Weathering damage detection method for exposed brick wall
Through the combination of deep learning models and three-dimensional point cloud data, the depth information of weathering damage of clear water brick walls is identified and evaluated, and the problem of the existing technology being unable to identify depth direction information is solved, achieving more efficient damage diagnosis and quantitative evaluation, for history Building protection provides a scientific basis.
Patent Information
- Application Number
- CN202411420686.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-12
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-10-12
AI Technical Summary
Existing historical building apparent damage recognition and diagnosis technology cannot effectively identify and extract the depth direction information of weathered damage in clean water brick walls, resulting in low recognition and diagnostic efficiency and rely on qualitative description and manual examination.
Digital image recognition based on deep learning model is used to combine three-dimensional point cloud data, and the actual area and depth values of weathering damage are obtained by establishing the mapping relationship between digital images and point cloud data, and quantitative evaluation of weathering damage is achieved.
It improves the efficiency of identifying and diagnosing weathered damage in clean water brick walls, provides more comprehensive and accurate damage assessment results, lowers professional thresholds, and provides a scientific basis for preventive protection of historical buildings.
Smart Images

Figure CN118914238B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a method for detecting weathering damage of a plain brick wall. Background Art
[0002] my country has a huge stock of historical buildings with rich structures and diverse value characteristics. They are an important part of the urban and rural historical and cultural heritage system. During the use stage of historical buildings, as time goes by, due to the deterioration of material properties and the influence of the external environment, the buildings themselves will suffer various degrees of damage, among which the most common are surface damage represented by pollution, cracking, defects, and weathering. Due to the high value of preserving historical buildings, the identification and diagnosis of surface damage is an important part of the preventive protection of historical buildings and the basis for establishing scientific and effective maintenance methods. Traditional identification and diagnosis of surface damage relies on irregular inspections by professional and technical forces. The work is delayed, mainly based on qualitative descriptions, and has low levels of systematization and digitization.
[0003] At present, with the development of digital technology, a more efficient way is provided for the identification and diagnosis of apparent damage of historical buildings. At present, the conventional digital solution for intelligent identification and diagnosis of apparent damage of historical buildings is to realize the target detection of damage based on the deep learning method of digital images, on which the instance segmentation of damage and the calculation of index parameters can be further realized. However, in addition to the plane damage characteristics, weathering, defects and other types of damage in the apparent damage of historical buildings also include information in the depth direction. For example, weathering damage of exposed brick walls, at this time, the damage identification and diagnosis technology based on digital images cannot support the identification and extraction of depth direction information of this type of damage. Summary of the invention
[0004] The purpose of the present invention is to provide a method for detecting weathering damage of exposed brick walls.
[0005] In order to solve the above problems, the present invention provides a method for detecting weathering damage of a plain brick wall, comprising:
[0006] A method for detecting weathering damage of exposed brick walls, characterized by comprising:
[0007] Step 1: obtain a digital image of a plain brick wall, and identify the digital image of the plain brick wall using a trained weathering damage instance segmentation deep learning model to obtain a weathering damage identification result of the plain brick wall;
[0008] Step 2: Obtaining point cloud data of the surface of the exposed brick wall;
[0009] Step 3: Based on the digital image of the plain brick wall and the wall surface point cloud data, a first mapping relationship between the digital image of the plain brick wall and the wall surface point cloud data is obtained, and a pixel resolution is obtained based on the first mapping relationship;
[0010] Step 4: Based on the wall surface point cloud data, obtain the plane position of the undamaged wall;
[0011] Step 5, based on the weathering damage identification results, obtain the weathering damage morphology range;
[0012] Step six, based on the plane position of the damaged wall and the first mapping relationship, establish a second mapping relationship between the digital image and the wall depth deviation cloud map;
[0013] Step 7, based on the weathering damage morphological range and pixel resolution, obtaining the actual area of the weathering damage region;
[0014] Step eight, obtaining a corresponding weathering depth value based on the second mapping relationship;
[0015] Step nine, obtaining the evaluation result based on the actual area of the weathering damage region and the weathering depth value.
[0016] Furthermore, in the above method, in step 1, a digital image of a plain brick wall is obtained, and the digital image of the plain brick wall is recognized by using the trained weathering damage instance segmentation deep learning model to obtain a weathering damage recognition result of the plain brick wall, including:
[0017] Step 1, damage instance segmentation model training: Based on the instance segmentation deep learning model, images of plain brick walls with weathering damage are collected and annotated as a data set, and the deep learning model is trained to obtain a trained weathering damage instance segmentation deep learning model, so that the trained weathering damage instance segmentation deep learning model has the function of identifying weathering damage of plain brick walls and extracting instances after inputting images;
[0018] Step 2, using a camera to orthophotograph a high-definition digital image of the surface of the exposed brick wall, and performing distortion correction on the image to obtain a corrected digital image;
[0019] Step 4: Based on the trained weathering damage instance segmentation deep learning model, the corrected digital image obtained in step 2 is input to perform weathering damage recognition to obtain a weathering damage recognition result.
[0020] Furthermore, in the above method, step 2, obtaining the surface point cloud data of the exposed brick wall, includes:
[0021] Step 3: Use a scanner to obtain the wall surface point cloud data of the exposed brick wall, and perform denoising, registration and simplification processing on the wall surface point cloud data to obtain processed wall surface point cloud data.
[0022] Furthermore, in the above method, step three, based on the digital image of the clear brick wall and the wall surface point cloud data, obtains a first mapping relationship between the digital image of the clear brick wall and the wall surface point cloud data, and obtains a pixel resolution based on the first mapping relationship, including:
[0023] Step 5, based on the positions of the feature points with the same name, matching and registering the corrected digital image obtained in step 2 and the processed wall surface point cloud data obtained in step 3, and establishing a second mapping relationship between the positions of the corrected digital image and the processed wall surface point cloud data;
[0024] Step 6, combining the pixel resolution of the point cloud calculation: based on the first mapping relationship between the positions of the corrected digital image and the processed wall surface point cloud data obtained in step 5, establish a corresponding relationship between the pixel size of the digital image and the actual size data of the wall surface, and calculate the pixel resolution of the digital image based on the corresponding relationship.
[0025] Furthermore, in the above method, step 4, based on the wall surface point cloud data, obtaining the plane position of the undamaged wall includes:
[0026] Step 7: Based on the RANSAC algorithm, according to the processed wall surface point cloud data obtained in step 3, the influence of local damage data is eliminated, and the ideal plane of the wall is fitted as the plane position of the undamaged wall.
[0027] Furthermore, in the above method, in step 5, based on the weathering damage identification result, the weathering damage morphology range is obtained, including:
[0028] Step 8: Based on the weathering damage identification result obtained in step 4, perform morphological range extraction and establish a mask to obtain the weathering damage morphological range.
[0029] Furthermore, in the above method, step six, based on the plane position of the damaged wall and the first mapping relationship, establishing a second mapping relationship between the digital image and the wall depth deviation cloud map includes:
[0030] Step 9, generating a wall depth deviation cloud map: taking the undamaged wall plane position generated in step 7 as a reference, for the processed wall surface point cloud data obtained in step 3, calculate the distance from the undamaged wall plane position point by point to generate a wall depth deviation cloud map, and based on the first mapping relationship between the corrected digital image obtained in step 5 and the position of the processed wall surface point cloud data, establish a second mapping relationship between the corrected digital image and the wall depth deviation cloud map.
[0031] Furthermore, in the above method, step seven, based on the weathering damage morphological range and pixel resolution, obtaining the actual area of the weathering damage region includes:
[0032] Step 10, based on the weathering damage morphology range obtained in step 8, calculate the number of pixels within the weathering damage morphology range, and convert the calculated number of pixels according to the pixel resolution obtained in step 6 to obtain the actual area of the weathering damage region.
[0033] Furthermore, in the above method, step eight, based on the second mapping relationship, obtaining a corresponding weathering depth value includes:
[0034] Step 11: According to the second mapping relationship between the corrected digital image obtained in step 9 and the wall depth deviation cloud map, the weathering damage morphological range in the wall depth deviation cloud map is traversed, and the weathering depth of the corresponding position is obtained by comparing the RGB and HSV values of the color scale, and the maximum damage depth value in the weathering damage morphological range is selected as the weathering depth value of the weathering damage.
[0035] Furthermore, in the above method, step nine, based on the actual area of the weathering damage region and the weathering depth value, obtaining the evaluation result includes:
[0036] Step 12 evaluates the severity of the weathering damage on the wall surface by combining the actual area of the weathering damage area obtained in step 10 and the weathering depth value obtained in step 11 to evaluate the result;
[0037] Step 13: Based on the evaluation result, mark the area range of weathering damage and the corresponding weathering degree grade on the digital image of the exposed brick wall.
[0038] In response to the above-mentioned problem of detecting weathering damage of plain brick walls of historical buildings, the present invention proposes an intelligent detection method for weathering damage of plain brick walls based on multi-source data. The method comprehensively analyzes the wall texture color data captured by a camera and the wall geometry data acquired by a three-dimensional scanner, identifies the damage type by the texture color data, and extracts the damage area and depth data in combination with the point cloud data, thereby achieving quantitative evaluation and diagnosis of weathering damage of plain brick walls of historical buildings, laying a foundation for preventive protection of historical buildings.
[0039] The main idea of the present invention is to comprehensively analyze the wall texture color data taken by the camera and the wall geometry data obtained by the three-dimensional scanner. First, the weathering damage area is identified and extracted through the digital image of the plain brick wall based on the deep learning algorithm. Then, according to the feature points, the point cloud and the digital image are matched to calculate the pixel resolution. The actual area of the weathering damage area is calculated based on the pixel resolution. Then, the coordinates are matched with the wall depth cloud map generated by the wall point cloud and the weathering depth data of the corresponding position is extracted. Finally, the weathering area and depth are comprehensively considered to evaluate the damage and output the damage location range and level.
[0040] Compared with the prior art, the beneficial effects of the present invention are mainly as follows:
[0041] The existing weathering damage identification and detection technology for exposed brick walls is based on digital images and can only obtain plane index parameters. In this way, the three-dimensional scanning technology is used to collect point clouds to obtain size and depth information. After data processing, the two-dimensional information of weathering damage, plane and depth, is obtained, so as to more comprehensively evaluate the weathering damage of exposed brick walls.
[0042] Based on the present invention, an intelligent identification and diagnosis method for weathering damage of exposed brick walls is proposed. By collecting large-scale digital images of the wall and point cloud data to replace manual inspection, the efficiency of on-site damage investigation is improved. In addition, based on the intelligent algorithm of machine vision, the professional threshold for damage identification and diagnosis is lowered, laying a foundation for preventive protection of historical buildings.
[0043] The method proposed in the present invention is also applicable to other types of damage with depth information, such as defect, fall-off, decay, etc. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 The present invention is a flowchart of a method for detecting weathering damage of a plain brick wall according to an embodiment of the present invention. DETAILED DESCRIPTION
[0045] The present invention is further described in detail below in conjunction with the accompanying drawings.
[0046] 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.
[0047] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
[0048] 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.
[0049] like Figure 1 As shown, the present invention provides a method for detecting weathering damage of a plain brick wall, the method comprising:
[0050] Step 1: obtain a digital image of a plain brick wall, and identify the digital image of the plain brick wall using a trained weathering damage instance segmentation deep learning model to obtain a weathering damage identification result of the plain brick wall;
[0051] Preferably, step 1 comprises the following steps 1, 2 and 4;
[0052] Step 2: Obtaining point cloud data of the surface of the exposed brick wall;
[0053] Preferably, step 2 includes the following step 3;
[0054] Step 3: Based on the digital image of the plain brick wall and the wall surface point cloud data, a first mapping relationship between the digital image of the plain brick wall and the wall surface point cloud data is obtained, and a pixel resolution is obtained based on the first mapping relationship;
[0055] Preferably, the step three includes the following steps 5 and 6;
[0056] Step 4: Based on the wall surface point cloud data, obtain the plane position of the undamaged wall;
[0057] Preferably, the step 4 includes the following step 7;
[0058] Step 5, based on the weathering damage identification results, obtain the weathering damage morphology range;
[0059] Preferably, the step five comprises the following step 8;
[0060] Step six, based on the plane position of the damaged wall and the first mapping relationship, establish a second mapping relationship between the digital image and the wall depth deviation cloud map;
[0061] Preferably, the step six comprises the following step 9;
[0062] Step 7, based on the weathering damage morphological range and pixel resolution, obtaining the actual area of the weathering damage region;
[0063] Preferably, the step seven includes the following step 10;
[0064] Step eight, obtaining a corresponding weathering depth value based on the second mapping relationship;
[0065] Preferably, the step eight comprises the following step 11;
[0066] Step nine, obtaining the evaluation result based on the actual area of the weathering damage region and the weathering depth value.
[0067] Preferably, the step nine includes the following steps 12 and 13;
[0068] Specifically, the present invention includes:
[0069] Step 1, damage instance segmentation model training: Based on the instance segmentation deep learning model, images of plain brick walls with weathering damage are collected and annotated as a data set, and the deep learning model is trained to obtain a trained weathering damage instance segmentation deep learning model, so that the trained weathering damage instance segmentation deep learning model has the function of identifying weathering damage of plain brick walls and extracting instances after inputting images;
[0070] Step 2, using a camera to capture a digital image: using a camera to orthophotograph a high-definition digital image of the surface of the exposed brick wall, and performing distortion correction on the image to obtain a corrected digital image;
[0071] Step 3: Scanner collects wall point cloud: Use a scanner to obtain the wall surface point cloud data of the plain brick wall, and perform denoising, registration and simplification on the wall surface point cloud data to obtain the processed wall surface point cloud data;
[0072] Step 4, damage identification based on machine learning: Based on the trained weathering damage instance segmentation deep learning model, the corrected digital image obtained in step 2 is input to perform weathering damage identification to obtain the weathering damage identification result;
[0073] Step 5, matching the digital image with the point cloud data: based on the positions of the feature points with the same name, the corrected digital image obtained in step 2 and the processed wall surface point cloud data obtained in step 3 are matched and registered to establish a second mapping relationship between the positions of the corrected digital image and the processed wall surface point cloud data;
[0074] Step 6, combining the pixel resolution of the point cloud calculation: based on the first mapping relationship between the positions of the corrected digital image and the processed wall surface point cloud data obtained in step 5, a corresponding relationship between the pixel size of the digital image and the actual size data of the wall surface is established, and based on the corresponding relationship, the pixel resolution of the digital image is calculated;
[0075] Step 7, RANSAC algorithm fitting the wall plane: Based on the RANSAC algorithm, according to the processed wall surface point cloud data obtained in step 3, the influence of local damage data is eliminated, and the ideal wall plane is fitted as the plane position of the undamaged wall;
[0076] Step 8, weathering damage morphological range extraction: based on the weathering damage identification result obtained in step 4, perform morphological range extraction and establish a mask to obtain the weathering damage morphological range;
[0077] Step 9, generating a wall depth deviation cloud map: taking the undamaged wall plane position generated in step 7 as a reference, for the processed wall surface point cloud data obtained in step 3, calculating the distance from the undamaged wall plane position point by point, generating a wall depth deviation cloud map, and based on the first mapping relationship between the corrected digital image obtained in step 5 and the position of the processed wall surface point cloud data, establishing a second mapping relationship between the corrected digital image and the wall depth deviation cloud map;
[0078] Step 10, calculating the area of the weathering damage region: based on the weathering damage morphological range obtained in step 8, calculating the number of pixels within the weathering damage morphological range, and converting the calculated number of pixels according to the pixel resolution obtained in step 6 to obtain the actual area of the weathering damage region;
[0079] Step 11, calculation of weathering damage depth: according to the second mapping relationship between the corrected digital image obtained in step 9 and the wall depth deviation cloud map, traverse the weathering damage morphological range in the wall depth deviation cloud map, obtain the weathering depth of the corresponding position by comparing the RGB and HSV values of the color scale, and select the maximum damage depth value within the weathering damage morphological range as the weathering depth value of the weathering damage;
[0080] Step 12, comprehensive weathering area and depth evaluation: Comprehensively evaluate the actual area of the weathering damage area obtained in step 10 and the weathering depth value obtained in step 11, and evaluate the severity of the weathering damage to the wall to obtain the evaluation result; wherein, the evaluation logic can be independently configured based on the actual area of the weathering damage area and the weathering depth value, these two indicator parameters.
[0081] Step 13, outputting the damage location range and grade: Based on the evaluation results, marking the area range of weathering damage and the corresponding weathering degree grade on the digital image of the exposed brick wall.
[0082] In response to the above-mentioned problem of detecting weathering damage of plain brick walls of historical buildings, the present invention proposes an intelligent detection method for weathering damage of plain brick walls based on multi-source data. The method comprehensively analyzes the wall texture color data captured by a camera and the wall geometry data acquired by a three-dimensional scanner, identifies the damage type by the texture color data, and extracts the damage area and depth data in combination with the point cloud data, thereby achieving quantitative evaluation and diagnosis of weathering damage of plain brick walls of historical buildings, laying a foundation for preventive protection of historical buildings.
[0083] The main idea of the present invention is to comprehensively analyze the wall texture color data taken by the camera and the wall geometry data obtained by the three-dimensional scanner. First, the weathering damage area is identified and extracted through the digital image of the plain brick wall based on the deep learning algorithm. Then, according to the feature points, the point cloud and the digital image are matched to calculate the pixel resolution. The actual area of the weathering damage area is calculated based on the pixel resolution. Then, the coordinates are matched with the wall depth cloud map generated by the wall point cloud and the weathering depth data of the corresponding position is extracted. Finally, the weathering area and depth are comprehensively considered to evaluate the damage and output the damage location range and level.
[0084] Compared with the prior art, the beneficial effects of the present invention are mainly as follows:
[0085] The existing weathering damage identification and detection technology for exposed brick walls is based on digital images and can only obtain plane index parameters. In this way, the three-dimensional scanning technology is used to collect point clouds to obtain size and depth information. After data processing, the two-dimensional information of weathering damage, plane and depth, is obtained, so as to more comprehensively evaluate the weathering damage of exposed brick walls.
[0086] Based on the present invention, an intelligent identification and diagnosis method for weathering damage of exposed brick walls is proposed. By collecting large-scale digital images of the wall and point cloud data to replace manual inspection, the efficiency of on-site damage investigation is improved. In addition, based on the intelligent algorithm of machine vision, the professional threshold for damage identification and diagnosis is lowered, laying a foundation for preventive protection of historical buildings.
[0087] The method proposed in the present invention is also applicable to other types of damage with depth information, such as defect, fall-off, decay, etc.
[0088] 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.
[0089] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, it 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 various steps or functions.
[0090] 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.
[0091] 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 detecting weathering damage of exposed brick walls, characterized in that: include: Step 1: obtain a digital image of a plain brick wall, and identify the digital image of the plain brick wall using a trained weathering damage instance segmentation deep learning model to obtain a weathering damage identification result of the plain brick wall; Step 2: Obtaining point cloud data of the surface of the exposed brick wall; Step 3: based on the digital image of the plain brick wall and the wall surface point cloud data, obtain a first mapping relationship between the digital image of the plain brick wall and the wall surface point cloud data, and obtain a pixel resolution based on the first mapping relationship; Step 4: Based on the wall surface point cloud data, obtain the plane position of the undamaged wall; Step 5, based on the weathering damage identification results, obtain the weathering damage morphology range; Step six, based on the plane position of the damaged wall and the first mapping relationship, establish a second mapping relationship between the digital image and the wall depth deviation cloud map; Step 7, based on the weathering damage morphological range and pixel resolution, obtaining the actual area of the weathering damage region; Step eight, obtaining a corresponding weathering depth value based on the second mapping relationship; Step nine, obtaining the evaluation result based on the actual area of the weathering damage region and the weathering depth value.
2. The method for detecting weathering damage of a plain brick wall according to claim 1, characterized in that: Step 1: Obtain a digital image of a plain brick wall, and use the trained weathering damage instance segmentation deep learning model to identify the digital image of the plain brick wall, and obtain the weathering damage identification result of the plain brick wall, including: Step 1, damage instance segmentation model training: Based on the instance segmentation deep learning model, images of plain brick walls with weathering damage are collected and annotated as a data set, and the deep learning model is trained to obtain a trained weathering damage instance segmentation deep learning model, so that the trained weathering damage instance segmentation deep learning model has the function of identifying weathering damage of plain brick walls and extracting instances after inputting images; Step 2, using a camera to orthophotograph a high-definition digital image of the surface of the exposed brick wall, and performing distortion correction on the image to obtain a corrected digital image; Step 4: Based on the trained weathering damage instance segmentation deep learning model, the corrected digital image obtained in step 2 is input to perform weathering damage recognition to obtain a weathering damage recognition result.
3. The method for detecting weathering damage of a plain brick wall according to claim 2, characterized in that: Step 2: Obtain the surface point cloud data of the exposed brick wall, including: Step 3: Use a scanner to obtain the wall surface point cloud data of the exposed brick wall, and perform denoising, registration and simplification processing on the wall surface point cloud data to obtain processed wall surface point cloud data.
4. The method for detecting weathering damage of a plain brick wall according to claim 3, characterized in that: Step three, based on the digital image of the plain brick wall and the wall surface point cloud data, obtain a first mapping relationship between the digital image of the plain brick wall and the wall surface point cloud data, and obtain a pixel resolution based on the first mapping relationship, including: Step 5, based on the positions of the feature points with the same name, matching and registering the corrected digital image obtained in step 2 and the processed wall surface point cloud data obtained in step 3, and establishing a second mapping relationship between the positions of the corrected digital image and the processed wall surface point cloud data; Step 6, combining the pixel resolution of the point cloud calculation: based on the first mapping relationship between the positions of the corrected digital image and the processed wall surface point cloud data obtained in step 5, establish a corresponding relationship between the pixel size of the digital image and the actual size data of the wall surface, and calculate the pixel resolution of the digital image based on the corresponding relationship.
5. The method for detecting weathering damage of exposed brick wall according to claim 4, characterized in that: Step 4: Based on the wall surface point cloud data, obtain the plane position of the undamaged wall, including: Step 7: Based on the RANSAC algorithm, according to the processed wall surface point cloud data obtained in step 3, the influence of local damage data is eliminated, and the ideal plane of the wall is fitted as the plane position of the undamaged wall.
6. The method for detecting weathering damage of exposed brick walls according to claim 5, characterized in that: Step 5: Based on the weathering damage identification results, the range of weathering damage morphology is obtained, including: Step 8: Based on the weathering damage identification result obtained in step 4, perform morphological range extraction and establish a mask to obtain the weathering damage morphological range.
7. The method for detecting weathering damage of a plain brick wall according to claim 6, characterized in that: Step six, based on the plane position of the damaged wall and the first mapping relationship, establishing a second mapping relationship between the digital image and the wall depth deviation cloud map, including: Step 9, generating a wall depth deviation cloud map: taking the undamaged wall plane position generated in step 7 as a reference, for the processed wall surface point cloud data obtained in step 3, calculate the distance from the undamaged wall plane position point by point to generate a wall depth deviation cloud map, and based on the first mapping relationship between the corrected digital image obtained in step 5 and the position of the processed wall surface point cloud data, establish a second mapping relationship between the corrected digital image and the wall depth deviation cloud map.
8. The method for detecting weathering damage of exposed brick walls according to claim 7, characterized in that: Step 7, based on the weathering damage morphological range and pixel resolution, obtaining the actual area of the weathering damage region, including: Step 10, based on the weathering damage morphology range obtained in step 8, calculate the number of pixels within the weathering damage morphology range, and convert the calculated number of pixels according to the pixel resolution obtained in step 6 to obtain the actual area of the weathering damage region.
9. The method for detecting weathering damage of a plain brick wall according to claim 8, characterized in that: Step eight, based on the second mapping relationship, obtaining a corresponding weathering depth value, including: Step 11, according to the second mapping relationship between the corrected digital image obtained in step 9 and the wall depth deviation cloud map, traverse the weathering damage morphology range in the wall depth deviation cloud map, obtain the weathering depth of the corresponding position by comparing the RGB and HSV values of the color scale, and select the maximum damage depth value within the weathering damage morphology range as the weathering depth value of the weathering damage.
10. The method for detecting weathering damage of exposed brick walls according to claim 9, characterized in that: Step nine: Based on the actual area of the weathering damage area and the weathering depth value, the evaluation results are obtained, including: Step 12 evaluates the severity of the weathering damage on the wall surface by combining the actual area of the weathering damage area obtained in step 10 and the weathering depth value obtained in step 11 to evaluate the result; Step 13: Based on the evaluation result, mark the area range of weathering damage and the corresponding weathering degree grade on the digital image of the exposed brick wall.
