Historical building bare brick wall degradation characteristic evaluation method and device

Abstract

The invention provides a historical building bare brick wall degradation characteristic evaluation method and equipment, and the method and equipment achieve the automatic recognition and precise evaluation of the historical building bare brick wall degradation damage characteristics based on a target detection algorithm through the fusion application of deep learning and computer vision technologies and the combination of a transfer learning optimization neural network architecture. According to the method, a bare brick wall degradation characteristic sample database is established, a PP-PicoDet algorithm is selected to carry out model training and characteristic increment superposition training, rapid and accurate automatic identification of damage types, positions and degrees is realized, and compared with a traditional manual investigation mode, the operation efficiency and the result accuracy are greatly improved; and a novel intelligent efficient investigation tool and method are provided for historical building protection and repair.

Description

Technical Field

[0001] The invention relates to a method and equipment for evaluating the deterioration characteristics of exposed brick walls of historical buildings. Background Art

[0002] As one of the important forms of the facade of historical buildings, the unique aesthetic characteristics and structural properties of the exposed brick wall not only demonstrate the exquisite craftsmanship of traditional construction technology, but also reflect the architectural concept and aesthetic pursuit of an era. However, with the passage of time, the exposed brick wall is also facing erosion from various natural and man-made factors, such as weathering, cracks, and biological erosion. These deterioration phenomena not only affect the appearance and structural safety of the building, but also pose a threat to the historical information and cultural value it carries. Therefore, the protection and restoration of the exposed brick wall is not only the maintenance of the building itself, but also the inheritance and respect for historical culture. How to efficiently and accurately detect and evaluate the deterioration and damage of the building facade has also become an urgent problem to be solved in the current field of cultural heritage protection.

[0003] In the traditional manual survey mode, damage surveys are mostly based on workers' intuitive feelings and experience judgments, combined with manual records. Due to the limitations of factors such as the structural characteristics of the building itself, site conditions, and available auxiliary measures, surveys and repairs often need to be carried out simultaneously, that is, "survey and repair". This working mode requires workers to have a high sense of responsibility and professional skills to ensure the accuracy of the survey and the effectiveness of the repair. Due to the intervention of human factors, misjudgments and omissions are difficult to avoid, which not only affects the pertinence and systematicness of the repair work, but also brings great difficulties to technical control and engineering quantity statistics. In actual operations, inaccurate surveys may lead to the inability to accurately implement repair measures, or the neglect of certain hidden damages, leaving safety hazards. Secondly, the efficiency of the traditional survey mode is low, and it is difficult to adapt to the needs of rapid identification and assessment of large-scale and multi-type degradation problems. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for evaluating the deterioration characteristics of exposed brick walls of historical buildings.

[0005] In order to solve the above problems, the present invention provides a method for evaluating the deterioration characteristics of exposed brick walls of historical buildings, comprising:

[0006] Establish a database of deterioration damage types of exposed brick walls in historical buildings;

[0007] Based on the database of deterioration damage types of exposed brick walls in historical buildings, train an intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls in historical buildings;

[0008] The image data of the exposed brick walls of the historical buildings to be inspected are input into the trained intelligent recognition and assessment diagnosis model of the deterioration characteristics of the exposed brick walls of the historical buildings to obtain the corresponding assessment results of the damage type, location, and degree of damage.

[0009] Furthermore, in the above method, a database of deterioration damage types of exposed brick walls of historical buildings is established, including:

[0010] Through the acquisition module, information and image data on the facade damage of the exposed brick walls of historical buildings are collected;

[0011] The analysis module obtains various damage types of deterioration of the exposed brick walls of historical buildings and the corresponding characteristics of each damage type based on the information and image data, and establishes a damage type database of deterioration of the exposed brick walls of historical buildings based on the various damage types and the corresponding characteristics of each damage type.

[0012] Furthermore, in the above method, the damage types include: crack damage, peeling damage, discoloration damage and rust damage.

[0013] Furthermore, in the above method, the database of deterioration damage types of exposed brick walls of historical buildings includes: image information of various damage types, and the causes, impact levels and repair methods of each damage type.

[0014] Furthermore, in the above method, based on the database of deterioration damage types of exposed brick walls of historical buildings, an intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls of historical buildings is trained, including:

[0015] Based on the database of deterioration damage types of exposed brick walls in historical buildings, a method combining neural network architecture and transfer learning is used to train an intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls in historical buildings.

[0016] Furthermore, in the above method, the neural network architecture adopts the PP-PicoDet algorithm.

[0017] Furthermore, in the above method, based on the database of deterioration damage types of exposed brick walls of historical buildings, a method combining a neural network architecture and transfer learning is used to train an intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls of historical buildings, including:

[0018] Annotate the image information of various types of damage in the database of deterioration damage types of exposed brick walls of historical buildings, and perform data feature analysis based on the annotations;

[0019] In the model verification phase, an independent test set was used to evaluate the performance of the model. By analyzing and comparing the recognition results of the images in the test set, the performance indicators of the intelligent recognition and evaluation diagnosis model for the deterioration characteristics of the exposed brick walls of historical buildings in terms of recognition accuracy, recall rate and F1 score were obtained.

[0020] Based on the performance indicators, the intelligent identification and evaluation diagnosis model for degradation characteristics of the exposed brick walls of historical buildings is continuously iterated and optimized.

[0021] Furthermore, in the above method, it also includes:

[0022] Uploading the trained intelligent recognition and evaluation diagnosis model for deterioration characteristics of the exposed brick walls of the historical buildings to the cloud computing platform;

[0023] Alternatively, the trained intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls of historical buildings can be deployed in a mini program.

[0024] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0025] According to another aspect of the present invention, there is provided a computer device, comprising:

[0026] Processor; and

[0027] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0028] Compared with the existing technology, the present invention constructs a real-time intelligent analysis system for the deterioration and damage characteristics of the exposed brick walls of historical buildings by applying an artificial intelligence-based target detection algorithm, thereby realizing automatic identification of the damage type, location and degree. In practical applications, this technology can be combined with drones, mobile devices, etc. to achieve large-scale, high-efficiency automatic detection of the facades of historical buildings. By providing real-time feedback on the detection results, the repair team can quickly formulate a repair plan to minimize damage to the building structure and appearance, thereby effectively extending the service life of the historical building and maintaining its historical value and aesthetic characteristics.

[0029] In view of the inefficiency and strong subjectivity of traditional manual survey methods in the repair of historical building facades, this paper uses deep learning and computer vision technology to select the PP-PicoDet algorithm, and constructs an efficient intelligent recognition and evaluation diagnosis model for the deterioration characteristics of exposed brick walls in historical buildings. Based on the learning of a large number of deterioration feature images, it realizes the automatic recognition of damage type, location and degree. Through actual project verification, the algorithm has shown certain advantages in recognition accuracy and real-time performance, reaching an accurate recognition rate of more than 86%, which can effectively improve the efficiency and quality of historical building protection work.

[0030] This invention uses deep learning and computer vision technology to optimize the neural network architecture through transfer learning, and realizes automatic recognition and accurate evaluation of the deterioration damage characteristics of the exposed brick walls of historical buildings based on the target detection algorithm. A sample database of exposed brick wall deterioration characteristics is established, and the PP-PicoDet algorithm is used for model training and feature increment superposition training to achieve rapid and accurate automatic recognition of damage type, location and degree. Compared with the traditional manual survey mode, it greatly improves the operation efficiency and result accuracy, and provides new intelligent and efficient survey tools and methods for the protection and repair of historical buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a schematic diagram of building facade damage according to an embodiment of the present invention;

[0032] Figure 2 is an image recognition learning logic diagram of an embodiment of the present invention;

[0033] Figure 3 is a schematic diagram of a mini-program interface according to an embodiment of the present invention;

[0034] Figure 4 It is a schematic diagram of intelligent identification and evaluation diagnosis of deterioration characteristics of exposed brick walls according to an embodiment of the present invention;

[0035] Figure 5 This is a diagram for analyzing the current status of deterioration and damage of a building facade according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0037] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPU), input / output interfaces, network interfaces and memories.

[0038] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0039] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0040] The present invention provides a method for evaluating the deterioration characteristics of exposed brick walls of historical buildings, the method comprising:

[0041] Step S1, establishing a database of deterioration damage types of exposed brick walls of historical buildings;

[0042] Preferably, step S1 comprises:

[0043] Step S11, collecting information and image data about the facade damage of the exposed brick wall of the historical building through the acquisition module;

[0044] Step S12, the analysis module obtains various damage types of the deterioration of the exposed brick walls of the historical buildings and the features corresponding to each damage type based on the information and image data, and establishes a database of damage types of the deterioration of the exposed brick walls of the historical buildings based on the various damage types and the features corresponding to each damage type;

[0045] Specifically, due to the long-term impact of the natural environment, the exposed brick walls of historical buildings often suffer from different degrees and types of surface damage, such as Figure 1As shown in the figure, common typical damage includes weathering, alkali efflorescence, and green plant coverage, each with its own unique visual characteristics. In order to effectively analyze these types of damage, we first conducted a detailed investigation and collected a large amount of information and image data on the damage of the exterior facades of the exposed brick walls of historical buildings. Through the analysis of these data, we summarized the main types of damage and conducted a characteristic analysis of typical cases of each type of damage.

[0046] For example, crack damage usually manifests itself as cracking of building facade materials, and its formation may be related to factors such as material aging, temperature changes, and structural deformation.

[0047] Peeling damage refers to the peeling of coatings or finishing materials on the building's facade, which may be caused by coating aging, decreased adhesion, etc.

[0048] Discoloration damage is the phenomenon that the color of the building facade materials changes due to environmental factors such as sunlight and rain.

[0049] Rust damage mainly occurs on metal facade components, which is caused by chemical reactions between metal and oxygen, moisture, etc. in the environment.

[0050] Preferably, in order to systematically manage the damage data including damage types and the characteristics corresponding to each damage type, a damage type database of the exterior facade of the exposed brick wall of a historical building can be established. The database contains image information of various damage types, and organizes and summarizes the causes, impacts and repair methods of each damage type, providing an important reference for subsequent protection and restoration work.

[0051] In addition, standardized data entry formats and classification methods can be used in the database to facilitate subsequent data analysis and application.

[0052] With the establishment of a database of damage types for the facades of exposed brick walls of historical buildings, it is possible to more conveniently obtain and analyze the deterioration and damage of different types of brick walls, providing strong data support for protection and restoration work.

[0053] Step S2, based on the historical building exposed brick wall deterioration damage type database, training the historical building exposed brick wall deterioration feature intelligent recognition and evaluation diagnosis model;

[0054] Preferably, step S2 comprises: based on the database of deterioration damage types of exposed brick walls of historical buildings, and using a method combining a neural network architecture with transfer learning, training an intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls of historical buildings.

[0055] Here, if Figure 2As shown in the figure, the neural network architecture is the core technology for realizing image recognition and target detection; while transfer learning can use existing pre-trained models to accelerate the training process of new models and improve the recognition accuracy of the models.

[0056] Preferably, the neural network architecture adopts the PP-PicoDet algorithm.

[0057] Specifically, the present invention first lists 20 algorithm models for horizontal comparison in the selection of algorithms. It can be seen from Table 1 below that the PP-PicoDet algorithm has achieved an excellent balance between accuracy and inference speed. The PicoDet-S model, despite having only 0.99M parameters, achieved a mAP of 30.6%, an increase of 4.8% over YOLOX-Nano, and a 55% reduction in inference latency. Compared with NanoDet, the mAP of PicoDet-S was also improved by 7.1%. The PicoDet-L model achieved a mAP of 40.9% using 3.3 million parameters, which is 44% faster than YOLOv5s. This excellent performance gives PP-PicoDet a significant advantage in scenarios with high real-time and accuracy requirements, such as the deterioration analysis of the exterior walls of cultural relics protection buildings. It can quickly and accurately identify deteriorated areas, providing strong support for cultural relics protection work.

[0058] Therefore, in the present invention, the PP-PicoDet algorithm is selected as the main neural network architecture. PP-PicoDet is a lightweight target detection algorithm that achieves an excellent balance between accuracy and inference speed. The algorithm uses an efficient feature extraction network and a sophisticated bounding box regression method to effectively identify damaged areas in building facade images. At the same time, due to its lightweight characteristics, the PP-PicoDet algorithm has low requirements for hardware resources during deployment and operation, and is suitable for practical application scenarios.

[0059] Table 1 Model application effect evaluation table

[0060]

[0061]

[0062] In order to further improve the recognition accuracy of the model, the transfer learning method uses the neural network model pre-trained on a large image dataset as the basic model and migrates it to the task for fine-tuning. This can fully utilize the powerful feature representation capabilities of the existing model while avoiding the large amount of time and computing resources required to train the model from scratch.

[0063] More preferably, step S2 comprises:

[0064] Step S21, annotating image information of various types of damage in the database of deterioration damage types of exposed brick walls of historical buildings, and performing data feature analysis based on the annotations;

[0065] Specifically, in the model training phase, image annotation is a key step in image recognition training, which involves accurately identifying and classifying objects and areas in the image. Through high-quality annotation, machine learning models can learn the characteristics and patterns of different objects, thereby performing better in recognition and classification tasks. Accurate image annotation helps to improve the accuracy and robustness of the model, reduce judgment errors and improve the effectiveness of the model in practical applications. Therefore, the facade deterioration pictures collected in the early stage were annotated multiple times, and data feature analysis was performed to ensure the correctness and balance of the data set and the priority of subsequent expansion training.

[0066] Step S22, in the model verification stage, an independent test set is used to evaluate the performance of the model; by analyzing and comparing the recognition results of the images in the test set, the performance indicators of the intelligent recognition and evaluation diagnosis model for the deterioration characteristics of the exposed brick walls of historical buildings in terms of recognition accuracy, recall rate, and F1 score are obtained.

[0067] Here, these performance indicators can help comprehensively evaluate the model's ability to distinguish positive and negative samples, and guide subsequent parameter tuning and model improvements.

[0068] Step S23, based on the performance indicators, continuously iterate and optimize the intelligent identification and evaluation diagnosis model for deterioration characteristics of the exposed brick walls of historical buildings.

[0069] Here, through continuous iteration and optimization, we have successfully developed an intelligent identification and evaluation diagnosis model for the deterioration characteristics of exposed brick walls in historical buildings based on a neural network architecture and transfer learning. This model can effectively identify damaged areas in building facade images and accurately evaluate them.

[0070] In order to make the intelligent identification and evaluation and diagnosis system of deterioration characteristics of historical building plain brick walls play a role in practical applications, the trained model can be deployed. During the deployment process, the cloud AI deployment solution is adopted, and the high performance and elastic scaling capabilities of the cloud computing platform are used to achieve rapid deployment and efficient operation of the model.

[0071] Upload the model file to the cloud computing platform and use the API interface provided by the platform to call and infer. In actual applications, users can upload building facade images to the platform and call the model for damage identification and analysis. The cloud computing platform will provide corresponding damage type and degree information based on the output results of the model and generate a corresponding analysis report.

[0072] The cloud AI deployment solution enables flexible calling and expansion of models to meet application requirements in different scenarios. At the same time, the stability and security of the cloud computing platform also provide strong guarantees for the operation of the system.

[0073] In addition, in order to facilitate users to use the intelligent identification and evaluation diagnosis system for deterioration characteristics of historical building exposed brick walls anytime and anywhere, a mini program can be developed simultaneously. In addition to basic functions such as image uploading, model calling and result display, auxiliary functions such as image preprocessing and result sharing are also added to enhance the application of the program.

[0074] like Figure 3 As shown in the figure, in the development process of the mini program, modern front-end development technologies and frameworks were fully utilized to achieve a beautiful interface and friendly interaction. In addition, the mini program has also been rigorously tested and optimized to ensure its stability and performance on different devices and network environments.

[0075] Scan the QR code of the mini program or search the name of the mini program to install and use it. During use, users only need to upload the image of the building facade, and the mini program can automatically call the model for damage identification and analysis, and display the corresponding results. Users can also share the results with others or save them locally for subsequent processing.

[0076] Step S3, input the image data of the exposed brick wall of the historical building to be detected into the trained intelligent recognition and evaluation diagnosis model of the deterioration characteristics of the exposed brick wall of the historical building, and obtain the corresponding evaluation results of the damage type, location, and degree of damage.

[0077] Preferably, the drone oblique photography technology can be used to achieve high-precision three-dimensional rapid real-scene reconstruction of the facade based on multi-source data fusion, extract image data of the exposed brick walls of the historical buildings to be detected, such as high-resolution orthophoto data, and use this training to develop an intelligent recognition and evaluation diagnosis system for the deterioration characteristics of the exposed brick walls of historical buildings, such as Figure 4 As shown in the figure, the damaged area in the image is automatically identified, and the corresponding damage type and degree assessment results are given, realizing batch intelligent assessment and diagnosis of the deterioration degree of exposed brick walls. The assessment results of damage type and damage degree are automatically aligned to the corresponding specific brick surface in the lightweight digital model to form a digital twin mapping.

[0078] Specifically, based on the output results of the system, the damage of the target building can be analyzed and evaluated in detail to form the following Figure 5The current status analysis diagram of the deterioration and damage of the building facade is shown. Many cracks, peeling and discoloration damage phenomena were found, and the causes and influencing factors of these damages were deeply discussed. On this basis, according to the evaluation results, the corresponding protection and restoration suggestions were matched, and the special repair plan was assisted in the formulation, which effectively avoided the influence of human subjective factors, accurately guided the on-site repair construction, and greatly improved the operation efficiency by nearly 40%.

[0079] In summary, the present invention constructs a real-time intelligent analysis system for the deterioration and damage characteristics of the exposed brick walls of historical buildings by applying an artificial intelligence-based target detection algorithm, thereby realizing automatic identification of the damage type, location, and degree. In practical applications, this technology can be combined with drones, mobile devices, etc. to achieve large-scale, high-efficiency automatic detection of the facades of historical buildings. By providing real-time feedback on the detection results, the repair team can quickly formulate a repair plan to minimize damage to the building structure and appearance, thereby effectively extending the service life of the historical building and maintaining its historical value and aesthetic characteristics.

[0080] In view of the inefficiency and strong subjectivity of traditional manual survey methods in the repair of historical building facades, this paper uses deep learning and computer vision technology to select the PP-PicoDet algorithm, and constructs an efficient intelligent recognition and evaluation diagnosis model for the deterioration characteristics of exposed brick walls in historical buildings. Based on the learning of a large number of deterioration feature images, it realizes the automatic recognition of damage type, location and degree. Through actual project verification, the algorithm has shown certain advantages in recognition accuracy and real-time performance, reaching an accurate recognition rate of more than 86%, which can effectively improve the efficiency and quality of historical building protection work.

[0081] This invention uses deep learning and computer vision technology to optimize the neural network architecture through transfer learning, and realizes automatic recognition and accurate evaluation of the deterioration damage characteristics of the exposed brick walls of historical buildings based on the target detection algorithm. A sample database of exposed brick wall deterioration characteristics is established, and the PP-PicoDet algorithm is used for model training and feature increment superposition training to achieve rapid and accurate automatic recognition of damage type, location and degree. Compared with the traditional manual survey mode, it greatly improves the operation efficiency and result accuracy, and provides new intelligent and efficient survey tools and methods for the protection and repair of historical buildings.

[0082] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0083] According to another aspect of the present invention, there is provided a computer device, comprising:

[0084] Processor; and

[0085] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0086] The detailed contents of the device embodiments of the present invention can be found in the corresponding parts of the method embodiments, which will not be described in detail here.

[0087] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0088] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0089] In addition, a part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instruction for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-bearing medium, and / or stored in a working memory of a computer device that runs according to the program instruction. Here, according to an embodiment of the present invention, a device is included, the device including a memory for storing computer program instructions and a processor for executing program instructions, wherein, when the computer program instruction is executed by the processor, the device is triggered to run the method and / or technical solution based on the aforementioned multiple embodiments of the present invention.

[0090] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for assessing the deterioration characteristics of exposed brick walls in historical buildings, characterized in that: include: Establish a database of deterioration damage types of exposed brick walls in historical buildings; Based on the database of deterioration damage types of exposed brick walls in historical buildings, train an intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls in historical buildings; The image data of the exposed brick walls of the historical buildings to be inspected are input into the trained intelligent recognition and assessment diagnosis model of the deterioration characteristics of the exposed brick walls of the historical buildings to obtain the corresponding assessment results of the damage type, location, and degree of damage.

2. The method for assessing deterioration characteristics of exposed brick walls of historic buildings as claimed in claim 1, characterized in that: Establish a database of deterioration damage types of exposed brick walls in historical buildings, including: Through the acquisition module, information and image data on the facade damage of the exposed brick walls of historical buildings are collected; The analysis module obtains various damage types of deterioration of the exposed brick walls of historical buildings and the corresponding characteristics of each damage type based on the information and image data, and establishes a damage type database of deterioration of the exposed brick walls of historical buildings based on the various damage types and the corresponding characteristics of each damage type.

3. The method for assessing deterioration characteristics of exposed brick walls of historic buildings as claimed in claim 2, characterized in that: The damage types include: crack damage, peeling damage, discoloration damage and rust damage.

4. The method for assessing deterioration characteristics of exposed brick walls of historic buildings as claimed in claim 2, characterized in that: The database of deterioration damage types of exposed brick walls of historical buildings includes: image information of various damage types, and the causes, impact levels and repair methods of each damage type.

5. The method for assessing deterioration characteristics of exposed brick walls of historic buildings as claimed in claim 1, characterized in that: Based on the damage type database of exposed brick walls in historical buildings, the intelligent identification and evaluation diagnosis model of exposed brick walls in historical buildings is trained, including: Based on the database of deterioration damage types of exposed brick walls in historical buildings, a method combining neural network architecture and transfer learning is used to train an intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls in historical buildings.

6. The method for assessing deterioration characteristics of exposed brick walls of historic buildings as claimed in claim 5, characterized in that: The neural network architecture uses the PP-PicoDet algorithm.

7. The method for assessing the deterioration characteristics of the exposed brick walls of historic buildings as claimed in claim 5, characterized in that Based on the damage type database of the exposed brick walls of historical buildings, and using a combination of neural network architecture and transfer learning, the intelligent identification and evaluation diagnosis model of the exposed brick walls of historical buildings is trained, including: Annotate the image information of various types of damage in the database of deterioration damage types of exposed brick walls of historical buildings, and perform data feature analysis based on the annotations; In the model verification phase, an independent test set was used to evaluate the performance of the model. By analyzing and comparing the recognition results of the images in the test set, the performance indicators of the intelligent recognition and evaluation diagnosis model for the deterioration characteristics of the exposed brick walls of historical buildings in terms of recognition accuracy, recall rate and F1 score were obtained. Based on the performance indicators, the intelligent identification and evaluation diagnosis model for degradation characteristics of the exposed brick walls of historical buildings is continuously iterated and optimized.

8. The method for assessing deterioration characteristics of exposed brick walls of historic buildings as claimed in claim 1, characterized in that: Also includes: Uploading the trained intelligent recognition and evaluation diagnosis model for deterioration characteristics of the exposed brick walls of the historical buildings to the cloud computing platform; Alternatively, the trained intelligent recognition and evaluation diagnosis model for deterioration characteristics of exposed brick walls of historical buildings can be deployed in a mini program.

9. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to: perform the method according to any one of claims 1 to 8.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: perform a method as claimed in any one of claims 1 to 8.

Images