A method and system for intelligent planning of geographic information surveying and mapping

Abstract

The present invention provides a method and system for intelligent planning of geographic information surveying and mapping, and relates to the technical field of data processing. The method comprises: determining an initial temperature, a termination temperature, and the number of iterations of each temperature, generating a new solution by randomly exchanging two points in the current path planning at the current temperature; determining an objective function for evaluating the quality of path planning, calculating the objective function values ​​of the current solution and the new solution according to the objective function, and replacing the current solution with the new solution if the objective function value of the new solution is better than the current solution; repeating the operation at each temperature until the number of iterations at the temperature is reached, reducing the temperature according to a set temperature drop rate, and repeating the steps until the temperature drops to the termination temperature; when the temperature drops to the termination temperature, the final planning path is obtained. The present invention can improve the accuracy and efficiency of surveying and mapping path planning.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for intelligent planning of geographic information surveying and mapping. Background Art

[0002] Traditional geographic information surveying and mapping planning methods, to a large extent, rely on manual experience and relatively simple planning algorithms. In the data processing stage, although these methods can process some basic geographic information data, there is still room for improvement in fully utilizing and integrating diversified geographic information data, such as terrain height, slope, and obstacle distribution. Therefore, in the planning process, some key terrain and obstacle information may not be considered comprehensively, which in turn has a certain impact on the accuracy and feasibility of the surveying and mapping path.

[0003] At the same time, when faced with large-scale geographic information data, the computational efficiency of traditional methods may be affected and may not fully meet the requirements of high real-time performance and high precision. Due to the limitations of algorithm complexity and computing power, these methods may sometimes find it difficult to break away from the local optimal limit when planning paths, and thus fail to stably find the global optimal solution. This situation may increase the cost of surveying and mapping work to a certain extent, and may bring additional challenges to surveying and mapping tasks due to unreasonable path planning. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for intelligent planning of geographic information surveying and mapping, which can improve the accuracy and efficiency of surveying and mapping path planning.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a method for intelligent planning of geographic information surveying and mapping is provided, the method comprising:

[0007] Obtain geographic information data of the area to be surveyed, including terrain, obstacles, and traversable paths;

[0008] Preprocessing the geographic information data to obtain preprocessed geographic information data;

[0009] According to the preprocessed geographic information data, an initial mapping path plan is randomly generated as the current solution;

[0010] Determine the initial temperature, the end temperature, and the number of iterations for each temperature, and generate a new solution by randomly exchanging two points in the current path planning at the current temperature;

[0011] Determine the objective function used to evaluate the quality of path planning, calculate the objective function values ​​of the current solution and the new solution based on the objective function, and replace the current solution with the new solution if the objective function value of the new solution is better than the current solution;

[0012] Repeat the operation at each temperature until the number of iterations at that temperature is reached, reduce the temperature according to the set temperature drop rate, and repeat the steps until the temperature drops to the termination temperature;

[0013] When the temperature drops to the termination temperature, the final planned path is obtained;

[0014] The final planned path is output to the surveying and mapping equipment.

[0015] Furthermore, the geographic information data of the area to be surveyed is obtained, including:

[0016] According to the scope of the area to be mapped, a set of initial geographic information data collection points are randomly generated to form an initial population, and each collection point represents a specific geographical location;

[0017] Define an evaluation function to evaluate the quality of each collection point;

[0018] Determine the corresponding individuals from the current population and perform a crossover operation to generate new individuals;

[0019] Perform mutation operation on new individuals and repeat the operation until the preset number of iterations is reached to obtain the final set of collection points;

[0020] Based on the final set of collection points, use surveying and mapping equipment to obtain actual geographic information data.

[0021] Furthermore, the calculation formula of the evaluation function is:

[0022] ;

[0023] in, Indicate point The traffic density is expressed as traffic flow and road capacity The ratio of , and represents the coefficient; Represents the importance attached to traffic flow; Indicate point To a specific point distance; Indicates the total number of reference points; Indicates a specific reference point; represents the coefficient; among them, , represents the road congestion index; represents the accident frequency; and Represents weight.

[0024] Further, the geographic information data is preprocessed to obtain preprocessed geographic information data, including:

[0025] The geographic information data will be cleaned to obtain cleaned data;

[0026] The cleaned data is divided into different categories according to the data type and source. For each category of data, key features are extracted, including terrain height, slope, road width and traffic flow;

[0027] Process spatial data, overlay and analyze different types of data layers, and fuse related features based on spatial location relationships;

[0028] For non-spatial attribute data, fusion is performed through statistical analysis;

[0029] According to the relevance of the data, a weight is assigned to each attribute, and the fused attribute value is calculated using weighted average to obtain a fused geographic information dataset;

[0030] The fused geographic information dataset is filtered to obtain preprocessed data.

[0031] Furthermore, the cleaned data is divided into different categories according to the data type and source, including:

[0032] Determine the number of clusters K, and determine the features used for clustering from the cleaned data;

[0033] Initialize K cluster centers and randomly determine K points in the cleaned data as the initial centers;

[0034] Assign each data point in the cleaned data to the corresponding cluster center to form K initial clusters, recalculate the center of each cluster, and repeat the steps until the preset number of iterations is reached to obtain the clustering result;

[0035] According to the clustering results, the cleaned data is divided into K categories.

[0036] Furthermore, spatial data is processed, different types of data layers are overlaid for analysis, and related features are fused according to spatial position relationships, including:

[0037] Determine the corresponding weights for the terrain height layer and slope layer respectively;

[0038] Traverse each pixel position, perform weighted calculation based on the weights of the two layers and the original pixel value, and get the pixel value of the new layer;

[0039] According to the pixel value of the new layer, create a new blank layer to store the merged data, and fill the calculated new pixel value into the corresponding position of the new layer.

[0040] Furthermore, the calculation formula of the objective function is:

[0041] ;

[0042] in, Is the path The number of points on Is the first The distance from the point to the nearest obstacle; is the safety radius of the obstacle; Indicates from point To point The cost of terrain relief; Indicates the path Each paragraph in; Is the path Total length; , and is the weight coefficient.

[0043] In a second aspect, a geographic information surveying and mapping intelligent planning system includes:

[0044] The acquisition module is used to obtain geographic information data of the area to be surveyed, including terrain, obstacles and traversable paths;

[0045] A preprocessing module, used for preprocessing geographic information data to obtain preprocessed geographic information data;

[0046] The initialization module is used to randomly generate an initial mapping path plan as the current solution based on the preprocessed geographic information data;

[0047] The exchange module is used to determine the initial temperature, the end temperature, and the number of iterations for each temperature. At the current temperature, a new solution is generated by randomly exchanging two points in the current path planning.

[0048] A calculation module is used to determine an objective function for evaluating the quality of path planning, and calculate the objective function values ​​of the current solution and the new solution according to the objective function. If the objective function value of the new solution is better than the current solution, the new solution is used to replace the current solution;

[0049] The iteration module is used to repeat the operation at each temperature until the number of iterations at that temperature is reached, and the temperature is reduced according to the set temperature reduction rate, and the steps are repeated until the temperature drops to the termination temperature; when the temperature drops to the termination temperature, the final planning path is obtained;

[0050] The sending module is used to output the final planned path to the surveying and mapping equipment.

[0051] According to a third aspect, a computing device includes:

[0052] one or more processors;

[0053] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0054] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0055] The above scheme of the present invention includes at least the following beneficial effects.

[0056] This method automatically performs path planning through intelligent algorithms, reducing the need for human intervention and manual planning and improving work efficiency. By preprocessing geographic information data, this method can more accurately understand the terrain, obstacles and traversable paths in the area to be surveyed, thereby generating a more optimized surveying and mapping path. Through the simulated annealing algorithm (indicated by steps such as initial temperature, termination temperature, and temperature iteration), this method can flexibly adjust path planning in different geographic information environments, find the relatively optimal solution, and enhance the adaptability of surveying and mapping path planning.

[0057] By continuously optimizing the path, this method can reduce the walking distance and time during the surveying process, thereby improving the overall efficiency of the surveying work. Optimized path planning means that the surveying equipment can complete more work in a shorter time, thereby reducing manpower, material and time costs. By avoiding obstacles and unfavorable terrain, this method can ensure the reliability and safety of the surveying path, reducing equipment damage and personnel safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flow chart of a method for intelligent planning of geographic information surveying and mapping provided by an embodiment of the present invention.

[0059] Figure 2 It is a schematic diagram of a geographic information surveying and mapping intelligent planning system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0061] like Figure 1 As shown, an embodiment of the present invention provides a method for intelligent planning of geographic information surveying and mapping, the method comprising the following steps:

[0062] Step 11, obtaining geographic information data of the area to be surveyed, including terrain, obstacles and traversable paths;

[0063] Step 12, preprocessing the geographic information data to obtain preprocessed geographic information data;

[0064] Step 13, randomly generating an initial mapping path plan based on the preprocessed geographic information data as the current solution;

[0065] Step 14, determine the initial temperature, the end temperature, and the number of iterations for each temperature, and generate a new solution by randomly exchanging two points in the current path planning at the current temperature;

[0066] Step 15, determining an objective function for evaluating the quality of path planning, calculating the objective function values ​​of the current solution and the new solution according to the objective function, and if the objective function value of the new solution is better than the current solution, replacing the current solution with the new solution;

[0067] Step 16, repeat the operation at each temperature until the number of iterations at that temperature is reached, reduce the temperature according to the set temperature drop rate, and repeat the steps until the temperature drops to the termination temperature;

[0068] Step 17, when the temperature drops to the termination temperature, the final planned path is obtained;

[0069] Step 18: Output the final planned path to the surveying and mapping equipment.

[0070] In the embodiment of the present invention, step 12, through preprocessing, can clean and organize the original data, remove noise and outliers, improve data quality and availability. Step 13, by randomly generating the initial solution, can ensure the diversity of the search process, avoid falling into the local optimal solution, and provide a reasonable starting point for the subsequent optimization process. Step 14, introduce the simulated annealing algorithm, by setting the temperature parameters and the number of iterations, achieve the balance between global search and local search, and improve the probability of finding the global optimal solution. Step 15, quantitatively evaluate the pros and cons of path planning through the objective function, so that the optimization process is more objective and measurable. At the same time, timely replace the current solution with a better solution to ensure that the search process is always moving in a better direction. Step 16, by repeating the search and iteration at different temperatures, the solution space can be fully explored to avoid premature convergence to the local optimal solution. The setting of the temperature drop rate ensures the smooth transition and convergence of the search process. Step 17, after the temperature drops to the termination temperature, it is considered that the search process has fully converged, and the planning path obtained at this time has a high global optimality. Step 18, directly outputting the optimized planned path to the surveying and mapping equipment can improve the efficiency and accuracy of surveying and mapping work and reduce manual intervention and errors.

[0071] In a preferred embodiment of the present invention, the above step 11, obtaining geographic information data of the area to be surveyed and mapped, may include:

[0072] Step 111, randomly generating a set of initial geographic information data collection points according to the scope of the area to be surveyed to form an initial population, each collection point representing a specific geographic location;

[0073] Step 112, defining an evaluation function for evaluating the quality of each collection point;

[0074] Step 113, determining the corresponding individual from the current population and performing a crossover operation to generate a new individual;

[0075] Step 114, performing mutation operation on the new individual, repeating the operation until a preset number of iterations is reached to obtain a final collection point set;

[0076] Step 115, using surveying and mapping equipment to obtain actual geographic information data based on the final collection point set.

[0077] In the embodiment of the present invention, step 111, by randomly generating initial collection points, the extensiveness and diversity of data collection can be ensured to avoid missing important areas. Step 112, the definition of the evaluation function can help quantify the value of each collection point, thereby optimizing the selection of data collection points, helping to pay more attention to key areas during the data collection process, and improving the efficiency and quality of data collection. Step 113, through the crossover operation, the advantages of different collection points can be combined to generate new and potentially better collection points. This helps to discover new and valuable areas during the data collection process and improve the comprehensiveness and accuracy of the data. Step 114, the mutation operation can increase the diversity of the population and avoid falling into a local optimal solution. Through multiple iterations and mutations, the selection of collection points can be gradually optimized, so that the final collection point set is more in line with actual needs, and the efficiency and quality of data collection are improved. Step 115, actual data collection is performed based on the optimized collection point set, which can ensure the accuracy and comprehensiveness of the data. At the same time, since the collection points have been optimized and selected, the surveying and mapping equipment can be used more efficiently for data collection, saving time and resource costs.

[0078] When specifically applied, this includes:

[0079] Step 111, determine the boundary of the area to be surveyed, such as the latitude and longitude range or specific geographic coordinates. Then, use a random number generation algorithm to randomly generate a set of coordinate points within this range, each point representing a potential location for collecting geographic information data. These points constitute the initial collection point population.

[0080] Step 112, defining an evaluation function for evaluating the quality of each collection point.

[0081] Step 113, in the genetic algorithm, the crossover operation simulates the gene crossover process in biological evolution. First, two collection points are randomly selected from the current population as parents. Then, a crossover point is selected to exchange part of the coordinates of the two parent collection points to generate two new collection points (offspring). In this way, the new collection point may inherit the advantages of the parent while introducing new changes.

[0082] Step 114, the mutation operation is to increase the diversity of the population. In each iteration step, a portion of new collection points are randomly selected for mutation. The mutation can be to randomly change a certain coordinate value of the collection point, or to randomly move the position of the collection point within a certain range. Through multiple iterations and mutations, the collection points in the population will be gradually optimized to meet the requirements of the evaluation function. When the preset number of iterations is reached, the iteration is stopped to obtain the final collection point set.

[0083] Step 115, after obtaining the final collection point set, use surveying and mapping equipment (such as drones, remote sensing satellites, etc.) to go to these collection points for actual data collection. According to specific surveying and mapping needs, various geographic information data such as terrain height, landform features, vegetation coverage, etc. can be collected.

[0084] In a preferred embodiment of the present invention, the calculation formula of the evaluation function is:

[0085] ;

[0086] in, Indicate point The traffic density is expressed as traffic flow and road capacity The ratio of , and represents the coefficient; Represents the importance attached to traffic flow; Indicate point To a specific point distance; Indicates the total number of reference points; Indicates a specific reference point; represents the coefficient; among them, , represents the road congestion index; represents the accident frequency; and Represents weight.

[0087] In an embodiment of the present invention, an intelligent planning method can be used to automatically determine the optimal surveying and mapping path, reduce manual intervention and errors, and thus improve the efficiency of surveying and mapping work. The method ensures the quality and comprehensiveness of the data by optimizing the selection of data collection points. The application of genetic algorithms makes the data collection points more reasonable and can cover key areas, thereby improving the accuracy and reliability of the data. The application of simulated annealing algorithms achieves a balance between global search and local search, which helps to find the global optimal solution. This can avoid falling into the local optimal solution and improve the quality of path planning. By defining an objective function to evaluate the pros and cons of path planning, the optimization process is made more objective and measurable. This helps to ensure that the search process always moves in a more optimal direction. The parameters in this method (such as , , , The method can be adjusted according to the actual situation, making it more flexible and adaptable. It can be adjusted and optimized for different surveying and mapping needs and scenarios.

[0088] In a preferred embodiment of the present invention, the above step 12, preprocessing the geographic information data to obtain preprocessed geographic information data, may include:

[0089] Step 121, cleaning the geographic information data to obtain cleaned data;

[0090] Step 122, classifying the cleaned data into different categories according to data type and source, and extracting key features for each category of data, the key features including terrain height, slope, road width and traffic flow;

[0091] Step 123, processing spatial data, overlaying and analyzing different types of data layers, and fusing related features according to spatial position relationships;

[0092] Step 124, for non-spatial attribute data, fusion is performed through statistical analysis;

[0093] Step 125, assigning a weight to each attribute according to the relevance of the data, and using weighted average to calculate the fused attribute value to obtain a fused geographic information dataset;

[0094] Step 126, filtering the fused geographic information data set to obtain pre-processed data.

[0095] In an embodiment of the present invention, by data cleaning (step 121), noise, outliers and duplicate data in the original data can be removed, thereby improving the quality and accuracy of the data. In step 122, the data is classified according to the data type and source, and key features are extracted for each type of data. This classification and feature extraction helps to better understand the nature and characteristics of the data, making subsequent data processing and analysis more accurate and efficient. The spatial data overlay analysis and feature fusion in step 123 can effectively integrate data from different layers. This fusion not only enriches the dimension and depth of the data, but also improves the utilization efficiency and accuracy of spatial data, and helps to more comprehensively reflect the actual situation of geographic information. Through the statistical analysis of step 124, non-spatial attribute data is effectively fused. In step 125, a weight is assigned to each attribute according to the relevance of the data, and the fused attribute value is calculated using weighted average. This method can more accurately reflect the importance of each attribute in geographic information, making the fused data set more representative and practical. Step 126 performs filtering on the fused geographic information data set, which can further remove noise and interference factors in the data, making the data smoother and more stable. This is crucial for subsequent path planning and decision analysis, and can improve the accuracy and reliability of planning.

[0096] The specific implementation process of step 121 can be divided into the following steps:

[0097] Collect geographic information data that needs to be cleaned, which may come from different resources, such as satellite images, map providers, open data, etc. Preliminary sorting of the collected data to ensure the uniformity of the data format for subsequent processing.

[0098] Check whether there are missing values ​​in the data set. For missing values, choose appropriate filling methods based on the characteristics of the data and business needs, such as using mean, median, mode, or using interpolation, prediction models, etc. to estimate. Use statistical methods (such as Z-score, IQR, etc.) or visualization tools (such as box plots) to detect outliers in the data. Determine whether the outliers are reasonable data based on the characteristics of the data. For unreasonable outliers, you can choose to delete or replace them with reasonable values. Check whether there are duplicate records in the data set. For duplicate records, choose to keep one record or merge them based on business needs, ensure that the format of all data fields is correct, such as date, time, coordinates, etc., and standardize the data, such as converting text data into numerical data (such as encoding), or scaling numerical data to a specific range. After cleaning is completed, sample or fully review the data to ensure the accuracy and completeness of the cleaning process, and adjust and optimize the cleaning process based on the audit results.

[0099] For example, suppose a geographic information dataset about urban traffic flow is collected, which contains traffic flow data for each intersection. When cleaning the data, the following problems were found and handled accordingly: When checking the data, it was found that traffic flow data for some intersections in certain time periods were missing. Filling was performed based on the average flow of adjacent time periods. Several abnormally high traffic flow values ​​were detected by the Z-score method. After verification, it was found that these values ​​were caused by special events (such as large-scale events or traffic accidents). It was decided to keep these abnormal values ​​because they reflect the actual situation. Some duplicate records were found in the dataset, which may be caused by repeated operations during data collection. These duplicate records were deleted and only one was retained. The date and time fields in the original data were not in a uniform format, so they were converted to a uniform format (such as YYYY-MM-DD HH:MM:SS). At the same time, in order to facilitate subsequent analysis, the traffic flow data was normalized and scaled to between 0 and 1.

[0100] In a preferred embodiment of the present invention, the above step 122, classifying the cleaned data into different categories according to data type and source, may include:

[0101] Step 1221, determine the number of clusters K, and determine the features used for clustering from the cleaned data;

[0102] Step 1222, initializing K cluster centers, and randomly determining K points in the cleaned data as initial centers;

[0103] Step 1223, assign each data point in the cleaned data to the corresponding cluster center to form K initial clusters, recalculate the center of each cluster, and repeat the steps until the preset number of iterations is reached to obtain the clustering result;

[0104] Step 1224, according to the clustering results, the cleaned data is divided into K categories.

[0105] In an embodiment of the present invention, by classifying the data, each type of data can be processed and analyzed more specifically. This helps to reduce the computing resources and time required to process a large amount of mixed data, thereby improving the efficiency of data processing. The clustered data is easier to understand and interpret. Understanding the different categories of data can help enterprises or researchers allocate resources more reasonably. For example, in marketing, more accurate marketing strategies can be formulated based on different categories of customer groups. The clustering results can provide valuable information for decision makers, helping to better understand the structure and characteristics of the data, so as to make more informed decisions. Clustering algorithms help to discover potential patterns and associations in the data. After simplifying complex data sets into several categories, data visualization can be more easily performed, helping users to understand the data more intuitively. The K-means algorithm is relatively simple and computationally efficient, and is suitable for processing large-scale data sets. At the same time, it can also adjust the number of clusters K according to specific needs to adapt to different application scenarios.

[0106] For example, in step 1221, a city planning department needs to classify urban geographic information data in order to better carry out traffic and urban planning. First, the number of clusters K is determined to be 4, which means that the data is expected to be divided into four categories. From the cleaned geographic information data, the following features are selected for clustering: terrain height, slope, road width and traffic flow. These features can comprehensively reflect various aspects of the urban geographical environment.

[0107] In step 1222, the planning department randomly selects 4 points from the cleaned data as initial cluster centers. These points represent different geographical environment features in the city, such as commercial areas, residential areas, industrial areas, and park areas.

[0108] Step 1223, next, the planning department begins to assign data points to the nearest cluster center, forming four initial clusters. Then, the center of each cluster is recalculated and the data points are redistributed according to the new center. This process is repeated many times until the location of the cluster center is basically stable and no longer changes significantly. Finally, four stable clustering results are obtained, corresponding to different areas in the city.

[0109] Step 1224, based on the clustering results, the planning department successfully classified the cleaned geographic information data into four categories. These categories represent commercial intensive areas (high traffic flow, low slope, low terrain height), residential quiet areas (medium traffic flow, gentle slope, medium terrain height), industrial production areas (low traffic flow, flat terrain, wide roads) and park recreation areas (low traffic flow, variable slope, high terrain height). Such classification results provide an important reference for urban planning, which helps to optimize urban traffic layout and improve the quality of life of residents.

[0110] In a preferred embodiment of the present invention, the above step 123, processing spatial data, overlaying and analyzing different types of data layers, and fusing related features according to spatial position relationships, may include:

[0111] Step 1231, determining corresponding weights for the terrain height layer and the slope layer respectively;

[0112] Step 1232, traverse each pixel position, perform weighted calculation according to the weights of the two layers and the original pixel value, and obtain the pixel value of the new layer;

[0113] Step 1233, based on the pixel values ​​of the new layer, create a new blank layer to store the merged data, and fill the calculated new pixel values ​​into the corresponding positions of the new layer.

[0114] In an embodiment of the present invention, by overlaying and analyzing different types of data layers (such as terrain height and slope), the comprehensive characteristics of the geographical environment can be more comprehensively reflected. This integration helps to form a more detailed and accurate spatial information expression. The new layer after weighted calculation provides decision makers with richer information, which helps to make more informed decisions in areas such as planning, design or crisis management. For example, in the process of urban planning, terrain and slope factors can be comprehensively considered to optimize road layout or determine the suitability of building land. Through one-time layer overlay and weighted calculation, the need for multiple queries and comparisons of different layer data can be reduced, thereby simplifying the analysis process and improving work efficiency. The method allows the weights of different layers to be adjusted according to actual needs to adapt to different analysis scenarios. At the same time, this overlay analysis method can also be extended to other types of spatial data layers, such as soil type, vegetation cover, etc. By merging multiple layer features, a more informative and intuitive visual map can be generated.

[0115] When specifically applied, this includes:

[0116] Step 1231, collect historical data of terrain height layer and slope layer, which may come from satellite remote sensing, laser radar scanning (LiDAR) or other geographic information collection technology. Ensure that the collected data has consistent spatial resolution and geographic coordinate system to facilitate subsequent analysis and layer overlay. According to application requirements, statistical analysis methods are used to determine the importance of terrain height and slope. For example, regression analysis can be used to study how terrain height and slope affect specific geographical phenomena (such as flood risk, land use type, etc.). Use GIS software to process and analyze terrain height and slope data.

[0117] Through regression analysis, the correlation between terrain height and slope and specific application goals is studied. For example, in flood risk assessment, how terrain height and slope affect the probability and severity of floods is analyzed. Based on the analysis results, the importance of terrain height and slope in specific applications is evaluated. If terrain height has a greater impact on the application goal, it will be assigned a higher weight. Based on the results of data analysis, weight values ​​are assigned to the terrain height layer and the slope layer respectively. These weight values ​​reflect the importance of each layer in a specific application. If the data analysis shows that terrain height has a greater impact on the application goal, the terrain height layer can be given a higher weight, such as 0.6. Correspondingly, the slope layer is assigned a lower weight, such as 0.4. Ensure that the sum of the weights of the two layers is 1 to maintain consistency in weight assignment. Record the determined weight values ​​in the configuration file or database. Clearly mark the weight value of each layer and its corresponding layer name in the configuration file to ensure the accuracy of subsequent processing. In actual applications, the rationality of the assigned weights is verified by comparing the results of layer overlay using different weights. If it is found that improper weight assignment causes the results to deviate from expectations, the weights can be fine-tuned according to the actual situation and re-verified.

[0118] Step 1232, load the data of the terrain height layer and the slope layer, and ensure that they have the same spatial resolution and alignment. Prepare a new layer to store the weighted pixel values. This new layer should have the same spatial resolution and range as the original layer. Use a nested loop to traverse each pixel position. For each position, read the pixel values ​​of the terrain height layer and the slope layer at that position. According to the weights determined in step 1231, the pixel values ​​of the terrain height and slope are weighted. For example, if the weight of the terrain height is 0.6 and the weight of the slope is 0.4, the pixel value of the new layer = (terrain height pixel value × 0.6) + (slope pixel value × 0.4). The new pixel value after weighted calculation is temporarily stored in memory so that it can be filled into the new layer in subsequent steps.

[0119] Step 1233, create a new blank layer in the GIS system, whose spatial resolution, range and coordinate system are consistent with the original layer. Fill the new pixel values ​​calculated in step 1232 into the corresponding positions of the new layer. This usually involves writing the calculation results in memory to the data structure of the new layer. Save the new layer filled with new pixel values ​​in a GIS file format (such as GeoTIFF, ESRI Shapefile, etc.) for subsequent use and analysis. Verify the new layer to ensure that all pixels are correctly filled and the data range and distribution are as expected. If necessary, a visual check can be performed to ensure the accuracy of the layer merge.

[0120] The above step 13 may include:

[0121] Preprocessed geographic information data, including terrain, obstacles, walkable areas, etc. Based on this data, an initial mapping path plan is randomly generated. An initial, possibly non-optimal mapping path plan is used as the current solution.

[0122] Step 14, determine the initial temperature (T_init), which is a relatively high temperature value used to start the simulated annealing algorithm. Determine the final temperature (T_final), which is the temperature at which the algorithm stops. Determine the number of iterations (N_iter) for each temperature, that is, how many new solutions to try at each temperature. At the current temperature, generate a new solution by randomly swapping two points in the current path plan. This swap is the "perturbation" step in the simulated annealing algorithm, which is used to generate new possible solutions.

[0123] Step 15, define an objective function to evaluate the quality of path planning. Use this objective function to calculate the objective function values ​​of the current solution and the new solution. If the objective function value of the new solution is better than the current solution (for example, the path is shorter and safer), replace the current solution with the new solution.

[0124] Step 16, at each temperature, repeatedly generate new solutions and evaluate their quality (as described in steps 14 and 15); after reaching the number of iterations at that temperature, reduce the temperature according to the set temperature drop rate (such as exponential drop, linear drop, etc.), and repeat the above process until the temperature drops to the termination temperature.

[0125] Step 17: When the temperature drops to the termination temperature, the algorithm stops, and the current solution at this time is the final planned path.

[0126] Step 18, output this path to the surveying and mapping equipment for use in surveying and mapping tasks.

[0127] For example, a surveying company needs to survey a complex terrain that includes mountains, rivers, forests, and multiple obstacles such as rocks and trees. In order to complete the surveying task efficiently and safely, the company decided to use the simulated annealing algorithm to plan an optimal surveying path.

[0128] Step 13, Preprocessed Geographic Information Data: The company first collected detailed data on the terrain, including the slope of the mountains, the width and depth of the rivers, the density of the forests, and the specific location of obstacles. Based on this data, the company used a random number generator to create an initial mapping path.

[0129] Step 14, Initial temperature (T_init): Set to 1000, which means that the algorithm is more likely to accept a bad solution at the beginning. Final temperature (T_final): Set to 1, which means that the algorithm will almost never accept a bad solution at the end. Number of iterations per temperature (N_iter): Set to 100, which means that at each temperature, the algorithm will try 100 new solutions. At the current temperature, the algorithm randomly selects two points on the path and swaps their positions to generate a new path plan.

[0130] Step 15: Define an objective function. For the current solution and the new solution, the algorithm calculates their objective function values ​​respectively. If the objective function value of the new solution is lower (i.e., the path is better), the new solution replaces the current solution.

[0131] Step 16, at each temperature, the algorithm repeatedly generates new solutions and evaluates their quality. After reaching 100 iterations, the temperature is reduced in an exponential manner, for example, each time it is reduced to half of the original value.

[0132] Step 17: When the temperature drops to the termination temperature 1, the algorithm stops searching, and the current solution at this time is the optimized final mapping path.

[0133] Step 18: Output the final path to the surveying equipment for use by the surveying team in actual operations. Through this case, the surveying company was able to use the simulated annealing algorithm to find a relatively optimal surveying path in a complex geographic information environment, thereby improving surveying efficiency and ensuring the safety of the team.

[0134] In a preferred embodiment of the present invention, the calculation formula of the objective function is:

[0135] ;

[0136] in, Is the path The number of points on Is the first The distance from the point to the nearest obstacle; is the safety radius of the obstacle; Indicates from point To point The cost of terrain relief; Indicates the path Each paragraph in; Is the path Total length; , and is the weight coefficient.

[0137] In the embodiment of the present invention, the objective function It takes into account several important factors in path planning, including path length, safety, and terrain undulation cost. , and , these factors can be flexibly balanced to generate an optimized path that meets actual needs. Path length is the most intuitive optimization goal. By minimizing path length, surveying efficiency can be improved and walking time can be reduced. Safety The distance from each point on the path to the nearest obstacle is considered. The farther the points on the path are from the obstacles, the higher the safety. By maximizing the average safety index, the risk of collision with obstacles can be reduced. Terrain undulation cost It reflects the difficulty of the path when crossing different terrains. In complex terrains, such as mountains and rivers, the walking cost will be relatively high. By minimizing the cost of terrain undulations, a flatter and easier-to-walk path can be selected. Combining these three aspects, the objective function The beneficial effects are:

[0138] By adjusting the weight coefficient, the optimized path planning can be flexibly generated according to different surveying and mapping tasks and environmental conditions. The path length, safety and terrain undulation cost are taken into account at the same time to ensure that the generated path is optimized in many aspects. This objective function is suitable for complex geographic information environments and can effectively guide the planning of surveying and mapping paths, improving surveying and mapping efficiency and safety.

[0139] like Figure 2 As shown, an embodiment of the present invention further provides a geographic information surveying and mapping intelligent planning system 20, comprising:

[0140] The acquisition module 21 is used to acquire geographic information data of the area to be surveyed, including terrain, obstacles and traversable paths;

[0141] The preprocessing module 22 is used to preprocess the geographic information data to obtain preprocessed geographic information data;

[0142] Initialization module 23, used to randomly generate an initial mapping path plan as the current solution based on the preprocessed geographic information data;

[0143] An exchange module 24 is used to determine an initial temperature, an end temperature, and the number of iterations for each temperature, and to generate a new solution by randomly exchanging two points in the current path plan at the current temperature;

[0144] A calculation module 25 is used to determine an objective function for evaluating the quality of path planning, and calculate the objective function values ​​of the current solution and the new solution according to the objective function. If the objective function value of the new solution is better than the current solution, the new solution is used to replace the current solution;

[0145] Iteration module 26 is used to repeat the operation at each temperature until the number of iterations at the temperature is reached, reduce the temperature according to the set temperature reduction rate, and repeat the steps until the temperature drops to the termination temperature; when the temperature drops to the termination temperature, the final planning path is obtained;

[0146] The sending module 27 is used to output the final planned path to the surveying and mapping equipment.

[0147] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0148] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0149] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0150] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for intelligent planning of geographic information surveying and mapping, characterized in that: The method comprises: Obtain geographic information data of the area to be surveyed, including terrain, obstacles, and traversable paths; Preprocessing the geographic information data to obtain preprocessed geographic information data; According to the preprocessed geographic information data, an initial mapping path plan is randomly generated as the current solution; Determine the initial temperature, the end temperature, and the number of iterations for each temperature, and generate a new solution by randomly exchanging two points in the current path planning at the current temperature; Determine the objective function used to evaluate the quality of path planning, calculate the objective function values ​​of the current solution and the new solution based on the objective function, and replace the current solution with the new solution if the objective function value of the new solution is better than the current solution; Repeat the operation at each temperature until the number of iterations at that temperature is reached, reduce the temperature according to the set temperature drop rate, and repeat the steps until the temperature drops to the termination temperature; When the temperature drops to the termination temperature, the final planned path is obtained; Output the final planned path to the surveying and mapping equipment; Obtain geographic information data of the area to be surveyed, including: According to the scope of the area to be mapped, a set of initial geographic information data collection points are randomly generated to form an initial population, and each collection point represents a specific geographical location; Define an evaluation function to evaluate the quality of each collection point; Determine the corresponding individuals from the current population and perform a crossover operation to generate new individuals; Perform mutation operation on new individuals and repeat the operation until the preset number of iterations is reached to obtain the final set of collection points; Based on the final set of collection points, use surveying and mapping equipment to obtain actual geographic information data; The calculation formula of the evaluation function is: ； in, Indicate point The traffic density is expressed as traffic flow and road capacity The ratio of represents the coefficient; Represents the importance attached to traffic flow; Indicate point To a specific point distance; Indicates the total number of reference points; Indicates a specific reference point; represents the coefficient; among them, , represents the road congestion index; represents the accident frequency; represents weight; Preprocessing the geographic information data to obtain preprocessed geographic information data includes: The geographic information data will be cleaned to obtain cleaned data; The cleaned data is divided into different categories according to the data type and source. For each category of data, key features are extracted, including terrain height, slope, road width and traffic flow; Process spatial data, overlay and analyze different types of data layers, and fuse related features based on spatial location relationships; For non-spatial attribute data, fusion is performed through statistical analysis; According to the relevance of the data, a weight is assigned to each attribute, and the fused attribute value is calculated using weighted average to obtain a fused geographic information dataset; Filter the fused geographic information data set to obtain preprocessed data; The cleaned data is divided into different categories based on data type and source, including: Determine the number of clusters K, and determine the features used for clustering from the cleaned data; Initialize K cluster centers and randomly determine K points in the cleaned data as the initial centers; Assign each data point in the cleaned data to the corresponding cluster center to form K initial clusters, recalculate the center of each cluster, and repeat the steps until the preset number of iterations is reached to obtain the clustering result; According to the clustering results, the cleaned data is divided into K categories; Process spatial data, overlay and analyze different types of data layers, and fuse related features based on spatial location relationships, including: Determine the corresponding weights for the terrain height layer and slope layer respectively; Traverse each pixel position, perform weighted calculation based on the weights of the two layers and the original pixel value, and get the pixel value of the new layer; According to the pixel value of the new layer, create a new blank layer to store the merged data, and fill the calculated new pixel value into the corresponding position of the new layer; The calculation formula of the objective function is: ； in, Is the path The number of points on Is the first The distance from the point to the nearest obstacle; is the safety radius of the obstacle; Indicates from point To point The cost of terrain relief; Indicates the path Each paragraph in; Is the path Total length; is the weight coefficient.

2. A geographic information surveying and mapping intelligent planning system, characterized in that: Applied in the method as claimed in claim 1, comprising: The acquisition module is used to obtain geographic information data of the area to be surveyed, including terrain, obstacles and traversable paths; A preprocessing module, used for preprocessing geographic information data to obtain preprocessed geographic information data; The initialization module is used to randomly generate an initial mapping path plan as the current solution based on the preprocessed geographic information data; The exchange module is used to determine the initial temperature, the end temperature, and the number of iterations for each temperature. At the current temperature, a new solution is generated by randomly exchanging two points in the current path planning. A calculation module is used to determine an objective function for evaluating the quality of path planning, and calculate the objective function values ​​of the current solution and the new solution according to the objective function. If the objective function value of the new solution is better than the current solution, the new solution is used to replace the current solution; The iteration module is used to repeat the operation at each temperature until the number of iterations at that temperature is reached, and the temperature is reduced according to the set temperature reduction rate, and the steps are repeated until the temperature drops to the termination temperature; when the temperature drops to the termination temperature, the final planning path is obtained; The sending module is used to output the final planned path to the surveying and mapping equipment.

Images