Terrain classification method, device and equipment for power transmission line project

Abstract

The invention relates to the technical field of terrain classification, and discloses a terrain classification method, device and equipment for power transmission line engineering, and the method comprises the steps: collecting the digital elevation data of each grid unit in a target region, and determining a plurality of terrain indexes of each grid unit based on the digital elevation data; determining a terrain classification rule; adopting a pre-trained random forest model to predict and obtain a first terrain classification result of each grid unit based on the plurality of terrain indexes of each grid unit; determining a second terrain classification result of each grid unit based on the plurality of terrain indexes and terrain classification rules of each grid unit; and for any grid unit, obtaining a target terrain classification result based on the first terrain classification result and the second terrain classification result of the grid unit. According to the method, the plurality of terrain indexes are determined through the digital elevation data, the terrain classification is predicted by using the pre-trained random forest model, and the target terrain classification result is obtained in combination with the terrain classification rule, so that the terrain classification accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of terrain classification, and in particular to a terrain classification method, device and equipment for power transmission line engineering. Background Art

[0002] As a key infrastructure of the power system, the scale of transmission line projects continues to grow with the rapid development of the economy. Different terrain conditions have a direct impact on the design of transmission line projects. For example, the design requirements for tower height, foundation type, line path, etc. in mountainous areas and flat areas are very different. Through terrain classification, suitable design schemes can be adopted for different types of terrain. In addition, terrain classification can help evaluate the feasibility and difficulty of transmission line projects, predict possible obstacles such as mountainous areas and river crossings, so as to make construction plans and budgets in advance. In addition, clear terrain classification can also help to estimate project costs more accurately, especially in terms of material, manpower and special equipment requirements, which is conducive to controlling overall expenses. Therefore, how to classify the terrain of transmission line projects is a problem that needs to be solved.

[0003] At present, Digital Elevation Model (DEM) is mainly used for terrain classification. However, when terrain classification is based on DEM model, it often relies on a single terrain indicator, which cannot fully reflect the complexity of the terrain, and lacks clear quantitative standards in the terrain classification process, resulting in low accuracy of terrain classification results. Summary of the invention

[0004] In view of this, the present invention provides a terrain classification method, device and equipment for power transmission line projects to solve the problem that terrain classification using a DEM model relies on a single terrain indicator, cannot fully reflect the complexity of the terrain, and lacks clear quantitative standards in the terrain classification process, resulting in low accuracy of terrain classification results.

[0005] In a first aspect, the present invention provides a method for terrain classification of a power transmission line project, the method comprising:

[0006] For a target area in a power transmission line project, digital elevation data of each grid cell in the target area is collected, and multiple terrain indicators corresponding to each grid cell are determined based on the digital elevation data of each grid cell, wherein the multiple terrain indicators include average slope, relative elevation and terrain undulation;

[0007] Determine terrain classification rules, which represent the corresponding relationship between terrain categories and terrain indicators;

[0008] A pre-trained random forest model is used to make predictions based on multiple terrain indicators corresponding to each grid cell to obtain the first terrain classification result of each grid cell;

[0009] Determine a second terrain classification result for each grid cell based on a plurality of terrain indicators and terrain classification rules corresponding to each grid cell;

[0010] For any grid cell in the target area, a target terrain classification result of the grid cell is obtained based on the first terrain classification result and the second terrain classification result of the grid cell.

[0011] The terrain classification method for a power transmission line project provided by an embodiment of the present invention collects digital elevation data of each grid cell in a target area, lays a foundation for subsequent terrain classification analysis, determines multiple terrain indicators based on the digital elevation data, quantifies terrain features, and uses a pre-trained random forest model to perform terrain classification prediction to obtain a first terrain classification result for each grid cell. Combined with a second terrain classification result determined according to a terrain classification rule, the target terrain classification result for each grid cell in the target area is jointly determined. Compared with relying on a single terrain indicator and lacking a clear quantitative standard, the terrain classification accuracy is significantly improved.

[0012] In an optional implementation, multiple terrain indicators corresponding to each grid cell are determined based on the digital elevation data of each grid cell, including:

[0013] For any grid cell, multiple neighboring points of the center point of the grid cell are determined from the target area;

[0014] Based on the digital elevation data of each grid cell, the elevation value of the center point of the grid cell and the elevation values ​​of multiple adjacent points are obtained;

[0015] For any adjacent point, the slope between the center point and the adjacent point is determined based on the elevation value of the center point, the elevation value of the adjacent point and the side length of the grid unit;

[0016] The average slope of the grid cell is the average of the slopes between the center point of the grid cell and each adjacent point.

[0017] The terrain classification method for a power transmission line project provided in an embodiment of the present invention determines the slope between the center point of any grid unit and multiple adjacent points to obtain the average slope of the grid unit, which can reflect the inclination of the surface where the grid unit is located and is helpful for subsequent terrain classification analysis.

[0018] In an optional implementation, determining a plurality of terrain indicators corresponding to each grid cell based on the digital elevation data of each grid cell further includes:

[0019] Based on the digital elevation data of each grid cell, the lowest elevation value is determined from the elevation values ​​corresponding to each grid cell in the target area;

[0020] For any grid cell, based on the digital elevation data of each grid cell, obtain the elevation value of the grid cell;

[0021] The difference between the elevation value of the grid cell and the minimum elevation value is used as the relative elevation of the grid cell.

[0022] The terrain classification method for the power transmission line project provided by the embodiment of the present invention determines the lowest elevation value in the target area, thereby obtaining the relative elevation between any grid unit and the lowest elevation value, which can reflect the relative height of the location of the grid unit and facilitate subsequent terrain classification analysis.

[0023] In an optional implementation, determining a plurality of terrain indicators corresponding to each grid cell based on the digital elevation data of each grid cell further includes:

[0024] For any grid cell, multiple neighboring points of the center point of the grid cell are determined from the target area;

[0025] Based on the digital elevation data of each grid cell, the elevation value of the center point of the grid cell and the elevation values ​​of multiple adjacent points are obtained;

[0026] For any adjacent point, determine the difference between the elevation value of the center point and the elevation value of the adjacent point;

[0027] The terrain relief of the grid cell is determined based on the difference between the elevation value of the center point and the elevation value of each adjacent point.

[0028] The terrain classification method for transmission line projects provided in an embodiment of the present invention determines the difference between the elevation value of the center point of any grid unit and the elevation values ​​of multiple adjacent points to obtain the severity of the terrain change at the location of the grid unit, which is helpful for subsequent terrain classification analysis.

[0029] In an optional implementation, a pre-trained random forest model is used to perform prediction based on multiple terrain indicators corresponding to each grid cell to obtain a first terrain classification result for each grid cell, including:

[0030] For any grid cell, multiple terrain indicators corresponding to the grid cell are preprocessed to obtain a preprocessed feature vector;

[0031] Based on multiple decision trees in the pre-trained random forest model and the depth of each decision tree, the pre-processed feature vector is predicted to obtain multiple predicted terrain classification results;

[0032] A plurality of predicted terrain classification results are aggregated to obtain a first terrain classification result of a grid unit.

[0033] The terrain classification method for a power transmission line project provided in an embodiment of the present invention preprocesses multiple terrain indicators to obtain a preprocessed feature vector suitable for input into a pretrained random forest model, and uses the pretrained random forest model to predict the preprocessed feature vector, so as to predict the terrain of the grid unit and obtain a first terrain classification result. Compared with the terrain classification result obtained by using a single terrain indicator, the accuracy of terrain classification is improved.

[0034] In an optional implementation, for any grid cell in the target area, obtaining a target terrain classification result of the grid cell based on the first terrain classification result and the second terrain classification result of the grid cell includes:

[0035] Assigning a first weight to the first terrain classification result, and assigning a second weight to the second terrain classification result;

[0036] Performing numerical mapping on the first terrain classification result and the second terrain classification result respectively to obtain a first mapping value and a second mapping value;

[0037] Determining a terrain classification weighted score based on the first mapping value, the second mapping value, the first weight, and the second weight;

[0038] Determine a first difference between the weighted score of the terrain classification and the first mapped value, and determine a second difference between the weighted score of the terrain classification and the second mapped value;

[0039] The terrain classification result of the mapping value corresponding to the smaller difference between the first difference and the second difference before the numerical mapping is used as the target terrain classification result of the grid unit.

[0040] The terrain classification method for a power transmission line project provided in an embodiment of the present invention performs numerical mapping on a first terrain classification result obtained by predicting a plurality of terrain indicators based on a pre-trained random forest model and a second terrain classification result determined from a terrain classification rule based on the plurality of terrain indicators, respectively, so that the terrain classification result is quantified, and a terrain classification weighted score is obtained by assigning weights to terrain classification results from different sources, thereby determining a target terrain classification result based on the difference between the two mapped values ​​and the terrain classification weighted score, thereby improving the accuracy of terrain classification.

[0041] In an optional embodiment, the method further includes:

[0042] A terrain classification map is generated based on the target terrain classification results of each grid cell in the target area.

[0043] The terrain classification method for a power transmission line project provided by an embodiment of the present invention makes the terrain classification of the power transmission line project more intuitive by presenting the target terrain classification result of each grid unit in the target area in a graphical manner, namely, a terrain classification map.

[0044] In an optional implementation, the random forest model is pre-trained in the following manner:

[0045] Obtain a pre-training data set, and divide the pre-training data set into a training data set and a test data set, wherein each data in the pre-training data set includes a plurality of terrain indicators and terrain categories;

[0046] Determine the preset number of decision trees and the preset decision tree depth of the random forest model;

[0047] The random forest model is used to predict the training data set. Based on the difference between the predicted terrain classification results and the terrain categories corresponding to the training data set, the random forest model is trained to obtain a trained random forest model.

[0048] The performance of the trained random forest model is evaluated using the test data set, the number of decision trees and the depth of the decision trees of the trained random forest model are adjusted, and training and performance evaluation are performed again until the results of the performance evaluation meet the preset conditions to obtain a pre-trained random forest model.

[0049] The terrain classification method for power transmission line projects provided by the embodiment of the present invention scientifically divides the pre-training data set into a training data set and a test data set, thereby ensuring that the model can learn rich terrain features on the training data set and verify its generalization ability through an independent test data set, thereby avoiding the risk of overfitting, and adjusting the model parameters according to the evaluation results until the preset conditions are met, thereby ensuring that the final model not only performs well on the training data, but also makes more reliable predictions on unknown data, thereby improving the generalization ability and prediction accuracy of the pre-trained random forest model.

[0050] In a second aspect, the present invention provides a terrain classification device for a power transmission line project, the device comprising:

[0051] A collection module, for collecting digital elevation data of each grid cell in a target area in a power transmission line project, and determining a plurality of terrain indicators corresponding to each grid cell based on the digital elevation data of each grid cell, wherein the plurality of terrain indicators include an average slope, a relative elevation and a terrain undulation;

[0052] A first determination module is used to determine a terrain classification rule, where the terrain classification rule represents a corresponding relationship between terrain categories and terrain indicators;

[0053] A prediction module, used to use a pre-trained random forest model to make predictions based on multiple terrain indicators corresponding to each grid cell, and obtain a first terrain classification result for each grid cell;

[0054] A second determination module, configured to determine a second terrain classification result for each grid cell based on a plurality of terrain indicators and terrain classification rules corresponding to each grid cell;

[0055] The third determination module is used to obtain, for any grid cell in the target area, a target terrain classification result of the grid cell based on the first terrain classification result and the second terrain classification result of the grid cell.

[0056] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the terrain classification method for transmission line projects of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0057] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the terrain classification method for a power transmission line project according to the first aspect or any corresponding embodiment thereof.

[0058] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the terrain classification method for a power transmission line project according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 is a flow chart of a terrain classification method for a power transmission line project according to an embodiment of the present invention;

[0061] Figure 2 is a flow chart of another method for terrain classification of a power transmission line project according to an embodiment of the present invention;

[0062] Figure 3 is a flow chart of another method for terrain classification of a power transmission line project according to an embodiment of the present invention;

[0063] Figure 4is a flow chart of a method for terrain classification of a power transmission line project provided in an optional embodiment of the present invention;

[0064] Figure 5 is a structural block diagram of a terrain classification device for a power transmission line project according to an embodiment of the present invention;

[0065] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0067] Different terrain conditions have a direct impact on the design of transmission line projects. Therefore, how to classify the terrain of transmission line projects is a problem that needs to be solved. In the related art, a digital elevation model (DEM) is used for terrain classification. However, when performing terrain classification based on the DEM model, it often relies on a single terrain indicator, which cannot fully reflect the complexity of the terrain, and lacks clear quantitative standards in the terrain classification process, resulting in low accuracy of the terrain classification results. The terrain classification method for transmission line projects provided in an embodiment of the present invention determines multiple terrain indicators based on digital elevation data, uses a pre-trained random forest model to perform terrain classification prediction, and combines terrain classification rules to jointly determine the target terrain classification results, thereby significantly improving the accuracy of terrain classification.

[0068] According to an embodiment of the present invention, an embodiment of a terrain classification method for a transmission line project is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0069] In this embodiment, a method for terrain classification of a power transmission line project is provided, which can be used for electronic equipment, Figure 1 FIG. 1 is a flow chart of a terrain classification method for a power transmission line project according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0070] Step S101, for the target area in the power transmission line project, collect the digital elevation data of each grid unit in the target area, and determine multiple terrain indicators corresponding to each grid unit based on the digital elevation data of each grid unit, and the multiple terrain indicators include average slope, relative elevation and terrain undulation. Specifically, the target area is any area in the power transmission line project that needs to be classified. DEM divides the target area into multiple grid units of equal size, and collects DEM data of each grid unit. Optionally, the DEM divides the target area into grid units with a length and width of 100 meters as an example for explanation. Since there are differences in the terrain categories corresponding to the grid units in the target area, multiple terrain indicators reflecting the terrain characteristics of the location of the grid unit, such as average slope, relative elevation and terrain undulation, are determined based on the DEM data corresponding to each grid unit, which helps to classify the terrain according to the terrain characteristics. Optionally, other terrain indicators can also be determined, and the embodiment of the present invention does not limit this.

[0071] Step S102, determine the terrain classification rules, the terrain classification rules represent the corresponding relationship between terrain categories and terrain indicators. Specifically, in combination with the actual needs of the construction of the transmission line project, based on multiple terrain indicators, the terrain classification rules shown in Table 1 below are designed, for example, according to different values ​​of the average slope, relative elevation and terrain undulation, the terrain is divided into flat land, hills, mountains and other terrain categories. Optionally, Table 1 below is only an example, and the corresponding relationship between terrain indicators and terrain categories can be adjusted according to actual needs, and the embodiments of the present invention do not limit this. By determining the terrain classification rules, a reference quantitative standard is provided for terrain classification.

[0072] Table 1 Terrain classification rules

[0073]

[0074]

[0075] Step S103, using a pre-trained random forest model, predicting based on multiple terrain indicators corresponding to each grid unit, and obtaining a first terrain classification result for each grid unit. Specifically, the pre-trained random forest model can predict the terrain classification of the location of the grid unit based on the terrain features reflected by the multiple terrain indicators, and obtain a first terrain classification result, which improves the accuracy of terrain classification compared to using a single terrain indicator for terrain classification.

[0076] Step S104, based on the multiple terrain indicators and terrain classification rules corresponding to each grid unit, determine the second terrain classification result of each grid unit. Specifically, the second terrain classification result is obtained by matching the calculated multiple terrain indicators of each grid unit with the terrain classification rules determined in step S102, such as Table 1.

[0077] Step S105, for any grid cell in the target area, based on the first terrain classification result and the second terrain classification result of the grid cell, a target terrain classification result of the grid cell is obtained. Specifically, the target terrain classification result is determined by combining the first terrain classification result predicted by the pre-trained random forest model and the second terrain classification result determined from the terrain classification rule based on multiple terrain indicators, thereby improving the accuracy of terrain classification.

[0078] The terrain classification method for a power transmission line project provided by an embodiment of the present invention collects digital elevation data of each grid cell in a target area, lays a foundation for subsequent terrain classification analysis, determines multiple terrain indicators based on the digital elevation data, quantifies terrain features, and uses a pre-trained random forest model to perform terrain classification prediction to obtain a first terrain classification result for each grid cell. Combined with a second terrain classification result determined according to a terrain classification rule, the target terrain classification result for each grid cell in the target area is jointly determined. Compared with relying on a single terrain indicator and lacking a clear quantitative standard, the terrain classification accuracy is significantly improved.

[0079] In this embodiment, a method for terrain classification of a power transmission line project is provided, which can be used for electronic equipment, Figure 2 FIG. 1 is a flow chart of another method for terrain classification of a power transmission line project according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0080] Step S201, for a target area in a power transmission line project, collect digital elevation data of each grid cell in the target area, and determine multiple terrain indicators corresponding to each grid cell based on the digital elevation data of each grid cell, wherein the multiple terrain indicators include average slope, relative elevation and terrain undulation.

[0081] Specifically, the above step S201 determines a plurality of terrain indicators corresponding to each grid unit based on the digital elevation data of each grid unit, including:

[0082] Step S2011, for any grid cell, determine multiple adjacent points of the center point of the grid cell from the target area. Specifically, the embodiment of the present invention is explained by taking the determination of three terrain indicators: average slope, relative elevation and terrain undulation as an example, and the average slope of the grid cell is determined by steps S2011 to S2014, the relative elevation of the grid cell is determined by steps S2015 to S2017, and the terrain undulation of the grid cell is determined by steps S2018 to S20111. When determining the average slope of the grid cell, for any grid cell, since the grid cell is a square with a length and width of 100 meters, the center point of the square is the center point of the grid cell. The grid cell is taken as the center of a nine-square grid, and the other eight grid cells that form the nine-square grid together with the grid cell are taken as adjacent grid cells, and the center points of these eight grid cells are determined as adjacent points.

[0083] Step S2012, based on the digital elevation data of each grid cell, obtain the elevation value of the center point of the grid cell and the elevation values ​​of multiple adjacent points. Specifically, obtain the elevation values ​​of the center point and 8 adjacent points from the DEM data of all grid cells respectively, so as to calculate the average slope.

[0084] Step S2013, for any adjacent point, based on the elevation value of the center point, the elevation value of the adjacent point and the side length of the grid unit, determine the slope between the center point and the adjacent point. Specifically, the slope between the center point and each adjacent point can be determined by the following formula (1), thereby obtaining the degree of inclination of the center point and each adjacent point in the direction.

[0085]

[0086] Where i represents the i-th neighboring point; j represents the j-th grid unit; P i represents the slope between the ith adjacent point and the center point; h i represents the elevation value of the i-th adjacent point; h j represents the elevation value of the center point of the jth grid unit; d represents the side length of the grid unit, and in the embodiment of the present invention, the value is 100.

[0087] Step S2014, the average value of the slope between the center point of the grid unit and each adjacent point is used as the average slope of the grid unit. Specifically, the average value of the eight slopes obtained by the center point and the eight adjacent points through the above formula (1) is used as the average slope of the grid unit, which can reflect the inclination of the surface where the grid unit is located. The larger the average slope, the steeper the terrain. Conversely, the flatter the terrain is, which is helpful for subsequent terrain classification analysis.

[0088] Step S2015, based on the digital elevation data of each grid cell, determine the lowest elevation value from the elevation values ​​corresponding to each grid cell in the target area. Specifically, when determining the relative slope of the grid cell, the lowest elevation value is first determined. Since the elevation values ​​of different terrain categories vary greatly, calculating the relative elevation between the grid cell and the lowest elevation value is helpful for terrain classification analysis.

[0089] Step S2016: For any grid cell, based on the digital elevation data of each grid cell, obtain the elevation value of the grid cell. Specifically, obtain the elevation value of the center point of the grid cell from the DEM data of all grid cells as the elevation value of the grid cell.

[0090] Step S2017, the difference between the elevation value of the grid cell and the minimum elevation value is used as the relative elevation of the grid cell. Specifically, the relative elevation between the elevation value of the grid cell and the minimum elevation value is determined by the following formula (2), which can reflect the relative height of the location of the grid cell, which is helpful for subsequent terrain classification analysis.

[0091] Hre=h j -h min (2)

[0092] Where, j represents the jth grid unit; h j represents the elevation value of the center point of the jth grid cell; h min Represents the lowest elevation value; Hre represents the relative elevation between the elevation value of the center point of the jth grid cell and the lowest elevation value.

[0093] Step S2018: for any grid cell, determine multiple adjacent points of the center point of the grid cell from the target area. Specifically, when determining the terrain relief of the grid cell, refer to the above step S2011 to determine 8 adjacent points of the center point of the grid cell.

[0094] Step S2019, based on the digital elevation data of each grid cell, obtain the elevation value of the center point of the grid cell and the elevation values ​​of multiple adjacent points. Specifically, obtain the elevation values ​​of the center point and 8 adjacent points from the DEM data of all grid cells respectively, so as to calculate the terrain relief.

[0095] Step S20110: for any adjacent point, determine the difference between the elevation value of the central point and the elevation value of the adjacent point. Specifically, determine the difference between the elevation value of the central point and each adjacent point.

[0096] Step S20111, based on the difference between the elevation value of the center point and the elevation value of each adjacent point, determine the terrain undulation of the grid unit. Specifically, the terrain undulation of the grid unit can be determined by the following formula (3), which can reflect the severity of the terrain change at the location of the grid unit. The greater the terrain undulation, the more rugged the terrain is. Conversely, the terrain is relatively flat, which is helpful for subsequent terrain classification analysis.

[0097]

[0098] Among them, T und represents the terrain relief of the jth grid cell; i represents the ith neighboring point; j represents the jth grid cell; h i represents the elevation value of the i-th adjacent point; h j Represents the elevation value of the center point of the jth grid cell.

[0099] Step S202: determine the terrain classification rule, which represents the corresponding relationship between terrain categories and terrain indicators. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0100] Step S203, using the pre-trained random forest model, predicting based on multiple terrain indicators corresponding to each grid unit, to obtain the first terrain classification result of each grid unit. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0101] Step S204: Determine the second terrain classification result of each grid unit based on the multiple terrain indicators and terrain classification rules corresponding to each grid unit. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0102] Step S205: for any grid cell in the target area, based on the first terrain classification result and the second terrain classification result of the grid cell, obtain the target terrain classification result of the grid cell. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0103] Step S206, based on the target terrain classification result of each grid unit in the target area, a terrain classification map is generated. Specifically, the target terrain classification result of each grid unit in the target area is graphically presented to obtain a terrain classification map, which may include identifications, color codes, legends and notes of different terrain categories, so that the terrain classification of the transmission line project is more intuitive.

[0104] The terrain classification method for a power transmission line project provided by an embodiment of the present invention collects digital elevation data of each grid cell in a target area, lays a foundation for subsequent terrain classification analysis, determines multiple terrain indicators based on the digital elevation data, quantifies terrain features, and uses a pre-trained random forest model to perform terrain classification prediction to obtain a first terrain classification result for each grid cell. Combined with a second terrain classification result determined according to a terrain classification rule, the target terrain classification result for each grid cell in the target area is jointly determined. Compared with relying on a single terrain indicator and lacking a clear quantitative standard, the terrain classification accuracy is significantly improved.

[0105] In this embodiment, a method for terrain classification of a power transmission line project is provided, which can be used for electronic equipment, Figure 3 FIG. 1 is a flow chart of another method for terrain classification of a power transmission line project according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0106] Step S301: For the target area in the power transmission line project, collect the digital elevation data of each grid unit in the target area, and determine multiple terrain indicators corresponding to each grid unit based on the digital elevation data of each grid unit. The multiple terrain indicators include average slope, relative elevation and terrain undulation. For details, please refer to Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0107] Step S302: determine the terrain classification rule, which represents the corresponding relationship between terrain categories and terrain indicators. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0108] Step S303, using a pre-trained random forest model, predicting based on multiple terrain indicators corresponding to each grid unit, to obtain a first terrain classification result for each grid unit.

[0109] Specifically, the above step S303 includes:

[0110] Step S3031, for any grid unit, preprocess multiple terrain indicators corresponding to the grid unit to obtain a preprocessed feature vector. Specifically, the multiple terrain indicators are standardized or normalized and converted into a vector form to obtain a preprocessed feature vector suitable for input into a pre-trained random forest model.

[0111] Step S3032, based on the multiple decision trees in the pre-trained random forest model and the depth of each decision tree, the pre-processed feature vector is predicted to obtain multiple predicted terrain classification results. Specifically, the pre-trained random forest model has better prediction ability and generalization ability, and performs terrain classification on the terrain features reflected by the input pre-processed feature vector, and more accurately predicts the terrain category of each grid unit, that is, the predicted terrain classification result.

[0112] In some optional embodiments, the random forest model is pre-trained in the following manner: obtaining a pre-training data set, dividing the pre-training data set into a training data set and a test data set, each data in the pre-training data set includes multiple terrain indicators and terrain categories; determining the preset number of decision trees and the preset decision tree depth of the random forest model; using the random forest model to predict the training data set, based on the difference between the predicted terrain classification result and the terrain category corresponding to the training data set, training the random forest model to obtain a trained random forest model; using the test data set to evaluate the performance of the trained random forest model, adjusting the number of decision trees and the depth of decision trees of the trained random forest model, and re-training and performance evaluation until the result of the performance evaluation meets the preset conditions, and obtaining a pre-trained random forest model. Specifically, a large-scale pre-training data set containing multiple terrain indicators and terrain categories is obtained for model pre-training. The pre-training data set is divided into a training data set and a test data set, the training data set is used to teach the random forest model to learn the relationship between terrain features and terrain categories, and the test data set is used to evaluate the generalization ability of the model to ensure that the model can not only perform well on known data, but also have good prediction performance on unknown data. Before training begins, the key parameters of the random forest model, including the number of decision trees and the maximum depth of a single decision tree, are set, which can directly affect the complexity, training time and prediction performance of the random forest model. During training, a training data set is used to adjust the internal parameters of the random forest model through an iterative optimization process so that the predicted terrain classification results are as close to the actual terrain categories as possible, and the trained random forest model is obtained after the preset rounds of training. The performance of the trained random forest model is evaluated using evaluation indicators using a test data set, such as accuracy, recall, F1 score, etc. According to the performance evaluation results, parameters such as the number and depth of decision trees are adjusted, and the prediction and performance evaluation of the terrain classification results are re-performed until the preset conditions are met, such as the error rate is lower than a certain threshold or meets specific business requirements, etc., to obtain a pre-trained random forest model. Assume that the model parameters of the random forest model obtained by pre-training are that the number of decision trees is 100 and the maximum depth of each decision tree is 20, so that the pre-trained random forest model is predicted based on the above model parameters through the above step S3032. By pre-training the random forest model, the generalization ability and prediction accuracy of the pre-trained random forest model are improved.

[0113] Step S3033, multiple predicted terrain classification results are aggregated to obtain a first terrain classification result of the grid unit. Specifically, since the pre-trained random forest model contains multiple decision trees, each decision tree will obtain a predicted terrain classification result. In order to obtain the final terrain classification result, a voting mechanism or other statistical methods are usually used to aggregate, so as to obtain a more reliable first terrain classification result for each grid unit.

[0114] Step S304: Determine the second terrain classification result of each grid unit based on the multiple terrain indicators and terrain classification rules corresponding to each grid unit. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0115] Step S305 : for any grid cell in the target area, based on the first terrain classification result and the second terrain classification result of the grid cell, obtain a target terrain classification result of the grid cell.

[0116] Specifically, the above step S305 includes:

[0117] Step S3051, assign a first weight to the first terrain classification result, and assign a second weight to the second terrain classification result. Specifically, the first terrain classification result and the second terrain classification result are respectively assigned a first weight and a second weight, and the sum of the first weight and the second weight is 1. The weight reflects the trust or importance of the two terrain classification results. If the source of the terrain classification results is different, that is, determined by terrain classification rules or determined by a pre-trained random forest model, the source of the terrain classification results has a higher historical classification accuracy, and a higher weight can be assigned. Assuming that the pre-trained random forest model has a higher accuracy in multiple historical terrain classifications, the first terrain classification result obtained by the pre-trained random forest model is assigned a first weight of 0.7, and the second weight is 0.3. Optionally, the above weight determination process is only an example, and can be personalized according to actual needs, and the embodiments of the present invention are not limited to this.

[0118] Step S3052, numerically map the first terrain classification result and the second terrain classification result respectively to obtain a first mapping value and a second mapping value. Specifically, in order to quantify the first terrain classification result and the second terrain classification result, numerical mapping can be performed respectively to obtain different mapping values. Assume that the numerical mapping rule is that "flat land" is mapped to 1, "mountain" is mapped to 2, and "high mountain" is mapped to 3. If the first terrain classification result is "high mountain", the first mapping value obtained after the numerical mapping is 3, and the second terrain classification result is "mountain", the second mapping value obtained after the numerical mapping is 2. Optionally, the embodiment of the present invention does not limit the mapping rules during numerical mapping.

[0119] Step S3053, based on the first mapping value, the second mapping value, the first weight and the second weight, determine the weighted score of the terrain classification. Specifically, referring to the assumptions in the above steps S3051 and S3052, the first mapping value is multiplied by the first weight to obtain 2.1, and the second mapping value is multiplied by the second weight to obtain 0.6, so the weighted score of the terrain classification is 2.7 when the two products are added together.

[0120] Step S3054, determine the first difference between the terrain classification weighted score and the first mapping value, and determine the second difference between the terrain classification weighted score and the second mapping value. Specifically, determine that the first difference between the terrain classification weighted score 2.7 and the first mapping value 3 is 0.3, and the second difference between the terrain classification weighted score and the second mapping value 2 is 0.7.

[0121] Step S3055, the terrain classification result before numerical mapping corresponding to the smaller difference between the first difference and the second difference is used as the target terrain classification result of the grid unit. Specifically, by comparing the first difference of 0.3 and the second difference of 0.7, the first terrain classification result "high mountain" corresponding to the smaller first difference is used as the target terrain classification result of the grid unit. By selecting the terrain classification result corresponding to the mapping value with a smaller difference as the final target terrain classification result, when the difference between the terrain classification weighted score and the mapping value of a certain terrain classification result is small, it means that the comprehensive evaluation of the terrain classification result after weighted calculation is very close to the mapping value and the degree of deviation is low, which can indicate that the terrain classification result is more reliable, thereby improving the accuracy of terrain classification.

[0122] Step S306: Generate a terrain classification map based on the target terrain classification results of each grid cell in the target area. Figure 2 Step S206 of the illustrated embodiment will not be described in detail here.

[0123] In some optional embodiments, after obtaining the target terrain classification result of each grid unit, the accuracy of the terrain classification method for the transmission line project proposed in the embodiment of the present invention can be evaluated based on the actual terrain category of each grid unit, and the terrain classification rules and the model parameters of the pre-trained random forest model can be adjusted to improve the accuracy of terrain classification and achieve continuous optimization.

[0124] In some optional embodiments, Figure 4 is a flow chart of a method for terrain classification of a power transmission line project according to an optional embodiment of the present invention. Figure 4As shown in the figure, the digital elevation data of the target area of ​​the transmission line project is collected, and the terrain indicators are determined based on the digital elevation data: average slope, relative elevation and terrain undulation. Then, based on the three terrain indicators, the first terrain classification result is determined by the pre-trained random forest model, and the second terrain classification result is determined by the terrain classification rules. Finally, the target terrain classification result is obtained by comprehensively analyzing the first terrain classification result and the second terrain classification result.

[0125] The terrain classification method for a power transmission line project provided by an embodiment of the present invention collects digital elevation data of each grid cell in a target area, lays a foundation for subsequent terrain classification analysis, determines multiple terrain indicators based on the digital elevation data, quantifies terrain features, and uses a pre-trained random forest model to perform terrain classification prediction to obtain a first terrain classification result for each grid cell. Combined with a second terrain classification result determined according to a terrain classification rule, the target terrain classification result for each grid cell in the target area is jointly determined. Compared with relying on a single terrain indicator and lacking a clear quantitative standard, the terrain classification accuracy is significantly improved.

[0126] In this embodiment, a terrain classification device for a power transmission line project is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0127] This embodiment provides a terrain classification device for a power transmission line project, such as Figure 5 As shown, including:

[0128] The acquisition module 501 is used to collect digital elevation data of each grid cell in the target area of ​​the transmission line project, and determine multiple terrain indicators corresponding to each grid cell based on the digital elevation data of each grid cell, and the multiple terrain indicators include average slope, relative elevation and terrain undulation.

[0129] The first determination module 502 is used to determine a terrain classification rule, where the terrain classification rule represents a corresponding relationship between terrain categories and terrain indicators.

[0130] The prediction module 503 is used to use a pre-trained random forest model to perform prediction based on multiple terrain indicators corresponding to each grid unit to obtain a first terrain classification result for each grid unit.

[0131] The second determination module 504 is used to determine a second terrain classification result for each grid unit based on a plurality of terrain indicators and terrain classification rules corresponding to each grid unit.

[0132] The third determination module 505 is configured to obtain, for any grid cell in the target area, a target terrain classification result of the grid cell based on the first terrain classification result and the second terrain classification result of the grid cell.

[0133] In some optional implementations, the acquisition module 501 includes:

[0134] The first determining unit is used to determine, for any grid unit, a plurality of adjacent points of a center point of the grid unit from a target area.

[0135] The first acquisition unit is used to acquire the elevation value of the center point of each grid unit and the elevation values ​​of multiple adjacent points based on the digital elevation data of each grid unit.

[0136] The second determining unit is used to determine the slope between the center point and the adjacent point for any adjacent point based on the elevation value of the center point, the elevation value of the adjacent point and the side length of the grid unit.

[0137] The third determining unit is used to take the average value of the slopes between the center point of the grid unit and each adjacent point as the average slope of the grid unit.

[0138] In some optional implementations, the acquisition module 501 further includes:

[0139] The fourth determining unit is used to determine the lowest elevation value from the elevation values ​​corresponding to each grid cell in the target area based on the digital elevation data of each grid cell.

[0140] The second acquisition unit is used to acquire the elevation value of any grid cell based on the digital elevation data of each grid cell.

[0141] The fifth determining unit is used to use the difference between the elevation value of the grid cell and the minimum elevation value as the relative elevation of the grid cell.

[0142] In some optional implementations, the acquisition module 501 further includes:

[0143] The sixth determining unit is used to determine, for any grid unit, a plurality of adjacent points of the center point of the grid unit from the target area.

[0144] The third acquisition unit is used to acquire the elevation value of the center point of each grid cell and the elevation values ​​of multiple adjacent points based on the digital elevation data of each grid cell.

[0145] The seventh determination unit is used to determine, for any adjacent point, the difference between the elevation value of the central point and the elevation value of the adjacent point.

[0146] The eighth determination unit is used to determine the terrain relief of the grid cell based on the difference between the elevation value of the central point and the elevation value of each adjacent point.

[0147] In some optional implementations, the prediction module 503 includes:

[0148] The preprocessing unit is used to preprocess a plurality of terrain indicators corresponding to any grid unit to obtain a preprocessing feature vector.

[0149] The prediction unit is used to predict the preprocessed feature vector based on multiple decision trees in the pre-trained random forest model and the depth of each decision tree to obtain multiple predicted terrain classification results.

[0150] The aggregation unit is used to aggregate multiple predicted terrain classification results to obtain a first terrain classification result of the grid unit.

[0151] In some optional implementations, the third determining module 505 includes:

[0152] The mapping unit is used to perform numerical mapping on the first terrain classification result and the second terrain classification result respectively to obtain a first mapping value and a second mapping value.

[0153] The assigning unit is used to assign a first weight to the first terrain classification result and assign a second weight to the second terrain classification result.

[0154] The ninth determining unit is configured to determine a terrain classification weighted score based on the first mapping value, the second mapping value, the first weight, and the second weight.

[0155] The difference determination unit is used to determine a first difference between the weighted score of the terrain classification and the first mapped value, and to determine a second difference between the weighted score of the terrain classification and the second mapped value.

[0156] The result determination unit is used to use the terrain classification result of the mapping value corresponding to the smaller difference between the first difference and the second difference before the numerical mapping as the target terrain classification result of the grid unit.

[0157] In some optional embodiments, the device further comprises:

[0158] The generation module is used to generate a terrain classification map based on the target terrain classification result of each grid cell in the target area.

[0159] In some optional implementations, the random forest model is pre-trained in the following manner:

[0160] Obtain a pre-training data set, and divide the pre-training data set into a training data set and a test data set, wherein each data in the pre-training data set includes a plurality of terrain indicators and terrain categories;

[0161] Determine the preset number of decision trees and the preset decision tree depth of the random forest model;

[0162] The random forest model is used to predict the training data set. Based on the difference between the predicted terrain classification results and the terrain categories corresponding to the training data set, the random forest model is trained to obtain a trained random forest model.

[0163] The performance of the trained random forest model is evaluated using the test data set, the number of decision trees and the depth of the decision trees of the trained random forest model are adjusted, and training and performance evaluation are performed again until the results of the performance evaluation meet the preset conditions to obtain a pre-trained random forest model.

[0164] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0165] The terrain classification device for the transmission line project in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0166] The embodiment of the present invention also provides a computer device having the above Figure 5 The terrain classification device for the transmission line project is shown.

[0167] See also Figure 6 , Figure 6 Schematic diagram of the hardware structure of the computer device according to the embodiment of the present invention. Figure 6As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0168] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0169] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0170] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0171] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0172] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0173] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0174] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0175] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the present invention.

Claims

1. A terrain classification method for power transmission line engineering, characterized in that: The method comprises: For a target area in a power transmission line project, digital elevation data of each grid cell in the target area is collected, and multiple terrain indicators corresponding to each grid cell are determined based on the digital elevation data of each grid cell, wherein the multiple terrain indicators include average slope, relative elevation and terrain undulation; Determining a terrain classification rule, wherein the terrain classification rule represents a corresponding relationship between terrain categories and terrain indicators; A pre-trained random forest model is used to make predictions based on multiple terrain indicators corresponding to each grid cell to obtain the first terrain classification result of each grid cell; Determine a second terrain classification result of each grid cell based on a plurality of terrain indicators corresponding to each grid cell and the terrain classification rule; For any grid cell in the target area, a target terrain classification result of the grid cell is obtained based on the first terrain classification result and the second terrain classification result of the grid cell.

2. The method according to claim 1, characterized in that The determining of a plurality of terrain indicators corresponding to each grid unit based on the digital elevation data of each grid unit comprises: For any grid cell, determining a plurality of adjacent points of a center point of the grid cell from the target area; Based on the digital elevation data of each grid cell, obtaining the elevation value of the center point of the grid cell and the elevation values ​​of the plurality of adjacent points; For any adjacent point, based on the elevation value of the central point, the elevation value of the adjacent point and the side length of the grid unit, determine the slope between the central point and the adjacent point; The average value of the slopes between the center point of the grid unit and each adjacent point is taken as the average slope of the grid unit.

3. The method according to claim 1, characterized in that The method of determining a plurality of terrain indicators corresponding to each grid cell based on the digital elevation data of each grid cell further includes: Based on the digital elevation data of each grid cell, determining the lowest elevation value from the elevation values ​​corresponding to each grid cell in the target area; For any grid cell, based on the digital elevation data of each grid cell, obtaining the elevation value of the grid cell; The difference between the elevation value of the grid cell and the minimum elevation value is used as the relative elevation of the grid cell.

4. The method according to claim 1, characterized in that: The method of determining a plurality of terrain indicators corresponding to each grid cell based on the digital elevation data of each grid cell further includes: For any grid cell, determining a plurality of adjacent points of a center point of the grid cell from the target area; Based on the digital elevation data of each grid cell, obtaining the elevation value of the center point of the grid cell and the elevation values ​​of the plurality of adjacent points; For any adjacent point, determining the difference between the elevation value of the central point and the elevation value of the adjacent point; The terrain relief of the grid cell is determined based on the difference between the elevation value of the central point and the elevation value of each adjacent point.

5. The method according to claim 1, characterized in that The pre-trained random forest model is used to predict based on multiple terrain indicators corresponding to each grid unit to obtain a first terrain classification result for each grid unit, including: For any grid cell, preprocessing a plurality of terrain indicators corresponding to the grid cell to obtain a preprocessing feature vector; Based on the multiple decision trees in the pre-trained random forest model and the depth of each decision tree, the pre-processed feature vector is predicted to obtain multiple predicted terrain classification results; The multiple predicted terrain classification results are aggregated to obtain a first terrain classification result of the grid unit.

6. The method according to claim 1, characterized in that For any grid cell in the target area, obtaining a target terrain classification result of the grid cell based on the first terrain classification result and the second terrain classification result of the grid cell includes: Assigning a first weight to the first terrain classification result, and assigning a second weight to the second terrain classification result; Performing numerical mapping on the first terrain classification result and the second terrain classification result respectively to obtain a first mapping value and a second mapping value; Determining a terrain classification weighted score based on the first mapping value, the second mapping value, the first weight, and the second weight; Determine a first difference between the weighted score of the terrain classification and the first mapped value, and determine a second difference between the weighted score of the terrain classification and the second mapped value; The terrain classification result of the mapping value corresponding to the smaller difference between the first difference and the second difference before the numerical mapping is used as the target terrain classification result of the grid unit.

7. The method according to claim 1, characterized in that The method further comprises: A terrain classification map is generated based on the target terrain classification result of each grid cell in the target area.

8. The method according to claim 1, characterized in that The random forest model is pre-trained in the following way: Acquire a pre-training data set, and divide the pre-training data set into a training data set and a test data set, wherein each data in the pre-training data set includes the plurality of terrain indicators and terrain categories; Determining the preset number of decision trees and the preset decision tree depth of the random forest model; The random forest model is used to predict the training data set, and based on the difference between the predicted terrain classification result and the terrain category corresponding to the training data set, the random forest model is trained to obtain a trained random forest model; The trained random forest model is performance evaluated using the test data set, the number of decision trees and the depth of decision trees of the trained random forest model are adjusted, and training and performance evaluation are performed again until the result of the performance evaluation meets the preset conditions, thereby obtaining the pre-trained random forest model.

9. A terrain classification device for power transmission line engineering, characterized in that: The device comprises: A collection module, for collecting digital elevation data of each grid cell in a target area in a power transmission line project, and determining a plurality of terrain indicators corresponding to each grid cell based on the digital elevation data of each grid cell, wherein the plurality of terrain indicators include an average slope, a relative elevation and a terrain undulation; A first determination module is used to determine a terrain classification rule, wherein the terrain classification rule represents a corresponding relationship between a terrain category and a terrain index; A prediction module, used to use a pre-trained random forest model to make predictions based on multiple terrain indicators corresponding to each grid cell, and obtain a first terrain classification result for each grid cell; A second determination module, configured to determine a second terrain classification result of each grid cell based on a plurality of terrain indicators corresponding to each grid cell and the terrain classification rule; The third determination module is used to obtain, for any grid cell in the target area, a target terrain classification result of the grid cell based on the first terrain classification result and the second terrain classification result of the grid cell.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the terrain classification method for a power transmission line project according to any one of claims 1 to 8 by executing the computer instructions.

Images