, extract tree crowns from the height map, perform vegetation classification, perform growth prediction based on the classification results, and determine the contact risk and damage risk of power facilities.

[0044] For vegetation growth prediction, there is a bottleneck in the traditional classification of detailed tree species. Traditional classification uses the order, family, etc. to which trees belong in botany. Therefore, it is difficult to determine the detailed species of trees.

[0045] The disclosed system provides a new tree classification method to solve the traditional bottleneck problem. Specifically, the disclosed system classifies trees according to actual tree vitality (the degree of future growth potential). The embodiment shows an example in which trees are classified into "dead trees (no vitality)", "slow-growing trees (low vitality)", "fast-growing trees (medium vitality)" and "special-growing trees (high vitality)" according to vitality. When classifying by tree vitality, estimation is performed by analyzing remote sensing data and introducing a machine learning model.

[0046] Furthermore, in the present invention, different criteria are used to predict growth and determine contact with the power lines based on vitality.

[0047] Figure 11 is a block diagram illustrating the configuration of a vegetation management system 100 for power facility maintenance in a first embodiment. The vegetation management system 100 for power facility maintenance includes a plurality of different data 101 (remote sensing image data 101a, vegetation information data 101b, geographic information data 101c, environmental information data 101d, and management information data 101e), a remote sensing data acquisition unit 102, a geographic information acquisition unit 103, an environmental information acquisition unit 104, a management information acquisition unit 105, a database generation unit 106, a dead tree extraction unit 107, a tree height estimation unit 108, a crown extraction unit 109, a time series analysis unit 110, a vegetation classification unit 111, and a growth prediction unit 112. The vegetation management system 100 acquires time series remote sensing image data, vegetation information data, geographic information data, and environmental data for observing vegetation, and provides these data to a database 116. Note that the remote sensing image data, vegetation information, geographic information data, and environmental data will be referred to as “remote sensing image data”. Figure 1 is described, and the database will refer to Fig.18 Give a description.

[0048] The vegetation management system 100 provides the data managed in the database 116 to the risk determination unit 113 to determine the contact risk between the power facility and the vegetation, and enables the visualization unit 114 to visualize the contact risk. In addition, the vegetation management system 100 provides the information stored in the risk determination unit 113 and the visualization unit 114 to the maintenance instruction unit 115, and uses the information for facility maintenance support.

[0049] Figure 2 The diagram shows the overall hardware status of the vegetation management system described above. The remote sensing observation device 120 captures remote sensing images. The remote sensing observation device 120 is not limited to any specific type of device and can be, for example, a photographing device of an observation satellite or an aircraft. In this embodiment, a satellite image captured by an observation satellite will be described. The computer system 121 acquires remote sensing image data and uses it as Figure 1 The vegetation management system 100 in the computer system 121 is operated. The computer system 121 has a typical hardware configuration, including a CPU, a RAM, a storage unit, and the like.

[0050] Return to Figure 1 The explanation continues. The remote sensing image data 101a is image data obtained from a remote sensing sensor and any aerial photograph. Note that although the time series low-resolution and high-resolution remote sensing images are described as different remote sensing images in this embodiment, the type of data is not limited to any specific type. In addition, time series images in the same remote sensing image can also be used. Note that the difference in resolution is based on relative comparison.

[0051] The vegetation information data 101b is vegetation distribution information, spectrum information, species information, tree crown height information, etc., and the type of data is not limited to any specific type.

[0052] Vegetation distribution information is information on latitude and longitude, distribution shape position, and the like.

[0053] Spectral information is spectral or spatial information (color or shape) obtained by an optical sensor. In particular, an optical sensor is a passive sensor that uses light from an object to be observed to obtain information. Like a camera, an optical sensor basically has the same structure and function as an eye (naked eye), and an optical system (lens) such as a lens collects light from an object and forms an image on a detection system (retina). Especially for the spectrum (color), the eye can only capture visible light, while an optical sensor can detect light in a larger wavelength range from visible light to infrared. This makes it possible to obtain a lot of useful information, such as identifying minerals and vegetation that cannot be identified by the eye, ground temperature, land use, and water and plankton resources in oceans, lakes, and swamps. These can also be obtained as two-dimensional images over a large range. Vegetation species data and tree height data are data obtained through field sampling and actual measurement.

[0054] The geographic information data 101c is data necessary for sharing local data and satellite data, such as polygon data and location information data. Examples of the environmental information data 101d include soil data, meteorological data, altitude data, gradient data, and many other data. Examples of meteorological data include various data such as AMeDAS data, MODIS surface temperature satellite data, and weather bureau data, but the type of data is not limited to any specific type. The management information data 101e is operation data such as power company operation and maintenance memos, logs, and histories. Other data may be used.

[0055] The remote sensing data acquisition unit 102, the geographic information acquisition unit 103, the environmental information acquisition unit 104, the management information acquisition unit 105, the database generation unit 106, the dead tree extraction unit 107, the tree height estimation unit 108, the crown extraction unit 109, the time series analysis unit 110, the vegetation classification unit 111, the growth prediction unit 112, the risk determination unit 113 and the visualization unit 114 are implemented as a combination of a plurality of CPUs and RAMs divided according to roles to perform various arithmetic processing. Each of the units described above adopts a hard disk, a USB memory, etc. as an external storage device.

[0056] Figure 31 is a flowchart for explaining an example of the processing of the entire vegetation management system 100 for power facility maintenance in the first embodiment. First, in S302, the vegetation management system 100 inputs the acquired remote sensing image data and vegetation information data as different data into the remote sensing data acquisition unit 102. The geographic information data is input into the geographic information acquisition unit 103. The environmental information data is input into the environmental information acquisition unit 104. In the present embodiment, the environmental information mainly includes meteorological data, but the environmental information may also include other data. The meteorological data includes air temperature, rainfall, and sunshine, but the meteorological data may also include other data. The management information data is input into the management information acquisition unit 105. In the present embodiment, the management information data includes a monitoring log, a logging log, a maintenance location, and a time history, but the management information data may also include other data.

[0057] At S303, the vegetation management system 100 provides all input data to the database generation unit 106. The geographic information data includes location information and shape information, and the remote sensing data is masked based on the location and shape. The masked part is extracted, and this part of the remote sensing data and environmental data is generated by the database generation unit, and the data is provided to the database 112. The management information data is provided to the database 116.

[0058] In S304, the vegetation management system 100 extracts dead tree areas from the remote sensing image data, vegetation geographic information data and vegetation information data stored in the database 116, and provides the map of the extracted dead tree areas to the database 116. The extraction method will be described in the description of the dead tree extraction unit 107.

[0059] In S305, using the geographic information data of classified vegetation, remote sensing image data showing a digital surface model, multi-band satellite image data, meteorological data, altitude model data, etc. stored in the database 116, the vegetation management system 100 removes the dead tree area map extracted by the dead tree extraction unit 107 stored in the database 116, constructs a model for estimating the crown height of the vegetation area, and provides the crown height map of the vegetation area together with the model to the database 116. The details of the model construction and height estimation method will be further described below.

[0060] In S306, the vegetation management system 100 extracts the tree crowns of the vegetation using the tree crown height map of the vegetation area stored in the database 116, and provides geographic information data of the tree crown results to the database 116. The details of the extraction method will be further described below.

[0061] In S307, using the results of multiple executions of the time series-based processes S305 and S306, the vegetation management system 100 calculates tree crown changes and tree height changes, and provides the calculation results to the database 116. The details of the time series analysis method will be further described below.

[0062] In S308, the vegetation management system 100 classifies trees based on tree growth vitality using the tree crown changes and tree height changes stored in the database 116, and provides geographic information data of the classification results to the database 116. Details of the classification method will be further described below.

[0063] In S309, using the tree species information stored in the database 116, the vegetation management system 100 constructs different growth prediction models based on different species, predicts future growth, and provides the predicted future tree height and crown size to the database 116. The details of the growth prediction method based on different species will be further described below.

[0064] In S310, using the geographic information data of the predicted vegetation growth results (i.e., the predicted tree crown size and tree height data) and the power facility geographic information data, the vegetation management system 100 evaluates the two-dimensional positional relationship between the time series changes in the vegetation over a wide range and the power facilities, and uses the physical models of invasion risk, flyout risk, and lodging risk to evaluate the three-dimensional positional relationship between the time series changes in the vegetation tree height and the power facilities. The vegetation management system 100 determines the risk of each classified power facility according to the tree growth vitality in consideration of the evaluation results, and provides the determination results to the database 116. The details of the risk determination model construction and calculation method will be further described below.

[0065] In S311, the vegetation management system 100 performs mapping on the remote sensing image using the geographic information data of the predicted vegetation growth results (i.e., the predicted tree crown size and tree height data), the power facility geographic information data, and the geographic information data of the risk determination results. Using the time series changes in vegetation growth and the risk determination results, a two-dimensional or three-dimensional display is performed at a specific time or at a specific time interval. The details of the visualization will be further described below.

[0066] In S312, the vegetation management system 100 waits for the analysis results and presents maintenance instructions using the management information data stored in the database 116. All data is stored in the database. Fig.18 shown.

[0067] The remote sensing data acquisition unit 102 acquires remote sensing image data 101 a , receives input of vegetation information data 101 b , and provides these data to the database generation unit 106 .

[0068] The geographic information acquisition unit 103 acquires the geographic information data 101 c and provides the acquired data to the database generation unit 106 .

[0069] The environmental information acquisition unit 104 acquires the environmental information data 101 d and provides the acquired data to the database generation unit 106 .

[0070] The management information acquisition unit 105 acquires the management information data 101 e and supplies the acquired data to the database generation unit 106 .

[0071] Then, the database generation unit 106 maps the remote sensing image data, vegetation information data, environment data, and geographic information data stored in the database 116 together.

[0072] The dead tree extraction unit 107 extracts a dead tree area using the mapping result generated by the database generation unit 106 . Figure 4 is a flowchart for explaining the processing of the dead tree extraction unit 107 in the first embodiment.

[0073] In S402 , the dead tree extraction unit 107 inputs the mapping data of the remote sensing image and the geographic information generated by the database generation unit 106 .

[0074] In S403, using remote sensing mapping data, vegetation information data and environmental data, the dead tree extraction unit 107 generates a model for determining an area corresponding to a dead tree within the mapping range of the remote sensing image data. As an example of a dead tree area determination model, a machine learning method is used to extract pixel-based spectral information of a target pixel, and texture information in a window range set within a specific range around the target pixel is calculated as a feature value. The spectral information includes, for example, R, G, B or infrared. Using different remote sensing images will produce different spectral information. Texture information indicates, for example, the texture, touch, pattern of the surface of an object. Texture analysis quantifies general textures such as roughness, smoothness, silk gloss or concave and convex according to the image spatial variation of pixel intensity. As an example of a calculation method, a GLCM matrix is ​​first calculated, and then the calculated GLCM matrix is ​​used to calculate feature values ​​such as entropy or energy. Texture information is not limited to GLCM, and another calculation method can be used. In this way, three categories of dead trees, healthy trees and grass can be learned, and a model can be generated using the feature values ​​of texture information within a specific range around the target pixel. Note that the classification category is not limited to these three categories, and can be a dead tree and another classification category.

[0075] In S404 , the dead tree extraction unit 107 extracts a dead tree region using the generated dead tree extraction model, and stores the extracted dead tree region in the database 116 .

[0076] In S405 , the dead tree extraction unit 107 converts the dead tree area stored in the database 116 into geographic information data, and provides the geographic information data to the database 116 . Fig.11 is a schematic diagram illustrating the results of dead tree areas. Fig.11 In the satellite image, the dead tree area is circled with a white frame. Fig.11 The area enclosed by a black frame is also shown in the figure. The area enclosed by the black frame is a dead tree area added to the generated image by, for example, an operator.

[0077] The tree height estimation unit 108 uses the generated dead tree area geographic information data to exclude dead tree areas, uses the remote sensing data and multi-band satellite images showing digital surface models stored in the database 116 to estimate the tree crown height in the corresponding vegetation area, and provides the tree crown estimation model together with the estimated height to the database 116.

[0078] Figure 5 1 is a flowchart for explaining the processing of the tree height estimation unit in the first embodiment. In S502 , the tree height estimation unit 108 inputs a multi-band satellite image of remote sensing data representing a digital surface model stored in the database 116 .

[0079] In S503 , the tree height estimation unit 108 inputs the generated geographical information data, environmental information data, and vegetation information data.

[0080] In S504 , the tree height estimation unit 108 inputs the generated dead tree area geographical information data.

[0081] In S505 , the tree height estimation unit 108 excludes the dead tree area from the geographical information data of the relevant dead tree area.

[0082] In S506, the tree height estimation unit 108 generates a crown height estimation model using the generated mapping of remote sensing image data, geographic information data, and environmental data. As an example of an estimation method, a random forest machine learning model can be used, and the value of a digital surface model can be used as a target variable, and spectral data, meteorological data, altitude data, vegetation data, etc. can be used as explanatory variables to construct a crown height estimation model. The tree height estimation unit 108 estimates the crown height using the constructed tree height estimation model. The estimation method can be another method.

[0083] In S507 , the tree height estimation unit 108 generates a tree height map using the generated tree crown height estimation model, and stores the tree height map in the database 116 . Fig.12 is a schematic diagram illustrating a tree height estimation process. A map image showing tree heights is generated from a normal satellite image, and changes in tree heights are shown by color changes from white to black.

[0084] The tree crown extraction unit 109 extracts the tree crowns of the trees using the tree height map within the vegetation area stored in the database 116 . Figure 6 is a flowchart for explaining the processing of the tree crown extraction unit in the first embodiment.

[0085] In S602 , the tree crown extraction unit 109 inputs a tree height map within the vegetation area stored in the database 116 .

[0086] In S603, the crown extraction unit 109 detects tree vertices using the tree height map in the vegetation area. The crown extraction unit 109 converts the detected vertices into point geographic information data and stores the point geographic information data in the database 116. As an example of a method for detecting tree vertices, the tree height map may be searched pixel by pixel, and the highest pixel point within a window range of a specific size may be detected as a tree vertex. The vertex detection method may be another method. The size of the search window is preset.

[0087] In S604 , the tree crown extraction unit 109 draws a tree crown polygon using the tree vertex geographic information data stored in the database 116 .

[0088] In S605 , the tree crown extraction unit 109 converts the drawn polygon into geographic information data, and provides the geographic information data to the database 116 . Fig.13 is a schematic diagram illustrating the crown extraction process. Fine crown polygons are extracted from the tree height map, converted to a shape file, and mapped.

[0089] The time series analysis unit 110 analyzes the time series remote sensing image data generated by the database generation unit 106 and calculates the tree crown size change and the vegetation height change using the tree crown extraction method and the vegetation area height estimation method stored in the database 116 .

[0090] Figure 7 is a flowchart for explaining the processing of the time series analysis unit in the first embodiment.

[0091] In S702 , the time series analysis unit 110 obtains the height at each time point in the time series.

[0092] In S703 , the time series analysis unit 110 calculates the tree crown size at each time point in the time series.

[0093] In S704 , the time series analysis unit 110 performs time series analysis on the calculated time series tree crown size data and time series height data.

[0094] In S705 , the time series analysis unit 110 calculates the height changes of the relevant trees and provides the height changes to the database 116 .

[0095] In S706 , the time series analysis unit 110 calculates the crown size changes of the relevant trees and provides the crown size changes to the database 116 .

[0096] The vegetation classification unit 111 performs vegetation classification by growth vitality indicating future growth potential using the crown size change rate and height change rate of relevant trees stored in the database 116 .

[0097] Figure 8 It is a flowchart for explaining the processing of the vegetation classification unit in the first embodiment.

[0098] In S802 , the vegetation classification unit 111 inputs the crown size change rate and height change rate of the relevant trees stored in the database 116 .

[0099] In S803, the vegetation classification unit 111 uses the input crown size change rate and height change rate of the relevant trees to determine the tree growth potential. An example of a method for determining the tree growth potential will be described. When the calculated crown size change rate and height change rate of a tree tend to decrease over time, the tree is likely to enter maturity and is therefore classified as a slow-growing tree. On the other hand, when the calculated crown size change rate and height change rate of a tree tend to increase over time, the tree is likely to be a small tree and is therefore classified as a fast-growing tree. The method for classification into fast growth and slow growth may be another method.

[0100] In S804, the vegetation classification unit 111 extracts special growth tree areas using the felling records and felling location information data stored in the management database.

[0101] In S805, using the dead tree area extracted by the dead tree extraction unit 107, the special growth tree area extracted in S804, the fast-growing tree area and the slow-growing tree area classified in S803, the vegetation classification unit 111 generates vegetation classification results according to growth vitality, and provides the vegetation classification results to the database 116. Fig.14 is a schematic diagram illustrating the vegetation classification process. The map is in polygonal format, where different tree species have different colors.

[0102] The growth prediction unit 112 uses the vegetation classification map stored in the database 116 and the remote sensing image data, environmental data and vegetation information data generated by the database generation unit 106 to predict the future growth of the corresponding species in different methods, and provides the future crown size and future height to the database 116.

[0103] Fig. 9 is a flowchart for explaining the growth prediction process in the first embodiment.

[0104] In S902 , the growth prediction unit 112 inputs a vegetation classification map stored in the database 116 .

[0105] In S903, the growth prediction unit 112 introduces different growth prediction methods for different vegetation categories. The growth prediction unit 112 refers to the vegetation classification map stored in the database 116, calculates the future growth of trees classified as dead trees, and provides the calculation results to the database 116 because the trees have no growth vitality and their growth is zero.

[0106] In S904, the growth prediction unit 112 generates a growth prediction model and predicts the future growth of trees classified as fast-growing trees and slow-growing trees. As an example of a growth prediction model, future growth is estimated using deep learning. Examples of eigenvalues ​​include height maps of time series analysis, spectral information calculated from remote sensing image data, and vegetation indices (e.g., NDVI) calculated from remote sensing image data. These are examples, and any eigenvalues ​​can be used. Examples of eigenvalues ​​may also include maps of meteorological data, environmental data, and terrain data generated by the database generation unit 106. The target variables are the height of the tree and the size of the crown after growth. For these data, ground truth data is obtained through field surveys, and a model is learned. Future height and crown size can be estimated based on the height map of time series analysis, and can be further corrected by deep learning. As an example of a prediction model, a recurrent neural network (RNN) is used, and time series changes are predicted. Based on the satellite images of the past time t1 and time t2, the wide range change at time t3 or later is predicted, the tree height map is generated based on the wide range map at time t3 or later, and the tree height change and the crown size are predicted. However, this is not a limitation, and another model may be used.

[0107] In S905, the growth prediction unit 112 inputs the growth rules stored in the management database and simulates the future growth of the trees classified as special growth trees by the prediction method. In S906, the growth prediction unit 112 converts the predicted future crown size and height into data in the geographic information data format and provides the converted data to the database 116.

[0108] The risk determination unit 113 determines the contact risk using the predicted tree growth state and the predicted crown size change and tree height change in consideration of the positional relationship with the power facility, and provides the contact risk to the database 116. Examples of contact risk include different physical models. Examples of contact risk include invasion risk, lodging risk, and fly-out risk. The risk determination unit 113 applies different physical models to different tree species classified by the vegetation classification unit.

[0109] Fig.10 is a flowchart for explaining the processing of the risk determination unit in the first embodiment.

[0110] In S1002 , the risk determination unit 113 inputs the generated vegetation classification map and the predicted tree crown size change and height change at a specific time.

[0111] In S1003, the risk determination unit 113 uses different physical models to perform risk determination for different tree species. The risk determination unit 113 refers to the vegetation classification map stored in the database 116 and determines the flying risk and the lodging risk of trees classified as dead trees. In addition, the risk determination unit 113 determines the invasion risk and the lodging risk of trees classified as fast-growing trees and slow-growing trees. In addition, the risk determination unit 113 determines the invasion risk of trees classified as special-growth trees.

[0112] The flying risk, intrusion risk and lodging risk will be described in S1004, S1006 and S1005 respectively.

[0113] In S1004, the risk determination unit 113 determines the fly-out risk based on the predicted tree crown size and height at a specific time. The fly-out risk is the risk of a dead tree flying in and coming into contact with power facilities due to strong winds, etc. The determination of the fly-out risk involves the strength and direction of the wind, and in the case of a mountain range, the direction and slope of the mountain range. These parameters are used to perform a dead tree fly-out simulation. When a dead tree is likely to come into contact with a power facility, it is highlighted for visualization. The risk determination unit 113 converts the detected high-risk area into geographic information data and provides the geographic information data to the database 116.

[0114] Fig.17 2 is a schematic diagram illustrating the fly-out risk processing of the risk determination unit in the first embodiment.

[0115] In S1005, the risk determination unit 113 determines the risk of lodging based on the predicted crown size and height at a specific time. In this determination, the predicted crown size and height changes and the positional relationship with the distribution line or transmission line are used to estimate the location with a high possibility of contact in the event of a lodging. As an example of an estimation method, the risk of lodging is determined using a three-dimensional model of the distribution line or transmission line and vegetation while taking into account the height of the trees and the area occupied by the fallen trees. The risk determination method is not limited to the method in the present embodiment and may be another method. The risk determination unit 113 converts the detected area with a high risk into geographic information data and provides the geographic information data to the database 116.

[0116] Fig.16 2 is a schematic diagram illustrating a lodging risk process of the risk determination unit in the first embodiment.

[0117] In S1006, the risk determination unit 113 determines the intrusion risk based on the predicted crown size and height at a specific time. In this determination, the predicted crown size and height changes and the positional relationship with the distribution line or transmission line are used to estimate the location with a high possibility of contact based on the size of the crown. As an example of an estimation method, the intrusion risk is determined using a three-dimensional model of the distribution line or transmission line and vegetation while taking into account the height of the tree and the area occupied by the tree whose crown has changed. The risk determination method is not limited to the method in the present embodiment and may be another method. The risk determination unit 113 converts the detected area with a high risk into geographic information data and provides the geographic information data to the database 116.

[0118] Fig.15 is a schematic diagram illustrating the intrusion risk processing of the risk determination unit in the first embodiment.

[0119] The visualization unit 114 performs processing using the prediction results stored in the database 116 to visualize the predicted vegetation crown size changes and vegetation tree height changes and the risk determination results.

[0120] The maintenance instructing unit 115 acquires and inputs the management information data stored in the database 116 .

[0121] Fig. 20 is a flowchart for explaining the processing of the maintenance instructing unit in the first embodiment.

[0122] In S1102, the maintenance instruction unit 115 inputs remote sensing data stored in the database 116. Examples of remote sensing data include satellite images, drone images, and onboard camera images, but the remote sensing images may be other data.

[0123] In S1103, the maintenance instruction unit 115 uses the input remote sensing data to check the risk determination result. Specifically, the maintenance instruction unit 115 checks the distribution of the risk determination result visualized by the visualization unit 114 and selects a region of interest. The region of interest is selected using a threshold based on the quantified risk value, but another method may also be used.

[0124] In S1104, the maintenance instruction unit 115 checks the detailed risk of the selected area of ​​interest. The detailed risk determination result in the risk determination unit and the detailed risk visualization result in the visualization unit are obtained to identify the detailed area. In order to identify the detailed area, a threshold is used to select based on the quantitative risk value, but another method can also be used.

[0125] In S1105, the maintenance instruction unit 115 obtains the selected detailed area, the contact risk determination result and the management information data from the database 116, and identifies the location with high risk and requiring maintenance work as a risk location. Then, the identified risk location is listed, and the route and time of personnel dispatch and equipment transportation are optimized. Fig.21 is an example of a maintenance instruction map. In the figure, the locations of an office and two equipment warehouses are shown for four risk locations. Further, the best route is searched, the walking time and working time when the best route is adopted are calculated to estimate the maintenance time required for maintenance, and the route indication and time indication are also shown in the figure. The maintenance instruction screen changes depending on the risk location and the locations of the office and equipment warehouse. In addition, the degree or type of risk can also be used to search for the best route. For example, a search can also be performed to eliminate routes with higher priority risks of lodging.

[0126] The visualization unit 114 and the maintenance instruction unit 115 support maintenance work using the display on the management GUI. Fig.19 is an example of a GUI schematic diagram illustrating visualization and maintenance instructions in the first embodiment. Fig.19 The screen shown has display blocks for tree growth changes and risk changes of contact with power facilities, and these changes can be visualized by moving on the time axis. In addition, a list of risk locations is displayed so that information such as latitude and longitude, risk level and forecast time can be displayed. Fig.21 The maintenance instruction diagram is displayed on the maintenance instruction block. The detailed design and detailed items of the GUI may be other designs and other items.

[0127] As described above, the vegetation management system of the present invention is a vegetation management system that manages the impact of vegetation on predetermined features, and the vegetation management system includes: an acquisition unit, which acquires remote sensing image data of the vegetation; a classification unit, which classifies trees included in the vegetation according to growth vitality representing future growth potential based on the remote sensing image data; a growth prediction unit, which predicts the growth of the trees based on the classification results obtained by the classification unit; a risk determination unit, which determines the risk of contact with the predetermined features; and a visualization unit, which outputs the determination results obtained by the risk determination unit and visualizes them.

[0128] According to the above configuration and operation, the influence of vegetation on characteristics can be predicted with high accuracy by using a new method of classification by tree growth vigor.

[0129] In the vegetation management system of the present disclosure, different methods are used in growth prediction and / or contact risk determination according to the classification results.

[0130] Therefore, the growth of vegetation can be predicted with high accuracy by combining and using methods corresponding to the level of vegetation growth activity.

[0131] In the vegetation management system of the present invention, the classification results include dead trees that have withered and will not grow in the future, special growth trees that have been felled and / or have had their branches removed, fast-growing trees that are assessed to have high growth vitality based on time series changes in the remote sensing image data, and slow-growing trees that are assessed to have low growth vitality based on time series changes in the remote sensing image data.

[0132] By performing appropriate classification in this way, vegetation growth can be predicted efficiently and with high accuracy.

[0133] In the vegetation management system of the present disclosure, as for the dead tree, the dead tree is excluded from the prediction target for growth prediction, and a risk determination model for lodging and flying out is used for the contact risk determination.

[0134] In the vegetation management system of the present disclosure, for the fast-growing trees and the slow-growing trees, growth is predicted, and a risk determination model of invasion and lodging caused by size changes based on the predicted growth is used.

[0135] In the vegetation management system of the present disclosure, for the special growth trees, the growth is predicted and a risk determination model of invasion caused by size changes is used.

[0136] By performing growth prediction and risk determination based on classification in this way, the impact of vegetation on features can be predicted with high accuracy.

[0137] The vegetation management system of the present disclosure further comprises: a tree height estimation unit, which estimates the tree crown height according to the vegetation area in the remote sensing image data; a tree crown extraction unit, which extracts the tree crown according to the estimated tree crown height; and a time series analysis unit, which calculates the time series change of the size of the extracted tree crown and the estimated tree crown height. The classification unit uses the time series change to classify trees according to the growth vitality.

[0138] The growth vigor can be obtained by image processing an image taken from the sky using the tree crown height and size in this manner.

[0139] The vegetation management system of the present disclosure further includes a maintenance indication unit that uses the growth vitality of the tree and the location of the predetermined feature to develop and present a maintenance plan.

[0140] In the vegetation management system of the present disclosure, the predetermined feature is an electric power facility, and the maintenance instruction unit formulates an operation execution route corresponding to growth vitality of surrounding trees to maintain basic equipment and power lines of the electric power facility.

[0141] Therefore, efficient maintenance plans can be presented based on high-precision prediction results of the impact on vegetation.

[0142] For example, routes for introducing personnel and equipment into mountainous or hard-to-reach locations can be optimized, thereby reducing maintenance costs.

[0143] Note that the present invention is not limited to the embodiments described above, but includes various modifications. For example, the above embodiments are described in detail to explain the present invention in an easily understandable manner, and are not necessarily limited to the embodiments having all the configurations described above.

[0144] Furthermore, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment, and the configuration of one embodiment may be added to the configuration of another embodiment.

[0145] In addition, a part of the configuration of each embodiment may be added, deleted or replaced with another configuration. In addition, each of the configurations, functions, processing units, processing devices, etc. described above may be implemented as hardware, for example, by designing some or all of them with integrated circuits.

[0146] In addition, each of the configurations, functions, etc. described above can be implemented as software by a processor interpreting and executing a program that realizes each function.

[0147] Information about programs, tables, files, etc. that implement each function can be stored in a storage device (such as a memory, a hard disk, or a solid-state drive (SSD)) or a recording medium (such as an integrated circuit (IC) card, an SD card, or a digital versatile disk (DVD)).

[0148] Only control lines and information lines that are considered necessary for explanation are illustrated, and not all control lines and information lines required for the product are necessarily illustrated. In practice, it can be considered that almost all configurations are connected to each other.

[0149] List of Reference Numerals

[0150] 100: Vegetation management system for power facility maintenance

[0151] 101: Different Input Data

[0152] 101a: Remote Sensing Image Data

[0153] 101b: Vegetation Information Data

[0154] 101c: Geographic Information Data

[0155] 101d: Environmental Information Data

[0156] 101e: Management Information Data

[0157] 102: Remote sensing data acquisition unit

[0158] 103: Geographic Information Acquisition Unit

[0159] 104: Environmental information acquisition unit

[0160] 105: Management information acquisition unit

[0161] 106: Database generation unit

[0162] 107: Dead Tree Extraction Unit

[0163] 108: Tree height estimation unit

[0164] 109: Crown extraction unit

[0165] 110: Time Series Analysis Unit

[0166] 111: Vegetation taxonomic unit

[0167] 112: Growth prediction unit

[0168] 113: Risk Determination Unit

[0169] 114: Visualization Unit

[0170] 115: Maintenance indication unit

[0171] 116: Database Unit

Claims

1. A vegetation management system for managing the impact of vegetation on a predetermined feature, the vegetation management system comprising: An acquisition unit, wherein the acquisition unit acquires remote sensing image data of the vegetation; a classification unit that classifies trees included in the vegetation according to growth vitality indicating future growth potential based on the remote sensing image data; a growth prediction unit that predicts the growth of the tree based on the classification result obtained by the classification unit; a risk determination unit, the risk determination unit determining a risk of contact with the predetermined feature; as well as A visualization unit outputs and visualizes a determination result obtained by the risk determination unit.

2. The vegetation management system according to claim 1, wherein: Depending on the classification results, different methods are used in growth prediction and / or exposure risk determination.

3. The vegetation management system according to claim 1, wherein: The classification results include dead trees that have withered and will not grow in the future, special growth trees that have been felled and / or have had their branches removed, fast-growing trees that are assessed to have high growth vigor based on time series changes in the remote sensing image data, and slow-growing trees that are assessed to have low growth vigor based on time series changes in the remote sensing image data.

4. The vegetation management system according to claim 3, wherein: For the dead tree, The dead trees are excluded from prediction targets for growth prediction, and Risk determination models for lodging and flying out are used for the contact risk determination.

5. The vegetation management system according to claim 3, wherein: For the fast-growing trees and the slow-growing trees, Growth is predicted and a risk determination model for invasion and lodging caused by size changes based on the predicted growth is used.

6. The vegetation management system according to claim 3, wherein: For the special growth trees, Growth was predicted and the risk of invasion caused by size variation was determined using a model.

7. The vegetation management system according to claim 1, further comprising: A tree height estimation unit, wherein the tree height estimation unit estimates the tree crown height according to the vegetation area in the remote sensing image data; A crown extraction unit, wherein the crown extraction unit extracts the crown of the tree according to the estimated crown height; as well as A time series analysis unit is used to calculate the time series changes of the extracted tree crown size and the estimated tree crown height, wherein: The classification unit classifies trees according to the growth vigor using the time series changes. 8 . The vegetation management system of claim 1 , further comprising a maintenance indication unit that uses the growth vitality of the tree and the location of the predetermined feature to develop and present a maintenance plan.

9. The vegetation management system according to claim 8, wherein: The predetermined feature is an electric utility, and The maintenance instruction unit formulates an operation execution route corresponding to the growth vitality of surrounding trees to maintain the basic equipment and power lines of the electric power facility.

10. A method of vegetation management performed by a vegetation management system for managing the impact of vegetation on a predetermined feature, the method comprising: By the vegetation management system, Acquiring remote sensing image data of the vegetation; Based on the remote sensing image data, classifying trees included in the vegetation according to growth vitality indicating future growth potential; predicting the growth of the tree based on the classification results obtained through the classification; determining a risk of exposure to the predetermined characteristic; as well as The determination results obtained by determining the risks are output and visualized.

Images