Glass curtain wall intelligent safety monitoring method and system, electronic device and storage medium

Abstract

A glass curtain wall intelligent safety monitoring method and system, electronic equipment and storage medium, relate to the technical field of curtain wall detection. The method comprises: acquiring multi-source image data of the outer facade of the glass curtain wall, the multi-source image data comprising front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall collected at different time periods and from different angles; performing registration fusion and identification analysis on the multi-source image data to obtain crack features, deformation features and temperature distribution features of the surface of the glass curtain wall; establishing an abnormal feature atlas of the glass curtain wall based on the crack features, deformation features and temperature distribution features; performing spatio-temporal evolution analysis on the abnormal feature atlas to determine multi-level risk areas of the glass curtain wall; and generating a monitoring report of the glass curtain wall according to the multi-level risk areas. The technical solution provided by the present application can realize comprehensive monitoring of the glass curtain wall, thereby improving the monitoring accuracy of the glass curtain wall.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of curtain wall detection, and particularly relates to a glass curtain wall intelligent safety monitoring method and system, an electronic device and a storage medium. BACKGROUND

[0002] With the development of modern buildings towards high-rise and large-scale, glass curtain walls are widely used due to their aesthetic, transparent, energy-saving and other advantages. However, due to the long-term exposure of glass curtain walls to outdoor environments, they are affected by various factors such as temperature changes, wind loads, building settlement, etc., and are prone to safety hazards.

[0003] At present, the safety monitoring of glass curtain walls mainly uses fixed monitoring equipment. By installing strain sensors, displacement sensors and other sensors on the surface of the glass curtain wall, the stress and deformation of the glass curtain wall can be monitored in real time. However, this monitoring method has limitations: the installation of fixed monitoring equipment affects the aesthetics of the building, and the number of monitoring points is limited, making it difficult to achieve comprehensive monitoring of the glass curtain wall, resulting in low monitoring accuracy of the glass curtain wall. SUMMARY

[0004] The present application provides a glass curtain wall intelligent safety monitoring method, system, electronic device and storage medium, which can realize comprehensive monitoring of the glass curtain wall, thereby improving the monitoring accuracy of the glass curtain wall.

[0005] In a first aspect, the present application provides a glass curtain wall intelligent safety monitoring method, the method comprising:

[0006] Obtaining multi-source image data of the outer facade of the glass curtain wall, the multi-source image data comprising front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall collected at different time periods and different angles;

[0007] Performing registration fusion and identification analysis on the multi-source image data to obtain crack features, deformation features and temperature distribution features of the surface of the glass curtain wall;

[0008] Establishing an abnormal feature map of the glass curtain wall based on the crack features, deformation features and temperature distribution features;

[0009] Performing spatio-temporal evolution analysis on the abnormal feature map to determine multi-level risk areas of the glass curtain wall;

[0010] Generating a monitoring report of the glass curtain wall according to the multi-level risk areas.

[0011] By adopting the technical scheme, the multi-source image data of the glass curtain wall facade is acquired, the multi-source image data includes front view images, infrared thermal imaging images and ultraviolet spectrum images collected at different time periods and different angles, surface state information of the glass curtain wall can be comprehensively collected, the multi-source image data is registered, fused and analyzed, crack features, deformation features and temperature distribution features of the glass curtain wall surface can be accurately extracted, then abnormal feature atlas of the glass curtain wall is established based on the features, multi-level risk areas are determined through space-time evolution analysis, and finally a monitoring report is generated, so that comprehensive monitoring of the glass curtain wall is realized, fixed monitoring equipment does not need to be installed on the glass curtain wall surface, the influence on the building appearance is avoided, and the problem of limited monitoring points is overcome, so that comprehensive and accurate monitoring of the glass curtain wall is realized.

[0012] In a second aspect of the present application, a glass curtain wall intelligent safety monitoring system is provided, the system comprising:

[0013] an image data acquisition module configured to acquire multi-source image data of a glass curtain wall facade, the multi-source image data comprising front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall collected at different time periods and different angles;

[0014] a feature recognition module configured to register, fuse and analyze the multi-source image data to obtain crack features, deformation features and temperature distribution features of the glass curtain wall surface;

[0015] a feature atlas generation module configured to establish an abnormal feature atlas of the glass curtain wall based on the crack features, deformation features and temperature distribution features;

[0016] a risk area determination module configured to perform space-time evolution analysis on the abnormal feature atlas to determine multi-level risk areas of the glass curtain wall;

[0017] a monitoring report generation module configured to generate a monitoring report of the glass curtain wall according to the multi-level risk areas.

[0018] In a third aspect of the present application, a computer storage medium is provided, the computer storage medium storing a plurality of instructions, the instructions being adapted to be loaded by a processor and to execute the method steps described above.

[0019] In a fourth aspect of the present application, an electronic device is provided, comprising a processor and a memory; wherein the memory stores a computer program, the computer program being adapted to be loaded by the processor and to execute the method steps described above.

[0020] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0021] The application obtains multi-source image data of the outer facade of the glass curtain wall, the multi-source image data includes front view images, infrared thermal imaging images and ultraviolet spectrum images collected at different time periods and different angles, and can comprehensively collect surface state information of the glass curtain wall; the multi-source image data is registered, fused and analyzed, crack features, deformation features and temperature distribution features of the surface of the glass curtain wall can be accurately extracted; then, an abnormal feature atlas is established based on the features, multi-level risk areas are determined through space-time evolution analysis, and a monitoring report is finally generated, so that comprehensive monitoring of the glass curtain wall is realized, fixed monitoring equipment does not need to be installed on the surface of the glass curtain wall, the influence on the building appearance is avoided, and the problem of limited monitoring points is overcome, so that comprehensive and accurate monitoring of the glass curtain wall is realized. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 is a flowchart of a glass curtain wall intelligent safety monitoring method provided by an embodiment of the application;

[0023] Figure 2 is a module schematic diagram of a glass curtain wall intelligent safety monitoring system provided by an embodiment of the application;

[0024] Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the application.

[0025] The reference signs are explained as follows: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0026] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in conjunction with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the application, not all the embodiments.

[0027] In the description of the embodiments of the application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0028] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first", "second", "third", etc. are used only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the technical features indicated. Therefore, the features defined with "first", "second", etc. can be explicitly or implicitly included one or more of the features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0029] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments.

[0030] Please refer to Figure 1 , a flowchart of a glass curtain wall intelligent safety monitoring method is proposed, which can be realized by a computer program, can be realized by a single-chip microcomputer, and can run on a glass curtain wall intelligent safety monitoring system. The computer program can be integrated in a computer device or run as an independent tool application. Specifically, the method includes steps 10 to 50, and the steps are as follows:

[0031] Step 10: Obtain multi-source image data of the glass curtain wall facade, and the multi-source image data includes front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall collected at different time periods and different angles.

[0032] In the embodiments of the present application, the multi-source image data refers to a set of image data obtained by photographing the glass curtain wall facade by a plurality of image acquisition devices carried by a UAV, including front view images, infrared thermal imaging images and ultraviolet spectrum images.

[0033] The front view image refers to the image of the glass curtain wall facade collected by the visible light camera carried by the UAV, which can record the defects such as cracks and damage on the surface of the glass curtain wall.

[0034] The infrared thermal imaging image refers to the temperature distribution image of the glass curtain wall collected by the infrared thermal imager carried by the UAV, which can reflect the temperature field distribution of the glass curtain wall surface and help to find the stress concentration area inside the glass curtain wall.

[0035] The ultraviolet spectrum image refers to the spectral feature image of the glass curtain wall surface collected by the ultraviolet spectrum camera carried by the UAV, which can reflect the structural changes and material performance degradation of the glass curtain wall surface.

[0036] Specifically, the unmanned aerial vehicle is controlled to cruise along a preset flight path outside the facade of the glass curtain wall, and the unmanned aerial vehicle carries a visible light camera, an infrared thermal imager and an ultraviolet spectrum camera to collect multi-source image data of the glass curtain wall. Specifically, under different weather conditions such as sunny and cloudy days, the unmanned aerial vehicle is controlled to take pictures of the glass curtain wall at three angles of vertical, left 30 degrees and right 30 degrees at three time periods of morning, noon and afternoon. Among them, the visible light camera collects front view images of the glass curtain wall to record visible defects such as surface cracks; the infrared thermal imager collects infrared thermal imaging images of the glass curtain wall to detect temperature abnormal areas; and the ultraviolet spectrum camera collects ultraviolet spectrum images of the glass curtain wall to identify material degradation. By collecting multi-source image data at different time periods and different angles, the surface state information of the glass curtain wall can be fully reflected, providing a complete data basis for subsequent analysis.

[0037] On the basis of the above embodiment, as an optional embodiment, the step of acquiring multi-source image data of the facade of the glass curtain wall can further include the following steps:

[0038] Step 101: dividing the glass curtain wall into a plurality of monitoring areas, each monitoring area including an image acquisition reference point.

[0039] Specifically, in this embodiment, first, the design drawings of the glass curtain wall are acquired, and the glass curtain wall is divided into a plurality of 10m x 10m square monitoring areas according to the overall size of the glass curtain wall. Image acquisition reference points are set at the four corners and the center of each monitoring area, and the spatial coordinate information of each reference point is recorded. This division method not only ensures that the size of the monitoring area is suitable for the shooting range of the unmanned aerial vehicle, but also ensures that there is a certain overlap between adjacent areas, which is conducive to subsequent image stitching and analysis. By reasonably dividing the monitoring area and setting the reference points, a spatial reference basis is provided for subsequent flight path planning and image acquisition.

[0040] Step 102: determining a monitoring flight path based on the image acquisition reference points, and controlling the unmanned aerial vehicle to fly according to the monitoring flight path.

[0041] Specifically, the shortest path algorithm is used to connect all the reference points to form an "S" shape return flight path, ensuring that the unmanned aerial vehicle can cover all the monitoring areas. When planning the flight path, the vertical distance between the unmanned aerial vehicle and the curtain wall is set to 5 meters, the flight speed is set to 2 meters per second, and a hovering point is preset at each reference point. At the same time, considering the distribution of obstacles around the building, an obstacle avoidance buffer zone is set in the flight path. By scientifically planning the monitoring flight path, the safety and integrity of the collection process are ensured, and the collection efficiency is improved.

[0042] Step 103: On the monitoring route, obtain the front view images of the glass curtain wall taken by the UAV every preset distance, the infrared thermal imaging images of the glass curtain wall taken every preset period, and the ultraviolet spectrum images of the glass curtain wall taken at different angles, wherein the ultraviolet spectrum images are taken when the ambient light intensity is greater than the light intensity threshold.

[0043] Specifically, based on the collection characteristics and data requirements of different types of images, a differentiated collection strategy is designed. The collection of front view images is based on spatial dimension control, which needs to ensure a certain degree of overlap between images for later splicing; the collection of infrared thermal imaging is based on time dimension control, which needs to consider the dynamic change characteristics of the temperature field; the collection of ultraviolet spectrum images needs to consider the influence of light conditions and shooting angles. In specific implementation, the UAV is controlled to fly according to the preset route, the visible light camera is used to collect front view images at fixed distance intervals, the infrared thermal imager is used to collect thermal imaging images at fixed time intervals, and the ultraviolet spectrum camera is controlled to collect spectrum images at multiple angles when the light conditions are met. During the collection process, the attitude control system of the UAV ensures that the camera maintains the correct shooting angle with the curtain wall surface, and the image anti-shake system ensures the quality of the collected images.

[0044] For example, when the UAV flies according to the monitoring route, the following strategy is used to collect images: front view images of the glass curtain wall taken by the UAV every preset distance, the visible light camera takes a front view image every 2 meters; the infrared thermal imager collects a thermal imaging image every 30 seconds; when the light sensor detects that the ambient light intensity exceeds 1000 lux, the ultraviolet spectrum camera is controlled to take ultraviolet spectrum images at three angles of vertical, left 15 degrees and right 15 degrees.

[0045] Step 104: Integrate the front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall into multi-source image data.

[0046] Specifically, a multi-level data organization method is used to integrate different types of image data. First, a unified data standard is established, and a metadata tag containing time information, spatial information and collection parameters is added to each image. Then, a hierarchical data structure is constructed, and the data is systematically managed according to the monitoring area, image type, collection time, etc. In the data integration process, the association between different types of images is established based on the spatio-temporal characteristics, forming a structured multi-source image data set.

[0047] Step 20: Perform registration fusion and recognition analysis on the multi-source image data to obtain the crack features, deformation features and temperature distribution features of the glass curtain wall surface.

[0048] In the embodiments of the present application, the crack feature refers to various damage conditions appearing on the surface of the glass curtain wall, including cracks, scratches, notches and other surface damages of the glass panel, which can be directly observed and identified through the front view image, and is an important indicator for evaluating the safety state of the glass curtain wall.

[0049] The deformation feature refers to the structural deformation of the glass curtain wall, including the concave-convex deformation, inclination, misplacement of the panel and the deformation of the supporting member, etc., which reflects the overall stress state and structural stability of the glass curtain wall, and can be obtained by analyzing the images taken from multiple angles.

[0050] The temperature distribution feature refers to the temperature field distribution on the surface of the glass curtain wall, including the temperature abnormal area, temperature gradient change and thermal stress concentration area, etc., which can reflect the internal stress state and potential structural hidden danger of the glass curtain wall, and can be quantitatively analyzed through the infrared thermal imaging image.

[0051] Specifically, the SIFT feature point matching algorithm is used to perform spatial registration on the front view image, the infrared thermal imaging image and the ultraviolet spectrum image, and the positional correspondence between the images is established. Then, the deep learning network is used to perform feature extraction and fusion analysis on the registered images: the crack feature in the front view image is identified through the convolutional neural network; the deformation feature of the glass curtain wall is analyzed by reconstructing a three-dimensional model based on the multi-view data after image registration; and the temperature distribution feature is extracted based on the temperature field model established by the infrared thermal imaging image. Through the collaborative analysis of multi-source image data, the surface state of the glass curtain wall is fully characterized.

[0052] Based on the above embodiments, as an optional embodiment, the step of registering, fusing and identifying the multi-source image data to obtain the crack feature, deformation feature and temperature distribution feature on the surface of the glass curtain wall can further include the following steps:

[0053] Step 201: Extract the feature points of the front view image in the multi-source image data, and establish the correspondence between the feature points.

[0054] Specifically, to achieve accurate registration of multi-source image data, stable and reliable feature points need to be extracted from the front view image. The improved SIFT (Scale-Invariant Feature Transform) algorithm is used to extract the feature points from the front view image. This algorithm detects local extreme points in different scale spaces by constructing a Gaussian difference pyramid, and extracts feature points with rotation invariance and scale invariance. For the extracted feature points, the local gradient direction histogram is calculated as the feature descriptor. Then, the nearest neighbor matching algorithm is used to match the feature points in different images, and the correspondence between the feature points is established. To improve the matching accuracy, the RANSAC algorithm is introduced to remove the false matching points, and finally the stable and reliable feature point correspondence is obtained.

[0055] Step 202: Based on the correspondence of feature points, the orthographic image, the infrared thermal imaging image and the ultraviolet spectral image are spatially registered.

[0056] Specifically, based on the established correspondence of feature points, the image spatial registration is realized in a multi-step iterative manner. First, the homography matrix between images is calculated based on the correspondence of feature points, which describes the spatial transformation relationship between different images. Then, the gradient descent method is used to optimize the homography matrix parameters to minimize the registration error. In the registration process, the orthographic image and the infrared thermal imaging image are registered first, and then the registration result is registered with the ultraviolet spectral image to ensure that the three types of images accurately correspond in space. Finally, the image is resampled by the bilinear interpolation method to eliminate the geometric distortion in the registration process.

[0057] Step 203: Perform edge enhancement processing on the registered orthographic image to extract the crack features of the glass curtain wall surface.

[0058] Specifically, the crack feature extraction is performed on the registered orthographic image. First, the adaptive histogram equalization method is used to enhance the image contrast and highlight the crack edge information. Then, an improved Canny operator is designed for edge detection, which improves the detection ability of small cracks through adaptive threshold selection. For the detected edge features, morphological processing method is used to remove noise, and complete crack contour is extracted through connected domain analysis. Finally, based on the geometric features of the crack (such as length, width, direction, etc.), a feature vector is established to represent the crack features of the glass curtain wall surface.

[0059] Step 204: Divide the temperature distribution region of the registered infrared thermal imaging image to obtain the temperature distribution features of the glass curtain wall.

[0060] Specifically, a multi-level temperature analysis method is used to process the infrared thermal imaging image. First, the thermal imaging image is temperature corrected to eliminate the influence of environmental temperature and measurement distance. Then, the K-means clustering algorithm is used to adaptively partition the temperature field, and the temperature distribution is divided into multiple hierarchical regions. On this basis, the temperature statistical features of each region are calculated, including average temperature, temperature gradient and temperature anomaly point distribution, etc. By analyzing the temperature difference and temperature gradient change between adjacent regions, the temperature anomaly region is identified, and finally the temperature distribution feature description of the glass curtain wall is formed.

[0061] Step 205: Perform pixel-level comparison between the registered orthographic image and the pre-set standard glass curtain wall image, and calculate the deformation deviation value. When the deformation deviation value is greater than the pre-set threshold, it is determined as a deformation feature.

[0062] Specifically, the registered front view image is calibrated with a preset standard glass curtain wall image to ensure that the two images correspond accurately in spatial position. Then, a phase correlation method is used to calculate the pixel displacement field between the two images to obtain the deformation deviation value of each pixel point. A deformation threshold based on engineering experience is set, and when the deformation deviation value of a certain region exceeds the preset threshold, the region is marked as a deformation feature region. Finally, the complete range of the deformation region is determined through a region growing algorithm, and the direction and amplitude of the deformation are calculated.

[0063] Step 30: Establishing an abnormal feature atlas of the glass curtain wall based on the crack features, deformation features, and temperature distribution features.

[0064] In the embodiments of the present application, the abnormal feature atlas refers to a feature description model generated in the safety state evaluation process of the glass curtain wall.

[0065] Specifically, a multi-layer neural network is used to construct the abnormal feature atlas. The extracted crack features, deformation features, and temperature distribution features are input into the feature encoding layer for dimension reduction processing to obtain low-dimensional representations of each type of feature. Then, the three types of features are adaptively weighted and fused through an attention mechanism fusion layer to highlight the contribution of key abnormal features. Finally, the decoder network is used to reconstruct the fused features into a structured abnormal feature atlas that contains comprehensive information such as crack distribution, deformation degree, and temperature abnormalities. This feature atlas construction method based on deep learning can automatically discover the relevance between features and improve the accuracy of abnormal state representation.

[0066] Based on the above embodiments, as an optional embodiment, the step of establishing an abnormal feature atlas of the glass curtain wall based on the crack features, deformation features, and temperature distribution features can further include the following steps:

[0067] Step 301: Establishing a crack distribution layer according to the length, width, and orientation of the crack features.

[0068] Specifically, to achieve visual representation of crack distribution, a hierarchical feature mapping method is used to establish the crack distribution layer. The detected crack features are quantified according to geometric properties, including dividing the crack length into three levels: micro (less than 5mm), medium (5-20mm), and large (greater than 20mm); dividing the crack width into three levels: fine (less than 0.1mm), general (0.1-0.5mm), and severe (greater than 0.5mm); and recording the orientation angle of the crack. Then, a vector graphic method is used to draw the crack in the spatial coordinate system, using different line types and color coding to represent the levels and properties of the crack, and finally forming a crack distribution layer representing the spatial distribution characteristics of the crack.

[0069] Step 302: Establish a deformation distribution layer according to the deformation deviation values of the deformation features.

[0070] Specifically, the deformation distribution layer is constructed by establishing a spatial distribution model of the deformation features. The calculated deformation deviation values are normalized, and an interpolation algorithm is used to construct a continuous deformation field on the entire curtain wall surface. Then, based on the size of the deformation deviation values, the deformation degree is divided into three levels: slight deformation (deviation value less than 5mm), moderate deformation (deviation value 5-15mm) and severe deformation (deviation value greater than 15mm). A pseudo-color mapping method is used to represent the deformation degree with different color depths, and contour lines are added to represent the deformation trend, and finally a deformation distribution layer reflecting the spatial distribution of deformation is generated.

[0071] Step 303: Establish a temperature anomaly layer according to the temperature gradient of the temperature distribution feature.

[0072] Specifically, the temperature anomaly layer is established based on temperature gradient analysis, and the spatial gradient of the temperature field is calculated, including the temperature change rate in the horizontal and vertical directions. Then, based on the size of the temperature gradient value, the temperature anomaly degree is divided into three levels: normal area (gradient less than 2℃ / m), attention area (gradient 2-5℃ / m) and warning area (gradient greater than 5℃ / m). The representation method of the heat map is used, and different temperature gradient areas are marked with gradient colors, and isotherm lines are added in the temperature anomaly area to form a temperature anomaly layer representing the temperature distribution feature.

[0073] Step 304: Superimpose and fuse the crack distribution layer, the deformation distribution layer and the temperature anomaly layer, and based on the preset abnormal level division standard, the superimposed and fused layer is marked and labeled, and an abnormal feature map is generated.

[0074] Specifically, a multi-layer feature fusion method is used to generate an abnormal feature map. The three layers are aligned and superimposed in the spatial coordinate system, and a weighted superimposition algorithm is used to determine the weight coefficients of each layer feature. Then, based on the preset abnormal level division standard, the superimposed features are evaluated as normal, mild abnormality, moderate abnormality and severe abnormality. Among them, when the region simultaneously appears cracks and large deformation, it is classified as severe abnormality; when the region appears moderate cracks or deformation, and is accompanied by temperature anomaly, it is classified as moderate abnormality; when the region only appears single mild abnormality feature, it is classified as mild abnormality. Finally, a layered coloring scheme is used to label different level areas, and a legend is added to generate a complete abnormal feature map.

[0075] Step 40: Perform spatio-temporal evolution analysis on the abnormal feature map to determine the multi-level risk areas of the glass curtain wall.

[0076] The multi-level risk region refers to a risk region of different levels of the glass curtain wall divided according to the superposition degree and distribution of each type of abnormal feature in the abnormal feature atlas in the embodiments of the present application.

[0077] Specifically, the time-space sequence analysis method is used to analyze the evolution of the abnormal feature atlas, a time sequence database is established, and the abnormal feature atlas collected at different time points is stored. Then, the feature data at different time points are aligned through a time sequence registration algorithm, and the feature change rate and development trend are calculated. Based on the feature evolution law, a Markov prediction model is used to evaluate the development trend of the abnormal feature, and a risk region is determined in combination with spatial clustering analysis. When there is no obvious abnormal feature in a region, the region is divided into a first-level risk region; when there is a single slight abnormal feature, the region is divided into a second-level risk region; when there are multiple abnormal features and an accelerating development trend, the region is divided into a third-level risk region; and when there are multiple serious abnormal features, the region is divided into a fourth-level risk region.

[0078] Based on the above embodiments, as another optional embodiment, the step of performing time-space evolution analysis on the abnormal feature atlas to determine the multi-level risk region of the glass curtain wall can further include the following steps:

[0079] Step 401: A multi-feature weight matrix is established based on the abnormal feature atlas, and the multi-feature weight matrix includes a crack weight coefficient, a deformation weight coefficient, and a temperature weight coefficient.

[0080] Specifically, the analytic hierarchy process is used to establish the multi-feature weight matrix to quantify the influence degree of different abnormal features on the safety state of the glass curtain wall. First, a judgment matrix of feature factors is constructed, and the importance ratio between features is determined based on engineering experience and expert evaluation. Then, the maximum eigenvalue and the corresponding eigenvector of the judgment matrix are calculated through the eigenvector method, and consistency check is performed. For example, the crack weight coefficient is finally obtained as 0.4 (because it directly reflects the structural damage), the deformation weight coefficient is 0.35 (because it represents the overall stability), and the temperature weight coefficient is 0.25 (because it reflects the potential risk).

[0081] Step 402: The abnormal feature atlas is divided into grids, and the abnormal feature comprehensive score of each grid unit is calculated, which is determined by the sum of the product of the crack feature, the deformation feature, and the temperature distribution feature and the corresponding weight coefficient.

[0082] Specifically, the abnormal feature map is finely divided into grids and scored, such as dividing the glass curtain wall into uniform grid units according to the size of 1 m x 1 m, and each grid unit contains complete feature information. Then, each feature is normalized: the crack feature is valued 0-1 according to the severity of length and width; the deformation feature is valued 0-1 according to the deviation value; and the temperature distribution feature is valued 0-1 according to the temperature gradient. Finally, the normalized feature value is multiplied by the corresponding weight coefficient and summed to obtain the abnormal feature comprehensive score of each grid unit. This grid scoring method realizes the quantitative expression of the abnormal state.

[0083] Step 403: Determine the multi-level risk area of the glass curtain wall according to the abnormal feature comprehensive score.

[0084] Specifically, in order to accurately identify the areas with similar abnormal features in the glass curtain wall, spatial statistics and clustering analysis methods are used to process the abnormal feature data. First, based on the Kriging interpolation method, a spatial distribution function of the abnormal feature comprehensive score is constructed, which is expressed as F(x, y) = ∑λiZ(xi, yi), where (x, y) is the coordinate of the point to be estimated, λi is the weight coefficient, and Z(xi, yi) is the abnormal feature comprehensive score of the known grid unit. Through this function, the abnormal feature comprehensive score value of any position can be estimated, realizing the continuous spatial distribution expression of the score. Then, the abnormal feature correlation between grid units is calculated, and the Moran's I index is used to evaluate the spatial correlation of the score values of adjacent grid units. For any two grid units i and j, the correlation formula is Rij = (Zi-Z̄)(Zj-Z̄) / σ², where Zi and Zj are the abnormal feature comprehensive scores of the corresponding grid units, Z̄ is the average value, and σ² is the variance. When the correlation is greater than a certain threshold (such as 0.7), it is considered that the two grid units have significant feature correlation.

[0085] Next, the DBSCAN density clustering algorithm is used to analyze the clustering of grid units. The algorithm takes the abnormal feature correlation as the distance measure, and the grid units that are spatially adjacent and have similar score features are aggregated into a region set. Specifically, set the minimum sample size MinPts = 4 and the neighborhood radius ε = 0.3, and through iterative search, all density-reachable grid units are classified into the same class, and finally a plurality of region sets with similar abnormal features are obtained. Finally, the average abnormal feature comprehensive score of each region set is calculated, and the risk level is divided based on the score interval: the region set with a score less than 0.3 is divided into a first-level risk area, the region set with a score between 0.3 and 0.6 is divided into a second-level risk area, the region set with a score between 0.6 and 0.8 is divided into a third-level risk area, and the region set with a score greater than 0.8 is divided into a fourth-level risk area.

[0086] Step 50: Generate a monitoring report of the glass curtain wall according to the multi-level risk area.

[0087] Specifically, the distribution of the multi-level risk area is drawn into a risk heat map, and the first to fourth level risk areas are marked with different colors. Then, the feature data of each risk area is extracted, including the size parameters of the crack feature, the deviation value of the deformation feature, and the gradient value of the temperature distribution feature, to generate a quantitative index curve graph. Finally, based on the evaluation results of the risk level, a monitoring report containing a risk distribution map, an abnormal feature statistical table, and a processing suggestion is automatically generated, wherein the specific performance and development trend of the abnormal feature are described for the third and fourth level risk areas, and the corresponding maintenance suggestions are given. This visual report form directly shows the safety state of the glass curtain wall.

[0088] On the basis of the above-mentioned embodiments, as another optional embodiment, the step of generating a monitoring report of the glass curtain wall according to the multi-level risk area can further include the following steps:

[0089] Step 501: Calculate the feature combination strength of each risk area, which is the superposition value of the crack feature, the deformation feature, and the temperature distribution feature.

[0090] Specifically, for each risk area, the weighted fusion method is used to calculate the feature combination strength. First, standardize each feature: the crack feature value Fc (0-1) is obtained by calculating the ratio of the crack length to the standard length, the deformation feature value Fd (0-1) is obtained by calculating the ratio of the actual displacement to the allowable displacement, and the temperature feature value Ft (0-1) is obtained by calculating the ratio of the temperature difference to the allowable temperature difference. Then, considering the influence degree of each feature on safety, set the weight coefficients: crack feature weight Wc = 0.4, deformation feature weight Wd = 0.35, and temperature feature weight Wt = 0.25. Finally, the feature combination strength S is obtained by weighted summation: S = Fc×Wc + Fd×Wd + Ft×Wt. This calculation method not only ensures the reasonable contribution of each feature, but also realizes the effective fusion of multi-dimensional features.

[0091] Step 502: Determine the risk state coefficient of each risk area based on the level and feature combination strength of each risk area.

[0092] Specifically, a two-factor risk state evaluation model is constructed based on the risk level and the feature combination strength. First, the basic coefficient a is determined according to the risk area level: a = 0.2 for a first-level risk area, a = 0.4 for a second-level risk area, a = 0.6 for a third-level risk area, and a = 0.8 for a fourth-level risk area. Then, the adjustment factor b of the feature combination strength is introduced, and the risk state coefficient is correspondingly improved when the feature combination strength S exceeds the warning value. The specific calculation formula is: risk state coefficient R = a x (1 + b x S), wherein b takes a value in the range of 0.1-0.5 and increases with the increase of the feature combination strength. When S≤0.3, b = 0.1; when 0.3<S≤0.6, b = 0.3; and when S>0.6, b = 0.5.

[0093] Step 503: generating a monitoring report containing the risk state coefficients of each risk area and the corresponding warning information.

[0094] Specifically, the embodiments of the present application adopt intelligent monitoring reports, and design hierarchical report templates including three parts of general situation, detailed analysis and warning suggestion. In the general situation, a risk area distribution map is generated, and different colors are used to identify different levels of risk areas; in the detailed analysis part, the risk state coefficients of each risk area and their constituent elements are listed, including the basic coefficient, the feature combination strength and the adjustment factor; in the warning suggestion part, the warning levels are set according to the risk state coefficients: R<0.3 is the normal state, showing a green prompt; 0.3≤R<0.5 is the attention state, showing a yellow prompt; 0.5≤R<0.7 is the warning state, showing an orange warning; and R≥0.7 is the danger state, showing a red warning. At the same time, the system automatically generates targeted processing suggestions such as "suggestion for regular inspection", "need to strengthen monitoring", "immediate repair" and the like.

[0095] See Figure 2 A module schematic diagram of a glass curtain wall intelligent safety monitoring system provided by the embodiments of the present application is shown in the figure, wherein the system comprises:

[0096] An image data acquisition module is configured to acquire multi-source image data of the outer facade of the glass curtain wall, wherein the multi-source image data comprises front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall collected at different time periods and from different angles;

[0097] A feature recognition module is configured to perform registration fusion and recognition analysis on the multi-source image data to obtain crack features, deformation features and temperature distribution features on the surface of the glass curtain wall;

[0098] A feature map generation module is configured to establish an abnormal feature map of the glass curtain wall based on the crack features, deformation features and temperature distribution features;

[0099] a risk area determination module configured to perform spatiotemporal evolution analysis on the abnormal feature atlas to determine multi-level risk areas of the glass curtain wall;

[0100] a monitoring report generation module configured to generate a monitoring report of the glass curtain wall according to the multi-level risk areas.

[0101] Optionally, the image data acquisition module is further configured to divide the glass curtain wall into a plurality of monitoring areas, and each monitoring area includes an image acquisition reference point;

[0102] determine a monitoring flight path based on each image acquisition reference point, and control the UAV to fly according to the monitoring flight path;

[0103] on the monitoring flight path, acquire the front view image of the glass curtain wall taken by the UAV at every preset distance, the infrared thermal imaging image of the glass curtain wall taken at every preset period, and the ultraviolet spectrum image of the glass curtain wall taken at different angles, wherein the ultraviolet spectrum image is taken when the ambient light intensity is greater than a light intensity threshold;

[0104] integrate the front view image, the infrared thermal imaging image, and the ultraviolet spectrum image of the glass curtain wall into multi-source image data.

[0105] Optionally, the feature recognition module is further configured to extract feature points of the front view image in the multi-source image data, and establish a corresponding relationship of the feature points;

[0106] based on the corresponding relationship of the feature points, perform spatial registration on the front view image, the infrared thermal imaging image, and the ultraviolet spectrum image;

[0107] perform edge enhancement processing on the registered front view image to extract crack features on the surface of the glass curtain wall;

[0108] perform temperature distribution area division on the registered infrared thermal imaging image to obtain temperature distribution features of the glass curtain wall;

[0109] perform pixel-level comparison between the registered front view image and a preset standard glass curtain wall image, and calculate a deformation deviation value, and determine a deformation feature when the deformation deviation value is greater than a preset threshold.

[0110] Optionally, the feature atlas generation module is further configured to establish a crack distribution layer according to the length, width, and direction of the crack features;

[0111] establish a deformation distribution layer according to the deformation deviation value of the deformation feature;

[0112] establish a temperature anomaly layer according to the temperature gradient of the temperature distribution features;

[0113] The crack distribution layer, the deformation distribution layer and the temperature anomaly layer are superimposed and fused, and based on a preset anomaly level division standard, the superimposed and fused layer is graded and labeled to generate an anomaly feature atlas.

[0114] Optionally, the risk area determination module is further configured to establish a multi-feature weight matrix based on the anomaly feature atlas, the multi-feature weight matrix including a crack weight coefficient, a deformation weight coefficient and a temperature weight coefficient.

[0115] The anomaly feature atlas is divided into grids, and an anomaly feature comprehensive score of each grid unit is calculated, the anomaly feature comprehensive score being determined by a sum of products of crack features, deformation features and temperature distribution features and corresponding weight coefficients.

[0116] According to the anomaly feature comprehensive score, a multi-level risk area of the glass curtain wall is determined.

[0117] Optionally, the risk area determination module is further configured to construct a spatial distribution function of the anomaly feature comprehensive score, and calculate an anomaly feature correlation degree between grid units based on the spatial distribution function.

[0118] According to the anomaly feature correlation degree, a clustering analysis is performed on the grid units to obtain a region set with similar anomaly features.

[0119] According to the anomaly feature comprehensive score of the region set, the glass curtain wall is divided into a multi-level risk area.

[0120] Optionally, the monitoring report generation module is further configured to calculate a feature combination strength of each risk area, the feature combination strength being a superimposed numerical value of crack features, deformation features and temperature distribution features.

[0121] Based on the level of each risk area and the feature combination strength, a risk state coefficient of each risk area is determined.

[0122] A monitoring report containing the risk state coefficient of each risk area and corresponding early warning information is generated.

[0123] It should be noted that: the system provided in the above embodiments, in realizing its functions, only takes the division of the above functional modules as an example, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0124] The embodiment of the application further provides a computer storage medium, which can store a plurality of instructions, the instructions being suitable for being loaded by a processor and performing the glass curtain wall intelligent safety monitoring method of the above embodiment, and the specific execution process can be referred to the specific description of the above embodiment, which will not be repeated here.

[0125] Please refer to Figure 3 The application further discloses an electronic device. Figure 3 is a structural schematic diagram of an electronic device disclosed by the embodiment of the application. The electronic device 300 can include at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0126] The communication bus 302 is configured to realize the connection and communication between the components.

[0127] The user interface 303 can include a display screen (Display) and a camera (Camera), and the optional user interface 303 can further include a standard wired interface and a wireless interface.

[0128] The network interface 304 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0129] The processor 301 can include one or more processing cores. The processor 301 connects various parts in the server through various interfaces and lines, executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be realized in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 301 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU is mainly used to process an operating system, a user interface, and an application program; the GPU is used to render and draw the content to be displayed on the display screen; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be realized by a separate chip.

[0130] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also optionally be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , as a computer storage medium, the memory 305 may include an operating system, a network communication module, a user interface module, and an application program of a glass curtain wall intelligent safety monitoring method.

[0131] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call an application program for storing a glass curtain wall intelligent safety monitoring method in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited to the described order of actions, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0132] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0133] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments is merely illustrative, and the division of units can be changed according to actual conditions, such as a combination or integration of some units, or a deletion of some features, or an addition of some features. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0135] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0136] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable memory. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory includes: U disk, mobile hard disk, magnetic disk or optical disk, and various media that can store program codes.

[0137] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practicing the true principles of the present disclosure.

[0138] The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not described in the present disclosure. The specification and examples are only considered as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for intelligent safety monitoring of a glass curtain wall, characterized in that, The method comprises: Obtaining multi-source image data of the glass curtain wall facade, the multi-source image data comprising front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall collected at different time periods and different angles; Performing registration fusion and identification analysis on the multi-source image data to obtain crack features, deformation features and temperature distribution features of the glass curtain wall surface; Establishing an abnormal feature atlas of the glass curtain wall based on the crack features, deformation features and temperature distribution features; Performing spatio-temporal evolution analysis on the abnormal feature atlas to determine multi-level risk areas of the glass curtain wall; Generating a monitoring report of the glass curtain wall according to the multi-level risk areas; The spatio-temporal evolution analysis on the abnormal feature atlas to determine the multi-level risk areas of the glass curtain wall comprises: Establishing a multi-feature weight matrix based on the abnormal feature atlas, the multi-feature weight matrix comprising crack weight coefficients, deformation weight coefficients and temperature weight coefficients; Dividing the abnormal feature atlas into grids and calculating abnormal feature comprehensive scores of each grid unit, the abnormal feature comprehensive score being determined by the sum of the products of the crack features, deformation features and temperature distribution features and the corresponding weight coefficients; Determining the multi-level risk areas of the glass curtain wall according to the abnormal feature comprehensive scores; The determination of the multi-level risk areas of the glass curtain wall according to the abnormal feature comprehensive scores comprises: Constructing a spatial distribution function of the abnormal feature comprehensive scores and calculating abnormal feature correlation degrees between grid units based on the spatial distribution function; Performing cluster analysis on the grid units according to the abnormal feature correlation degrees to obtain a region set with similar abnormal features; Dividing the glass curtain wall into multi-level risk areas according to the abnormal feature comprehensive scores of the region set. 2.The intelligent safety monitoring method for glass curtain wall according to claim 1, characterized in that, The obtaining of the multi-source image data of the glass curtain wall facade comprises: Dividing the glass curtain wall into a plurality of monitoring areas, each monitoring area comprising image collection reference points; Determining monitoring flight lines based on the image collection reference points and controlling a UAV to fly according to the monitoring flight lines; On the monitoring flight lines, obtaining front view images of the glass curtain wall taken by the UAV at every preset distance, infrared thermal imaging images of the glass curtain wall taken by the UAV at every preset period and ultraviolet spectrum images of the glass curtain wall taken at different angles, wherein the ultraviolet spectrum images are taken when the ambient light intensity is greater than a light intensity threshold; Integrating the front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall into multi-source image data. 3.The intelligent safety monitoring method for glass curtain wall according to claim 1, characterized in that, The registration fusion and identification analysis on the multi-source image data to obtain the crack features, deformation features and temperature distribution features of the glass curtain wall surface comprises: Extracting feature points of the front view images in the multi-source image data and establishing a feature point correspondence relationship; Performing spatial registration on the front view images, infrared thermal imaging images and ultraviolet spectrum images based on the feature point correspondence relationship; Performing edge enhancement processing on the registered front view images to extract the crack features of the glass curtain wall surface; The registered infrared thermal imaging image is subjected to temperature distribution region division, to obtain a temperature distribution characteristic of the glass curtain wall; The registered front view image is subjected to pixel-level comparison with a preset standard glass curtain wall image, and a deformation deviation value is calculated, and when the deformation deviation value is greater than a preset threshold value, the deformation characteristic is determined. 4.The intelligent safety monitoring method for glass curtain wall according to claim 1, characterized in that, The abnormal characteristic atlas of the glass curtain wall is established based on the crack characteristic, the deformation characteristic and the temperature distribution characteristic, including: A crack distribution layer is established according to the length, width and direction of the crack characteristic; A deformation distribution layer is established according to the deformation deviation value of the deformation characteristic; A temperature anomaly layer is established according to the temperature gradient of the temperature distribution characteristic; The crack distribution layer, the deformation distribution layer and the temperature anomaly layer are superimposed and fused, and the superimposed and fused layer is subjected to hierarchical labeling based on a preset abnormal level division standard, to generate the abnormal characteristic atlas. 5.The intelligent safety monitoring method for glass curtain wall according to claim 1, characterized in that, The monitoring report of the glass curtain wall is generated according to the multi-level The monitoring report of the glass curtain wall is generated according to the multi-level The monitoring report of the glass curtain wall is generated according to the multi-level The system for implementing the intelligent safety monitoring method of the glass curtain wall according to claim 1, including: An image data acquisition module for acquiring multi-source image data of the outer facade of the glass curtain wall, the multi-source image data including front view images, infrared thermal imaging images and ultraviolet spectrum images of the glass curtain wall collected at different time periods and from different angles; 6. A glass curtain wall intelligent safety monitoring system, characterized in that, A feature recognition module for performing registration fusion and recognition analysis on the multi-source image data, to obtain crack characteristics, deformation characteristics and temperature distribution characteristics of the surface of the glass curtain wall; A feature atlas generation module for establishing an abnormal characteristic atlas of the glass curtain wall based on the crack characteristics, the deformation characteristics and the temperature distribution characteristics; A risk region determination module for performing spatio-temporal evolution analysis on the abnormal characteristic atlas, to determine multi-level risk regions of the glass curtain wall; A monitoring report generation module for generating a monitoring report of the glass curtain wall according to the multi-level risk regions. A computer readable storage medium stores a plurality of instructions, the instructions being suitable for being loaded and executed by a processor to implement the method according to any one of claims 1-5. An electronic device including a processor, a memory, a user interface and a network interface, the memory being used to store instructions, the user interface and the network interface being used for communication, and the processor being used to execute the instructions stored in the memory, so that the electronic device implements the method according to any one of claims 1-5.

7. A computer readable storage medium characterized in that, ​ 8. An electronic device, comprising: ​

Images