Construction displacement monitoring method and device applied to high-altitude cantilever component

Abstract

The embodiment of the invention discloses a construction displacement monitoring method and device applied to a high-altitude cantilever component. A specific embodiment of the method comprises the following steps: acquiring a real-time image group in response to a real-time vibration signal representing that ground vibration is greater than preset vibration intensity or an image acquisition time point is reached; performing mark plate identification on each real-time image in the real-time image group to obtain a mark plate information set; in response to the fact that at least a target number of marking plate information meeting the screening condition exists in the marking plate information set, a component movement amount set is determined; in response to the existence of the camera offset, performing offset compensation on the component movement amount in the component movement amount group according to the camera offset amount; and in response to the compensated component movement amount greater than the early warning threshold value in the compensated component movement amount group, initiating component displacement early warning. According to the embodiment, automatic and effective displacement monitoring of the high-altitude cantilever component is realized.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the fields of computer technology and engineering construction, and particularly to a construction displacement monitoring method and device applied to high-altitude cantilevered components. Background Art

[0002] High-altitude cantilevered structures are those that extend from the main structure of a high-rise building (for example, a cantilevered porch). These structures are often stabilized by applying tension or weight. When subjected to external forces that disrupt their stability, cantilevered structures may experience displacement, impacting structural stability and building safety. Currently, displacement monitoring is typically performed using methods such as total stations.

[0003] However, when the above method is adopted, the following technical problems often occur:

[0004] Since the total station needs to be equipped with corresponding reflecting prisms, and high-altitude cantilevered components are often located in cantilevered positions at high altitudes, it is extremely difficult to monitor using the total station, making it impossible to effectively monitor the displacement changes of high-altitude cantilevered components.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure propose a construction displacement monitoring method and device for high-altitude cantilevered components to solve the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a construction displacement monitoring method for high-altitude cantilevered components, the method comprising: in response to a real-time vibration signal indicating that ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, acquiring a real-time image group, wherein the real-time vibration signal is acquired by a vibration sensor, the image acquisition time point is controlled by a preset image acquisition cycle, and the real-time images in the real-time image group are acquired by a first camera and a second camera, the first camera and the second camera are respectively directed to different image acquisition areas on the bottom surface of the high-altitude cantilevered component, and a matrix marker plate is fixedly arranged in each image acquisition area; performing marker plate recognition on each real-time image in the above-mentioned real-time image group to obtain a marker plate information set, wherein the marker plate The marking plate information includes: marking plate identification, marking plate position and marking plate effective area; in response to the presence of at least a target number of marking plate information meeting the screening conditions in the above marking plate information set, a component movement amount group is determined, wherein the above screening conditions are: the ratio of the marking plate effective area included in the marking plate information to the preset marking plate area is greater than the preset area ratio and there is a position offset between the marking plate position included in the marking plate information and the corresponding initial marking plate position; in response to the existence of a camera offset, the component movement amount in the above component movement amount group is offset compensated according to the camera offset to obtain a compensated component movement amount group; in response to the presence of a compensated component movement amount greater than a warning threshold in the above compensated component movement amount group, a component displacement warning is initiated.

[0009] In a second aspect, some embodiments of the present disclosure provide a construction displacement monitoring system, which is applied to the above-mentioned method in the first aspect, and is characterized in that it includes: a vibration sensor array, wherein the vibration sensors in the above-mentioned vibration sensor array are arranged in a surrounding manner around the high-altitude cantilevered component; a first camera and a corresponding matrix marker plate, wherein the above-mentioned first camera faces the corresponding matrix marker plate; a second camera and a corresponding matrix marker plate, wherein the matrix marker plate is fixed to the bottom surface of the high-altitude cantilevered component, wherein the above-mentioned first camera faces the corresponding matrix marker plate, and the first camera and the second camera are fixed on a fixed platform at a preset angle, and the fixed platform is arranged below the high-altitude cantilevered component; a first matrix ranging sensor, wherein the relative position between the above-mentioned first matrix ranging sensor and the above-mentioned first camera is fixed; a second matrix ranging sensor, wherein the relative position between the above-mentioned second matrix ranging sensor and the above-mentioned second camera is fixed; a data processing component, wherein the data processing component is used to perform data processing and analysis on the signals and images collected by the sensors and cameras.

[0010] In a third aspect, some embodiments of the present disclosure provide a construction displacement monitoring device for high-altitude cantilevered components, the device comprising: an acquisition unit, configured to acquire a real-time image group in response to a real-time vibration signal indicating that ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, wherein the real-time vibration signal is acquired by a vibration sensor, the image acquisition time point is controlled by a preset image acquisition cycle, and the real-time images in the real-time image group are acquired by a first camera and a second camera, the first camera and the second camera respectively face different image acquisition areas on the bottom surface of the high-altitude cantilevered component, and a matrix marker plate is fixedly arranged in each image acquisition area; a marker plate recognition unit, configured to perform marker plate recognition on each real-time image in the above-mentioned real-time image group to obtain a marker plate information set, wherein the marker plate information It includes: a marker plate identification, a marker plate position and a marker plate effective area; a determination unit is configured to determine a component movement amount group in response to the presence of at least a target number of marker plate information that meet the screening conditions in the above-mentioned marker plate information set, wherein the above-mentioned screening conditions are: the ratio of the marker plate effective area included in the marker plate information to the preset marker plate area is greater than the preset area ratio and there is a position offset between the marker plate position included in the marker plate information and the corresponding initial marker plate position; an offset compensation unit is configured to, in response to the existence of a camera offset, perform offset compensation on the component movement amount in the above-mentioned component movement amount group according to the camera offset to obtain a compensated component movement amount group; an early warning unit is configured to initiate a component displacement early warning in response to the presence of a compensated component movement amount greater than an early warning threshold in the above-mentioned compensated component movement amount group.

[0011] In a fourth aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0012] In a fifth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation of the first aspect above is implemented.

[0013] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the construction displacement monitoring method applied to high-altitude cantilevered components in some embodiments of the present disclosure, effective and accurate displacement change monitoring of high-altitude cantilevered components is achieved. Specifically, the reason for the inability to effectively monitor the displacement change of high-altitude cantilevered components is that since the total station requires the deployment of corresponding reflective prisms, and the high-altitude cantilevered components are often located in a cantilevered position at high altitude, the monitoring method using the total station is extremely difficult, and thus the displacement change of the high-altitude cantilevered components cannot be effectively monitored. Based on this, the construction displacement monitoring method applied to high-altitude cantilevered components in some embodiments of the present disclosure first collects a real-time image group in response to a real-time vibration signal indicating that the ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, wherein the real-time vibration signal is collected by a vibration sensor, the image acquisition time point is controlled by a preset image acquisition cycle, and the real-time images in the real-time image group are collected by a first camera and a second camera, the first camera and the second camera respectively facing different image acquisition areas on the bottom surface of the high-altitude cantilevered component, and a matrix marker plate is fixedly set in each image acquisition area. In practice, the use of cameras to monitor changes in cantilevered components significantly reduces real-time costs compared to methods such as total stations. Considering that component displacement changes are often subtle and occur over a long time span, real-time camera acquisition will generate a large number of invalid images, leading to meaningless data processing and thus consuming computing resources. Therefore, the present disclosure uses ground vibration intensity and image acquisition cycle to trigger the control of the camera for image acquisition. This method can significantly reduce the number of redundant images. Secondly, each real-time image in the above-mentioned real-time image group is subjected to marker plate recognition to obtain a marker plate information set, wherein the marker plate information includes: marker plate identification, marker plate position, and marker plate effective area. In practice, considering that components often have a certain height above the ground and component displacement changes are often subtle, the method of only capturing images of the component bottom surface and directly performing image analysis is not effective due to the lack of obvious change characteristics. Therefore, the present disclosure adopts a matrix marker plate and determines displacement changes through marker plate recognition. Next, in response to the presence of at least a target number of marker plate information items in the marker plate information set that meet a screening condition, a component movement amount group is determined, wherein the screening condition is that the ratio of the effective marker plate area included in the marker plate information to a preset marker plate area is greater than a preset area ratio, and there is a positional offset between the marker plate position included in the marker plate information and the corresponding initial marker plate position. In practice, due to the large distance between the camera and the component, environmental factors (e.g., weather) can affect image acquisition quality. Therefore, to ensure the validity of the determined displacement change, the screening condition and the target number are used to determine whether the component movement amount can be determined.Furthermore, in response to the presence of camera offset, the component movement in the above-mentioned component movement amount group is offset compensated according to the camera offset to obtain a compensated component movement amount group. In practice, although the camera can be fixed by a fixed platform, the vibrations existing in the construction environment (such as the vibrations caused by the movement of large engineering vehicles) will be transmitted to the camera through the ground. As the camera offset changes over time, it will accumulate and form a camera offset error that affects the component movement amount. Therefore, when there is a camera offset, it is necessary to compensate for the component movement amount according to the camera offset. Finally, in response to the presence of a compensated component movement amount greater than the warning threshold in the above-mentioned compensated component movement amount group, a component displacement warning is initiated. In summary, in this way, automated and effective displacement monitoring of high-altitude cantilevered components is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0015] Figure 1 is a flow chart of some embodiments of the construction displacement monitoring method applied to high-altitude cantilevered components according to the present disclosure;

[0016] Figure 2 It is a schematic diagram of the positional relationship between the high-altitude cantilevered components and the vibration sensor array;

[0017] Figure 3 Schematic diagram of the positional relationship between the first camera, the second camera, the image acquisition area, and the high-altitude cantilevered component;

[0018] Figure 4 It is a schematic diagram of the positional relationship between the matrix marker plate and the image acquisition area;

[0019] Figure 5 This is a schematic diagram of the scenario when the matrix marker plate deviates with the high-altitude cantilever component;

[0020] Figure 6 This is a schematic diagram of the system architecture of the construction displacement monitoring system;

[0021] Figure 7 1 is a schematic structural diagram of some embodiments of a construction displacement monitoring device applied to a high-altitude cantilevered component according to the present disclosure;

[0022] Figure 8 It is a structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0023] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0024] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0025] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0026] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0028] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0029] refer to Figure 1 , shows a process 100 of some embodiments of the construction displacement monitoring method applied to high-altitude cantilevered components according to the present disclosure. The construction displacement monitoring method applied to high-altitude cantilevered components includes the following steps:

[0030] Step 101 : In response to a real-time vibration signal indicating that ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, a real-time image group is acquired.

[0031] In some embodiments, the execution entity (e.g., a computing device) of the construction displacement monitoring method applied to high-altitude cantilevered components can collect a real-time image group in response to a real-time vibration signal indicating that the ground vibration is greater than a preset vibration intensity or reaches an image collection time point.

[0032] Among them, the real-time vibration signal is collected by the vibration sensor. For example, a vibration sensor array can be used to collect vibration signals around the high-altitude cantilevered components. Specifically, the vibration sensors in the vibration sensor array are arranged in a surround manner around the high-altitude cantilevered components. For example, since the high-altitude cantilevered structure is cantilevered outside the main structure and the vibration is conductive, the vibration sensors in the vibration sensor array can be arranged in a surround manner on the ground where the main structure is located, with the main structure connected to the high-altitude cantilevered structure as the center, so as to realize the collection of real-time vibration signals. In particular, since there are multiple vibration sensors, multiple real-time vibration signals will be collected. When there is a vibration amplitude greater than the preset vibration amplitude in the real-time vibration signal, it indicates that the ground vibration is greater than the preset vibration intensity. For example, see Figure 2 The diagram shows the positional relationship between the high-altitude cantilevered structure and the vibration sensor array, wherein, in a top-down view, the high-altitude cantilevered structure 201 is supported by the main member 202. The main member 202 may be a support column with a steel frame as the skeleton and filled with concrete. Figure 2 The vibration sensor array shown includes eight vibration sensors 203 arranged around the main structure 202 .

[0033] The image acquisition time point is controlled by a preset image acquisition period. The preset image acquisition period can be manually set. For example, the preset image acquisition period can be 24 hours.

[0034] The real-time images in the real-time image group are acquired by the first camera and the second camera. The first camera and the second camera are respectively directed to different image acquisition areas on the bottom surface of the high-altitude cantilevered component. In practice, since the high-altitude cantilevered component has a certain height from the ground, in order to ensure the image clarity of the acquired real-time images, the first camera and the second camera are telephoto cameras. For example, see Figure 3 The diagram shows the relationship between the first camera, the second camera, the image acquisition area, and the high-altitude cantilevered member. The first camera 301 and the second camera 302 are fixedly mounted on a mounting platform at a predetermined angle. The mounting platform is located below the high-altitude cantilevered member 201. The first camera 301 and the second camera 302 each face different image acquisition areas on the bottom surface of the high-altitude cantilevered member 201.

[0035] In each image acquisition area, a matrix marker is fixedly arranged. In practice, the markers in the matrix marker contain different ArUco codes (or ArUco markers). For example, see Figure 4The figure shows the relationship between the matrix marker plate and the image acquisition area, where marker plates 401 are evenly spaced within image acquisition area 402. During construction, the surface of high-altitude cantilevered components often appears cement gray. Therefore, the marker plates can be colored with a significant difference from cement gray.

[0036] It should be noted that the computing device described above can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules, for example, to provide distributed services, or as a single software or software module. No specific limitations are given here.

[0037] Step 102: perform marker plate recognition on each real-time image in the real-time image group to obtain a marker plate information set.

[0038] In some embodiments, the execution entity may perform marker plate recognition on each real-time image in the real-time image group to obtain a marker plate information set.

[0039] The marker information includes: marker identification, marker position, and marker effective area. The marker identification uniquely identifies the marker corresponding to the marker information. Because markers contain different ArUco codes, marker identification can be associated with a unique marker identification. The marker position represents the coordinate position of the marker in the real-time image. The marker effective area represents the unobstructed area of ​​the marker.

[0040] In practice, due to the distance between the camera and the marker, obstructions may occur, obstructing the marker. Specifically, for each marker, since the initial positional relationship between the camera and the marker is fixed, the pixel area of ​​the marker in the camera-captured image is fixed. Therefore, the corresponding fixed pixel area can be used as the preset marker area. Next, the area of ​​the obstructed area is subtracted from the preset marker area to obtain the marker's effective area, as included in the marker information.

[0041] In practice, a YOLO (You Only Look Once) model may be used to perform marker recognition on a real-time image to determine the marker position included in the marker information.

[0042] In practice, since different marker boards contain different ArUco codes, the boundary features of the ArUco code contained in the marker board can be extracted at the marker board position by, for example, edge extraction (edge ​​detection algorithm based on the Canny operator), and the boundary features are compared with a pre-built boundary feature library to determine the marker board identifier included in the marker board information.

[0043] In some optional implementations of some embodiments, the execution entity performs marker plate recognition on each real-time image in the real-time image group to obtain a marker plate information set, including:

[0044] Step S1: performing image enhancement on the real-time image to obtain an enhanced image.

[0045] In practice, the execution state can first filter the real-time image using a filter constructed based on the Laplacian operator to obtain a filtered image. The execution entity can then overlay the filtered image with the real-time image to produce an enhanced image. By combining the filter constructed with the Laplacian operator, grayscale contrast enhancement is achieved, thereby improving image clarity.

[0046] Step S2: determining the image difference between the enhanced image and the preset pure color image to obtain a difference image.

[0047] The image size of the preset pure color image is consistent with the image size of the enhanced image, and the color value corresponding to the preset pure color image is a preset color value. For example, the color value of the preset color value under the RGB (Red-Green-Blue) standard is (R: 95; G: 95; B: 90).

[0048] In practice, the surface of high-altitude cantilevered components often appears cement gray, and in the enhanced image, the image acquisition area only occupies a certain portion, while the rest appears cement gray. By calculating the phase difference, the distinguishability of the marking plate boundary can be improved.

[0049] Step S3: Perform edge detection with an adaptive threshold on the difference image to obtain an initial detection area set.

[0050] Among them, the initial detection area is a closed area.

[0051] In practice, first, non-maximum suppression can be performed on the difference image to obtain the corresponding gradient image. Second, an upper threshold is determined based on the OTSU (Otsu's method) algorithm and the gradient image. Next, the upper threshold is divided by two to obtain the lower threshold. Furthermore, based on the upper and lower thresholds, edge detection is performed on the difference image using a Canny-based edge detection method to obtain an initial set of detection regions.

[0052] Step S4: Based on the region boundary length and region type corresponding to the initial detection region, an initial detection region that meets the region screening condition is screened out from the above-mentioned initial detection region set as a target detection region.

[0053] Among them, the area boundary length represents the boundary length of the initial detection area. Specifically, for each marker plate, since the initial positional relationship between the camera and the marker plate is fixed, the boundary length of the marker plate in the image captured by the camera is fixed. Therefore, the fixed boundary length can be used as the preset boundary length. The area type can be determined by the rectangularity corresponding to the initial detection area. Specifically, rectangularity = area area of ​​the minimum circumscribed rectangle corresponding to the initial detection area / area area of ​​the initial detection area. The closer the rectangularity is to 1, the more the area type is a rectangular area type. The screening condition is: the difference between the area boundary length and the preset boundary length is less than the length threshold and the area type is a rectangular area type.

[0054] Step S5: setting the color values ​​of the areas outside the target detection area in the enhanced image to 0 to obtain an updated image.

[0055] Step S6: Using a pre-trained marker plate recognition model, perform marker plate recognition on the updated image to obtain the marker plate information set.

[0056] In practice, the marker recognition model can employ the NanoDet (Lightweight Object Detection) model. Specifically, after the marker recognition model locates the marker's corresponding marker position, it subtracts the occluded area from the preset marker area to obtain the effective marker area included in the marker information. Simultaneously, boundary matching is performed by identifying the marker's boundary features and associating them with the corresponding marker identifier.

[0057] Step 103 : In response to the presence of at least a target number of markboard information satisfying a screening condition in the markboard information set, determining a component movement amount group.

[0058] In some embodiments, the execution entity may determine the component movement amount group in response to at least a target number of markboard information satisfying a screening condition existing in the markboard information set.

[0059] Among them, the above-mentioned screening conditions are: the ratio of the effective area of ​​the mark plate included in the mark plate information to the preset mark plate area is greater than the preset area ratio and there is a position offset between the mark plate position included in the mark plate information and the corresponding initial mark plate position.

[0060] In practice, the component movement amount group can be determined by combining the positional relationship between the first camera, the second camera, and the corresponding matrix marker plate, as well as the marker plate position included in the marker plate information and the initial marker position of the marker plate, through coordinate transformation and three-dimensional relationships. Specifically, since multiple calibration plates are included, the corresponding component movement amount can be solved for each calibration plate, thereby minimizing movement errors caused by environmental factors and other factors.

[0061] In some optional implementations of some embodiments, the execution entity determines the component movement amount group in response to at least a target number of markboard information satisfying a screening condition existing in the markboard information set, including:

[0062] Step S1: Collect a set of real-time distance value groups.

[0063] The real-time distance value groups are organized in a matrix format. The real-time distance value groups in the set of real-time distance value groups are obtained by distance measurement using a first matrix distance sensor and a second matrix distance sensor. The first matrix distance sensor and the first camera are fixed relative to each other, and the second matrix distance sensor and the second camera are fixed relative to each other. The number and layout of the distance sensors in the first matrix distance sensor correspond to the number and layout of the marker plates in the matrix marker plate corresponding to the first camera, so that each distance sensor corresponds to a marker plate. The number and layout of the distance sensors in the second matrix distance sensor correspond to the number and layout of the marker plates in the matrix marker plate corresponding to the second camera, so that each distance sensor corresponds to a marker plate. In practice, although it is possible to calibrate the cameras and convert coordinates between the image coordinate system and the earth coordinate system using translation and rotation matrices, this can increase errors due to the large distance between the cameras and the overhead cantilevered structure. Therefore, the present disclosure determines real-time distance values ​​using matrix distance sensors.

[0064] Step S2: According to the relative position of the first matrix ranging sensor and the first camera, the relative position of the second matrix ranging sensor and the second camera, and the marker plate information set, the real-time distance values ​​in the real-time distance value group set are matched with the marker plate information in the marker plate information set to obtain a matching information set.

[0065] Among them, the matching information includes: the marker plate identification group, the real-time longitudinal distance value and the longitudinal calibration distance value. In practice, when the high-altitude cantilever component is displaced, since the marker plate is fixed to the bottom surface of the component, the marker plate will also be displaced. The ranging sensor and the marker plate have a one-to-one correspondence in the initial stage. Therefore, it is necessary to re-bind the positional relationship between the ranging sensor and the marker plate. Among them, since the relative position of the matrix ranging sensor and the camera is fixed, when the marker plate is offset in the real-time image, it is only necessary to re-bind the ranging sensor and the marker plate based on the offset. In particular, the offset can be decomposed into longitudinal offset (Z axis) and lateral offset (X axis or Y axis). Among them, the longitudinal offset is the amount of movement along the vertical direction. The lateral offset is the amount of movement along the horizontal direction. In particular, when the high-altitude cantilever component is offset along both the X axis and the Y axis, the lateral component movement includes two components along the X axis and the Y axis. For longitudinal offset, the correspondence between the ranging sensor and the calibration plate remains unchanged. The longitudinal component movement can be obtained by taking the difference between the longitudinal component of the real-time distance value collected by the ranging sensor (the real-time longitudinal distance value) and the longitudinal calibration distance value. For lateral offset, the correspondence between the ranging sensor and the calibration plate changes, so the binding relationship between the calibration plate and the ranging sensor needs to be re-bound based on the lateral position change.

[0066] For example, see Figure 5 The schematic diagram of the scenario in which the matrix marking plate deviates with the high-altitude cantilever component is shown, wherein the matrix marking plate includes 3×3 marking plates, namely marking plate A11, marking plate A12, marking plate A13, marking plate A21, marking plate A22, marking plate A23, marking plate A31, marking plate A32, and marking plate A33. Figure 5 The matrix marker shown can correspond to the first matrix distance sensor. Therefore, the first matrix distance sensor includes 3×3 distance sensors, namely, distance sensor S11, distance sensor S12, distance sensor S13, distance sensor S21, distance sensor S22, distance sensor S23, distance sensor S31, distance sensor S32, and distance sensor S33. Among them, in the initial state, marker A11 corresponds to distance sensor S11, marker A12 corresponds to distance sensor S12, marker A13 corresponds to distance sensor S13, marker A21 corresponds to distance sensor S21, marker A22 corresponds to distance sensor S22, marker A23 corresponds to distance sensor S23, marker A31 corresponds to distance sensor S31, marker A32 corresponds to distance sensor S32, and marker A33 corresponds to distance sensor S33. When the following occurs Figure 5During the lateral offset shown, the correspondence between the ranging sensors and the marker plates changes: marker plate A11 corresponds to ranging sensor S12, marker plate A21 corresponds to ranging sensor S22, marker plate A31 corresponds to ranging sensor S32, marker plate A12 corresponds to ranging sensor S13, marker plate A22 corresponds to ranging sensor S23, and marker plate A32 corresponds to ranging sensor S33. Taking ranging sensor S32 as an example, the corresponding matching information includes the marker plate identification group [marker plate A32, marker plate A31].

[0067] Step S3: For each matching information in the matching information set, perform the following processing steps:

[0068] Step S31: determining the amount of movement of the transverse member according to the marking plate interval between two marking plates corresponding to the marking plate identification group included in the matching information.

[0069] In practice, the amount of movement of the transverse member may be obtained by multiplying the number of intervals of the marker plate interval between two marker plates corresponding to the marker plate identification group included in the matching information by the interval length.

[0070] Step S32: The distance difference between the real-time longitudinal distance value and the longitudinal calibration distance value included in the matching information is determined as the longitudinal component movement amount.

[0071] Step S33: determining the transverse member movement amount and the longitudinal member movement amount as the member movement amounts in the member movement amount group corresponding to the matching information.

[0072] Step 104 : In response to the camera offset, offset compensation is performed on the component movement amounts in the component movement amount group according to the camera offset to obtain a compensated component movement amount group.

[0073] In some embodiments, in response to the presence of camera offset, the above execution may perform offset compensation on the component movement amounts in the component movement amount group according to the camera offset to obtain the compensated component movement amount group.

[0074] The camera offset can be measured by an IMU (Inertial Measurement Unit) module. An IMU module is embedded in both the first camera and the second camera.

[0075] In practice, the camera offset can be decomposed along the X, Y, and Z axes and applied separately to the lateral and longitudinal component movements included in the compensated component movement. In particular, since the lateral component movement includes two components along the X and Y axes, the corresponding offset components need to be applied separately.

[0076] In some optional implementations of some embodiments, in response to a camera offset, the execution entity performs offset compensation on the component movement amounts in the component movement amount group according to the camera offset to obtain the compensated component movement amount group, including:

[0077] Step S1: Decompose the camera offset to obtain a horizontal camera offset and a vertical camera offset.

[0078] The horizontal camera offset includes two offset components along the X and Y axes, and the vertical camera offset includes the offset component along the Z axis.

[0079] Step S2: performing lateral offset compensation and longitudinal offset compensation on each component movement in the component movement group according to the lateral camera offset and the longitudinal camera offset, respectively, to generate compensated component movement, thereby obtaining the compensated component movement group.

[0080] As an example, since the relative position relationship between the first camera and the second camera is fixed, the lateral offset compensation and longitudinal offset compensation can be performed on each component movement in the above-mentioned component movement group through the lateral camera offset and longitudinal camera offset corresponding to any camera (the first camera or the second camera) to generate the compensated component movement and obtain the above-mentioned compensated component movement group.

[0081] As another example, in order to apply offset compensation more accurately, the corresponding component movement is offset compensated by the horizontal camera offset and the vertical camera offset corresponding to the camera (the first camera or the second camera).

[0082] Step 105 : In response to the presence of a compensated component movement amount greater than a warning threshold in the compensated component movement amount group, a component displacement warning is initiated.

[0083] In some embodiments, in response to a compensated component movement amount in the compensated component movement amount group being greater than a warning threshold, a component displacement warning is initiated.

[0084] In practice, corresponding warning thresholds can be set for the X-axis, Y-axis, and Z-axis. When the movement of the component after compensation is greater than the corresponding warning threshold, a component displacement warning is initiated to the monitoring terminal.

[0085] Optionally, the above method further includes:

[0086] Step S1: In response to the absence of at least a target number of marker information satisfying a screening condition in the marker information set, real-time particle concentration is collected through a dust sensor, and real-time humidity is collected through a humidity sensor.

[0087] In practice, both the dust sensor and humidity sensor can be arranged in a sensor array, evenly and circumferentially, on the main member connected to the high-altitude cantilever member. By being arranged on the main member, that is, between the high-altitude cantilever member and the camera, better information about the particle concentration and humidity in the environment between the high-altitude cantilever member and the camera can be collected.

[0088] Specifically, when there are no at least a target number of marking plate information that meets the screening conditions, it indicates that there is occlusion or the marking plate is missing. The occlusion may be caused by environmental factors or obstruction by construction equipment. As for environmental factors, it is mainly due to reduced visibility caused by dust raised due to construction; and reduced visibility due to weather reasons (such as rainy and snowy weather). Therefore, the present disclosure first uses a dust sensor and a humidity sensor to determine whether the visibility is low due to environmental factors, making it impossible to effectively identify the marking plate, which in turn leads to the absence of at least a target number of marking plate information that meets the screening conditions.

[0089] Step S2: In response to the real-time particulate matter concentration being less than a preset particulate matter concentration and the real-time humidity being less than a preset humidity, performing obstruction recognition on each real-time image in the real-time image group to generate obstruction information.

[0090] The occluder information includes: occluder type and occluder confidence.

[0091] In practice, an occlusion type classifier can be added to the marker recognition model to distinguish between occlusion types. This model reuse reduces the training overhead of separate recognition models. Specifically, the marker recognition model and occlusion type classifier are trained as a whole in a supervised manner.

[0092] In some optional implementations of some embodiments, the execution entity performs occlusion recognition on each real-time image in the real-time image group to generate occlusion information, including:

[0093] Step S21: constructing a region of interest according to the marker plate identifier and the marker plate position included in the marker plate information in the above marker plate information set.

[0094] The region of interest refers to the region of interest in the real-time image. Therefore, the size of the marker plate needs to be mapped to the image coordinate system. The region of interest can be the region of the marker plate corresponding to the marker plate identifier.

[0095] Step S22: Determine the direction of the obstruction according to the effective area of ​​the marker plate included in the marker plate information in the above marker plate information set.

[0096] In practice, you can rotate along the center of the region where the marker's effective area is located to obtain K line segments. Each line segment crosses the region center, and its endpoints fall on the region boundary where the marker's effective area is located. From these K line segments, select the longest one, and use the direction of the longest line segment as the obstruction direction.

[0097] Step S23: generating occluder information according to the pre-trained occluder recognition model, the real-time image, the region of interest, and the occluder direction.

[0098] The occlusion direction controls the convolution kernel's scanning direction. Regions outside the ROI in the real-time image correspond to random probabilities, which control the probability of setting features to zero before convolution. The occlusion recognition model uses the same architecture as the marker recognition model, but adds an occlusion type classifier.

[0099] In practice, for the convolutional layers included in the Backbone structure and PAN (Pyramid Attention Network) structure in the marker recognition model, the horizontal convolution kernel scanning method is abandoned and replaced by an oblique scanning method. The direction of the oblique scanning is controlled by the direction of the obstruction. In addition, since the region of interest has been set to ensure a relatively high degree of attention during the recognition process, for areas outside the region of interest, in order to reduce the attention and data processing volume, the probability of setting the random probability control feature to 0 is set. When the random probability representation feature is set to 0, the convolution kernel will skip the scanning area with a random probability of 0 during the scanning process, thereby reducing the convolution calculation volume and reducing the attention of areas outside the region of interest.

[0100] Step S3: In response to the obstruction information indicating that an obstruction exists, a delay timer is set.

[0101] The delay timer is used to control the first camera and the second camera to perform delayed re-acquisition of images, and the timing interval of the delay timer is smaller than the image acquisition period.

[0102] In practice, after the image is recaptured, steps 102 to 105 may be re-executed, and will not be described in detail here.

[0103] Step S4: In response to the obstruction information indicating that there is no obstruction, a marker board abnormality prompt is initiated.

[0104] In practice, when the particle size concentration and humidity are normal and there is no obstruction, there may be an abnormality in the marking plate (for example, the marking plate falls off), etc., so a corresponding marking plate abnormality prompt is required.

[0105] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the construction displacement monitoring method applied to high-altitude cantilevered components in some embodiments of the present disclosure, effective and accurate displacement change monitoring of high-altitude cantilevered components is achieved. Specifically, the reason for the inability to effectively monitor the displacement change of high-altitude cantilevered components is that since the total station requires the deployment of corresponding reflective prisms, and the high-altitude cantilevered components are often located in a cantilevered position at high altitude, the monitoring method using the total station is extremely difficult, and thus the displacement change of the high-altitude cantilevered components cannot be effectively monitored. Based on this, the construction displacement monitoring method applied to high-altitude cantilevered components in some embodiments of the present disclosure first collects a real-time image group in response to a real-time vibration signal indicating that the ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, wherein the real-time vibration signal is collected by a vibration sensor, the image acquisition time point is controlled by a preset image acquisition cycle, and the real-time images in the real-time image group are collected by a first camera and a second camera, the first camera and the second camera respectively facing different image acquisition areas on the bottom surface of the high-altitude cantilevered component, and a matrix marker plate is fixedly set in each image acquisition area. In practice, the use of cameras to monitor changes in cantilevered components significantly reduces real-time costs compared to methods such as total stations. Considering that component displacement changes are often subtle and occur over a long time span, real-time camera acquisition will generate a large number of invalid images, leading to meaningless data processing and thus consuming computing resources. Therefore, the present disclosure uses ground vibration intensity and image acquisition cycle to trigger the control of the camera for image acquisition. This method can significantly reduce the number of redundant images. Secondly, each real-time image in the above-mentioned real-time image group is subjected to marker plate recognition to obtain a marker plate information set, wherein the marker plate information includes: marker plate identification, marker plate position, and marker plate effective area. In practice, considering that components often have a certain height above the ground and component displacement changes are often subtle, the method of only capturing images of the component bottom surface and directly performing image analysis is not effective due to the lack of obvious change characteristics. Therefore, the present disclosure adopts a matrix marker plate and determines displacement changes through marker plate recognition. Next, in response to the presence of at least a target number of marker plate information items in the marker plate information set that meet a screening condition, a component movement amount group is determined, wherein the screening condition is that the ratio of the effective marker plate area included in the marker plate information to a preset marker plate area is greater than a preset area ratio, and there is a positional offset between the marker plate position included in the marker plate information and the corresponding initial marker plate position. In practice, due to the large distance between the camera and the component, environmental factors (e.g., weather) can affect image acquisition quality. Therefore, to ensure the validity of the determined displacement change, the screening condition and the target number are used to determine whether the component movement amount can be determined.Furthermore, in response to the presence of camera offset, the component movement in the above-mentioned component movement amount group is offset compensated according to the camera offset to obtain a compensated component movement amount group. In practice, although the camera can be fixed by a fixed platform, the vibrations existing in the construction environment (such as the vibrations caused by the movement of large engineering vehicles) will be transmitted to the camera through the ground. As the camera offset changes over time, it will accumulate and form a camera offset error that affects the component movement amount. Therefore, when there is a camera offset, it is necessary to compensate for the component movement amount according to the camera offset. Finally, in response to the presence of a compensated component movement amount greater than the warning threshold in the above-mentioned compensated component movement amount group, a component displacement warning is initiated. In summary, in this way, automated and effective displacement monitoring of high-altitude cantilevered components is achieved.

[0106] The present disclosure further provides a construction displacement monitoring system, which is applied to Figure 1 For details of the method embodiments shown in Figure 6 The system architecture diagram of the construction displacement monitoring system shown in FIG. 1 is shown, wherein the construction displacement monitoring system includes:

[0107] A vibration sensor array, wherein the vibration sensors in the vibration sensor array are arranged in a surrounding manner around the high-altitude cantilevered component.

[0108] The first camera and the corresponding matrix marker plate are oriented toward the corresponding matrix marker plate. In particular, the vibration sensors in the vibration sensor array can be arranged around the main structure connected to the high-altitude cantilever structure and on the ground where the main structure is located, thereby realizing real-time vibration signal collection.

[0109] The second camera and the corresponding matrix marker plate are fixed to the bottom surface of the high-altitude cantilevered component. The first camera is oriented toward the corresponding matrix marker plate. The first and second cameras are fixed to a fixed platform at a predetermined angle. The fixed platform is located below the high-altitude cantilevered component. In particular, the fixed platform can use a concrete pile as its main structure. The fixed platform can be embedded in the ground to ensure stability.

[0110] A first matrix ranging sensor, wherein the first matrix ranging sensor and the first camera are fixed relative to each other. In particular, the number and distribution of the ranging sensors included in the first matrix ranging sensor are the same as the number and distribution of the marker plates included in the matrix marker plate corresponding to the first camera.

[0111] A second matrix ranging sensor, wherein the second matrix ranging sensor and the second camera are fixed relative to each other. In particular, the number and distribution of ranging sensors included in the second matrix ranging sensor are the same as the number and distribution of marker plates included in the matrix marker plate corresponding to the second camera.

[0112] A data processing component is configured to process and analyze signals and images captured by sensors and cameras. Specifically, the data processing component can interact with and transmit data to and from the vibration sensors in the vibration sensor array, the first camera, the second camera, the ranging sensors in the first matrix ranging sensor, and the ranging sensors in the second matrix ranging sensor. The data processing component can be the aforementioned execution entity.

[0113] Further references Figure 7 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a construction displacement monitoring device for high-altitude cantilevered components. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the construction displacement monitoring device applied to high-altitude cantilevered components can be specifically applied to various electronic devices.

[0114] like Figure 7As shown, some embodiments of the construction displacement monitoring device 700 applied to high-altitude cantilevered components include: an acquisition unit 701, a marker plate recognition unit 702, a determination unit 703, an offset compensation unit 704, and an early warning unit 705. The acquisition unit 701 is configured to acquire a real-time image group in response to a real-time vibration signal indicating that the ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, wherein the real-time vibration signal is acquired by a vibration sensor, the image acquisition time point is controlled by a preset image acquisition cycle, and the real-time images in the real-time image group are acquired by a first camera and a second camera, the first camera and the second camera are respectively directed to different image acquisition areas on the bottom surface of the high-altitude cantilevered component, and a matrix marker plate is fixedly arranged in each image acquisition area; the marker plate recognition unit 702 is configured to perform marker plate recognition on each real-time image in the above-mentioned real-time image group to obtain a marker plate information set, wherein the marker plate information includes: marker plate identification, marker plate position, and marker plate effective area. ; The determination unit 703 is configured to determine the component movement amount group in response to the presence of at least a target number of marker plate information that meet the screening conditions in the above-mentioned marker plate information set, wherein the above-mentioned screening conditions are: the ratio of the effective area of ​​the marker plate included in the marker plate information to the preset marker plate area is greater than the preset area ratio and there is a position offset between the marker plate position included in the marker plate information and the corresponding initial marker plate position; the offset compensation unit 704 is configured to compensate the component movement amount in the above-mentioned component movement amount group according to the camera offset in response to the existence of a camera offset, and obtain a compensated component movement amount group; the early warning unit 705 is configured to initiate a component displacement early warning in response to the presence of a compensated component movement amount greater than the early warning threshold in the above-mentioned compensated component movement amount group. It can be understood that the units recorded in the construction displacement monitoring device 700 for high-altitude cantilevered components are the same as those in the reference. Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the construction displacement monitoring device 700 for high-altitude cantilevered components and the units included therein, and will not be repeated here.

[0115] Reference below Figure 8 , which shows a schematic structural diagram of an electronic device (eg, a computing device) suitable for implementing some embodiments of the present disclosure. Figure 8 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure. Figure 8As shown, the computer device includes a processor, a memory and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions, which, when executed, may enable the processor to execute any of the above methods. The processor is used to provide computing and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium, which, when executed by the processor, may enable the processor to execute any of the above methods. The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0116] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0117] In one embodiment, the processor is used to run a computer program stored in a memory to implement the following steps: in response to a real-time vibration signal indicating that the ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, a real-time image group is acquired, wherein the real-time vibration signal is acquired by a vibration sensor, the image acquisition time point is controlled by a preset image acquisition cycle, and the real-time images in the real-time image group are acquired by a first camera and a second camera, the first camera and the second camera are respectively directed to different image acquisition areas on the bottom surface of the high-altitude cantilevered component, and a matrix marker plate is fixedly arranged in each image acquisition area; each real-time image in the real-time image group is subjected to marker plate recognition to obtain a marker plate information set, wherein the marker The plate information includes: a marking plate identification, a marking plate position and an effective marking plate area; in response to the presence of at least a target number of marking plate information that meet the screening conditions in the above-mentioned marking plate information set, a component movement amount group is determined, wherein the above-mentioned screening conditions are: a ratio of the effective marking plate area included in the marking plate information to a preset marking plate area is greater than a preset area ratio and there is a position offset between the marking plate position included in the marking plate information and the corresponding initial marking plate position; in response to the presence of a camera offset, the component movement amount in the above-mentioned component movement amount group is offset compensated according to the camera offset to obtain a compensated component movement amount group; in response to the presence of a compensated component movement amount greater than a warning threshold in the above-mentioned compensated component movement amount group, a component displacement warning is initiated.

[0118] An embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the method described above in the present disclosure.

[0119] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., provided on the computer device.

[0120] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0121] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A construction displacement monitoring method for high-altitude cantilevered components, characterized in that: include: In response to a real-time vibration signal indicating that ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, a real-time image group is acquired, wherein the real-time vibration signal is acquired by a vibration sensor, the image acquisition time point is controlled by a preset image acquisition cycle, and the real-time images in the real-time image group are acquired by a first camera and a second camera, the first camera and the second camera are respectively directed toward different image acquisition areas on the bottom surface of the high-altitude cantilevered component, and a matrix marking plate is fixedly disposed in each image acquisition area; Performing marker plate recognition on each real-time image in the real-time image group to obtain a marker plate information set, wherein the marker plate information includes: a marker plate identifier, a marker plate position, and a marker plate effective area; In response to at least a target number of marker plate information satisfying a screening condition existing in the marker plate information set, determining a component movement amount group, wherein the screening condition is: a ratio of a marker plate effective area included in the marker plate information to a preset marker plate area is greater than a preset area ratio and a position offset exists between a marker plate position included in the marker plate information and a corresponding initial marker plate position; In response to the presence of camera offset, offset compensation is performed on the component movement amounts in the component movement amount group according to the camera offset to obtain a compensated component movement amount group; In response to the presence of a compensated component movement amount greater than a warning threshold in the compensated component movement amount group, a component displacement warning is initiated.

2. The method according to claim 1, characterized in that The method further comprises: In response to the absence of at least a target number of pieces of signboard information meeting a screening condition in the signboard information set, collecting real-time particle concentration via a dust sensor and collecting real-time humidity via a humidity sensor; In response to the real-time particulate matter concentration being less than a preset particulate matter concentration and the real-time humidity being less than a preset humidity, performing obstruction identification on each real-time image in the real-time image group to generate obstruction information, wherein the obstruction information includes: an obstruction type and an obstruction confidence level; In response to the obstruction information indicating the presence of an obstruction, setting a delay timer, wherein the delay timer is used to control the first camera and the second camera to perform delayed re-acquisition of images, and a timing interval of the delay timer is less than the image acquisition period; In response to the obstruction information indicating that no obstruction exists, a marker board abnormality prompt is initiated.

3. The method according to claim 2, characterized in that In response to at least a target number of marking plate information satisfying a screening condition existing in the marking plate information set, determining a component movement amount group includes: Collecting a set of real-time distance value groups, wherein the real-time distance value groups are constituted in a matrix form, and the real-time distance value groups in the real-time distance value group set are obtained by measuring distances using a first matrix ranging sensor and a second matrix ranging sensor, wherein the first matrix ranging sensor and the first camera are fixed relative to each other, and the second matrix ranging sensor and the second camera are fixed relative to each other; According to the relative position of the first matrix ranging sensor and the first camera, the relative position of the second matrix ranging sensor and the second camera, and the marker plate information set, the real-time distance values ​​in the real-time distance value group set are matched with the marker plate information in the marker plate information set to obtain a matching information set, wherein the matching information includes: a marker plate identification group, a real-time longitudinal distance value, and a longitudinal calibrated distance value; For each matching information in the matching information set, perform the following processing steps: determining a movement amount of the transverse member according to a marking plate interval between two marking plates corresponding to the marking plate identification group included in the matching information; Determine the distance difference between the real-time longitudinal distance value and the longitudinal calibration distance value included in the matching information as the longitudinal component movement amount; The transverse member movement amount and the longitudinal member movement amount are determined as the member movement amounts corresponding to the matching information in the member movement amount group.

4. The method according to claim 3, characterized in that In response to the camera offset, performing offset compensation on the component movement amounts in the component movement amount group according to the camera offset to obtain the compensated component movement amount group, comprising: Decompose the camera offset to obtain the horizontal camera offset and the vertical camera offset; According to the horizontal camera offset and the vertical camera offset, each component movement in the component movement amount group is subjected to horizontal offset compensation and vertical offset compensation to generate compensated component movement amounts, thereby obtaining the compensated component movement amount group.

5. The method according to claim 4, characterized in that The performing marker plate recognition on each real-time image in the real-time image group to obtain a marker plate information set includes: Performing image enhancement on the real-time image to obtain an enhanced image; Determining an image difference between the enhanced image and a preset pure color image to obtain a difference image, wherein an image size of the preset pure color image is consistent with an image size of the enhanced image, and a color value corresponding to the preset pure color image is a preset color value; Performing edge detection with an adaptive threshold on the difference image to obtain an initial detection area set, wherein the initial detection area is a closed area; Filtering, based on the region boundary length and region type corresponding to the initial detection region, an initial detection region that meets the region screening condition from the initial detection region set as a target detection region; Setting the color values ​​of the areas outside the target detection area in the enhanced image to 0 to obtain an updated image; The marker plate recognition model trained in advance is used to perform marker plate recognition on the updated image to obtain the marker plate information set.

6. The method according to claim 5, characterized in that The performing occlusion recognition on each real-time image in the real-time image group to generate occlusion information includes: Constructing a region of interest according to the marker plate identifier and the marker plate position included in the marker plate information in the marker plate information set; determining a direction of the obstruction according to an effective area of ​​the marker plate included in the marker plate information in the marker plate information set; Occlusion information is generated based on a pre-trained occlusion recognition model, the real-time image, the region of interest, and the occlusion direction, wherein the occlusion direction is used to control the scanning direction of the convolution kernel, and the area outside the region of interest in the real-time image corresponds to a random probability, wherein the random probability is used to control the probability of setting the feature to 0 before convolution.

7. A construction displacement monitoring system, applied to the method according to any one of claims 1 to 6, characterized in that: include: A vibration sensor array, wherein the vibration sensors in the vibration sensor array are arranged in a surrounding manner around the high-altitude cantilevered component; A first camera and a corresponding matrix marker plate, wherein the first camera faces the corresponding matrix marker plate; a second camera and a corresponding matrix marking plate, wherein the matrix marking plate is fixed to the bottom surface of the high-altitude cantilevered member, wherein the first camera faces the corresponding matrix marking plate, and the first camera and the second camera are fixed to a fixing platform at a preset angle, and the fixing platform is arranged below the high-altitude cantilevered member; A first matrix distance measuring sensor, wherein the relative positions of the first matrix distance measuring sensor and the first camera are fixed; A second matrix distance measuring sensor, wherein the relative positions of the second matrix distance measuring sensor and the second camera are fixed; Data processing component, wherein the data processing component is used to process and analyze the signals and images collected by sensors and cameras.

8. A construction displacement monitoring device for high-altitude cantilevered components, characterized in that: include: The acquisition unit is configured to acquire a real-time image group in response to a real-time vibration signal indicating that ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point, wherein the real-time vibration signal is acquired by a vibration sensor, the image acquisition time point is controlled by a preset image acquisition cycle, and the real-time images in the real-time image group are acquired by a first camera and a second camera, the first camera and the second camera respectively facing different image acquisition areas on the bottom surface of the high-altitude cantilevered component, and a matrix marker plate is fixedly disposed in each image acquisition area; a marker plate recognition unit configured to perform marker plate recognition on each real-time image in the real-time image group to obtain a marker plate information set, wherein the marker plate information includes: a marker plate identifier, a marker plate position, and a marker plate effective area; a determining unit configured to determine a component movement amount group in response to at least a target number of marker plate information satisfying a screening condition existing in the marker plate information set, wherein the screening condition is: a ratio of a marker plate effective area included in the marker plate information to a preset marker plate area is greater than a preset area ratio and a position offset exists between a marker plate position included in the marker plate information and a corresponding initial marker plate position; an offset compensation unit configured to, in response to a camera offset, perform offset compensation on the component movement amounts in the component movement amount group according to the camera offset amount, to obtain a compensated component movement amount group; The early warning unit is configured to initiate a component displacement early warning in response to a compensated component movement amount greater than an early warning threshold in the compensated component movement amount group.

9. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6 and the construction displacement monitoring system according to claim 7.

10. A computer-readable medium, characterized in that A computer program is stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 and the construction displacement monitoring system according to claim 7 are implemented.

Images