Method for detecting quality of functional layer of building outer wall by using unmanned aerial vehicle

Abstract

This invention discloses a method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles (UAVs), specifically relating to the field of building exterior wall inspection technology. The invention first uses a UAV to acquire infrared images of the building exterior wall cladding, identifying pixels in severely hollow areas and remaining pixels, and calculating the degree of abnormality of the remaining pixels. Clustering is performed using a region growing method based on defect probability. Seed points are selected based on morphological preprocessing, and structural elements of different sizes are comprehensively determined by weighted summation calculation based on UAV jitter frequency and image resolution, filtering noise level by level. A multi-scale pyramid is generated from the original image, and candidate seed points are detected at each level. Candidate seed points are ranked and selected based on their morphological closure and shape regularity. Pixels within the neighborhood of the grown seed points are merged to obtain all connected regions of hollow defects. The quality of the functional layers of the building exterior walls is judged based on the area of ​​the connected regions of hollow defects.

Description

Technical Field

[0001] This invention relates to the field of building exterior wall inspection technology, and more specifically, to a method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles (UAVs). Background Technology

[0002] Because facing bricks are more stain-resistant than paint, they are used to decorate building exteriors. The traditional method for using facing bricks is to directly bond them to the wall surface using adhesive mortar. However, due to environmental factors or construction quality issues, facing bricks often detach from the exterior wall. Over time, under the influence of rain, strong winds, and earthquakes, the detached area gradually increases, eventually causing the facing bricks to peel off and fall from the main structure, leading to safety accidents. Therefore, it is essential to conduct leak detection on building exteriors.

[0003] Currently, the main methods for inspecting the adhesion quality of building exterior wall cladding include visual inspection, hammering, pull-out testing, and infrared technology. Visual inspection relies on the inspector's subjective experience to judge the adhesion quality; the hammering method uses the frequency emitted from the struck surface of the cladding to determine internal defects; the pull-out method uses sampling to inspect for damage to the exterior wall; and infrared technology analyzes the internal condition of an object by detecting the temperature field distribution on its surface.

[0004] In existing technologies, if the seed point is located in a noisy region, it may lead to the spread of erroneous connected components. The selection of the initial seed point directly affects the generation result of the connected components and thus the generation of the final result. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles (UAVs) to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The method for inspecting the quality of functional layers of building exterior walls using drones includes the following steps:

[0008] First, the drone collects infrared images of the building's exterior wall cladding to identify pixels in areas with severe hollowing and the remaining pixels, and calculates the degree of abnormality of the remaining pixels; then, a region growing method based on defect probability is used for clustering.

[0009] Seed point selection based on morphological preprocessing uses structuring elements of different sizes to filter noise step by step and select stable candidate regions. The specific size of the structuring elements is determined by weighted summation calculation based on the drone jitter frequency and image resolution.

[0010] A multi-scale pyramid is generated from the original image, and candidate seed points are detected at each level. Only pixels that are judged as high-probability hollow areas at multiple scales are retained as seed points. The candidate seed points are sorted and selected based on their morphological closure and shape regularity. The optimal seed point is selected.

[0011] The pixels in the neighborhood of the seed point are merged to obtain the connected domains of all hollow defects.

[0012] In a preferred embodiment, the seed point screening based on morphological preprocessing eliminates noise interference through morphological operations. First, an opening operation is performed to remove isolated noise points and small interference areas, while retaining the main hollow areas. Then, a closing operation is performed to fill the holes inside the hollow areas and enhance connectivity.

[0013] In a preferred embodiment, structural elements of different sizes are used to filter noise step by step to select stable candidate regions, which contain candidate seed points; the specific size of the structural elements is determined by weighted summation calculation based on the drone jitter frequency and image resolution.

[0014] In a preferred embodiment, the original image is generated into a multi-scale pyramid, and candidate seed points are detected at each level; only pixels that are determined to be high-probability hollow areas at multiple scales are retained as seed points; and the candidate seed points are sorted and selected based on the morphological closure and shape regularity of each candidate seed point.

[0015] In a preferred embodiment, the morphological closure and shape regularity of each candidate seed point are determined, the priority coefficient of each candidate seed point is calculated by weighted summation, and the seed point is selected according to the priority coefficient value, with the one with the largest value being selected as the seed point.

[0016] In a preferred embodiment, the morphological closure degree is a core indicator for quantifying the effect of the closing operation, used to evaluate the integrity of the target region and the quality of internal structure repair after preprocessing. Its calculation needs to combine the changes in image features before and after the closing operation, and mainly includes the following two key dimensions: area closure rate and hole filling integrity index. Area closure rate: determined by the area of ​​the region after the opening operation and the area of ​​the region after the closing operation; a positive value indicates that the closing operation fills the boundary loss caused by the opening operation, and a negative value indicates the risk of over-corrosion; the hole filling integrity index is determined by the number of holes inside the region before the closing operation and the number of remaining holes after the closing operation.

[0017] In a preferred embodiment, the shape regularity is expressed by converting the geometric features of the shape into comparable numerical values ​​using mathematical indicators.

[0018] In a preferred embodiment, a seed point is determined, and a search is performed in the neighborhood of the selected seed point. Pixels in the neighborhood that belong to the defect probability are retained and merged into a region. This region is then used as a new growth seed point, and a search is performed again in its neighborhood. Pixels in the neighborhood that belong to the defect probability are retained, and the new region is updated to obtain a new seed point region. This process is repeated multiple times until there are no pixels with the defect probability in the neighborhood. At this point, the hollow defect connected region is obtained.

[0019] By selecting marked pixels and using them as a reference, the defect probability of non-marked pixels is calculated, and the connected region of the hollow defect is obtained; then the area of ​​the connected region of the hollow defect is obtained.

[0020] In a preferred embodiment, the area of ​​the connected region of the hollow defect is determined. For hollow defects, the more severe the hollow defect, the larger the area occupied by the hollow, and the worse the quality of the corresponding building exterior wall.

[0021] In a preferred embodiment, the drone is selected as a highly stable industrial-grade drone, equipped with an obstacle avoidance system and an RTK positioning module to ensure hovering accuracy.

[0022] The technical effects and advantages of this invention are as follows:

[0023] This invention first uses a drone to collect infrared images of building exterior wall finishes to identify pixels in areas with severe hollowing and the remaining pixels, and calculates the degree of abnormality of the remaining pixels; it then uses a region growing method based on defect probability for clustering; based on seed point screening using morphological preprocessing, it uses structural elements of different sizes to filter noise step by step to select stable candidate regions. The specific size of the structural elements is determined comprehensively by weighted summation calculation based on the drone jitter frequency and image resolution.

[0024] A multi-scale pyramid is generated from the original image, and candidate seed points are detected at each level. Only pixels that are identified as high-probability hollow areas at multiple scales are retained as seed points. The candidate seed points are sorted and selected based on their morphological closure and shape regularity. The optimal seed point is selected. The selected seed points are more in line with the actual requirements and avoid seed points located in noisy areas, thus avoiding errors in the generation of connected components in subsequent operations due to seed points located in noisy areas. Then, the pixels in the neighborhood of the seed point are merged to obtain all connected components of hollow defects. The quality of the functional layer of the building's exterior wall is judged based on the area of ​​the connected components of hollow defects. Attached Figure Description

[0025] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0026] Figure 1 This is a flowchart illustrating the method for detecting the quality of functional layers of building exterior walls using an unmanned aerial vehicle (UAV) according to the present invention.

[0027] Figure 2 This is a schematic diagram of the region growth algorithm of the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] This invention first uses a drone to collect infrared images of building exterior wall finishes to identify pixels in areas with severe hollowing and the remaining pixels, and calculates the degree of abnormality of the remaining pixels; it then uses a region growing method based on defect probability for clustering; based on seed point screening using morphological preprocessing, it uses structural elements of different sizes to filter noise step by step to select stable candidate regions. The specific size of the structural elements is determined comprehensively by weighted summation calculation based on the drone jitter frequency and image resolution.

[0030] A multi-scale pyramid is generated from the original image, and candidate seed points are detected at each level. Only pixels that are identified as high-probability hollow areas at multiple scales are retained as seed points. The candidate seed points are sorted and selected based on their morphological closure and shape regularity. The optimal seed point is selected. The pixels in the neighborhood of the seed point are merged to obtain all hollow defect connected regions. The quality of the functional layer of the building's exterior wall is judged based on the area of ​​the hollow defect connected regions.

[0031] Example: The present invention provides a method for detecting the quality of functional layers of building exterior walls using a drone, such as... Figure 1 As shown, it includes the following steps:

[0032] First, infrared images of the building's exterior wall cladding are collected using drones to identify pixels in areas with severe hollowing and the remaining pixels, and the degree of abnormality of the remaining pixels is calculated; then, a region growing method based on defect probability is used for clustering.

[0033] Seed point selection based on morphological preprocessing uses structuring elements of different sizes to filter noise step by step and select stable candidate regions. The specific size of the structuring elements is determined by weighted summation calculation based on the drone jitter frequency and image resolution.

[0034] A multi-scale pyramid is generated from the original image, and candidate seed points are detected at each level. Only pixels that are judged as high-probability hollow areas at multiple scales are retained as seed points. The candidate seed points are sorted and selected based on their morphological closure and shape regularity. The optimal seed point is selected.

[0035] The pixels in the neighborhood of the seed point are merged to obtain the connected domains of all hollow defects;

[0036] The stable candidate region contains candidate seed points.

[0037] Specific;

[0038] Infrared images of building exterior facades are captured using a camera carried on a drone. The drone camera is a high-resolution thermal imaging camera (such as the FLIR series) to ensure that the thermal sensitivity (NETD≤50mk) and spatial resolution meet the requirements for building defect detection. At the same time, the infrared sensor is calibrated to eliminate errors caused by ambient temperature fluctuations, and a blackbody calibration tool is used when necessary.

[0039] The selected drone is an industry-grade drone with high stability, equipped with an obstacle avoidance system and RTK positioning module to ensure hovering accuracy; gimbal compatibility is checked to avoid image blurring caused by infrared camera shake.

[0040] Furthermore, before the drone takes off, use 3D modeling software (such as Pix4Dcapture) to preset the flight path and set an image overlap rate of over 70% to facilitate later stitching; keep the drone 5-15 meters away from the wall and shoot vertically or at an angle (30°-60°) to cover the details of the entire facade; the drone must comply with local airspace regulations and avoid no-fly zones; set an automatic return-to-home battery threshold and equip it with a parachute to prevent sudden malfunctions; avoid rain, strong winds, or extreme temperatures (such as midday heat), as excessive temperature differences will interfere with heat conduction characteristics.

[0041] The best time to shoot is within 2 hours before sunrise or after sunset, when the temperature distribution on the building surface is stable and it is easy to capture abnormal areas such as water seepage and hollow areas. If conditions permit, artificial heat sources such as air conditioning units and lighting equipment around the building can be turned off. At the same time, the direct sunlight surface or reflective materials (such as glass curtain walls) should be marked and avoided to reduce reflected thermal noise.

[0042] During the construction and use of building exterior wall finishes, defects such as hollow areas (in mortar finishes) or delamination (in brick finishes) can easily form between the wall structure and the finish. These defects lead to the formation of air layers, thereby reducing the thermal conductivity of the wall. Under solar radiation, the surface temperature of the defective area will differ from that of the intact area, and these defects can be effectively detected using infrared thermal imaging technology.

[0043] Infrared thermal imagers do not directly measure the temperature of objects. Instead, they receive radiation from the object being inspected through infrared detectors. This radiation includes the object's own radiation, reflected radiation from surrounding objects, and atmospheric radiation. Because infrared radiation is absorbed and scattered by certain gases and particles as it propagates through the atmosphere, its energy is attenuated. Therefore, the acquired infrared images often have low contrast, poor signal-to-noise ratio, and poor image quality, which affects the accuracy of defect identification and leads to inaccurate defect location and detection. Therefore, by processing the grayscale information of the image, extracting target pixels, and combining the distribution patterns of these target pixels, the relationships between neighboring pixels, and gradient directions, defect areas can be located more accurately, thus obtaining more precise defect area and severity.

[0044] To obtain target pixels, for building exterior wall cladding, hollow defects cause air layers to form inside the cladding. Since the thermal resistance of air is greater than that of the wall material, heat transfer is reduced at the location of the hollow defect, causing heat to accumulate on the exterior wall surface at the defect location. This results in the exterior wall surface temperature at the hollow location being higher than that of the normal area, meaning the hollow area has a higher brightness in the infrared thermal grayscale image, corresponding to a larger grayscale value. Other normal areas of the cladding layer have similar or identical temperatures due to the same internal medium, resulting in similar or identical grayscale levels. For the cladding layer, most areas are typically normal. When the area of ​​the hollow area exceeds a certain critical point, the cladding layer will peel off from the main structure. Therefore, the corresponding normal area accounts for a large proportion of the infrared thermal grayscale image, meaning the normal area has the most pixels at the corresponding grayscale level.

[0045] The degree of abnormality for each remaining pixel is calculated based on the average grayscale value of each remaining pixel and its corresponding neighboring pixels. Specifically, the greater the difference in grayscale between a remaining pixel and the background, and the greater the grayscale fluctuation in its region, the higher the degree of abnormality for that pixel.

[0046] Pixels with a large difference in grayscale from the background are more likely to be in areas of severe hollowness. Under the influence of rain, strong winds, and earthquakes, the area of ​​hollowness will gradually increase, meaning severe hollowness will spread, eventually turning minor hollowness into severe hollowness, and the normal area at the edge of a minor hollowness will gradually become a minor hollowness, until the hollowness reaches a critical point, causing the finish layer to peel off. Due to the extension of hollowness, the grayscale level of the hollowness area fluctuates, with a fluctuation level comparable to that of normal areas. The degree of abnormality of each remaining pixel is calculated based on the average grayscale value of each remaining pixel and its corresponding neighboring pixels. Specifically, the greater the difference in grayscale between a remaining pixel and the background, and the greater the grayscale fluctuation in the area where it is located, the greater the degree of abnormality of that pixel. A sliding window traversal is performed with each remaining pixel as the center point, and each sliding window contains pixels in severely hollow areas. The probability that each remaining pixel is a pixel in a hollow area is calculated using the anomaly degree of the center point of each sliding window, the gradient direction of the center point, and the gradient direction of the pixels in the window that contain severely hollow areas. To avoid randomness, each sliding window should contain at least two pixels in severely hollow areas.

[0047] Since hollow defects usually exist in patches, a region growing method based on defect probability is used for clustering, specifically as follows: Figure 2 As shown, the steps are as follows:

[0048] The choice of the initial seed point directly affects the generation of connected components; if the seed point is located in a noisy region (such as a local thermal radiation anomaly point), it may lead to the spread of erroneous connected components, affecting the generation of the final result.

[0049] Seed point selection based on morphological preprocessing eliminates noise interference and improves seed point reliability through morphological operations. First, an opening operation (erosion followed by dilation) is performed to remove isolated noise points and small interference areas, preserving the main hollow areas. Then, a closing operation (dilation followed by erosion) fills the voids within the hollow areas, enhancing connectivity.

[0050] Using structuring elements of different sizes, noise is filtered step-by-step to select stable candidate regions, which contain candidate seed points. The specific size of the structuring element is determined by a weighted summation calculation based on the drone's jitter frequency and image resolution; the specific formula is as follows: Where C represents the size of the structural element; PL represents the drone jitter frequency, the larger the drone jitter frequency, the larger the size of the structural element should be, and vice versa; FB represents the image resolution, the larger the image resolution, the smaller the size of the structural element, and vice versa; α and β are the weighting coefficients of the drone jitter frequency and the image resolution, respectively, which are set by the staff.

[0051] The drone's shaking frequency is obtained by the drone's built-in shaking sensor; in strong wind conditions, the size magnification factor is set to 1.5-1.8 times based on the drone's shaking frequency; high-resolution images allow the use of small-sized structural elements; low-resolution images need to be enlarged to avoid the false filtering of effective features.

[0052] Then, seed point selection is performed for multi-scale feature fusion; combining image features at different resolutions avoids misjudgment at a single scale.

[0053] A multi-scale pyramid (e.g., original resolution, 1 / 2, 1 / 4) is generated from the original image, and candidate seed points are detected at each level. Only pixels that are judged as high-probability hollow areas at multiple scales are retained as seed points. The candidate seed points are sorted and selected based on their morphological closure and shape regularity.

[0054] Specifically, the morphological closure and shape regularity of each candidate seed point are determined, and the priority coefficient of each candidate seed point is calculated by weighted summation, as shown in the following formula: Where Y represents the priority coefficient of the candidate seed point; BH represents the morphological closure of the candidate seed point, the larger the morphological closure, the larger the priority coefficient, and vice versa; XZ represents the shape regularity of the candidate seed point, the larger the shape regularity, the larger the priority coefficient, and vice versa; γ and δ represent the weight coefficients of the morphological closure and shape regularity of the candidate seed point, respectively, which are set by the staff as needed. Seed points are selected based on the priority coefficient values, and the one with the largest value is selected as the seed point.

[0055] The morphological closure is a core indicator for quantifying the effect of the closing operation, used to evaluate the integrity of the target region and the quality of internal structure repair after preprocessing. Its calculation requires consideration of image feature changes before and after the closing operation, mainly including the following two key dimensions: area closure rate and hole filling integrity index. Area closure rate: determined by the area of ​​the region after the opening operation and the area of ​​the region after the closing operation; reflects the expansion compensation ability of the closing operation on the target region, a positive value indicates that the closing operation fills the boundary loss caused by the opening operation, and a negative value indicates the risk of over-erosion. The hole filling integrity index is determined by the number of holes inside the region before the closing operation and the number of remaining holes after the closing operation. The shape regularity uses mathematical indicators to transform the geometric features of the shape into comparable numerical values.

[0056] A search is performed within the neighborhood of the selected seed point. Pixels in the neighborhood that belong to the defect probability are retained and merged into a region. This region is then used as the new growth seed point. The search is performed again within its neighborhood. Pixels in the neighborhood that belong to the defect probability are retained. The new region is updated to obtain a new seed point region. This process is repeated multiple times until there are no pixels with the defect probability in the neighborhood. At this point, the hollow defect connected region is obtained.

[0057] By selecting marked pixels and using them as a reference, the defect probability of non-marked pixels is calculated, and the connected region of the hollow defect is obtained; then the area of ​​the connected region of the hollow defect is obtained.

[0058] For hollow defects, the more severe the hollow defect and the larger the area it occupies, the worse the quality of the corresponding building exterior wall. This makes it more likely that the facing bricks will peel off or fall off the main structure, thus causing a safety accident. For hollow defects of the same area, the larger the proportion of severe hollow defects, the worse the corresponding quality.

[0059] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0060] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0061] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0062] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0063] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles (UAVs), characterized in that, Includes the following steps: First, the drone collects infrared images of the building's exterior wall cladding to identify pixels in areas with severe hollowing and the remaining pixels, and then calculates the degree of abnormality of the remaining pixels. Clustering is performed using a region growing method based on defect probability. Seed point selection based on morphological preprocessing uses structuring elements of different sizes to filter noise step by step and select stable candidate regions. The specific size of the structuring elements is determined by weighted summation calculation based on the drone jitter frequency and image resolution. Generate a multi-scale pyramid from the original image and detect candidate seed points at each level; Only pixels that are identified as high-probability hollow areas at multiple scales are retained as seed points; the candidate seed points are sorted and selected based on their morphological closure and shape regularity; the optimal seed point is selected. The pixels in the neighborhood of the seed point are merged to obtain the connected domains of all hollow defects; The method uses structural elements of different sizes to filter noise step by step and select stable candidate regions, which contain candidate seed points; the specific size of the structural elements is determined by weighted summation calculation based on the drone jitter frequency and image resolution. The specific formula is as follows: C = α*PL - β*FB; Where C represents the size of the structuring element; PL represents the drone jitter frequency; FB represents the image resolution; α and β are the weighting coefficients for the drone jitter frequency and the image resolution, respectively. The original image is generated into a multi-scale pyramid, and candidate seed points are detected at each level. Only pixels that are identified as high-probability hollow areas at multiple scales are retained as seed points; Candidate seed points are ranked and selected based on their morphological closure and shape regularity. Determine the morphological closure and shape regularity of each candidate seed point, calculate the priority coefficient of each candidate seed point by weighted summation, select the seed point according to the priority coefficient value, and select the seed point with the largest value as the seed point. The morphological closure is a core indicator for quantifying the effect of the closing operation, used to evaluate the integrity of the target region and the quality of internal structure repair after preprocessing. Its calculation needs to combine the changes in image features before and after the closing operation, and mainly includes the following two key dimensions: area closure rate and hole filling integrity index. Area closure rate: determined by the area of ​​the region after the opening operation and the area of ​​the region after the closing operation; a positive value indicates that the closing operation fills the boundary loss caused by the opening operation, and a negative value indicates the risk of over-corrosion; Hole filling integrity index is determined by the number of holes inside the region before the closing operation and the number of remaining holes after the closing operation.

2. The method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles (UAVs) according to claim 1, characterized in that: The seed point screening based on morphological preprocessing eliminates noise interference through morphological operations. First, an opening operation is performed to remove isolated noise points and small interference areas, while retaining the main hollow areas. Then, a closing operation is performed to fill the holes inside the hollow areas and enhance connectivity.

3. The method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles (UAVs) according to claim 1, characterized in that: The shape regularity is expressed by converting the geometric features of a shape into comparable numerical values ​​through mathematical indicators.

4. The method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles (UAVs) according to claim 1, characterized in that: Determine a seed point, and search within its neighborhood. Pixels in the neighborhood that have a defect probability are retained and merged into a region. This region is then used as the new growth seed point. The search within its neighborhood is repeated, and pixels in the neighborhood that have a defect probability are retained. The new region is updated to obtain a new seed point region. This process is repeated multiple times until no pixels with a defect probability remain in the neighborhood. At this point, the connected component of the hollow defect is obtained. By selecting marked pixels and using them as a reference, the defect probability of non-marked pixels is calculated, and the connected region of the hollow defect is obtained; then the area of ​​the connected region of the hollow defect is obtained.

5. The method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles according to claim 4, characterized in that: Determine the area of ​​the connected region of the hollow defect. For hollow defects, the more severe the hollow defect, the larger the area occupied by the hollow, and the worse the quality of the corresponding building exterior wall.

6. The method for detecting the quality of functional layers of building exterior walls using unmanned aerial vehicles according to claim 1, characterized in that: The drone selected is a highly stable industrial-grade drone, equipped with an obstacle avoidance system and an RTK positioning module to ensure hovering accuracy.

Images