Traditional village rural house building style and appearance evaluation method and device, electronic equipment and medium

Abstract

The invention provides a traditional village rural house building style and appearance evaluation method and device, electronic equipment and a medium, and relates to the field of building evaluation. The method comprises the following steps: inputting a residential building image into a trained style and feature recognition model, and outputting style and feature information of various building components in the residential building image by the style and feature recognition model; for the style and feature information of each building component, determining the style and feature grade of each building component according to the corresponding grading rule and style and feature information; determining a repairing strategy of the traditional village rural house building according to the style and feature grade corresponding to each building component; and under the condition that the repair strategy does not need to be repaired, performing assignment according to the style and appearance grade corresponding to each building component to obtain an overall style and appearance score of the traditional village rural house building. The method is advantaged in that rapid processing of the traditional village rural house building image and quantitative evaluation of the traditional village rural house building are realized, relatively high processing efficiency and accuracy are realized, and scientificity, effectiveness and high efficiency of implementation of related policies are realized.

Description

Technical Field

[0001] The present invention relates to the field of building evaluation, and in particular to a method, device, electronic equipment and medium for evaluating the architectural features of traditional village farmhouses. Background Art

[0002] With the rapid advancement of urbanization and the accelerating pace of modernization, the protection and inheritance of traditional village features are increasingly valued. As an excellent cultural heritage of my country, traditional villages carry rich historical and cultural heritage and unique folk customs. As an important carrier of traditional village features, objective and accurate evaluation of residential buildings is particularly important.

[0003] At present, the evaluation of existing residential buildings mainly relies on manual work. Specifically, the evaluators conduct offline evaluations based on relevant policies and standards. This evaluation method has the following defects: the evaluated party needs to provide more supporting materials, which makes the process cumbersome. Usually, the evaluation results are obtained through subjective judgment of the evaluators. There are also problems such as the evaluation results are not objective enough and the evaluation cycle is long. Therefore, it is urgently needed to be improved. Summary of the invention

[0004] The present invention provides a method, device, electronic equipment and medium for evaluating the architectural style of traditional village farmhouses, so as to solve the defect of low efficiency in the evaluation of traditional residential buildings in the prior art, realize the evaluation of residential buildings assisted by the application of intelligent recognition models, greatly shorten the style evaluation cycle, and improve the efficiency and quality of traditional village style protection and renewal.

[0005] According to a first aspect of the present invention, the present invention provides a method for evaluating the architectural style of traditional village farmhouses, the method comprising: Get residential building images based on traditional village farmhouse architecture; Inputting the residential building image into a trained style recognition model, and having the style recognition model output style information of various building components in the residential building image; For the style and appearance information of each building component, the style and appearance grade of each building component is determined according to the corresponding grading rules and the style and appearance information; Determining the repair strategy of the traditional village farmhouse building according to the style level corresponding to each building component, wherein the repair strategy includes no need for repair, recommended repair and required repair; When the repair strategy does not require repair, a value is assigned according to the style and appearance level corresponding to each building component to obtain an overall style and appearance score of the traditional village farmhouse building.

[0006] According to the traditional village farmhouse architectural style evaluation method of the present invention, the image of the traditional village farmhouse building is obtained to obtain the residential building image, including: Acquire images of traditional village farmhouse buildings taken from multiple angles, wherein each image includes at least one building component; For each acquired image, the building components in the image are enhanced and the image is sharpened.

[0007] According to the traditional village farmhouse architectural style evaluation method of the present invention, the architectural components identified by the style recognition model include roofs, doors and windows, and walls; among them, the style information corresponding to the roof is the roof shape and roof material, the style information of the doors and windows is the material and style, and the style information of the walls is the material and craftsmanship.

[0008] According to the traditional village farmhouse architectural style evaluation method of the present invention, the style information of each building component is determined according to the corresponding classification rules and style information, including: In the case where the building component is a roof: if the roof is a double-slope hard roof with a slope of less than 30 degrees and the roof material is small green tiles or flat tiles, the roof is of excellent grade; if the roof is a double-slope hard roof with a slope of more than 30 degrees and the roof material is antique glazed tiles or fiberglass tiles, the roof is of good grade; if the roof is a double-slope hard roof with a roof material of concrete tiles or asphalt, the roof is of qualified grade; if the roof is a flat roof or the roof material is linoleum or stacked roof, the roof is of unqualified grade; In the case of building components such as doors and windows: if the material and style of the doors and windows are traditional wooden doors and windows, they are of excellent grade; if the material and style of the doors and windows are imitation wood grain broken bridge aluminum doors and windows, they are of good grade; if the material and style of the doors and windows are aluminum alloy, wood color plastic steel, they are of qualified grade; if the material and style of the doors and windows are Western-style doors, French windows, white plastic steel, they are of unqualified grade; In the case where the building component is a wall: if the material and craftsmanship of the wall are blue brick, rough stone, blue brick with soft core, the wall is of excellent grade; if the material and craftsmanship of the wall are gray sand brick, blue brick veneer, blue stone, the wall is of good grade; if the material and craftsmanship of the wall are real stone paint, cement brick, steam plastering, the wall is of qualified grade; if the material and craftsmanship of the wall are large area gray wall, dark gray wall, or wooden strip veneer, the wall is of unqualified grade.

[0009] According to the traditional village farmhouse architectural style evaluation method of the present invention, the repair strategy of the traditional village farmhouse building is determined according to the style level corresponding to each building component, including: Traverse the style and appearance levels corresponding to the roof, doors and windows, and walls to determine whether each style and appearance level is a qualified level; If the style and appearance levels of the roof, doors, windows, and walls are all excellent, it is confirmed that the traditional village farmhouse building does not need to be repaired; If the style grades corresponding to the roof, doors, windows, and walls are not all excellent and there is no unqualified grade, the repair strategy is confirmed and repair suggestions are made, and repair suggestions are returned to adjust the building components that are in the qualified and good grades to the excellent grade; If the style grades corresponding to the roof, doors, windows, and walls are unqualified, the repair strategy is confirmed as necessary repair, and repair suggestions are returned to improve the building components that are unqualified to any one of the qualified, good, or excellent grades.

[0010] According to the traditional village farmhouse architectural style evaluation method of the present invention, a value is assigned according to the style grade corresponding to each building component to obtain the overall style score of the traditional village farmhouse building, including: Traversing each building component to match the style grade corresponding to the building component with the preset grade-score correspondence relationship to obtain the score corresponding to each building component; The score corresponding to each building component is multiplied by the corresponding coefficient, and the sum of all products is calculated to obtain the overall appearance score of the traditional village farmhouse architecture.

[0011] According to the traditional village farmhouse architectural style evaluation method of the present invention, the method further includes: When the repair strategy indicates that repair is necessary and the traditional village farmhouse building has been repaired, an image of the residential building is obtained based on the image of the repaired traditional village farmhouse building, and the overall appearance score of the repaired traditional village farmhouse building is determined based on the obtained image of the residential building.

[0012] According to a second aspect of the present invention, the present invention further provides a device for evaluating the architectural style of traditional village farmhouses, comprising: An acquisition module is used to obtain residential building images based on traditional village farmhouse buildings; A recognition module, used for inputting the residential building image into a trained style recognition model, and having the style recognition model output style information of various building components in the residential building image; A grading module is used to determine the style and appearance level of each building component according to the corresponding grading rules and style and appearance information of each building component; A confirmation module, used to determine the repair strategy of the traditional village farmhouse building according to the style level corresponding to each building component, wherein the repair strategy includes no need for repair, recommended repair and required repair; The calculation module is used to assign values ​​according to the style and appearance grades corresponding to each building component when the repair strategy does not require repair, so as to obtain the overall style and appearance score of the traditional village farmhouse building.

[0013] According to the third aspect of the present invention, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for evaluating the architectural style of traditional village farmhouses as described in any one of the above is implemented.

[0014] According to a fourth aspect of the present invention, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for evaluating the architectural style of traditional village farmhouses as described in any one of the above-mentioned methods.

[0015] The present invention provides a method, device, electronic equipment and medium for evaluating the architectural style of traditional village farmhouses. The method obtains images of traditional village farmhouses, uses a trained style recognition model to recognize the style information of multiple building components in the image, converts the style information of each building component into a style grade, then determines the repair strategy using the style grade of each building component, and finally calculates the overall style score of the traditional village farmhouse building according to the style grades corresponding to all building components when the repair strategy does not require repair. The trained style recognition model is used to quickly process the images of traditional village farmhouses, a specific grading rule is used to implement the style grading of building components, and the style grades are converted into values ​​to achieve quantitative evaluation of traditional village farmhouses. The method has high processing efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the method for evaluating the architectural style of traditional village farmhouses provided by the present invention.

[0018] Figure 2 It is a schematic diagram of the style and appearance grade of the roof provided by the present invention.

[0019] Figure 3 It is a schematic diagram of the style and grade of the doors and windows provided by the present invention.

[0020] Figure 4 It is a schematic diagram of the style and grade of the wall provided by the present invention.

[0021] Figure 5 It is a structural schematic diagram of a device for evaluating the architectural features of traditional village farmhouses provided by the present invention.

[0022] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Combine the following Figures 1 to 6 The present invention describes a method, device, electronic device and non-transitory computer-readable storage medium for evaluating the architectural features of traditional village farmhouses.

[0025] Figure 1 This is a flow chart of the traditional village farmhouse architectural style evaluation method provided by the embodiment of the present invention. Please refer to Figure 1 As shown, this embodiment provides a method for evaluating the architectural style of traditional village farmhouses. The method can be implemented through steps S101 to S105. Each step will be described in detail below: Step S101, obtaining residential building images based on traditional village farmhouse buildings.

[0026] In this embodiment, traditional village farmhouses refer to buildings used for residents in traditional villages. Traditional residential buildings are roughly divided into five categories: houses built during the Republic of China and the early years of the founding of the People's Republic of China with gray tiles and straw mud walls as the main materials are traditional style traditional houses, houses with red bricks and red tiles and modern red tiles reflecting the characteristics of the 1970s to 1990s are modern local traditional houses, houses that partially retain traditional structures and partially use modern building materials and designs, and have mixed characteristics of the ages and have undergone later reconstruction are classified as multi-mixed traditional houses, newly built houses that are out of place in traditional style areas and have very different design styles are defined as newly built abrupt traditional houses, and rebuilt houses that deliberately imitate ancient architectural craftsmanship and style during the design and construction process are rebuilt antique traditional houses.

[0027] In the specific implementation process, the residential building image is obtained by taking pictures of traditional residential buildings through an image acquisition device. The image acquisition device can be any existing camera or a smart terminal with a camera, such as a mobile phone, a notebook, etc.

[0028] Step S102, inputting the residential building image into the trained style recognition model, and the style recognition model outputs the style information of various building components in the residential building image.

[0029] In this embodiment, the style recognition model is obtained by training a pre-built target recognition model with a large amount of sample data. Building components refer to objects with the same attributes in the entire building, such as doors, windows, roofs, floors, etc. Style information corresponds to building components, and style information refers to attribute information that characterizes building components, such as shape, material, etc. The style information of different building components can be the same or different.

[0030] Step S103, for the style information of each building component, determine the style grade of each building component according to the corresponding grading rules and the style information.

[0031] In this embodiment, the classification rules correspond to each building component, and the classification rules are pre-set; assuming that there are two building components, the classification rules can be pre-defined for the two building components, respectively, and the classification rules can be divided into a specific number of levels according to the style information of the corresponding building components. For example, the classification rules corresponding to the roof can divide the roof into three levels, and the classification rules corresponding to the doors and windows can divide the doors and windows into four levels. It should be noted that the building components and style levels understood in this embodiment are only for illustration and should not be understood as limiting this embodiment.

[0032] Step S104, determining the repair strategy of the traditional village farmhouse building according to the style level corresponding to each building component, wherein the repair strategy includes no repair required, recommended repair and required repair.

[0033] Step S105, when the repair strategy does not require repair, assign values ​​according to the style and appearance levels corresponding to each building component to obtain an overall style and appearance score for the traditional village farmhouse building.

[0034] In this embodiment, the overall style score is obtained by mapping the style grades of all building components into scores. When mapping the scores of each style grade, a positive correlation mapping can be used. The positive correlation mapping means that the higher the style grade, the higher the mapped score. Similarly, the overall style score obtained can also be evaluated accordingly according to the mapping method. The higher the overall style score, the better the state of the traditional village farmhouse building. Similarly, in the specific implementation process, an anti-correlation mapping can also be used. The anti-correlation mapping means that the higher the style grade, the lower the mapped score. At this time, the higher the overall style score, the worse the state of the traditional village farmhouse building.

[0035] The traditional village farmhouse architectural style evaluation method of the present embodiment obtains images of traditional village farmhouse buildings, and uses a trained style recognition model to recognize the style information of multiple building components in the image, and then converts the style information of each building component into a style grade, and then uses the style grade of each building component to determine the repair strategy, and finally calculates the overall style score according to the style grades corresponding to all building components when the repair strategy does not require repair. With the help of the trained style recognition model, the traditional village farmhouse architectural image is quickly processed, and specific grading rules are used to implement the style grading of building components. The style grades are converted into values ​​to achieve quantitative evaluation of traditional village farmhouse buildings, and the processing efficiency and accuracy are high.

[0036] In some possible implementations, step S101, obtaining a residential building image according to an image of a traditional village farmhouse building, specifically includes: Acquire images of traditional village farmhouse buildings taken from multiple angles, wherein each image includes at least one building component; For each acquired image, the building components in the image are enhanced and the image is sharpened.

[0037] The traditional village farmhouse architectural style evaluation method of this embodiment ensures the integrity of the style recognition model input data by acquiring traditional residential building images taken from multiple angles. In addition, the enhanced processing of building components ensures the global contrast of the image, and the sharpening optimization of the building image can enhance the edges and details, making the outline and texture of the building clearer, which helps to improve the accuracy of recognition.

[0038] In some possible implementations, the architectural components recognized by the style recognition model include roofs, doors and windows, and walls; among them, the style information corresponding to the roof is the roof shape and roof material, the style information of the doors and windows is the material and style, and the style information of the walls is the material and craftsmanship.

[0039] In the specific implementation process, the building component style recognition model mainly includes four parts: multi-dimensional building component feature fusion network, style recognition model scaling based on connection model, dynamic parameter optimizer, and dual-level precision building label enhancer: The proposed extended ELAN (E-ELAN) does not change the gradient transmission path of the original architecture at all, but uses group convolution to increase the cardinality of the added features and combines different groups of features by shuffling and merging the cardinality. This operation can enhance the features learned by different feature maps and improve the use of parameters and calculations.

[0040] Model Scaling for Architectural Style Recognition Based on Concatenative Models considers scaling the depth factor of the computational module while also considering the width factor of the transition layer to change by the same amount. When scaling the network of the connection structure, only the depth of the computational block is scaled, and the rest of the transition layer is only scaled in width.

[0041] Dynamic Parameter Optimizer, IdentityConnection in RepConv destroys the residual in ResNet and Concatenation in DenseNet. In the proposed reparameterized model, for layers with residual or cascade connections, their RepConv should not have Identity Connection. In this case, replace it with RepConvN that does not contain Identity Connection.

[0042] Dual-level Precision Building Label Enhancer sets the head responsible for the final output as the Lead head and the head used for auxiliary training as the Auxiliary head. Two labels (coarse labels and fine labels) are generated. The fine label is the same as the soft label generated by the Lead head on the label distributor, while the coarse label is generated by relaxing the conditions for identifying positive examples.

[0043] In the specific implementation process, in order to obtain a style recognition model with better performance, the following method can be used to construct training samples to train the style recognition model of building components. The specific method of constructing the model training samples is as follows: First, collect data; determine the target area, building type, style and features of sample collection, and clarify the details of the roofs, doors, windows, walls and other parts that need to be collected. Plan the itinerary according to the research objectives and resource conditions, including the villages to be visited, the expected number of samples to be collected, the time required, etc. Then visit the selected traditional villages on the spot to record the overall layout of the village, the distribution of buildings, the natural environment and other background information. Based on the diversity and representativeness of the style and features, initially select typical houses as sample collection objects, covering buildings of different ages, styles and preservation conditions. According to the era characteristics, style and use of village buildings, preset building classifications, such as traditional style type, modern local type, multi-mixed type, newly built abrupt type, and rebuilt antique type. Use drone mapping, three-dimensional scanning, high-resolution photography and other technologies to collect high-precision image data of style and features of village houses, such as roofs, doors, windows, walls, etc., and record the physical location, structure, material and other information of the houses. Take all-round and multi-angle photos of the roofs, doors, windows, walls, etc. of each house, including panoramic, close-up and detailed pictures. Try to shoot in natural light to avoid shadows and reflections that affect image quality. Also record the surrounding environment, such as vegetation, roads, adjacent buildings, etc., as these factors may affect the recognition of the house style. Each photo is accompanied by metadata such as shooting time, location, weather, basic building information, etc., to facilitate later sorting and analysis.

[0044] Then, data processing; for the collected traditional village house image data, the cutting-edge algorithms in the field of image processing are used to pre-process the images, optimize data quality, and improve the accuracy and efficiency of feature extraction. The image pixel intensity distribution is adjusted by using building components to enhance the global contrast of the image, making the details of the originally dim or overly bright areas clearly visible. The noise suppression technology effectively removes random interference in the image, such as graininess or electromagnetic interference during camera capture, ensuring the purity of the image content. The building image sharpening process enhances the edges and details to make the outline and texture of the building clearer, which is convenient for subsequent feature recognition. For the elimination of outliers, combined with the intelligent recognition ability of the machine learning model, by building an adaptive threshold model or cluster analysis, outliers that do not conform to the normal distribution law, such as abnormal measurement errors or data entry errors, are automatically identified and excluded. Compared with traditional methods, this anomaly detection mechanism that integrates machine learning can better adapt to complex data patterns and reduce misjudgments. In data standardization processing, it is not limited to simple data format unification, but through methods such as minimum-maximum scaling and Z-score standardization, detailed data conversion is performed to ensure that all data are compared on the same dimension and scale, ensuring that the model is not affected by differences in data units or magnitudes, thereby improving the consistency and stability of model training.

[0045] Finally, feature extraction and annotation; in the feature extraction stage, the deep learning model is innovatively applied to automatically identify the architectural features in the image. The deep learning model can learn and identify complex visual features, such as the geometry of the roof, the style of doors and windows, and the material texture of the wall. It can maintain high recognition accuracy even under different lighting and viewing angles, greatly improving the recognition efficiency and accuracy, and showing the strong potential of artificial intelligence in the field of complex image processing. In the annotation process, a set of semi-automated intelligent auxiliary annotation tools is designed, which cleverly combines computer recognition with human expert review to form an efficient and accurate annotation process. First, the computer is used to preliminarily identify and propose feature annotation suggestions, such as roof type, door and window location, etc., and then it is submitted to field experts for review, correction and confirmation. It not only gives full play to the efficiency of computer automation, but also ensures the accuracy of annotation, avoids the deviation of pure automation, and reflects the innovative idea of ​​human-computer collaboration.

[0046] In the specific implementation process, in order to further improve the recognition accuracy of the style recognition model, the training samples can be expanded by regularly collecting images of renovated traditional buildings, that is, an online learning mechanism is introduced. The model continuously receives feedback from photos of houses that have been repaired and updated on the spot, automatically adjusts the weight parameters, and achieves self-optimization. This dynamic learning mode ensures the real-time and adaptability of the model, and can evolve with the changes in the village style and maintain the sharpness of recognition. In addition, the early stop training strategy and learning rate decay method are used to effectively prevent overfitting and ensure the generalization ability of the model.

[0047] In some possible implementations, the aforementioned step S103, for the style information of each building component, determines the style grade of each building component according to the corresponding grading rules and the style information, specifically includes: Please refer to Figure 2 As shown, in the case where the building component is a roof: if the roof is a double-slope hardtop with a slope of less than 30 degrees and the roof material is small green tiles or flat tiles, the roof is of excellent grade; if the roof is a double-slope hardtop with a slope of more than 30 degrees and the roof material is antique glazed tiles or fiberglass tiles, the roof is of good grade; if the roof is a double-slope hardtop with a roof material of concrete tiles or asphalt, the roof is of qualified grade; if the roof is a flat roof or the roof material is linoleum or stacked roof, the roof is of unqualified grade; Please refer to Figure 3 As shown, in the case where the building components are doors and windows: if the material and style of the doors and windows are traditional wooden doors and windows, then the doors and windows belong to the excellent grade; if the material and style of the doors and windows are imitation wood grain broken bridge aluminum doors and windows, then the doors and windows belong to the good grade; if the material and style of the doors and windows are aluminum alloy, wood color plastic steel, then the doors and windows belong to the qualified grade; if the material and style of the doors and windows are Western-style doors, French windows, white plastic steel, then the doors and windows belong to the unqualified grade; Please refer to Figure 4 As shown, in the case where the building component is a wall: if the material and craftsmanship of the wall are blue brick, rough stone, blue brick with soft core, the wall is of excellent grade; if the material and craftsmanship of the wall are gray sand brick, blue brick veneer, blue stone, the wall is of good grade; if the material and craftsmanship of the wall are real stone paint, cement brick, steam plastering, the wall is of qualified grade; if the material and craftsmanship of the wall are large area gray wall, dark gray wall, and wooden strip veneer, the wall is of unqualified grade.

[0048] The residential building evaluation method of this embodiment sets four levels of judgment rules according to the situations where the building components are roofs, doors and windows, and walls, so as to achieve accurate classification of each component by utilizing the style information corresponding to the building components identified by the model. The style classification corresponding to each element can better characterize the state of the evaluated object and has high reliability.

[0049] In some possible implementations, the aforementioned step S104, determining the repair strategy of the traditional village farmhouse building according to the style level corresponding to each building component, specifically includes: Traverse the style and appearance levels corresponding to the roof, doors and windows, and walls to determine whether each style and appearance level is a qualified level; If the style and appearance levels of the roof, doors, windows, and walls are all excellent, it is confirmed that the traditional village farmhouse building does not need to be repaired; If the style grades corresponding to the roof, doors, windows, and walls are not all excellent and there is no unqualified grade, the repair strategy is confirmed and repair suggestions are made, and repair suggestions are returned to adjust the building components that are in the qualified and good grades to the excellent grade; If the style grades corresponding to the roof, doors, windows, and walls are unqualified, the repair strategy is confirmed as necessary repair, and repair suggestions are returned to improve the building components that are unqualified to any one of the qualified, good, or excellent grades.

[0050] The residential building evaluation method of this embodiment formulates three types of repair suggestions for all possible combinations of three building components, so that situations where there are elements that are unqualified and situations where some elements are good or qualified are gathered into the excellent level, providing reliable data support for the repair of traditional village farmhouses.

[0051] In some possible implementations, the above step S105 assigns values ​​according to the style and appearance grades corresponding to each building component to obtain the overall style and appearance score of the traditional village farmhouse architecture, specifically including: Traversing each building component to match the style grade corresponding to the building component with the preset grade and score correspondence, and obtaining the score corresponding to each building component; The score corresponding to each building component is multiplied by the corresponding coefficient, and the sum of all products is calculated to obtain the overall appearance score.

[0052] It should be noted that when calculating the overall score, the corresponding relationship between the preset grades and scores corresponding to different elements may be the same or different. For example, an excellent-grade house may correspond to a score of 20, while an excellent wall may correspond to a score of 18. In addition, the coefficients corresponding to each building component may be the same or different. For example, the coefficient corresponding to the roof may be set to 0.4, and the coefficients corresponding to doors, windows and walls may be set to 0.3. In the specific implementation process, reasonable adjustments may be made based on the contribution and influence of the components on the traditional architectural style. The specific scores and coefficients listed above are only for illustrative purposes and should not be construed as additional limitations on the scheme of the present invention.

[0053] The traditional village farmhouse architectural style evaluation method of this embodiment sets corresponding grade and score conversion rules for each building component, sets corresponding coefficients for each building component, and finally uses the total sum to evaluate the traditional village farmhouse architecture. This quantitative parameter covers the various building component states of the evaluated building and has good versatility.

[0054] In some possible implementations, the method further includes: When the repair strategy is that repair is necessary and the traditional village farmhouse building has been repaired, the residential building image is obtained based on the image of the repaired traditional village farmhouse building, and the overall appearance score of the repaired traditional village farmhouse building is determined based on the re-obtained residential building image.

[0055] The traditional village farmhouse architectural style evaluation method of this embodiment re-evaluates the traditional village farmhouse architecture by re-acquiring the image of the evaluated traditional village farmhouse architecture after each repair. The overall style score of the two evaluations can reflect the degree of restoration of the evaluated object, thereby providing reliable data support for the restoration evaluation of traditional village farmhouse architecture.

[0056] The following is a description of the traditional village farmhouse architectural style evaluation device provided by the present invention. The traditional village farmhouse architectural style evaluation device described below and the traditional village farmhouse architectural style evaluation method described above can be referenced to each other.

[0057] Please refer to Figure 5 As shown, this embodiment provides a device for evaluating the architectural style of traditional village farmhouses. Specifically, the device includes: an acquisition module 510, an identification module 520, a classification module 530, a confirmation module 540 and a calculation module 550. The above modules are described in detail below: An acquisition module 510 is used to obtain residential building images based on the images of traditional village farmhouse buildings; The recognition module 520 is used to input the residential building image into the trained style recognition model, and the style recognition model outputs the style information of various building components in the residential building image; A grading module 530 is used to determine the style and appearance level of each building component according to the corresponding grading rules and the style and appearance information of each building component; A confirmation module 540 is used to determine the repair strategy of the traditional village farmhouse building according to the style level corresponding to each building component, wherein the repair strategy includes no repair, recommended repair and required repair; The calculation module 550 is used to assign values ​​according to the style and appearance grades corresponding to each building component when the repair strategy does not require repair, so as to obtain the overall style and appearance score of the traditional village farmhouse building.

[0058] The traditional village farmhouse architectural style evaluation device of the present embodiment obtains images of traditional village farmhouse buildings, and uses a trained style recognition model to recognize style information of multiple building components in the image, and then converts the style information of each building component into a style grade, and then uses the style grade of each building component to determine the repair strategy, and finally calculates the overall style score according to the style grades corresponding to all building components when the repair strategy does not require repair. With the help of the trained style recognition model, the traditional village farmhouse architectural image is quickly processed, and specific grading rules are used to implement the style grading of building components. The style grades are converted into values ​​to realize quantitative evaluation of traditional village farmhouse buildings, and the processing efficiency and accuracy are high.

[0059] It should be noted that each module in the above-mentioned traditional village farmhouse architectural style evaluation device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0060] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6As shown, the electronic device may include: a processor (processor) 610 , a communication interface (Communications Interface) 620 , a memory (memory) 630 and a communication bus 640 , wherein the processor 610 , the communication interface 620 , and the memory 630 communicate with each other through the communication bus 640 . The processor 610 can call the logic instructions in the memory 630 to execute the traditional village farmhouse architectural style evaluation method, which includes: obtaining a residential building image based on the image of the traditional village farmhouse building; inputting the residential building image into a trained style recognition model, and the style recognition model outputs the style information of multiple building components in the residential building image; for the style information of each building component, determining the style grade of each building component according to the corresponding grading rules and style information; determining the repair strategy of the traditional village farmhouse building according to the style grade corresponding to each building component, wherein the repair strategy includes no repair, recommended repair and required repair; when the repair strategy does not belong to required repair, assigning values ​​according to the style grade corresponding to each building component to obtain the overall style score of the traditional village farmhouse building.

[0061] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0062] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the traditional village farmhouse architectural style evaluation method provided by the above-mentioned methods, the method including: obtaining a residential building image based on the image of the traditional village farmhouse building; inputting the residential building image into a trained style recognition model, and the style recognition model outputs style information of multiple building components in the residential building image; for the style information of each building component, determining the style grade of each building component according to the corresponding grading rules and style information; determining the repair strategy of the traditional village farmhouse building according to the style grade corresponding to each building component, wherein the repair strategy includes no repair required, recommended repair and required repair; when the repair strategy does not belong to required repair, assigning values ​​according to the style grade corresponding to each building component to obtain an overall style score of the traditional village farmhouse building.

[0063] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the traditional village farmhouse architectural style evaluation method provided by the above-mentioned methods, the method comprising: obtaining a residential building image based on an image of a traditional village farmhouse building; inputting the residential building image into a trained style recognition model, and the style recognition model outputs style information of a plurality of building components in the residential building image; for the style information of each building component, determining the style grade of each building component according to the corresponding grading rules and style information; determining the repair strategy of the traditional village farmhouse building according to the style grade corresponding to each building component, wherein the repair strategy includes no repair required, recommended repair and required repair; when the repair strategy does not belong to required repair, assigning values ​​according to the style grade corresponding to each building component to obtain an overall style score of the traditional village farmhouse building.

[0064] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0065] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the architectural style of traditional village farmhouses, characterized in that: The method comprises: Get residential building images based on traditional village farmhouse architecture; Inputting the residential building image into a trained style recognition model, and having the style recognition model output style information of various building components in the residential building image; For the style and appearance information of each building component, the style and appearance grade of each building component is determined according to the corresponding grading rules and the style and appearance information; Determining the repair strategy of the traditional village farmhouse building according to the style level corresponding to each building component, wherein the repair strategy includes no need for repair, recommended repair and required repair; When the repair strategy does not require repair, a value is assigned according to the style and appearance level corresponding to each building component to obtain an overall style and appearance score of the traditional village farmhouse building.

2. The method for evaluating the architectural style of traditional village farmhouses according to claim 1 is characterized in that: Based on the traditional village farmhouse architecture, residential building images are obtained, including: Acquire images of traditional village farmhouse buildings taken from multiple angles, wherein each image includes at least one building component; For each acquired image, the building components in the image are enhanced and the image is sharpened.

3. The method for evaluating the architectural style of traditional village farmhouses according to claim 1 is characterized in that: The building components identified by the style recognition model include roofs, doors and windows, and walls; among them, the style information corresponding to the roof is the roof shape and roof material, the style information of the doors and windows is the material and style, and the style information of the walls is the material and craftsmanship.

4. The method for evaluating the architectural style of traditional village farmhouses according to claim 3 is characterized in that: For the style and appearance information of each building component, the style and appearance grade of each building component is determined according to the corresponding grading rules and style and appearance information, including: (1) Where the building element is a roof: If the roof is a double-slope hardtop with a slope of less than 30 degrees and the roof material is small green tiles or flat tiles, the roof is of excellent grade; If the roof is a double-slope hardtop with a slope greater than 30 degrees and the roof material is antique glazed tiles or fiberglass tiles, the roof is considered good. If the roof shape is a double-slope hardtop and the roof material is concrete tiles or asphalt, the roof is of qualified grade; If the roof is flat or the material is linoleum or stacked, the roof is classified as unqualified; (2) When the building components are doors and windows: If the material and style of the doors and windows are traditional wooden doors and windows, then the doors and windows are of excellent grade; If the material and style of the doors and windows are imitation wood grain broken bridge aluminum doors and windows, the doors and windows are of good grade; If the material and style of the doors and windows are aluminum alloy, wood-colored plastic steel, then the doors and windows are of qualified grade; If the material and style of the doors and windows are Western-style doors, French windows, or white plastic steel, then the doors and windows are classified as unqualified; (3) When the building component is a wall: If the material and craftsmanship of the wall are blue brick, rough stone, blue brick with soft core, the wall is of excellent grade; If the material and craftsmanship of the wall are lime sand brick, blue brick veneer, or bluestone, the wall is of good grade; If the material and craftsmanship of the wall are real stone paint, cement brick, or steam plastering, the wall is of qualified grade; If the material and craftsmanship of the wall are large areas of gray walls, dark gray walls, and wooden strips, the wall is considered unqualified.

5. The method for evaluating the architectural style of traditional village farmhouses according to claim 4 is characterized in that: The repair strategy of the traditional village farmhouse building is determined according to the style level corresponding to each building component, including: Traverse the style and appearance levels corresponding to the roof, doors and windows, and walls to determine whether each style and appearance level is a qualified level; If the style and appearance levels of the roof, doors, windows, and walls are all excellent, it is confirmed that the traditional village farmhouse building does not need to be repaired; If the style grades corresponding to the roof, doors, windows, and walls are not all excellent and there is no unqualified grade, the repair strategy is confirmed and repair suggestions are made, and repair suggestions are returned to adjust the building components that are in the qualified and good grades to the excellent grade; If the style grades corresponding to the roof, doors, windows, and walls are unqualified, the repair strategy is confirmed as necessary repair, and repair suggestions are returned to improve the building components that are unqualified to any one of the qualified, good, or excellent grades.

6. The method for evaluating the architectural style of traditional village farmhouses according to claim 1, characterized in that: The overall style score of the traditional village farmhouse building is obtained by assigning values ​​according to the style level corresponding to each building component, including: Traversing each building component to match the style grade corresponding to the building component with the preset grade and score correspondence, and obtaining the score corresponding to each building component; The score corresponding to each building component is multiplied by the corresponding coefficient, and the sum of all products is calculated to obtain the overall appearance score of the traditional village farmhouse architecture.

7. The method for evaluating the architectural style of traditional village farmhouses according to claim 1, characterized in that: The method further comprises: When the repair strategy indicates that repair is necessary and the traditional village farmhouse building has been repaired, an image of the residential building is obtained based on the image of the repaired traditional village farmhouse building, and the overall appearance score of the repaired traditional village farmhouse building is determined based on the obtained image of the residential building.

8. A device for evaluating the architectural style of traditional village farmhouses, characterized in that: include: An acquisition module is used to obtain residential building images based on traditional village farmhouse buildings; A recognition module, used for inputting the residential building image into a trained style recognition model, and having the style recognition model output style information of various building components in the residential building image; A grading module is used to determine the style and appearance level of each building component according to the corresponding grading rules and style and appearance information of each building component; A confirmation module, used to determine the repair strategy of the traditional village farmhouse building according to the style level corresponding to each building component, wherein the repair strategy includes no need for repair, recommended repair and required repair; The calculation module is used to assign values ​​according to the style and appearance grades corresponding to each building component when the repair strategy does not require repair, so as to obtain the overall style and appearance score of the traditional village farmhouse building.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for evaluating the architectural style of traditional village farmhouses as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for evaluating the architectural style of traditional village farmhouses as described in any one of claims 1 to 7 is implemented.

Images