Defect repairing method, device and equipment for building outer wall

Abstract

The invention relates to the field of building detection, and discloses a defect repairing method, device and equipment for a building outer wall, and the method comprises the steps: building an outer wall surface image set of a target building; identifying defect type, size and depth information of each defect in the outer wall surface image; establishing a target three-dimensional model of the target building, and generating a position coordinate corresponding to each defect; and generating a repair path of each defect according to the type, the size, the depth and the position coordinates of the defect. The building outer wall defect detection efficiency and accuracy can be effectively improved, a detailed report of the defects can be automatically generated, analysis and future defect development state prediction can be performed according to the actual situation and historical data of the building, reasonable maintenance suggestions are provided, the safety of the building outer wall is ensured, and the method is suitable for popularization and application. And long-term maintenance of the outer wall is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of building inspection, and particularly to a method, device, and equipment for repairing defects in building exterior walls. Background Art

[0002] External thermal insulation layers or exterior wall tiles are usually provided on building exterior walls to achieve the purposes of exterior wall decoration and thermal insulation. Due to long-term exposure to wind, sun, rain, and snow, the shape and structure of the outer layer of the exterior wall will change, mainly manifested as surface pollution on the outer layer, such as mildew, discoloration, or peeling, efflorescence, cracks, leakage, powdering, etc. More seriously, voids and hollowing may occur in the adhesion layer between the outer layer structure and the internal main structure, resulting in the detachment of the outer layer of the exterior wall. In order to ensure the aesthetics of the target building and avoid the risk of high-altitude falling objects caused by the detachment of the exterior wall, it is necessary to regularly detect and evaluate the defects of the exterior wall and repair them in a timely manner. Although existing technologies provide some exterior wall detection methods, they usually only detect the detachment of exterior wall tiles, and the types of defects that can be identified are relatively single. It is difficult to detect various types of defects in building exterior walls and give comprehensive evaluation opinions and targeted repair suggestions. Summary of the Invention

[0003] The present invention provides a method, device, and equipment for repairing defects in building exterior walls, which solve the above-mentioned technical problems.

[0004] The first aspect of the embodiment of the present invention provides a method for repairing defects in a building exterior wall, including the following steps:

[0005] Step 1, establish an image set of the exterior wall surface of the target building, where the image set of the exterior wall surface includes multiple frames of exterior wall surface images;

[0006] Step 2, generate defect information of the exterior wall surface image according to a preset defect recognition model, and perform defect marking at the corresponding position of the exterior wall surface image to generate a defect photo set of the target building, where the defect information includes defect type, size, and depth;

[0007] Step 3, establish a target three-dimensional model of the target building based on the defect photo set, mark each defect in the target three-dimensional model, and generate the position coordinates corresponding to each defect;

[0008] Step 4, generate a repair path for each defect according to the defect type, the size, the depth, and the position coordinates.

[0009] The second aspect of the embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for repairing defects in a building exterior wall described above.

[0010] The third aspect of the embodiments of the present invention provides a defect repair device for building exterior walls, including a computer-readable storage medium and a processor. When the processor executes the computer program on the computer-readable storage medium, the steps of the above-mentioned defect repair method for building exterior walls are implemented.

[0011] The fourth aspect of the embodiments of the present invention provides a defect repair device for building exterior walls, including an image acquisition module, a defect identification module, a model reconstruction module, and a repair planning module.

[0012] The image acquisition module is used to establish an exterior wall surface image set of the target building, and the exterior wall surface image set includes multiple frames of exterior wall surface images.

[0013] The defect identification module is used to generate defect information of the exterior wall surface image according to a preset defect identification model, and perform defect marking at the corresponding position of the exterior wall surface image to generate a defect photo set of the target building. The defect information includes defect type, size, and depth.

[0014] The model reconstruction module is used to establish a target three-dimensional model of the target building based on the defect photo set, mark each defect in the target three-dimensional model, and generate the corresponding position coordinates of each defect.

[0015] The repair planning module is used to generate a repair path for each defect according to the defect type, the size, the depth, and the position coordinates.

[0016] The beneficial effects of the present invention are as follows: The present invention provides a defect repair method, device, and equipment for building exterior walls, which can effectively improve the efficiency and accuracy of building exterior wall defect detection. It can not only automatically generate a detailed report of the defects, but also analyze according to the actual situation and historical data of the building and predict the future defect development status, and put forward reasonable maintenance suggestions to ensure the safety of the building exterior wall and facilitate the long-term maintenance of the exterior wall.

[0017] To make the above objects, features, and advantages of the invention more obvious and understandable, the following specifically enumerates preferred embodiments of the present invention and, in conjunction with the accompanying drawings, makes a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0019] Figure 1It is a schematic flowchart of the method for repairing defects on the exterior wall of a building provided in Embodiment 1;

[0020] Figure 2 It is a schematic structural diagram of the device for repairing defects on the exterior wall of a building provided in Embodiment 2;

[0021] Figure 3 It is a schematic structural diagram of the equipment for repairing defects on the exterior wall of a building provided in Embodiment 3. Detailed implementation manners

[0022] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0023] It should be noted that if there is no conflict, the various features in the embodiments of the present invention can be combined with each other and all fall within the protection scope of the present invention. In addition, although functional module division is performed in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the flowchart. Furthermore, the terms "first", "second", "third", etc. adopted by the present invention do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0024] Figure 1 It is a schematic flowchart of a method for repairing defects on the exterior wall of a building provided in Embodiment 1. As Figure 1 shown, it includes the following steps:

[0025] Step 1, establish an image set of the exterior wall surface of the target building, and the exterior wall surface image set includes multiple frames of exterior wall surface images;

[0026] Step 2, generate defect information of the exterior wall surface image according to a preset defect recognition model, and perform defect marking at the corresponding positions to generate a defect photo set of the target building, where the defect information includes defect type, size and depth;

[0027] Step 3, establish a target 3D model of the target building based on the defect photo set, mark each defect in the target 3D model, and generate the position coordinates corresponding to each defect;

[0028] Step 4, generate a repair path for each defect according to the defect type, the size, the depth and the position coordinates.

[0029] It can be understood that the repair path referred to in the present invention means a repair plan generated according to a certain priority order and logic during the building defect detection and repair process, including repair steps, methods, and materials, to ensure the efficient, accurate, and economical completion of the repair work. Specifically, during the detection process, various defects (such as cracks, peeling, water seepage, etc.) on the building facade are first identified and located based on the detection results. According to the type, depth, and impact of the defects, the system assigns a priority to each defect. For example, cracks with a greater depth and defects that may threaten the structural safety will be given priority, while some small surface cracks can be repaired later. In a specific embodiment, the repair path arranges the repair steps according to the actual situation of the building. Usually, the repair starts from the most urgent and significant defects and gradually proceeds to the minor defects. For example, defects with water seepage or structural risks are repaired first, followed by the repair of the surface decoration layer, and finally other minor defects. When the urgency of the defects is the same, the repair steps will be arranged based on the defect coordinates with the goal of facilitating the repair.

[0030] Once the repair object is determined, the system selects a suitable repair method according to the requirements of architectural specifications and repair techniques. For example, for cracks, grouting may be selected for filling, and for the peeling facade, bonding or replacing materials may be used. The system also optimizes the repair method for each defect based on factors such as repair effect, construction difficulty, and cost.

[0031] Meanwhile, in the repair path, the construction sequence is an important link. The repair of different areas is reasonably arranged according to the actual situation. For example, some areas may require a longer repair time or may be affected by the weather (such as the repair of the exterior wall). Through this method, the repair path will be dynamically adjusted to ensure the reasonable allocation of construction resources, avoid repeated construction or affecting other repair steps. If new problems or unexpected results are found, the present invention will also give real-time feedback and automatically adjust the repair path. For example, if the cracks in a certain area expand or new problems occur during the repair process, the system will re-evaluate and adjust the repair plan and sequence.

[0032] The above embodiments provide a method for repairing defects in a building exterior wall, which can effectively improve the efficiency and accuracy of building exterior wall defect detection, identify the danger level for each defect according to parameters such as defect type, size, and depth, thereby determining the repair order and path for all defects, and putting forward reasonable maintenance suggestions to ensure the safety of the building exterior wall and facilitate the long-term maintenance of the exterior wall.

[0033] The following uses specific embodiments to explain each step of the above method in detail.

[0034] It is understandable that before repairing the defects of the building exterior wall, it is first necessary to collect images or videos of the building exterior wall, especially exterior wall pictures containing various defects such as hollowing, leakage, cracks, peeling, stains, rust, etc. The prior art can collect the required exterior wall surface images by manual photography or by using a drone to conduct a circumferential shoot of the target building.

[0035] In one embodiment, the exterior wall surface images of the target building are collected by a high-resolution camera and a drone platform. Specifically, the drone is equipped with a multi-functional camera, such as a high-definition RGB camera and an infrared thermal imaging camera, and the exterior wall surface images are collected in real time by controlling the drone to fly around the building. The exterior wall surface images include natural light images of the exterior wall and thermal imaging images corresponding to the abnormal temperature areas of the exterior wall. In order to make the collected exterior wall defect images more complete, the preferred embodiment specifically includes the following steps:

[0036] S101, obtain the information of key parts of the exterior wall of the target building, such as parts prone to defects like window sills, joints, and protrusions, etc.;

[0037] S102, generate the flight path of the drone according to the information of the key parts of the exterior wall. The flight path at least includes the flight control height and flight control angle corresponding to each key part of the exterior wall, so as to ensure covering each exterior wall surface;

[0038] S103, control the drone to fly around the exterior wall of the target building according to the flight route to generate a target circumferential shooting video, and then slice the target circumferential shooting video at a preset frequency, such as 2 frames per minute, to generate several frames of exterior wall surface images, and establish an exterior wall surface image set.

[0039] Then execute step 2 to identify the defects in the collected exterior wall surface images to obtain the corresponding defect information. In a preferred embodiment, the neural network recognition method can be adopted. First, noise removal and edge extraction are performed on the exterior wall surface images, and then the neural network model is used to identify defects such as cracks, peeling, stains, rust, etc. in the images, and information such as their positions, sizes, and types on the exterior wall surface images is marked. In addition, the thermal imaging images are analyzed by a thermal anomaly detection algorithm to identify the heat changes caused by building structure defects or water leakage.

[0040] Specifically, the pre-trained preset defect recognition model includes a defect type recognition model, a thermal anomaly detection model, and a depth recognition model.

[0041] The defect type recognition model is used to identify and mark the first defect type and the corresponding defect size (such as defect area or defect length) of the natural light image through a first preset neural network, so as to generate a first defect photo. The first defect type includes at least one of crack, spalling, stain, and rust;

[0042] The thermal anomaly detection model is used to identify and mark the second defect type and the corresponding defect size of the thermal imaging image. The second defect type includes external wall leakage defect and / or facing tile hollowing defect;

[0043] The depth recognition model is used to identify and mark the depth corresponding to the crack defect, spalling defect, and rust defect in the first defect photo through a second preset neural network. Here, the depth refers to the distance from the surface of the epitaxial layer to the inside of the defect. The neural network models involved in the above embodiments can adopt the cnn model. Specific methods such as historical image marking, training set establishment, and model training are all well documented in the prior art and will not be elaborated here.

[0044] Then, step 3 is executed. After obtaining a large number of defect photos marked with defect information, a target 3D model of the target building is established through the defect photos, and the position coordinates corresponding to each defect are generated.

[0045] In a preferred embodiment, establishing the target 3D model of the target building based on the defect photo set specifically includes the following steps:

[0046] S301, construct a 3D visualization system;

[0047] S302, generate a point cloud model corresponding to the defect photo set through the SFM structure measurement algorithm;

[0048] S303, import the point cloud model into the 3D visualization system, and generate the target 3D model corresponding to the target building after iterative training.

[0049] In another preferred embodiment, generating the position coordinates corresponding to each defect specifically includes the following steps:

[0050] S304, obtain defect photos with marked defect positions and defect information, and convert the two-dimensional defect area of the defect photos into corresponding three-dimensional point cloud data by using the binocular grating projection reconstruction method;

[0051] S305, perform meshing processing on the three-dimensional point cloud data to generate a contour model of the external wall of the target building, perform texture mapping processing on the contour model, and perform occlusion judgment on the point cloud projected onto each pixel area during the texture mapping process to remove the occluded and mis-matched point cloud data;

[0052] S306. Obtain the target pixel points within the defect contour, and calculate and generate the three-dimensional position coordinates corresponding to the target pixel points through quadrant proximity search and linear interpolation method based on distance weighted average.

[0053] It can be understood that according to whether a structured light source is projected into the scene during the measurement process, the existing technology can divide visual three-dimensional reconstruction into active vision reconstruction and passive vision reconstruction. The binocular grating projection reconstruction method belongs to a kind of active vision reconstruction. It encodes the phase of the horizontal and vertical grating stripes projected onto the object surface, and uses these phase encodings as features for binocular stereo matching, so as to reconstruct a high-density spatial point cloud (reflecting the surface topography of the object to be measured), with good reconstruction effect. The above embodiment provides a visual three-dimensional reconstruction method, adding a texture camera on the basis of a binocular grating projection system, and establishing the mapping relationship between the texture image and the point cloud at different shooting positions through stereo calibration and rotation axis calibration. Aiming at the problem of texture mapping error caused by occlusion during the projection of multi-view stitching point cloud onto the image, an occlusion point removal method based on distance criterion is adopted. On this basis, the three-dimensional projection points adjacent to the target pixels in the texture image are found by the method of quadrant adjacent point search, and combined with the linear interpolation method based on distance weighted average, the high-resolution three-dimensional reconstruction of the internal area of the defect contour in the image is completed, so as to obtain accurate three-dimensional position coordinates. Of course, this is just a three-dimensional reconstruction method with better effect. Other embodiments of the present invention can also adopt other three-dimensional reconstruction methods of the existing technology and obtain the three-dimensional position coordinates corresponding to each defect, which will not be elaborated here.

[0054] It can be understood that after obtaining the defect type, size, depth and position coordinates, step 4 can be executed to generate the repair path for each defect. In a specific embodiment, generating the repair path for each defect specifically includes the following steps:

[0055] S401. Generate the corresponding first repair weight according to the position coordinates of each defect;

[0056] S402. Adjust the first repair weight according to the size and depth of the corresponding defect to generate the second repair weight;

[0057] S403. Generate the corresponding first repair urgency score result according to the defect type of each defect and the second repair weight. Specifically, a preset query table can be established and an urgency model can be fitted according to big data, such as historical external wall damage data at different times and different geographical locations. The preset query table sets the corresponding repair weights for each defect type with different position coordinates, different sizes and depths, and at the same time, the first repair urgency score result considering factors such as defect type, defect size, defect depth, defect position, etc. can be calculated through the preset urgency model.

[0058] S404. Screen out the first-level defect set based on the first repair urgency score result and the first comprehensive evaluation result of the preset expert system. It can be understood that the preset expert system is an intelligent decision-making system built based on expert experience and professional knowledge. It has established a quantitative database for building defect assessment and classification through big data, such as interviews and surveys of many expert professors in the architecture department. Thus, by comprehensively analyzing information such as the type, location, and depth of building defects, it helps to evaluate the harm degree of each defect and gives a scientific score.

[0059] Through the database provided by the expert system, each building defect has a clear classification standard. The expert system quantifies the severity and possible consequences of defects based on factors such as the location of the defect (such as load-bearing structure or non-load-bearing structure), type (such as cracks, water seepage, peeling, etc.), depth (such as surface cracks, structural cracks, etc.), combined with historical data and expert opinions. Specifically, the expert system assigns a harm degree score to each defect. This score reflects the impact of the defect on aspects such as the safety, service function, and aesthetics of the building. For example:

[0060] Minor defects: Such as stains or small cracks on the exterior wall surface, with a low harm degree and a low score.

[0061] Medium defects: Such as local water seepage or larger cracks, which may affect the durability and living comfort of the building, with a higher harm degree score.

[0062] Severe defects: Such as structural cracks or water pipe ruptures, with an extremely high harm degree score and may pose a threat to the safety of the building.

[0063] It can be understood that the location also has a great impact on the harm degree score of the defect. For example, the harm degree score of load-bearing structure defects is usually higher. The expert system not only considers the type of the defect (such as crack depth, width) and the specific location (such as the junction of beams and columns, column feet, etc.), but also comprehensively considers the impact that the defect may have on the overall structural stability. Severe defects will affect the load-bearing capacity of the structure and even cause local or overall collapse. For example, cracks on a beam may cause a decrease in the bending capacity of the beam, thus affecting the stability of the entire floor system. The harm degree score of non-load-bearing structure defects is lower, and the repair suggestions usually focus on maintaining the appearance and comfort of the building. Such as water seepage on the exterior wall or peeling of the decorative layer, which may cause water leakage or affect the appearance, but generally will not affect the overall stability of the building. During the detection process, the expert system combines the results of automatic defect identification and, according to the harm degree score of the defect, automatically provides corresponding repair suggestions and treatment priorities for each defect, which helps the maintenance team to prioritize the treatment of those defects with high harm degree and urgent need for repair.

[0064] In a preferred embodiment, the method first scores each detected defect (such as crack depth, water seepage area, etc.), and then compares the scores with the preset scoring criteria in the expert system. For each type of defect, if the defect score reaches a certain threshold, it is considered to need repair and is added to the set of primary defects. Suppose during the inspection of the exterior wall of a certain building, several areas of peeling wall paint are found, and the area of each peeling is 50 cm 2 , according to the preset standard, the defect of peeling wall paint with an area exceeding 30 cm 2 needs to be repaired. Therefore, these areas of peeling wall paint are included in the set of primary defects. In addition, water seepage stains are detected, and the area of each stain is 40 cm 2 , and the locations are relatively concentrated, meeting the repair criteria, so they are also added to the set of primary defects; if a crack with a depth of 3 mm and a length of 30 cm is detected in the beam-column load-bearing structure of the building, according to the scoring standard of the expert system, this defect is also judged as a primary defect and needs to be repaired. Through this step, all defects that need repair (such as peeling wall paint, cracks, water seepage stains, etc.) are screened out to form a set of primary defects.

[0065] S405, generate a set of secondary defects with different repair paths according to the repair methods corresponding to each type of defect in the set of primary defects.

[0066] Specifically, there may be intersections between the types of defects in the set of primary defects. That is to say, the same defect may involve multiple repair methods, so it can appear in multiple sets of secondary defects at the same time. For example, all defects need to be subjected to surface cleaning before repair, which means that almost all defects (such as peeling wall paint, cracks, water seepage stains, etc.) will be classified into a set of secondary defects for surface cleaning. Therefore, it needs to be further subdivided according to the specific repair methods of each defect. For example, peeling wall paint may require surface cleaning and filling repair, while cracks may require surface cleaning and structural reinforcement, and these defects will be classified into different sets of secondary defects according to the repair methods.

[0067] Taking a specific embodiment as an example, since almost all types of defects (including peeling wall paint, water seepage stains, cracks) need to be subjected to surface cleaning first, therefore, all defects (whether it is peeling wall paint or cracks, etc.) are uniformly classified into the set of secondary defects for surface cleaning. And peeling wall paint and water seepage stains need to be subjected to filling repair, so these defects are classified into the set of secondary defects for filling repair. In addition, cracks in the load-bearing structure may require structural reinforcement, so the crack defects will also enter the set of secondary defects for structural reinforcement. In summary, this step will generate multiple sets of secondary defects, and there will be intersections between different defects, reflecting the diversity and complexity of the repair paths.

[0068] S406. Obtain the central position coordinates of each defect in the secondary defect set, and calculate and generate the corresponding repair path distance matrix.

[0069] It can be understood that each defect has a unique central position coordinate (x, y, z) in three-dimensional space. Through three-dimensional reconstruction technology, this method has accurately obtained the coordinate information of each defect. Based on this coordinate information, the system will calculate the repair path distance matrix between the defect points within each secondary defect set.

[0070] Specifically, since the defects in a building are usually not two-dimensional, each defect position will have three-dimensional coordinates (x, y, z). The present invention needs to calculate the distance of each defect to optimize the repair order. In this step, the distance matrix will show which defects are closer and which are farther, and provide a basis for subsequent repair path planning through this matrix.

[0071] Suppose that during the detection process, a certain secondary defect set (such as peeling wall paint) contains the following three defects:

[0072] 1. Defect 1: Coordinates (3, 5, 10)

[0073] 2. Defect 2: Coordinates (6, 8, 10)

[0074] 3. Defect 3: Coordinates (2, 4, 12)

[0075] First, calculate the three-dimensional distances between these defects:

[0076] The distance between Defect 1 and Defect 2 is:

[0077] The distance between Defect 2 and Defect 3 is:

[0078] The distance between Defect 1 and Defect 3 is: Thus, a repair path distance matrix is generated based on these calculations, providing data support for subsequent repair work.

[0079] Finally, execute S407. According to the repair path distance matrix and the second comprehensive evaluation result of the preset expert system, and based on the preset greedy algorithm, generate the repair path corresponding to each defect.

[0080] In this step, according to the generated repair path distance matrix and in combination with the preset greedy algorithm, the repair path will be optimized. The basic idea of the greedy algorithm is to select the defect closest to the current repair point for repair each time, so as to minimize the repair time and path cost.

[0081] For example, the generation of the repair path will be carried out according to the following steps:

[0082] 1. Start the repair from the defect with the closest distance selected from the set of secondary defects cleaned from the surface. Based on the distance matrix in S406, select to repair the defect with the closest distance first.

[0083] 2. After completing the repair of one defect, the system continues to select the next defect with the closest distance until all defects are repaired.

[0084] 3. Each repair method (such as surface cleaning, filling repair, structural reinforcement, etc.) is independently repaired according to its corresponding set of secondary defects.

[0085] Taking the repair process of wall peeling as an example, first select the two wall peeling defects with the closest distance (such as defect 1 and defect 3), perform surface cleaning in sequence, then perform filling repair to fill all the repaired wall defects, and finally perform structural reinforcement to repair the cracks on the load-bearing structure (such as defect 2).

[0086] Through these steps, this method can efficiently complete all repair tasks according to the optimized results of the repair path, reduce the repair time and lower the cost.

[0087] In a preferred embodiment, all the collected image data, analysis results, and defect information can also be stored in the cloud server. The cloud server provides data backup and retrieval functions to ensure that all detection records are available for future query and reference, so as to conduct subsequent trend analysis and prediction. At the same time, it is convenient for users to access the historical detection data through the background management system.

[0088] It can be understood that in a preferred embodiment, the defect repair method further includes an analysis and prediction step, specifically:

[0089] S501, collect the historical repair data and historical environmental data of the target building. The historical repair data includes the above-mentioned image data, analysis results, and defect information, and the historical environmental data includes temperature and humidity data, weather data, etc.

[0090] S501, analyze the historical repair data, associate the defect information corresponding to the same position coordinates, and sort them in chronological order to generate the historical development data corresponding to each defect;

[0091] S502, combine the historical development data of all defects and the historical environmental data and establish an aging model of the target building based on a deep learning algorithm;

[0092] S503. Predict the defect status of the target building at a future time through the aging model, and adjust the current repair path or the current exterior wall repair report for each defect according to the prediction result. For example, when it is predicted that a certain defect will develop rapidly based on the current defect information, defect location, etc., the current repair urgency score result of this defect can be increased to the next level and given priority during the exterior wall repair, further improving the actual effect of the building exterior wall repair.

[0093] In another preferred embodiment, the defect repair method can also generate an exterior wall repair report for the target building by combining big data in the construction field. The exterior wall repair report includes the recommended repair time, repair material information, personnel allocation information, repair cost information, etc. for each defect. It can not only automatically generate a detailed report on the defects, but also analyze based on the actual situation and historical data of the building, and put forward reasonable maintenance suggestions to ensure the safety and long-term maintainability of the building exterior wall.

[0094] It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0095] The embodiment of the present invention also provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the steps of the above-mentioned defect repair method for the building exterior wall.

[0096] Figure 2 It is a schematic structural diagram of the defect repair device for the building exterior wall provided in Embodiment 2. As Figure 2 shown, it includes an image acquisition module 100, a defect recognition module 200, a model reconstruction module 300, and a repair planning module 400.

[0097] The image acquisition module 100 is used to establish an exterior wall surface image set of the target building, and the exterior wall surface image set includes multiple frames of exterior wall surface images.

[0098] The defect recognition module 200 is used to generate defect information of the exterior wall surface image according to a preset defect recognition model, and perform defect marking at the corresponding position of the exterior wall surface image to generate a defect photo set of the target building. The defect information includes defect type, size, and depth.

[0099] The model reconstruction module 300 is used to establish a target three-dimensional model of the target building based on the defect photo set, mark each defect in the target three-dimensional model, and generate the corresponding position coordinates for each defect.

[0100] The repair planning module 400 is used to generate a repair path for each defect according to the defect type, the size, the depth, and the position coordinates.

[0101] The above embodiments provide a defect repair device for building exterior walls, which can effectively improve the efficiency and accuracy of building exterior wall defect detection. It can not only automatically generate a detailed report of the defects, but also analyze according to the actual situation and historical data of the building and predict the future defect development status, and put forward reasonable maintenance suggestions to ensure the safety of the building exterior wall and facilitate the long-term maintenance of the exterior wall.

[0102] In a preferred embodiment, the image acquisition module 100 specifically includes:

[0103] A first acquisition unit, configured to acquire information on key parts of the exterior wall of the target building;

[0104] A path setting unit, configured to generate a flight path of the unmanned aerial vehicle according to the information on the key parts of the exterior wall, where the flight path includes at least a flight control height and a flight control angle corresponding to each key part of the exterior wall;

[0105] A first acquisition unit, configured to control the unmanned aerial vehicle to fly around the exterior wall of the target building according to the flight route, generate a target panoramic video, and perform slicing processing on the target panoramic video at a preset frequency to generate a plurality of frames of exterior wall surface images, where the exterior wall surface images include a natural light image of the exterior wall and a thermal imaging image corresponding to an abnormal temperature area of the exterior wall.

[0106] In a preferred embodiment, the repair planning module 400 specifically includes:

[0107] A first generation unit, configured to generate a corresponding first repair weight according to the position coordinates of each defect;

[0108] A second generation unit, configured to adjust the first repair weight according to the size and depth of the corresponding defect to generate a second repair weight;

[0109] A third generation unit, configured to generate a corresponding first repair urgency score result according to the defect type of each defect and the second repair weight;

[0110] An evaluation unit, configured to screen out a set of first-level defects by integrating the first repair urgency score result and the first comprehensive evaluation result of a preset expert system;

[0111] A fourth generation unit, configured to generate a set of second-level defects with different repair paths according to the repair methods corresponding to each defect type in the set of first-level defects;

[0112] A calculation unit, configured to obtain the central position coordinates of each defect in the secondary defect set, and calculate and generate a corresponding repair path distance matrix;

[0113] A fifth generation unit, configured to generate a repair path corresponding to each defect based on the repair path distance matrix and the second comprehensive evaluation result of the preset expert system, and based on a preset greedy algorithm.

[0114] In a preferred embodiment, the defect repair device for the building exterior wall further includes an analysis and prediction module, specifically including:

[0115] A second acquisition unit, configured to acquire historical repair data and historical environment data of the target building;

[0116] An analysis unit, configured to analyze the historical repair data, associate defect information corresponding to the same position coordinates, and sort them in chronological order to generate historical development data corresponding to each defect;

[0117] A model establishment unit, configured to establish an aging model of the target building by combining the historical development data of all defects and the historical environment data and based on a deep learning algorithm;

[0118] A prediction unit, configured to predict the defect state of the target building at a future moment through the aging model, so as to adjust the current repair path or the current exterior wall repair report of each defect according to the prediction result.

[0119] It should be noted that the foregoing explanation of the embodiments of the defect repair method for the building exterior wall also applies to the defect repair device for the building exterior wall in the above embodiments, and will not be elaborated here.

[0120] An embodiment of the present invention further provides a defect repair device for a building exterior wall, including a computer-readable storage medium and a processor. When the processor executes a computer program on the computer-readable storage medium, the steps of the above-mentioned defect repair method for the building exterior wall are implemented.

[0121] Figure 3 FIG. is a schematic structural diagram of the defect repair device for a building exterior wall provided in Embodiment 3 of the present invention. As Figure 3 shown, the defect repair device 8 for the building exterior wall in this embodiment includes: a processor 80, a readable storage medium 81, and a computer program 82 stored in the readable storage medium 81 and executable on the processor 80. When the processor 80 executes the computer program 82, the steps in the above-mentioned method embodiments are implemented, such as Figure 1 the steps shown. Or, when the processor 80 executes the computer program 82, the functions of each module in the above-mentioned device embodiments are implemented, such as Figure 2 the functions of the modules shown.

[0122] Exemplarily, the computer program 82 may be divided into one or more modules. The one or more modules are stored in the readable storage medium 81 and executed by the processor 80 to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 82 in the building exterior wall defect repair device 8.

[0123] The building exterior wall defect repair device 8 may include, but is not limited to, a processor 80 and a readable storage medium 81. Those skilled in the art can understand that Figure 3 merely examples of the building exterior wall defect repair device 8, which do not constitute a limitation on the building exterior wall defect repair device 8. It may include more or fewer components than those shown in the figure, or combine certain components, or different components. For example, the building exterior wall defect repair device may further include a power management module, an arithmetic processing module, input / output devices, network access devices, a bus, etc.

[0124] The so-called processor 80 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0125] The readable storage medium 81 may be an internal storage unit of the building exterior wall defect repair device 8, such as a hard disk or memory of the building exterior wall defect repair device 8. The readable storage medium 81 may also be an external storage device of the building exterior wall defect repair device 8, such as a plug-in hard disk equipped on the building exterior wall defect repair device 8, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the readable storage medium 81 may also include both an internal storage unit and an external storage device of the building exterior wall defect repair device 8. The readable storage medium 81 is used to store the computer program and other programs and data required by the building exterior wall defect repair device. The readable storage medium 81 may also be used to temporarily store data that has been output or is to be output.

[0126] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0127] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] Those of ordinary skill in the art can realize that the units and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0129] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0132] The present invention is not limited only to what is described in the specification and embodiments. Therefore, for those skilled in the art, additional advantages and modifications can be easily achieved. Therefore, without departing from the spirit and scope of the general concept defined by the claims and their equivalents, the present invention is not limited to specific details, representative devices, and the illustrated examples shown and described here.

Claims

1. A method for repairing defects in a building exterior wall, characterized in that: The following steps are involved: Step 1, establishing an exterior wall surface image set of a target building, wherein the exterior wall surface image set includes multiple frames of exterior wall surface images; Step 2: Generate defect information of each frame of the exterior wall surface image according to a preset defect recognition model, mark the defect at the corresponding position, and generate a defect photo set of the target building, wherein the defect information includes defect type, size and depth; Step 3, establishing a target three-dimensional model of the target building based on the defect photo set, marking each defect in the target three-dimensional model, and generating position coordinates corresponding to each defect; Step 4: Generate a repair path for each defect according to the defect type, the size, the depth and the position coordinates.

2. The defect repair method of the building exterior wall according to claim 1, characterized in that: Generating a repair path for each defect according to the defect type, the size, the depth and the position coordinates specifically includes the following steps: S401, generating a corresponding first repair weight according to the position coordinates of each defect; S402, adjusting the first repair weight according to the size and depth of the corresponding defect to generate a second repair weight; S403, generating a corresponding first repair urgency score result according to the defect type and the second repair weight of each defect; S404, combining the first repair urgency score result and the first comprehensive evaluation result of a preset expert system to select a first-level defect set; S405, generating a secondary defect set of different repair paths according to the repair method corresponding to each defect type in the primary defect set; S406, obtaining the center position coordinates of each defect in the secondary defect set, and calculating and generating a corresponding repair path distance matrix; S407: Generate a repair path corresponding to each defect according to the repair path distance matrix and the second comprehensive evaluation result of the preset expert system and based on a preset greedy algorithm.

3. The defect repair method of the building exterior wall according to claim 1 is characterized in that: The method also includes generating an exterior wall repair report for the target building, wherein the exterior wall repair report includes a recommended repair time, repair material information, staffing information, and repair cost information for each repair area.

4. The defect repair method of a building exterior wall according to any one of claims 1 to 3, characterized in that: Establishing a target three-dimensional model of the target building based on the defect photo set specifically includes the following steps: S301, build a 3D visualization system; S302, generating a point cloud model corresponding to the defect photo set by using an SFM structure measurement algorithm; S303, importing the point cloud model into the 3D visualization system, and generating a target three-dimensional model corresponding to the target building after iterative training.

5. The defect repair method of the building exterior wall according to claim 4, characterized in that: The generating of the position coordinates corresponding to each defect specifically includes the following steps: S304, obtaining a defect photo with defect positions and defect information marked, and converting a two-dimensional defect area of ​​the defect photo into corresponding three-dimensional point cloud data using a binocular grating projection reconstruction method; S305, gridding the three-dimensional point cloud data to generate a contour model of the target building's exterior wall, performing texture mapping on the contour model, and performing occlusion judgment on the point cloud projected to each pixel area during the texture mapping process to remove occluded and incorrectly matched point cloud data; S306, obtaining a target pixel point within the defect contour, and calculating and generating a three-dimensional position coordinate corresponding to the target pixel point by using a four-quadrant neighbor search and a linear interpolation method based on distance weighted average.

6. The defect repair method of the building exterior wall according to claim 4, characterized in that: The acquisition of the exterior wall surface image of the target building is specifically: Obtain information on key parts of the exterior wall of the target building; Generate a flight path of the UAV according to the information of the key parts of the exterior wall, wherein the flight path at least includes a flight control height and a flight control angle corresponding to each key part of the exterior wall; The drone is controlled to fly around the outer wall of the target building according to the flight route to generate a target surround video, and the target surround video is sliced ​​according to a preset frequency to generate a plurality of frames of outer wall surface images, wherein the outer wall surface images include natural light images of the outer wall and thermal imaging images corresponding to the temperature abnormality areas of the outer wall.

7. The defect repair method of the building exterior wall according to claim 4, characterized in that: The preset defect recognition model includes a defect type recognition model, a thermal anomaly detection model and a depth recognition model. The defect type recognition model is used to identify and mark the first defect type and the corresponding defect size of the natural light image through a first preset neural network to generate a first defect photo, wherein the first defect type includes at least one of cracks, peeling, stains, and rust; The thermal anomaly detection model is used to identify and mark a second defect type and a corresponding defect size of the thermal imaging image, wherein the second defect type includes an external wall leakage defect and / or a brick hollowing defect; The depth recognition model is used to identify and mark the depths corresponding to crack defects, spalling defects and rust defects in the first defect photo through a second preset neural network.

8. The defect repair method of the building exterior wall according to claim 4, characterized in that: It also includes analysis and prediction steps, specifically: Collecting historical restoration data and historical environmental data of the target building; Analyze the historical repair data, associate defect information corresponding to the same position coordinates, and sort them in chronological order to generate historical development data corresponding to each defect; Combining the historical development data of all defects and the historical environmental data and establishing an aging model of the target building based on a deep learning algorithm; The defect state of the target building at a future moment is predicted by the aging model, so that the current repair path of each defect or the current exterior wall repair report is adjusted according to the prediction result.

9. A defect repair device for a building exterior wall, based on the defect repair method for a building exterior wall according to any one of claims 1 to 8, characterized in that: It includes image acquisition module, defect recognition module, model reconstruction module and repair planning module. The image acquisition module is used to establish an external wall surface image set of a target building, wherein the external wall surface image set includes multiple frames of external wall surface images; The defect recognition module is used to generate defect information of the exterior wall surface image according to a preset defect recognition model, and mark defects at corresponding positions of the exterior wall surface image to generate a defect photo set of the target building, wherein the defect information includes defect type, size and depth; The model reconstruction module is used to establish a target three-dimensional model of the target building based on the defect photo set, mark each defect in the target three-dimensional model, and generate position coordinates corresponding to each defect; The repair planning module is used to generate a repair path for each defect according to the defect type, the size, the depth and the position coordinates.

10. A defect repair device for a building exterior wall, comprising a computer-readable storage medium and a processor, characterized in that: When the processor executes the computer program on the computer-readable storage medium, the processor implements the steps of the method for repairing defects of the building exterior wall according to any one of claims 1 to 8.

Images