Rural settlement texture extension quantitative evaluation method and system

Abstract

The invention discloses a rural settlement texture extension quantitative evaluation method and system, and the method comprises the steps: selecting a typical village, and obtaining the index data of the typical village; generating a plurality of texture plane graphs according to the typical villages, and performing texture extension degree scoring on the texture plane graphs; generating a texture scoring sample according to the index parameters and scores corresponding to the texture plane graph; training a village texture extensibility evaluation model according to the texture scoring sample; and evaluating the extension degree of the village settlement by using the village texture extension degree evaluation model. By using the scheme of the invention, efficient, objective and automatic guidance control and evaluation of village texture can be realized, and effective support is provided for village planning practice of different types and regions.

Description

Technical Field

[0001] The present invention relates to the field of rural settlement planning, and in particular to a rural settlement texture inheritance quantitative evaluation method and system. Background Art

[0002] Rural settlements refer to various forms of human habitation in rural areas (i.e., villages). The spatial texture of rural settlements refers to the organic spatial characteristics formed through the integration of natural systems that reflect rural ecology and artificial systems that reflect rural historical traditions through historical evolution and long-term effects. This overall reflects a settlement form with a certain scale and organic growth structure, and also reflects the historical, cultural, and natural characteristics of the local environment. This natural and organic spatial form that appears to be disordered but actually hides an inherent order is the essential feature that distinguishes rural areas from cities. However, the current domestic rural planning and construction practices have the following situations, which have led to a trend of homogenization and one-sidedness in the style of rural settlements: (1) Lack of basic research data on village spatial morphological parameters: The current assessment of village planning is limited to the surface due to the lack of comprehensive data support. (2) Lack of guidance and control strategies for village spatial morphology at the meso level: Relevant documents and guidelines mainly start from the macro-control of villages or the construction of micro-elements, while ignoring the importance of village spatial morphology at the meso level. (3) Lack of quantitative evaluation system and guidance strategy: At present, the planning of rural characteristic spatial texture mainly relies on descriptive texts, and there is a lack of quantitative evaluation system to provide more objective guidance for rural planning. Therefore, in the context of rapid urbanization, it is urgent to comprehensively study and protect the spatial form of rural settlements. At present, there have been a lot of studies on the analysis of the spatial form texture of rural settlements, but most quantitative indicators focus on the descriptive analysis of rural spatial texture and fail to provide constructive guidance in actual planning; and the existing texture quantitative evaluation mainly adopts subjective evaluation methods and qualitative evaluation indicators, lacks quantitative evaluation of objective indicators, and is difficult to use the evaluation results of spatial form texture to guide rural planning and spatial construction in practical projects. Summary of the invention

[0003] The present invention provides a method and system for quantitative evaluation of rural settlement texture inheritance, so as to realize efficient, objective and automated control and evaluation of village texture, and provide effective support for village planning practices of different types and regions.

[0004] To this end, the present invention provides the following technical solutions: In one aspect, the present invention provides a method for quantitatively evaluating the inheritance of rural settlement texture, the method comprising: Selecting typical villages and obtaining indicator data of the typical villages; generating a plurality of texture plane maps according to the typical village, and scoring the texture continuity of the texture plane maps; Generate a texture score sample according to the index parameters and scores corresponding to the texture plane map; Training a village texture continuity evaluation model according to the texture scoring samples; The village texture continuity evaluation model is used to evaluate the continuity of rural settlements.

[0005] Optionally, the method further comprises: determining an indicator parameter for evaluating village texture; The step of obtaining the indicator data of the typical village includes: The indicator data of the typical village is extracted according to the indicator parameters.

[0006] Optionally, the indicator parameters determined for evaluating the village texture include: According to the screening principle, the quantitative indicators with high frequency of occurrence for characterizing the plane dimension of village building mechanism are screened from the relevant literature to obtain the initial screening indicators; the screening principle includes: excluding non-quantifiable indicators; excluding linear description indicators; excluding indicators unrelated to building texture; excluding three-dimensional morphology related indicators; Classifying the initial screening indicators; Select representative indicator parameters according to different categories of the initial screening indicators; The indicator parameters for evaluating village texture were determined through correlation analysis.

[0007] Optionally, the classifying the preliminary screening indicators includes: classifying the preliminary screening indicators into the following four categories: building density, building distribution disorder, building base shape, and building base shape complexity.

[0008] Optionally, the representative index parameters include: building density, building unit angle disorder index, building unit spacing disorder index, building width-to-depth ratio, and building base area variation coefficient.

[0009] Optionally, the method further comprises: Establishing a village texture database, wherein the village texture database includes basic village information and indicator data; The selected typical villages include: A typical village is selected from the village texture database.

[0010] Optionally, the method further comprises: performing data enhancement on the texture score sample by random rotation and / or horizontal mirroring.

[0011] Optionally, the method further comprises: performing the following processing on the score in sequence: data standardization, extreme value removal and average value calculation, and outlier removal.

[0012] Optionally, the village texture continuity evaluation model adopts a convolutional neural network model based on a residual network.

[0013] On the other hand, the present invention also provides a rural settlement texture inheritance quantitative evaluation system, the system comprising: A data acquisition module, used to select typical villages and obtain indicator data of the typical villages; An image generation module, used for generating a plurality of texture plane images according to the typical village; A scoring module, used for scoring the texture continuity of the texture plan; A sample generation module, used to generate a texture scoring sample according to the index parameters and scores corresponding to the texture plan; A training module, used for training a village texture continuity evaluation model according to the texture scoring samples; An evaluation module is used to evaluate the continuity of rural settlements using the village texture continuity evaluation model.

[0014] Optionally, the system further includes: an indicator parameter determination module, which determines indicator parameters for evaluating village texture.

[0015] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the rural settlement texture inheritance quantitative evaluation method are executed.

[0016] The method and system for quantitative evaluation of rural settlement texture inheritance provided by the present invention select typical villages and obtain indicator data of typical villages; generate corresponding texture plan maps, and score the texture inheritance of the texture plan maps, generate texture scoring samples, and combine machine learning to train a village texture inheritance evaluation model to achieve automatic, objective and efficient evaluation of rural settlement inheritance, provide theoretical basis and technical support for village planning and design for rural planners, designers and decision makers, and help achieve rural revitalization, traditional village protection and sustainable development goals.

[0017] Furthermore, the key evaluation indicators proposed in this invention can comprehensively and accurately reflect the complexity and continuity of the spatial morphological texture of rural settlements. These indicators lay a theoretical foundation for the systematic analysis and evaluation of rural settlement texture.

[0018] Compared with the existing texture quantitative evaluation scheme, the scheme of the present invention has the following beneficial effects: 1) Guiding rural planning practice through quantitative evaluation indicators: Through the quantitative evaluation indicators of rural settlement texture, the quantitative analysis results of spatial morphological texture can guide rural planning and space construction in practical projects and provide effective data support.

[0019] 2) Improve the scientific objectivity of the evaluation: By combining scoring with machine learning, the subjective errors caused by relying solely on manual judgment are eliminated, ensuring the objectivity and consistency of the evaluation process; moreover, through the mutual complementation and verification of manual scoring and machine learning, the texture continuity of rural settlements can be evaluated more objectively and accurately, effectively improving the scientificity and practicality of the evaluation.

[0020] 3) Improve evaluation efficiency: Traditional evaluation methods often require experts to score and analyze each item or manually conduct comparative analysis of data, which is time-consuming and prone to errors. The solution of the present invention can quickly process a large amount of image data and significantly improve evaluation efficiency, especially when facing large-scale village data, which has obvious advantages.

[0021] 4) Expanding the scope of application: The scheme of the present invention can be widely applied to different types of rural settlements. By adding texture planes from different regions and types of villages to the training set of the machine learning model, it can support large-scale identification and evaluation work and realize the quantitative evaluation of the inheritance of village textures in various regions.

[0022] 5) The quantitative evaluation of rural settlement texture inheritance has high accuracy: The quantitative evaluation model of village texture inheritance constructed in the scheme of the present invention has an overall accuracy of 71%, which performs well and can effectively support the evaluation of village texture. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a quantitative evaluation method for rural settlement texture inheritance according to an embodiment of the present invention; Figure 2 is a schematic diagram of the score distribution of the texture plane map in an embodiment of the present invention; Figure 3 This is a structural schematic diagram of a rural settlement texture inheritance quantitative evaluation system according to an embodiment of the present invention; Figure 4 It is another structural schematic diagram of the rural settlement texture inheritance quantitative evaluation system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] like Figure 1 FIG. 1 is a flow chart of a method for quantitatively evaluating the inheritance of rural settlement texture provided by an embodiment of the present invention, comprising the following steps: Step 101: Select a typical village and obtain indicator data of the typical village.

[0028] In the embodiment of the present invention, the index parameters for evaluating the village texture may be determined first, and the index data of the typical village may be extracted according to the determined index parameters.

[0029] In order to evaluate the inheritance of rural settlement texture more accurately and comprehensively, we can conduct a literature survey and conduct a preliminary screening of relevant indicators that appear frequently in the literature; then select indicator parameters for evaluating village texture from the preliminary screened indicators.

[0030] Since the scheme of the present invention only focuses on the quantitative indicators of the village building texture in the plane dimension, the following screening principles can be followed: (1) exclude non-quantifiable indicators; (2) exclude linear description indicators; (3) exclude indicators that are not related to the building texture; (4) exclude three-dimensional morphology related indicators.

[0031] In other words, according to the above screening principles, quantitative indicators with higher frequency of occurrence used to characterize the village construction mechanism in the plane dimension are screened from relevant literature to obtain preliminary screening indicators.

[0032] Then, the initial screening indicators are classified, for example, into the following four categories: building density, building distribution disorder, building base shape and building base shape complexity.

[0033] According to these classifications, representative indicator parameters are selected. For example, the selected representative indicator parameters may include the following five: building density, building unit angle disorder index, building unit spacing disorder index, building width-to-depth ratio, and building base area variation coefficient, as shown in Table 1.

[0034] Table 1

[0035] When selecting representative indicator parameters, one or more representative indicators can be selected from each type of indicator parameters. For example, among the four indicator parameters in the category of building base shape, the building width-to-depth ratio can more comprehensively reflect the indicator category of building base shape than the average building base area, building width, and building depth. Therefore, in the category of building base shape, the building width-to-depth ratio is selected. The same is true for other categories, which will not be described one by one.

[0036] The definitions and calculation formulas of the above five representative indicator parameters are as follows: (1) Building density It refers to the ratio of the total base area of ​​buildings to the occupied land area within a certain range. The formula is as follows: (1.1) In the formula, Indicates building density; Indicates the total base area of ​​the building (unit: m 2 ); Indicates the floor area (unit: m 2 ).

[0037] (2) Building width-to-depth ratio Refers to the ratio of building width to building depth, and the formula is as follows: (1.2) In the formula, Indicates the building width-to-depth ratio; Indicates the building width (m); Indicates the building depth (unit: m).

[0038] (3) Coefficient of variation of building base area Refers to the ratio of the standard deviation of the building base area to the average value, which is mainly used to reflect the changing trend of the building base area. The formula is as follows: (1.3) In the formula, represents the coefficient of variation of building base area; represents the standard deviation of the building base area; Represents the average building base area.

[0039] (4) Building unit angle disorder index Regarding the orientation of the village residences, it is assumed that only the relative angle of each residence in the village relative to the south is considered, and the south direction is set to 0 degrees, the eastward direction is positive, and the westward direction is negative. The orientation of the settlement is only controlled within plus or minus 45 degrees, and when -45 degrees appears, it is converted to positive by default. The indicator calculation formula is as follows: (1.4) In the formula, It indicates the angle disorder index of a building unit; Indicates the average value of building angles; represents the standard deviation of building angles; Indicates the mean of the absolute values ​​of the building angles.

[0040] (5) Building unit spacing disorder index It refers to the degree of variation of the distance order element between building units in the village. The calculation formula is as follows: (1.5) In the formula, It indicates the disorder index of the distance between building units; It represents the average building spacing; represents the standard deviation of building spacing; Represents the standard deviation of the minimum distance between buildings in the village.

[0041] Finally, the indicator parameters for evaluating village texture were determined through correlation analysis.

[0042] In a non-limiting embodiment, it can be found through Pearson correlation analysis (as shown in Table 2) that the building spacing disorder index and the building density and base area variation coefficient show a significance of 0.01 level, and the correlation coefficients are -0.655 and 0.565 respectively. Therefore, the building spacing disorder index is eliminated, and the other four items selected in Table 1, namely building density, building width-to-depth ratio, building base area variation coefficient, and building angle disorder index, are used as key indicators for texture evaluation, that is, the indicator parameters for evaluating village texture.

[0043] For example, the Pearson correlation analysis in the existing SPSS (Statistical Package for the Social Sciences) data analysis software can be used to detect the correlation between continuous numerical variables. By importing the five indicator data that have been collected, the software can analyze the data. The results automatically output after the software analysis are shown in Table 2.

[0044] Table 2

[0045] In Table 2, Indicates correlation p<0.05, Indicates a correlation of p < 0.01.

[0046] It should be noted that, in order to facilitate the subsequent use of the collected village texture data, in a non-limiting embodiment, a village texture database can also be established through data collection, and the village texture database includes basic village information and indicator data.

[0047] Accordingly, typical villages can be selected from the established village texture database and corresponding indicator data can be extracted.

[0048] In specific implementation, the basic information and texture data of the village can be collected through various methods, such as: On the one hand, relevant data on the above four key indicator parameters of the target area can be collected through literature and atlas surveys.

[0049] On the other hand, drone oblique photography technology can be used for field research to obtain two-dimensional and three-dimensional spatial information of the village, and combined with the existing village floor plans collected on the planning cloud and Open Street Map (OSM, an open source map data source), and further supplemented with two-dimensional information. Subsequently, the outline of the residential buildings in the village floor plan is outlined by using CAD, and statistical analysis of all buildings in the village is performed. For example, the Grasshopper plug-in based on Rhino (a 3D modeling design software) is used to extract the outline of all building monomers in the village, calculate the side length and area, calculate the angle, and other analysis and calculation steps, thereby realizing the data collection of the four indicator parameters, establishing the corresponding land texture database, and determining the threshold range of the key texture evaluation indicator parameters, as shown in Table 3.

[0050] Table 3

[0051] The selection criteria for typical villages can take into account factors such as geographical location, village type, and scale differences to ensure the typicality and breadth of the sample.

[0052] Step 102: Generate multiple texture plan maps based on the typical village, and score the texture continuity of the texture plan maps.

[0053] For example, for the above-mentioned XX plain water village, 6 strip villages and 6 cluster villages were selected as prototype villages for expert scoring. The name, scale and other information of the prototype villages are shown in Table 4.

[0054] Table 4

[0055] It should be noted that, in specific implementation, the texture plan of a typical village can be adjusted through some image processing to provide richer texture plan samples.

[0056] For example, by using basic operations in CGA (Computer Generated Architecture) in CityEngine software (such as s(), r(), etc.), buildings with a scale of 25%, 50% or 100% can be randomly scaled, rotated, and transformed to adjust the four key indicator parameters of building density, building width-to-depth ratio, building base area variation coefficient, and building unit spacing disorder index, thereby generating more different texture plan views.

[0057] In the embodiment of the present invention, the ratio of the changed indicator data to the original indicator data can be used as the fluctuation degree of the indicator, and the calculation formula is as follows: (1.6) In the formula, Indicates the volatility of the indicator; Indicates the changed indicator data; Represents the original indicator data.

[0058] For example, a non-restrictive indicator parameter adjustment rule is shown in Table 5.

[0059] Table 5

[0060] In a non-limiting embodiment, an expert scoring method may be used to score the texture continuity.

[0061] For example, an expert scoring platform can be built based on Python language to evaluate the generated village texture plan. The platform interface displays the prototype village plan on the left, and the plan with adjusted texture parameters on the right. Experts judge the continuity of the newly generated texture by comparing it with the original texture, and give a score of 1 to 5, where 1 indicates the lowest degree of texture continuity and 5 indicates the highest degree of texture continuity.

[0062] In order to ensure the authority and professionalism of the scoring, several experts in the field of architecture with many years of experience can be invited to participate in the scoring. These experts can come from multiple related fields such as urban planning, architectural design and rural construction. They can comprehensively evaluate the continuity of rural settlement texture from different professional perspectives. In order to improve the accuracy and consistency of the scoring, the scoring process is divided into two rounds. Specifically, in the first round of scoring, in order to avoid scoring deviations due to expert fatigue, multiple experts can score all (for example, 648) texture plan drawings independently twice. The number of pictures scored in the first round is N1 (for example, 270 pictures), and the number of pictures scored in the second round is N2 (for example, 378 pictures). In the second round, for sample drawings with large differences in scores, an expert is invited to re-evaluate to ensure the accuracy and consistency of the results. Through this double-verified scoring mechanism, the fairness and objectivity of the scoring can be guaranteed to the greatest extent, thus providing a reliable basis for subsequent data analysis.

[0063] Furthermore, in order to ensure the accuracy of the scoring, the scoring can also be processed as follows: (1) Data standardization Z-score (standard score) is a statistic used to measure the distance between a data point and the mean, with standard deviation as the unit. It describes the relative position of the data point to the mean and is a dimensionless value that can be used to compare the distribution of different data sets. In order to eliminate the differences in scores between different experts, the scores of each expert are first Z-score standardized. Through this method, the mean of each expert's score is adjusted to 0 and the standard deviation is 1. The calculation formula is shown in (1.7). The purpose of standardization is to convert all scores to the same scale, thereby eliminating deviations caused by individual scoring habits or different scoring standards, and improving the consistency and accuracy of data analysis.

[0064] (1.7) In the formula, represents the standardized expert rating score; It represents the average of the expert's ratings; Indicates the standard value of the expert's score.

[0065] (2) Extreme value removal and average value calculation On the basis of standardized scoring, we further exclude extreme values ​​in the scoring, and then calculate the mean of all expert scores for each floor plan. The purpose of this step is to reduce the impact of extreme values ​​(such as abnormally high or low scores) on the final score, thereby ensuring the stability and representativeness of the scoring results. The final score of each picture is the mean of the expert scores after removing extreme values.

[0066] (3) Outlier removal Outliers are data points that differ significantly from other scores, which may be caused by scoring errors or other factors. The purpose of this step is to exclude these abnormal data to improve the quality of the dataset and the reliability of the analysis results.

[0067] Step 103: Generate a texture score sample according to the index parameters and scores corresponding to the texture plan map.

[0068] In a non-limiting embodiment, the quartile method may be used to rank pictures with different scores.

[0069] for example Figure 2 As shown in the figure, according to the scoring results, the 575 texture plane images after the above data processing are divided into three levels: "Excellent" level refers to images with a score greater than 0.5 points, with a total of 174 images; "Medium" level refers to images with a score between -0.6 points and 0.5 points, with a total of 221 images; "Poor" level refers to images with a score lower than -0.6 points, with a total of 180 images. Among them, "Excellent" level means that the texture has a high degree of continuity, and "Poor" level means that the texture has a low degree of continuity.

[0070] Step 104: training a village texture continuity evaluation model based on the texture score samples.

[0071] In the embodiment of the present invention, the village texture continuity refers to the continuity and inheritance of spatial morphological features such as the village spatial structure, building layout, and building form.

[0072] In a non-limiting embodiment, the village texture continuity evaluation model can adopt a convolutional neural network model based on a residual network. Since the residual network performs well in image classification and recognition tasks, and considering that the data set of this model is small and the task is relatively simple (for example, it is divided into three categories: excellent, medium, and poor), a lightweight ResNet-18 can be selected as the basic model. This model can effectively balance performance and computational efficiency, especially when the data set is small, it can achieve better classification results without requiring too many computing resources. In addition, in order to further improve the training efficiency, generalization ability, performance performance, etc. of the model in specific tasks, a pre-trained ResNet-18 model can be used. The model has learned rich features on large-scale data sets such as ImageNet. These features can help the model converge quickly and reduce training time and computing resources. And transfer learning enables the pre-trained model to quickly adapt to new tasks. In addition, the pre-trained model borrows knowledge from large-scale data sets, which can effectively improve the generalization ability of the model and avoid overfitting on small data sets.

[0073] Furthermore, in order to increase the diversity of the data set and improve the robustness of the model, the training data can also be enhanced. Since random rotation and horizontal mirroring have a wide range of applications and good performance in data enhancement, one or both of the above two methods can be selected for data enhancement. Thus, two additional samples are generated for each original image, so that the size of the data set can be expanded to three times the original size (for example, a total of 1725 images). The image data set used in the present invention can include three types of labels: excellent, medium and poor, and they are mapped to numerical values ​​(excellent = 2, medium = 1, poor = 0). To ensure the scientific nature of model training and evaluation, the data set is divided into a training set (80%), a validation set (10%) and a test set (10%). In the process of data division, in order to ensure that the proportion of each category label in each subset is consistent, a stratified sampling method is adopted. This method avoids the deviation that may be caused by uneven data distribution by ensuring that the distribution of each category label in each subset is the same as that of the original data set, thereby ensuring the stability and fairness of model training.

[0074] The specific training process of the village texture continuity evaluation model can refer to the existing relevant model training process, which will not be repeated here.

[0075] Step 105: Use the village texture continuity evaluation model to evaluate the continuity of rural settlements.

[0076] When using the above-mentioned village texture continuity evaluation model to evaluate the continuity of rural settlements, the texture plan of the corresponding village can be input into the village texture continuity evaluation model according to the set size (for example, length and width are (224, 224)), and the texture continuity evaluation result of the village can be obtained according to the output of the model.

[0077] Accordingly, the embodiment of the present invention also provides a rural settlement texture inheritance quantitative evaluation system, such as Figure 3 The figure shows a structural diagram of the system.

[0078] The rural settlement texture inheritance quantitative evaluation system 300 includes the following modules: The data acquisition module 301 is used to select typical villages and obtain indicator data of the typical villages; An image generation module 302 is used to generate a plurality of texture plane images according to the typical village; A scoring module 303 is used to score the texture continuity of the texture plane map; A sample generation module 304 is used to generate a texture score sample according to the index parameters and scores corresponding to the texture plane map; A training module 305, for training a village texture continuity evaluation model 30 according to the texture scoring samples; The evaluation module 306 is used to evaluate the continuity of rural settlements using the village texture continuity evaluation model 30.

[0079] like Figure 4 As shown, in some embodiments, the rural settlement texture inheritance quantitative evaluation system 300 may further include: an indicator parameter determination module 307, which determines the indicator parameters used to evaluate the village texture.

[0080] The indicator parameter determination module 307 can screen out quantitative indicators with higher frequency of occurrence for characterizing the planar dimension of village building mechanisms from relevant literature according to the screening principle, obtain preliminary screening indicators, and then classify the preliminary screening indicators, select representative indicator parameters according to different categories of the preliminary screening indicators, and determine the indicator parameters for evaluating village texture through correlation analysis.

[0081] In some embodiments, the rural settlement texture inheritance quantitative evaluation system 300 may further include: a database establishment module (not shown in the figure), which establishes a village texture database, and the village texture database includes basic village information and its indicator data.

[0082] Accordingly, the data acquisition module 301 can directly select a typical village from the village texture database and obtain the indicator data of the typical village.

[0083] For detailed description of the above modules, please refer to the relevant description in the data quality assessment method of the present invention, which will not be repeated here.

[0084] The rural settlement texture inheritance quantitative evaluation method and system provided by the embodiment of the present invention reveals the correlation mechanism between spatial morphological texture and various index parameters by determining the key evaluation indicators of rural settlement texture, and realizes the transformation from traditional subjective evaluation to scientific and objective evaluation by combining scoring with machine learning. The scheme of the present invention can effectively improve the decision-making efficiency and objectivity in rural planning and design, and promote the sustainable development and texture protection of rural settlements.

[0085] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0086] The present invention also provides a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and the computer program can be executed when it is run. Figure 1 The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. The storage medium may also include a non-volatile memory (non-volatile) or a non-transitory memory, etc.

[0087] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data provider to another website site, a computer, a server or a data provider by wired or wireless means.

[0088] The embodiments of the present invention are described in detail above. The present invention is described in detail using specific implementation methods herein. The description of the above embodiments is only used to help understand the method and system of the present invention. It is only a 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 ordinary technicians in this field without creative work should belong to the scope of protection of the present invention, and the content of this specification should not be understood as limiting the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A quantitative evaluation method for rural settlement texture inheritance, characterized in that: The method comprises: Selecting typical villages and obtaining indicator data of the typical villages; generating a plurality of texture plane maps according to the typical village, and scoring the texture continuity of the texture plane maps; Generate a texture score sample according to the index parameters and scores corresponding to the texture plane map; Training a village texture continuity evaluation model according to the texture scoring samples; The village texture continuity evaluation model is used to evaluate the continuity of rural settlements.

2. The method for quantitative evaluation of rural settlement texture inheritance according to claim 1 is characterized in that: The method further comprises: determining an indicator parameter for evaluating the village texture; The step of obtaining the indicator data of the typical village includes: The indicator data of the typical village is extracted according to the indicator parameters.

3. The method for quantitative evaluation of rural settlement texture inheritance according to claim 2 is characterized in that: The index parameters determined for evaluating village texture include: According to the screening principle, the quantitative indicators with high frequency of occurrence for characterizing the plane dimension of village building mechanism are screened from the relevant literature to obtain the initial screening indicators; the screening principle includes: excluding non-quantifiable indicators; excluding linear description indicators; excluding indicators unrelated to building texture; excluding three-dimensional morphology related indicators; Classifying the initial screening indicators; Select representative indicator parameters according to different categories of the initial screening indicators; The indicator parameters for evaluating village texture were determined through correlation analysis.

4. The rural settlement texture inheritance quantitative evaluation method according to claim 3 is characterized by: The classification of the initial screening indicators includes: The preliminary screening indicators are divided into the following four categories: building density, building distribution disorder, building base shape, and building base shape complexity; The representative index parameters include: building density, building unit angle disorder index, building unit spacing disorder index, building width-to-depth ratio, and building base area variation coefficient.

5. The method for quantitative evaluation of rural settlement texture inheritance according to claim 2 is characterized in that: The method further comprises: Establishing a village texture database, wherein the village texture database includes basic village information and indicator data; The selected typical villages include: A typical village is selected from the village texture database.

6. The method for quantitative evaluation of rural settlement texture inheritance according to any one of claims 1 to 5, characterized in that: The method further comprises: The texture score samples are subjected to data enhancement by random rotation and / or horizontal mirroring.

7. The method for quantitative evaluation of rural settlement texture inheritance according to any one of claims 1 to 5, characterized in that: The method further comprises: The scores were processed in the following order: data standardization, extreme value removal and average value calculation, and outlier removal.

8. The rural settlement texture inheritance quantitative evaluation method according to claim 1 is characterized by: The village texture continuity evaluation model adopts a convolutional neural network model based on a residual network.

9. A quantitative evaluation system for rural settlement texture inheritance, characterized in that: The system comprises: A data acquisition module, used to select typical villages and obtain indicator data of the typical villages; An image generation module, used for generating a plurality of texture plane images according to the typical village; A scoring module, used for scoring the texture continuity of the texture plan; A sample generation module, used to generate a texture scoring sample according to the index parameters and scores corresponding to the texture plan; A training module, used for training a village texture continuity evaluation model according to the texture scoring samples; An evaluation module is used to evaluate the continuity of rural settlements using the village texture continuity evaluation model.

10. The rural settlement texture inheritance quantitative evaluation system according to claim 9 is characterized in that: The system further comprises: The indicator parameter determination module determines the indicator parameters used to evaluate the village texture.

Images