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

Abstract

Embodiments of the present disclosure disclose a construction displacement monitoring method and device applied to a high-altitude overhanging component. A specific embodiment of the method comprises: in response to a real-time vibration signal representing that ground vibration is greater than a preset vibration intensity or reaching an image acquisition time point, acquiring a real-time image group; performing marker plate identification on each real-time image in the real-time image group to obtain a marker plate information set; in response to there being at least a target number of marker plate information in the marker plate information set that satisfies a screening condition, determining a component movement amount group; in response to there being 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 there being a compensated component movement amount greater than a warning threshold in the compensated component movement amount group, initiating component displacement warning. This embodiment realizes automatic and effective displacement monitoring of a high-altitude overhanging component.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of computer technology and the field of engineering construction, and particularly to a construction displacement monitoring method and device applied to high-altitude cantilever members. BACKGROUND

[0002] A high-altitude cantilever member refers to a member (for example, a balcony) cantilevered from a main structure of a high-rise building. The cantilever member is often kept stable by external tension or weight. When the stability of the member is broken due to external force, the high-altitude cantilever structure may change in displacement, thereby affecting the stability of the structure and the safety of the building. At present, displacement monitoring is usually performed by using a total station.

[0003] However, when the above method is used, the following technical problems often exist:

[0004] Since the total station needs to be arranged with a corresponding reflector prism, and the high-altitude cantilever member is often cantilevered at a high altitude, the monitoring difficulty is extremely high when the total station is used for monitoring, so that the displacement change of the high-altitude cantilever member cannot be effectively monitored.

[0005] The above information disclosed in the background section is only intended to enhance the understanding of the background of the present inventive concept and thus can include information that does not form the prior art known to those of ordinary skill in the art. SUMMARY

[0006] The summary section is provided to introduce the concepts briefly in a simplified form, which will be described in detail in the specific embodiments section. The summary section is not intended to identify key or essential features of the claimed technical solution nor is it intended to be used to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure propose a construction displacement monitoring method and device applied to high-altitude cantilever members to solve the technical problems mentioned in the background section.

[0008] In a first aspect, some embodiments of the present disclosure provide a construction displacement monitoring method applied to a high-altitude overhanging member, the method comprising: in response to a real-time vibration signal representing that ground vibration is greater than a preset vibration intensity or reaching 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 period, 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 towards different image acquisition areas on a member bottom surface of the high-altitude overhanging member, and a matrix type marker plate is fixedly arranged in each image acquisition area; performing marker plate identification on each real-time image in the real-time image group to obtain a marker plate information set, wherein the marker plate information comprises a marker plate identifier, a marker plate position, and a marker plate effective area; in response to there being at least a target number of marker plate information satisfying a screening condition in the marker plate information set, determining a member displacement amount group, wherein the screening condition is that the ratio of the marker plate effective area included in the marker plate information to a preset marker plate area is greater than a preset area ratio and there is a position offset between the marker plate position included in the marker plate information and a corresponding initial marker plate position; in response to there being a camera offset, offset compensating the member displacement amounts in the member displacement amount group according to the camera offset amount to obtain a compensated member displacement amount group; and in response to there being a compensated member displacement amount greater than a warning threshold in the compensated member displacement amount group, initiating a member displacement warning.

[0009] In a second aspect, some embodiments of the present disclosure provide a construction displacement monitoring system applied to the method of the first aspect, and characterized in that it comprises: a vibration sensor array, wherein the vibration sensors in the vibration sensor array are arranged around the high-altitude overhanging member in a ring shape; a first camera and a corresponding matrix type marker plate, wherein the first camera is directed towards the corresponding matrix type marker plate; a second camera and a corresponding matrix type marker plate, wherein the matrix type marker plate is fixed to a member bottom surface of the high-altitude overhanging member, and the first camera is directed towards the corresponding matrix type marker plate, the first camera and the second camera are fixed on a fixed table at a preset included angle, and the fixed table is arranged below the high-altitude overhanging member; a first matrix type distance measuring sensor, wherein the relative positions between the first matrix type distance measuring sensor and the first camera are fixed; a second matrix type distance measuring sensor, wherein the relative positions between the second matrix type distance measuring sensor and the second camera are fixed; and a data processing assembly, wherein the data processing assembly is used for data processing and analysis of 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 applied to a high-altitude overhanging component, the device comprising: a collection unit configured to collect a real-time image set in response to a real-time vibration signal representing that ground vibration is greater than a preset vibration intensity or reaches an image collection time point, wherein the real-time vibration signal is collected by a vibration sensor, the image collection time point is controlled by a preset image collection period, real-time images in the real-time image set are collected by a first camera and a second camera, the first camera and the second camera are respectively directed towards different image collection areas on a component bottom surface of the high-altitude overhanging component, and a matrix type marker plate is fixedly arranged in each image collection area; a marker plate recognition unit configured to recognize a marker plate in each real-time image in the real-time image set to obtain a marker plate information set, wherein the marker plate information comprises a marker plate identifier, a marker plate position and a marker plate effective area; a determination unit configured to determine a component movement amount set in response to at least a target number of marker plate information in the marker plate information set satisfying a screening condition, wherein the screening condition is that a ratio of the marker plate effective area included in the marker plate information to a preset marker plate area is greater than a preset area ratio and there is a position offset between the marker plate position included in the marker plate information and a corresponding initial marker plate position; an offset compensation unit configured to compensate for the component movement amount in the component movement amount set according to a camera offset amount in response to the existence of the camera offset to obtain a compensated component movement amount set; and a warning unit configured to initiate a component displacement warning in response to the existence of a compensated component movement amount greater than a warning threshold in the compensated component movement amount set.

[0011] In a fourth aspect, some embodiments of the present disclosure provide an electronic device, comprising: 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 described in any of the implementation manners of the 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 the program is executed by a processor to implement the method described in any of the implementation manners of the first aspect.

[0013] The above various embodiments of the present disclosure have the following beneficial effects: through the construction displacement monitoring method for the high-altitude overhanging member applied by some embodiments of the present disclosure, effective and accurate displacement change monitoring for the high-altitude overhanging member is realized. Specifically, the reason why the displacement change of the high-altitude overhanging member cannot be effectively monitored is that: since the total station needs to be arranged with a corresponding reflecting prism, and the high-altitude overhanging member is often located in a high-altitude overhanging position, therefore, the monitoring difficulty is extremely great by using the total station monitoring method, so that the displacement change of the high-altitude overhanging member cannot be effectively monitored. Based on this, the construction displacement monitoring method for the high-altitude overhanging member applied by some embodiments of the present disclosure, first, in response to that the real-time vibration signal represents that the ground vibration is greater than the preset vibration intensity or reaches the 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 period, 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 member bottom surface of the high-altitude overhanging member, and a matrix type marker plate is fixedly arranged in each image acquisition area. In practice, by using the camera to monitor the change of the overhanging member, the real-time cost is greatly reduced compared with the total station and the like. Considering that the member displacement change is often not obvious and has a long time span, therefore, a large amount of invalid images are generated by the real-time image acquisition by the camera, and meaningless data processing is generated to occupy the computing resources. Therefore, the ground vibration intensity and the image acquisition period are used to trigger the camera to acquire images in the present disclosure, and the number of redundant images can be greatly reduced in this way. Secondly, marker plate recognition is performed on each real-time image in the above 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. In practice, considering that the member often has a certain height from the ground and the member displacement change is often not obvious, the method of only acquiring images on the member bottom surface and directly performing image analysis has poor monitoring effect due to the unobvious change characteristics. Therefore, the matrix type marker plate is used in the present disclosure to determine the displacement change by marker plate recognition. Then, in response to that there are at least a target number of marker plate information meeting the screening condition in the above marker plate information set, a member movement amount group is determined, wherein the screening condition is that the ratio of the marker plate effective area included in the marker plate information to the preset marker plate area is greater than a 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. In practice, since there is a large distance between the camera and the member, the environmental factors (for example, weather) will affect the image acquisition quality, therefore, in order to ensure the effectiveness of the determined displacement change, the screening condition and the target number are used to determine whether the member movement amount can be determined.Further, in response to the existence of camera offset, the component movement amount in the above-mentioned component movement amount group is offset compensated according to the camera offset amount, to obtain a compensated component movement amount group. In practice, although the camera can be fixed by the fixed platform, the vibration existing in the construction environment (such as the vibration caused by the movement of large engineering vehicles) can be conducted to the camera through the ground, and the camera offset caused by the vibration changes over time and accumulates, thereby forming the camera offset error affecting the component movement amount. Therefore, when the camera offset exists, the component movement amount needs to be compensated according to the camera offset. Finally, in response to the existence of the compensated component movement amount greater than the early warning threshold in the above-mentioned compensated component movement amount group, the component displacement early warning is initiated. In summary, the displacement monitoring of the high-altitude cantilever component is realized in an automatic and effective manner through the above-mentioned manner. BRIEF DESCRIPTION OF DRAWINGS

[0014] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail some embodiments thereof with reference to the attached drawings. The same or similar elements are denoted by the same or similar reference numerals throughout the drawings. It is to be understood that the drawings are schematic, and elements and elements are not necessarily drawn to scale.

[0015] Figure 1 is a flowchart of some embodiments of the construction displacement monitoring method applied to the high-altitude cantilever component according to the present disclosure;

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

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

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

[0019] Figure 5 is a schematic diagram of the scene when the matrix type marker plate is offset with the high-altitude cantilever component;

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

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

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

[0023] Embodiments of the present disclosure will be described below in greater detail with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thoroughly and completely understood. It should be understood that the drawings of the present disclosure are only for illustrative purposes and should not be construed as limiting the scope of protection of the present disclosure.

[0024] In addition, it should be further noted that only parts related to the present application are shown in the drawings for ease of description. The embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0025] It should be noted that the concepts of "first", "second", etc. mentioned in the present 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 adjectives "one", "multiple" mentioned in the present disclosure are illustrative and not limiting, and those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more".

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

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

[0029] Reference Figure 1 , shows the flow 100 of some embodiments of the construction displacement monitoring method applied to the high-altitude cantilever member according to the present disclosure. The construction displacement monitoring method applied to the high-altitude cantilever member comprises the following steps:

[0030] Step 101, in response to the real-time vibration signal representing that the ground vibration is greater than the preset vibration intensity or reaching the image acquisition time point, a real-time image group is acquired.

[0031] In some embodiments, the execution subject (for example, a computing device) of the construction displacement monitoring method applied to the high-altitude cantilever member can acquire a real-time image group in response to the real-time vibration signal representing that the ground vibration is greater than the preset vibration intensity or reaching the image acquisition time point.

[0032] The real-time vibration signals are collected by vibration sensors. For example, a vibration sensor array can be used to collect vibration signals around the high-altitude overhanging component. Specifically, the vibration sensors in the vibration sensor array are arranged around the high-altitude overhanging component in a ring shape. For example, because the high-altitude overhanging 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 ring shape on the ground where the main structure is located, with the main structure connected by the high-altitude overhanging structure as the center, so as to realize the collection of real-time vibration signals. In particular, because there are multiple vibration sensors, multiple real-time vibration signals will be collected, and when the vibration amplitude in the real-time vibration signal is greater than the preset vibration amplitude, it indicates that the ground vibration is greater than the preset vibration intensity. For example, see Figure 2 The position relationship between the high-altitude overhanging component and the vibration sensor array is shown in the schematic diagram. In the top view, the high-altitude overhanging structure 201 is supported by the main component 202. The main component 202 can be a support column filled with concrete with a steel reinforcement framework as the framework. Figure 2 The vibration sensor array shown includes 8 vibration sensors 203 arranged around the main structure 202.

[0033] The image collection time points are controlled by a preset image collection period. The preset image collection period can be manually set. For example, the preset image collection period can be 24 hours.

[0034] The real-time images in the real-time image group are collected by the first camera and the second camera. The first camera and the second camera are respectively directed towards different image collection areas on the component bottom surface of the high-altitude overhanging component. In practice, because the high-altitude overhanging component has a certain height from the ground, in order to ensure the image clarity of the collected real-time images, the first camera and the second camera use long-focus cameras. For example, see Figure 3 The position relationship between the first camera, the second camera, the image collection area, and the high-altitude overhanging component is shown in the schematic diagram. The first camera 301 and the second camera 302 are fixedly arranged on the fixed table at a preset included angle. The fixed table is arranged below the high-altitude overhanging component 201. The first camera 301 and the second camera 302 are respectively directed towards different image collection areas on the component bottom surface of the high-altitude overhanging component 201.

[0035] Each image collection area is fixedly provided with a matrix-type marker plate. In practice, the marker plates in the matrix-type marker plate contain different ArUco codes (or ArUco markers). For example, see Figure 4A schematic diagram of the positional relationship between the matrix marker plate and the image acquisition area is shown, wherein the marker plates 401 in the matrix marker plate are uniformly arranged in the image acquisition area 402 at equal intervals. In particular, during the construction phase, the surface of the high-altitude cantilever component is often cement gray, so the marker plate can use a color with a large color difference from cement gray as the corresponding marker plate color.

[0036] It should be noted that the above computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or as a single server or single terminal device. When the computing device is software, it can be installed in the above-mentioned hardware devices. It can be implemented as, for example, multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.

[0037] At step 102, marker plate recognition is performed on each real-time image in the real-time image group to obtain a set of marker plate information.

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

[0039] The marker plate information includes: marker plate identification, marker plate position, and marker plate effective area. The marker plate identification is the unique identification of the marker plate corresponding to the marker plate information. Since the marker plate contains different ArUco codes, the marker plate identification can be associated to a unique marker plate identification through marker plate recognition. The marker plate position represents the coordinate position of the marker plate in the real-time image. The marker plate effective area represents the area of the marker plate that is not blocked.

[0040] In practice, due to the distance between the camera and the marker plate, there may be an obstruction causing the marker plate to be blocked. Specifically, for each marker plate, since the initial positional relationship between the camera and the marker plate is fixed, the pixel area of the marker plate in the camera-acquired image is fixed, and thus the corresponding fixed pixel area can be used as the preset marker plate area. Then, the preset marker plate area is subtracted by the blocked area to obtain the marker plate effective area included in the marker plate information.

[0041] In practice, a model such as YOLO (You Only Look Once) can be used to recognize the marker plate in the real-time image to determine the marker plate position included in the marker plate information.

[0042] In practice, since different marker plates contain different ArUco codes, the boundary features of the ArUco codes contained in the marker plates can be extracted at the positions of the marker plates by means of edge extraction (an edge detection algorithm based on the Canny operator), and the boundary features are compared with a pre-constructed boundary feature library to determine the marker plate identification included in the marker plate information.

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

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

[0045] In practice, first, the above execution state can be obtained by performing image filtering on the real-time image by means of a filter based on the Laplacian operator to obtain a filtered image. Then, the above execution subject can superimpose the filtered image and the real-time image as the enhanced image. By means of the filter based on the Laplacian operator, the gray contrast is enhanced to improve the image definition.

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

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

[0048] In practice, the surface of the high-altitude cantilever member is often cement gray, and in the enhanced image, the image acquisition area only occupies a certain part, and the remaining part is cement gray. By means of image difference, the distinguishability of the marker plate boundary is improved.

[0049] Step S3: edge detection of the difference image is performed by means of adaptive threshold to obtain an initial detection region set.

[0050] Wherein, the initial detection region is a closed region.

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

[0052] Step S4: According to the region boundary length and the region type corresponding to the initial detection region, the initial detection region meeting the region screening condition is screened from the initial detection region set as the target detection region.

[0053] The region boundary length represents the boundary length of the initial detection region. Specifically, for each marker plate, since the initial position 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 region type can be determined by the rectangularity of the initial detection region. Specifically, the rectangularity = the area of the minimum circumscribed rectangle corresponding to the initial detection region / the area of the initial detection region. The closer the rectangularity is to 1, the more the region type represents a rectangular region type. The screening condition is that the difference between the region boundary length and the preset boundary length is less than the length threshold value and the region type is a rectangular region type.

[0054] Step S5: The color value of the region in the enhanced image other than the target detection region is set to 0 to obtain an updated image.

[0055] Step S6: The marker plate recognition model is pre-trained, and the marker plate recognition is performed on the updated image to obtain the marker plate information set.

[0056] In practice, the marker plate recognition model can use the NanoDet (lightweight target detection) model. Specifically, after the marker plate recognition model is positioned to the marker plate position corresponding to the marker plate, the preset marker plate area is reduced by the area of the occlusion region to obtain the marker plate effective area included in the marker plate information. At the same time, the boundary matching is performed through the boundary features of the recognized marker plate, and the corresponding marker plate identifier is associated.

[0057] Step 103, in response to the existence of at least the target number of marker plate information meeting the screening condition in the marker plate information set, determining the component movement amount group.

[0058] In some embodiments, the above execution subject can determine the component movement amount group in response to the existence of at least the target number of marker plate information meeting the screening condition in the marker plate information set.

[0059] The screening condition is that 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.

[0060] In practice, the position relationship between the first camera, the second camera and the corresponding matrix type marker plate, and the marker plate position included in the marker plate information, and the initial marker position of the marker plate can be combined to determine the component movement amount group through coordinate conversion and three-dimensional relationship. Specifically, since multiple calibration plates are included, the corresponding component movement amount can be solved for each calibration plate to eliminate movement errors caused by environmental factors as much as possible.

[0061] In some optional implementations of some embodiments, the execution subject determines the component movement amount group in response to the presence of at least a target number of marker plate information in the above-mentioned marker plate information set that meets the screening condition, including:

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

[0063] The real-time distance value groups are in a matrix form, and the real-time distance value groups in the above-mentioned set of real-time distance value groups are obtained by distance measurement of the first matrix type distance measurement sensor and the second matrix type distance measurement sensor. The relative positions between the above-mentioned first matrix type distance measurement sensor and the above-mentioned first camera are fixed, and the relative positions between the above-mentioned second matrix type distance measurement sensor and the above-mentioned second camera are fixed. The number and layout of the distance measurement sensors included in the first matrix type distance measurement sensor correspond to the number and layout of the marker plates included in the matrix type marker plate corresponding to the first camera, so that each distance measurement sensor corresponds to a marker plate. The number and layout of the distance measurement sensors included in the second matrix type distance measurement sensor correspond to the number and layout of the marker plates included in the matrix type marker plate corresponding to the second camera, so that each distance measurement sensor corresponds to a marker plate. In practice, although the calibration camera can realize the conversion of coordinates in the image coordinate system and the geodetic coordinate system through the translation matrix and the rotation matrix, the distance between the camera and the high-suspended component is large, which increases the error. Therefore, the real-time distance is determined by the matrix type distance measurement sensor.

[0064] Step S2: According to the relative positions of the above-mentioned first matrix type distance measurement sensor and the above-mentioned first camera, the relative positions of the above-mentioned second matrix type distance measurement sensor and the above-mentioned second camera, and the above-mentioned set of marker plate information, the real-time distance value in the above-mentioned set of real-time distance value groups is matched with the marker plate information in the above-mentioned set of marker plate information to obtain a set of matching information.

[0065] The matching information includes a marker plate identification group, a real-time longitudinal distance value, and a longitudinal calibration distance value. In practice, when the high-altitude overhanging component is displaced, the marker plate is fixed to the bottom surface of the component, so the marker plate will be displaced. The ranging sensor and the marker plate have a one-to-one correspondence relationship in the initial stage, so it is necessary to rebind the position relationship between the ranging sensor and the marker plate. Since the relative positions of the matrix ranging sensor and the camera are fixed, when the marker plate is offset in the real-time image, it is only necessary to rebind the ranging sensor and the marker plate in combination with the offset. In particular, the offset can be decomposed into longitudinal offset (Z-axis) and transverse offset (X-axis or Y-axis). The longitudinal offset is the amount of movement in the vertical direction. The transverse offset is the amount of movement in the horizontal direction. In particular, when the high-altitude overhanging component is offset along the X-axis and the Y-axis, the transverse component movement includes two components along the X-axis and the Y-axis. For longitudinal offset, the correspondence relationship between the ranging sensor and the calibration plate does not change, and the longitudinal component (real-time longitudinal distance value) of the real-time distance value acquired by the ranging sensor and the distance value difference of the longitudinal calibration distance value can be used to obtain the longitudinal component movement. For transverse offset, the correspondence relationship between the ranging sensor and the calibration plate changes, so it is necessary to rebind the binding relationship between the calibration plate and the ranging sensor according to the position change in the transverse direction.

[0066] As an example, refer to Figure 5 The matrix marker plate shown in the scene diagram when the high-altitude overhanging component is offset, wherein the matrix marker plate includes 3x3 marker plates, namely marker plate A11, marker plate A12, marker plate A13, marker plate A21, marker plate A22, marker plate A23, marker plate A31, marker plate A32, and marker plate A33. Among them, Figure 5 The matrix marker plate can correspond to the first matrix ranging sensor, so the first matrix ranging sensor includes 3x3 ranging sensors, namely ranging sensor S11, ranging sensor S12, ranging sensor S13, ranging sensor S21, ranging sensor S22, ranging sensor S23, ranging sensor S31, ranging sensor S32, and ranging sensor S33. In the initial state, marker plate A11 corresponds to ranging sensor S11, marker plate A12 corresponds to ranging sensor S12, marker plate A13 corresponds to ranging sensor S13, marker plate A21 corresponds to ranging sensor S21, marker plate A22 corresponds to ranging sensor S22, marker plate A23 corresponds to ranging sensor S23, marker plate A31 corresponds to ranging sensor S31, marker plate A32 corresponds to ranging sensor S32, and marker plate A33 corresponds to ranging sensor S33. When the marker plate is offset as shown in Figure 5When the lateral offset is shown, the correspondence between the distance sensor and the marker plate changes, that is, the marker plate A11 corresponds to the distance sensor S12, the marker plate A21 corresponds to the distance sensor S22, the marker plate A31 corresponds to the distance sensor S32, the marker plate A12 corresponds to the distance sensor S13, the marker plate A22 corresponds to the distance sensor S23, and the marker plate A32 corresponds to the distance sensor S33. Taking the distance sensor S32 as an example, the corresponding matching information includes a marker plate identifier group [marker plate A32, marker plate A31].

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

[0068] Step S31: Determine the lateral member movement amount according to the marker plate interval between the two marker plates corresponding to the marker plate identifier group included in the above matching information.

[0069] In practice, the interval quantity x interval length of the marker plate interval between the two marker plates corresponding to the marker plate identifier group included in the matching information can be obtained to obtain the lateral member movement amount.

[0070] Step S32: Determine the distance difference between the real-time longitudinal distance value and the longitudinal calibration distance value included in the above matching information as the longitudinal member movement amount.

[0071] Step S33: Determine the above lateral member movement amount and the above longitudinal member movement amount as the member movement amount corresponding to the above matching information in the above member movement amount group.

[0072] Step 104, in response to the existence of camera offset, offset compensation is performed on the member movement amount in the member movement amount group according to the camera offset amount, to obtain a compensated member movement amount group.

[0073] In some embodiments, the above execution can be performed in response to the existence of camera offset, offset compensation is performed on the member movement amount in the member movement amount group according to the camera offset amount, to obtain a compensated member movement amount group.

[0074] Wherein, the camera offset amount can be measured by an IMU (Inertial Measurement Unit) module. An IMU module is embedded in each of the first camera and the second camera.

[0075] In practice, the camera offset amount can be decomposed along the X-axis, Y-axis and Z-axis, and respectively applied to the lateral member movement amount and the longitudinal member movement amount included in the compensated member movement amount. In particular, since the lateral member movement amount contains two components along the X-axis and Y-axis, it is necessary to respectively apply the corresponding offset components.

[0076] In some optional implementations of some embodiments, the execution subject described above, in response to the existence of the camera offset, offsets and compensates the component movement amount in the component movement amount group according to the camera offset amount to obtain a compensated component movement amount group, including:

[0077] Step S1: decompose the camera offset amount into a horizontal camera offset amount and a vertical camera offset amount.

[0078] The horizontal camera offset amount includes two offset components of the camera offset amount along the X-axis and the Y-axis. The vertical camera offset amount includes an offset component of the camera offset amount along the Z-axis.

[0079] Step S2: respectively offset and compensate each component movement amount in the component movement amount group according to the horizontal camera offset amount and the vertical camera offset amount to generate a compensated component movement amount, and obtain the compensated component movement amount group.

[0080] As an example, since the relative position relationship between the first camera and the second camera is fixed, the horizontal offset compensation and the vertical offset compensation can be performed on each component movement amount in the component movement amount group by the horizontal camera offset amount and the vertical camera offset amount corresponding to any one of the cameras (the first camera or the second camera) to generate a compensated component movement amount and obtain the compensated component movement amount group.

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

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

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

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

[0085] Optionally, the method further includes:

[0086] Step S1: in response to the absence of at least a target number of marker plate information satisfying the screening condition in the marker plate information set, collecting real-time particulate matter concentration by a dust sensor and collecting real-time humidity by a humidity sensor.

[0087] In practice, the dust sensor and the humidity sensor can both adopt the form of a sensor array and be uniformly arranged in a surrounding manner on the main body member connected to the high-altitude overhanging member. The dust sensor and the humidity sensor are arranged on the main body member, i.e., between the high-altitude overhanging member and the camera, so as to better collect the particulate matter concentration and humidity of the environment between the high-altitude overhanging member and the camera.

[0088] Specifically, when there is no at least a target number of marker board information meeting the screening condition, it is indicated that there is an occlusion or a missing marker board. The occlusion can be caused by environmental factors or construction equipment. For environmental factors, the visibility is reduced due to dust rising caused by construction, and the visibility is reduced due to weather (such as rainy and snowy weather). Therefore, the present disclosure first determines whether the visibility is low due to environmental factors through the dust sensor and the humidity sensor, so that the marker board cannot be effectively recognized, and thus there is no at least a target number of marker board information meeting the screening condition.

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

[0090] The occlusion object information includes an occlusion object type and an occlusion object confidence.

[0091] In practice, an occlusion object type classifier can be added to the marker board recognition model to distinguish the occlusion object type. The reuse of the model reduces the training overhead of training an additional recognition model. In particular, the marker board recognition model and the occlusion object type classifier are trained as a whole in a supervised manner.

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

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

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

[0095] Step S22: Determining an occlusion object direction according to the effective area of the marker board included in the marker board information in the marker board information set.

[0096] In practice, K line segments can be obtained by rotating the region center of the region where the effective area of the marker plate is located. Among them, the line segment crosses the region center, and the two endpoints of the line segment fall on the region boundary of the region where the effective area of the marker plate is located. The longest line segment is selected from the K line segments, and the direction of the longest line segment is taken as the direction of the occlusion.

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

[0098] Among them, the direction of the occlusion is used to control the scanning direction of the convolution kernel, and the region outside the region of interest in the real-time image corresponds to a random probability, wherein the random probability is used to control the 0 probability of the feature before convolution. The occlusion recognition model also adopts the architecture of adding an occlusion type classifier in the marker plate recognition model.

[0099] In practice, for the convolution layers included in the Backbone structure and the PAN (Pyramid Attention Network) structure in the marker plate recognition model, the horizontal convolution kernel is discarded layer by layer, and a diagonal scanning method is used instead. The direction of the diagonal scanning is controlled by the direction of the occlusion. In addition, since the region of interest has been set to ensure a relatively high attention during the recognition process, for the region outside the region of interest, in order to reduce the attention and the amount of data processing, a random probability is set to control the 0 probability of the feature. When the random probability represents the 0 of the feature, the scanning region with a random probability of 0 is skipped during the convolution kernel scanning process, thereby reducing the convolution calculation amount and the attention of the region outside the region of interest.

[0100] Step S3: setting a delay timer in response to the occlusion information indicating that there is an occlusion.

[0101] Among them, the delay timer is used to control the delay reacquisition of images by the first camera and the second camera, and the time interval of the delay timer is less than the image acquisition period.

[0102] In practice, when the image is reacquired, steps 102 to 105 can be re-executed, which will not be repeated here.

[0103] Step S4: initiating a marker plate abnormality prompt in response to the occlusion information indicating that there is no occlusion.

[0104] In practice, when the particle concentration and humidity are normal, and there is no occlusion, there may be abnormalities of the marker plate (such as marker plate falling off), etc., so a corresponding marker plate abnormality prompt is needed.

[0105] The above various embodiments of the present disclosure have the following beneficial effects: through the construction displacement monitoring method for the high-altitude overhanging member applied by some embodiments of the present disclosure, effective and accurate displacement change monitoring for the high-altitude overhanging member is realized. Specifically, the reason why the displacement change of the high-altitude overhanging member cannot be effectively monitored is that: since the total station needs to be arranged with a corresponding reflecting prism, and the high-altitude overhanging member is often located in a high-altitude overhanging position, therefore, the monitoring difficulty is extremely great by using the total station monitoring method, so that the displacement change of the high-altitude overhanging member cannot be effectively monitored. Based on this, the construction displacement monitoring method for the high-altitude overhanging member applied by some embodiments of the present disclosure, first, in response to that the real-time vibration signal represents that the ground vibration is greater than the preset vibration intensity or reaches the 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 period, 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 member bottom surface of the high-altitude overhanging member, and a matrix type marker plate is fixedly arranged in each image acquisition area. In practice, by using the camera to monitor the change of the overhanging member, the real-time cost is greatly reduced compared with the total station and the like. Considering that the member displacement change is often not obvious and has a long time span, therefore, a large amount of invalid images are generated by the real-time image acquisition by the camera, and meaningless data processing is generated to occupy the computing resources. Therefore, the ground vibration intensity and the image acquisition period are used to trigger the camera to acquire images in the present disclosure, and the number of redundant images can be greatly reduced in this way. Secondly, marker plate recognition is performed on each real-time image in the above 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. In practice, considering that the member often has a certain height from the ground and the member displacement change is often not obvious, the method of only acquiring images on the member bottom surface and directly performing image analysis has poor monitoring effect due to the unobvious change characteristics. Therefore, the matrix type marker plate is used in the present disclosure to determine the displacement change by marker plate recognition. Then, in response to that there are at least a target number of marker plate information meeting the screening condition in the above marker plate information set, a member movement amount group is determined, wherein the screening condition is that the ratio of the marker plate effective area included in the marker plate information to the preset marker plate area is greater than a 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. In practice, since there is a large distance between the camera and the member, the environmental factors (for example, weather) will affect the image acquisition quality, therefore, in order to ensure the effectiveness of the determined displacement change, the screening condition and the target number are used to determine whether the member movement amount can be determined.Further, in response to the existence of camera offset, the component movement amount in the above component movement amount group is offset compensated according to the camera offset amount, to obtain a compensated component movement amount group. In practice, although the camera can be fixed by the fixed table, the vibration existing in the construction environment (such as the vibration caused by the movement of large engineering vehicles) can be conducted to the camera through the ground, and the camera offset caused by the vibration changes over time and accumulates, thereby forming the camera offset error affecting the component movement amount. Therefore, when the camera offset exists, the component movement amount needs to be compensated according to the camera offset. Finally, in response to the existence of the compensated component movement amount greater than the early warning threshold in the above compensated component movement amount group, the component displacement early warning is initiated. In summary, the displacement monitoring of the high-altitude cantilever component is realized in an automatic and effective manner through the above method.

[0106] Further, the present disclosure provides a construction displacement monitoring system, which is applied to Figure 1 Specifically, refer to the system architecture schematic diagram of the construction displacement monitoring system shown in Figure 6 Specifically, refer to the system architecture schematic diagram of the construction displacement monitoring system shown in

[0107] The vibration sensor array, wherein the vibration sensors in the vibration sensor array are arranged around the high-altitude cantilever component in a ring shape.

[0108] The first camera and the corresponding matrix type marker plate, wherein the first camera faces the corresponding matrix type 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 in a ring shape on the ground where the main structure is located, so as to realize real-time vibration signal acquisition.

[0109] The second camera and the corresponding matrix type marker plate, wherein the matrix type marker plate is fixed to the component bottom surface of the high-altitude cantilever component, and the first camera faces the corresponding matrix type marker plate. The first camera and the second camera are fixed on the fixed table at a preset included angle, and the fixed table is arranged below the high-altitude cantilever component. In particular, the fixed table can adopt a concrete pile body as the main structure. The fixed table can be embedded in the ground to ensure stability.

[0110] The first matrix type distance measuring sensor, wherein the relative position between the first matrix type distance measuring sensor and the first camera is fixed. In particular, the number and distribution of the distance measuring sensors included in the first matrix type distance measuring sensor are the same as the number and distribution of the marker plates included in the corresponding matrix type marker plate of the first camera.

[0111] The second matrix ranging sensor, wherein the relative position between the second matrix ranging sensor and the second camera is fixed. 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] The data processing component, wherein the data processing component is configured to process and analyze the signals and images collected by the sensors and cameras. In particular, the data processing component can interact and transmit data with 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, respectively. The data processing component can be the execution subject mentioned above.

[0113] Further referring to 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 applied to a high-altitude overhanging member, which correspond to the method embodiments shown in Figure 1 , the construction displacement monitoring device applied to a high-altitude overhanging member can be applied to various electronic devices.

[0114] As Figure 7As shown, the construction displacement monitoring device 700 applied to the high-altitude cantilever member of some embodiments comprises: an acquisition unit 701, a marker plate identification unit 702, a determination unit 703, an offset compensation unit 704, and a warning unit 705. Among them, the acquisition unit 701 is configured to collect a real-time image set in response to a real-time vibration signal representing that the ground vibration is greater than a preset vibration intensity or reaching 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 period, and the real-time images in the real-time image set are collected by a first camera and a second camera. The first camera and the second camera are respectively directed towards different image acquisition areas on the member bottom surface of the high-altitude cantilever member, and a matrix marker plate is fixedly arranged in each image acquisition area; the marker plate identification unit 702 is configured to identify the marker plate in each real-time image in the above-mentioned real-time image set 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 a member movement amount group in response to the presence of at least a target number of marker plate information satisfying a screening condition in the above-mentioned marker plate information set, wherein the screening condition is that the ratio of the marker plate effective area included in the marker plate information to the preset marker plate area is greater than a 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 member movement amount in the above-mentioned member movement amount group according to the camera offset amount in response to the presence of camera offset to obtain a compensated member movement amount group; the warning unit 705 is configured to initiate member displacement warning in response to the presence of a compensated member movement amount greater than a warning threshold in the above-mentioned compensated member movement amount group. It can be understood that the units recorded in the construction displacement monitoring device 700 applied to the high-altitude cantilever member are described with reference to Figure 1 The various steps in the described methods correspond. Thus, the operations, features, and resulting benefits described above for the method equally apply to the construction displacement monitoring device 700 applied to the high-altitude cantilever member and the units contained therein, which will not be repeated here.

[0115] Reference is made below to Figure 8 which shows a structural schematic diagram of an electronic device (e.g., a computing device) suitable for use to implement some embodiments of the present disclosure. Figure 8 The electronic device shown is merely an example and should not impose any limitation on the function and use range of the embodiments of the present disclosure. As Figure 8As shown, the computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory can include a non-volatile storage medium and an internal memory. The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions which, when executed, can cause the processor to perform 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 computer program in the non-volatile storage medium to run, which, when executed by the processor, can cause the processor to perform any of the above methods. The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand, Figure 8 The structure shown in the figure is only a block diagram of part of the structure related to the present disclosure, and does not constitute a limitation on the computer device to which the present disclosure is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0116] It should be understood that the processor can be a central processing unit (CPU), and the processor can also be 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. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0117] In one embodiment, the processor is configured to run a computer program stored in the memory to implement the following steps: in response to a real-time vibration signal representing that the ground vibration is greater than a preset vibration intensity or reaching 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 period, 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 towards different image acquisition areas on the bottom surface of the high-suspended cantilever member, and a matrix type marker plate is fixedly arranged in each image acquisition area; performing marker plate identification on each real-time image in the 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; in response to there being at least a target number of marker plate information meeting a screening condition in the marker plate information set, determining a member movement quantity group, wherein the screening condition is that the ratio of the marker plate effective area included in the marker plate information to a preset marker plate area is greater than a 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; in response to there being a camera offset, offset compensation is performed on the member movement quantity in the member movement quantity group according to the camera offset quantity to obtain a compensated member movement quantity group; and in response to there being a compensated member movement quantity greater than a warning threshold in the compensated member movement quantity group, initiating member displacement warning.

[0118] The embodiments of the present disclosure further provide a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program includes program instructions. The method implemented by the program instructions can refer to various embodiments of the method of the present disclosure.

[0119] The computer readable storage medium can be an internal storage unit of the computer device, for example, a hard disk or a memory of the computer device. The computer readable storage medium can also be an external storage device of the computer device, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0120] It has to be understood that, in the present document, the terms "comprising", "including", "containing", or any other any other variant thereof are intended to cover a non-exclusive inclusion, such that processes, methods, articles, or systems that comprise, include or contain a list of elements, do not only include those elements, but can also include other elements not expressly listed or inherent to such processes, methods, articles, or systems. Without further limitation, an element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or system that includes the element.

[0121] The above description is merely exemplary of some embodiments of the present disclosure and of the application principles so as to appreciate the inventive aspects of the present disclosure. It is, therefore, to be understood that the inventive concepts disclosed herein are not limited to the particular embodiments described above and illustrated in the drawings, which are for exemplary purposes only. Accordingly, the scope of the present disclosure is not intended to be limited to the particular embodiments disclosed but is meant to cover all suitable structures described herein and equivalents thereof, which are within the scope of the inventive concepts disclosed herein.

Claims

1. A method for monitoring construction displacement of cantilevered structural members, characterized in that, include: In response to the real-time vibration signal indicating that the ground vibration is greater than the preset vibration intensity or reaches the image acquisition time point, a real-time image group is acquired. 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 facing different image acquisition areas on the bottom surface of the high-altitude cantilever component. A matrix-type marker plate is fixedly set in each image acquisition area. Each real-time image in the real-time image group is identified by a marker board to obtain a marker board information set, wherein the marker board information includes: marker board identifier, marker board position, and effective area of ​​the marker board; In response to the existence of at least a target number of marker information that meet the filtering conditions in the marker information set, a component movement amount group is determined, wherein the filtering conditions are: the ratio of the effective area of ​​the marker included in the marker information to the preset marker area is greater than the preset area ratio, and there is a positional offset between the position of the marker included in the marker information and the corresponding initial marker position; In response to the presence of camera offset, offset compensation is performed on the component movement amount in the component movement amount group according to the camera offset amount to obtain the compensated component movement amount group; In response to the presence of a component displacement exceeding the warning threshold in the compensated component displacement group, a component displacement warning is initiated.

2. The method according to claim 1, characterized in that, The method further includes: In response to the absence of at least a target number of marker information that meet the screening criteria in the marker information set, real-time particulate matter concentration is collected by a dust sensor, and real-time humidity is collected by 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, occlusion identification is performed on each real-time image in the real-time image group to generate occlusion information, wherein the occlusion information includes: occlusion type and occlusion confidence level; In response to the presence of an obstruction indicated by obstruction information, a delay timer is set, wherein the delay timer is used to control the first camera and the second camera to re-acquire images after a delay, and the timing interval of the delay timer is less than the image acquisition period; In response to the occlusion information indicating that there is no occlusion, an anomaly warning is issued for the marker board.

3. The method according to claim 2, characterized in that, The step of determining the component movement group in response to the existence of at least a target number of marker information pieces that meet the filtering conditions in the marker information set includes: A set of real-time distance values ​​is collected, wherein the real-time distance value sets are composed in matrix form, and the real-time distance values ​​in the set are obtained by measuring distances by a first matrix ranging sensor and a second matrix ranging sensor. The relative positions between the first matrix ranging sensor and the first camera are fixed, and the relative positions between the second matrix ranging sensor and the second camera are also fixed. Based on the relative positions of the first matrix ranging sensor and the first camera, the relative positions of the second matrix ranging sensor and the second camera, and the marker information set, the real-time distance values ​​in the real-time distance value set are matched with the marker information in the marker information set to obtain a matching information set, wherein the matching information includes: marker identification group, real-time longitudinal distance value, and longitudinal calibration distance value; For each matching piece of information in the matching information set, perform the following processing steps: The amount of lateral component movement is determined based on the marker interval between two markers corresponding to the marker group included in the matching information. 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; The lateral component movement amount and the longitudinal component movement amount are determined as the component movement amount in the component movement amount group that corresponds to the matching information.

4. The method according to claim 3, characterized in that, In response to camera offset, the component movement amount in the component movement amount group is offset compensated according to the camera offset amount, to obtain a compensated component movement amount group, including: The camera offset is decomposed to obtain the horizontal camera offset and the vertical camera offset; Based on the horizontal and vertical camera offsets, the horizontal offset compensation and vertical offset compensation are applied to the movement of each component in the component movement group to generate the compensated component movement, thus obtaining the compensated component movement group.

5. The method according to claim 4, characterized in that, The step of performing marker identification on each real-time image in the real-time image group to obtain a marker information set includes: The real-time image is enhanced to obtain the enhanced image; The image difference between the enhanced image and the preset solid color image is determined to obtain a difference image, wherein the image size of the preset solid color image is the same as the image size of the enhanced image, and the color value corresponding to the preset solid color image is a preset color value; Edge detection with an adaptive threshold is performed on the difference image to obtain an initial set of detection regions, where the initial detection regions are closed regions; Based on the region boundary length and region type corresponding to the initial detection region, the initial detection regions that meet the region selection conditions are selected from the set of initial detection regions and used as the target detection regions. Set the color value of the region outside the target detection area in the enhanced image to 0 to obtain the updated image; The updated image is subjected to label recognition using a pre-trained label recognition model to obtain the label information set.

6. The method according to claim 5, characterized in that, The step of identifying occlusions in each real-time image in the real-time image group to generate occlusion information includes: Based on the marker information, including marker identifiers and marker positions, in the marker information set, a region of interest is constructed; The direction of the obstruction is determined based on the effective area of ​​the markers included in the marker information set. Occlusion information is generated based on the pre-trained occlusion recognition model, the real-time image, the region of interest, and the occlusion orientation. The occlusion orientation is used to control the scanning direction of the convolution kernel. Regions in the real-time image outside the region of interest correspond to random probabilities, and the random probabilities are used to control the probability of setting features to zero before convolution.

7. A construction displacement monitoring system, applied to the method described in 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 cantilever component; A first camera and a corresponding matrix marker board, wherein the first camera faces the corresponding matrix marker board; The second camera and the corresponding matrix marking plate are fixed to the bottom surface of the high-altitude cantilever component. The first camera faces the corresponding matrix marking plate. The first camera and the second camera are fixed at a preset angle on the fixed platform, which is located below the high-altitude cantilever component. A first matrix ranging sensor, wherein the relative position between the first matrix ranging sensor and the first camera is fixed; The second matrix ranging sensor, wherein the relative position between the second matrix ranging sensor and the second camera is fixed; A data processing component, which is used to process and analyze the signals and images acquired by sensors and cameras.

8. A construction displacement monitoring device for high-altitude cantilever 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 the ground vibration is greater than a preset vibration intensity or reaches an image acquisition time point. 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 facing different image acquisition areas on the bottom surface of the high-altitude cantilever component. A matrix-type marker plate is fixedly set in each image acquisition area. The marker recognition unit is configured to perform marker recognition on each real-time image in the real-time image group to obtain a marker information set, wherein the marker information includes: marker identifier, marker position and effective area of ​​marker; The determining unit is configured to determine a component movement group in response to the existence of at least a target number of marker information that meet the filtering conditions in the marker information set, wherein the filtering conditions are: the ratio of the effective area of ​​the marker included in the marker information to the preset marker area is greater than the preset area ratio and there is a positional offset between the position of the marker included in the marker information and the corresponding initial marker position; An offset compensation unit is configured to compensate for the component movement in the component movement group based on the camera offset amount in response to the presence of camera offset, so as to obtain a compensated component movement group. The 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 compensated component movement amount group.

9. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6 and the construction displacement monitoring system as described in claim 7.

10. A computer-readable medium, characterized in that, It stores a computer program, wherein the computer program, when executed by a processor, implements the method as described in any one of claims 1 to 6 and the construction displacement monitoring system as described in claim 7.

Images