Building settlement monitoring method and device, and storage medium

Abstract

The present application relates to a building settlement monitoring method and device, and a storage medium. The method comprises: on the basis of a central monitoring video, obtaining a central settlement pixel time-history signal; then, on the basis of the central settlement pixel time-history signal, determining a proportionality factor; then on the basis of an integral monitoring video, obtaining an integral settlement pixel time-history signal; and finally, on the basis of the proportionality factor and the integral settlement pixel time-history signal, obtaining a target building settlement time-history signal.

Description

Building settlement monitoring method, equipment and storage medium

[0001] Related applications

[0002] This application claims priority to Chinese patent application No. 202410022462.7 filed on January 8, 2024, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the technical field of static settlement monitoring, and in particular to a building settlement monitoring method, device and storage medium. Background Art

[0004] Vision-based static settlement monitoring technology uses cameras or camera systems to monitor whether buildings or structures are settling. It has the advantages of high measurement accuracy, long monitoring distance, no need for direct contact with the measured object, and low monitoring costs. Compared with traditional measurement methods, it has a wider range of application scenarios and technical advantages. When applied to actual engineering settlement monitoring of building structures, vision-based static settlement monitoring technology requires the calculation of physical quantity conversion parameters (proportional factors). However, the existing calculation of physical quantity conversion parameters is not accurate enough, resulting in low measurement accuracy of building settlement.

[0005] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of this application is to provide a building settlement monitoring method, device and storage medium to obtain an accurate proportional factor, thereby improving the accuracy of building settlement monitoring.

[0007] To achieve the above objectives, the present application provides a building settlement monitoring method, which comprises the following steps:

[0008] Obtaining a central sedimentation pixel time course signal based on a central monitoring video, wherein the central monitoring video is a video shot with a preset marker as the center of the field of view;

[0009] determining a scaling factor according to the central sedimentation pixel time course signal;

[0010] Frame the overall monitoring video to obtain an overall frame set, wherein the frames in the overall frame set are arranged in chronological order, and the overall monitoring video is a video shot with the building as the center of the field of view;

[0011] Sequentially acquiring frames from the overall frame set as overall tracking templates, and removing the overall tracking templates from the overall frame set to obtain an overall matching video;

[0012] Normalizing the overall tracking template and the overall matching video respectively to obtain multiple normalized overall templates and multiple normalized overall videos;

[0013] Determining a plurality of overall mapping matrices according to the plurality of normalized overall templates and the plurality of normalized overall videos;

[0014] Selecting a maximum value corresponding to each overall mapping matrix from the plurality of overall mapping matrices to obtain a second maximum value set, and obtaining an overall sedimentation pixel time course signal based on the second maximum value set;

[0015] A target building settlement time-history signal is obtained according to the proportional factor and the overall settlement pixel time-history signal.

[0016] In addition, to achieve the above-mentioned purpose, the present application also proposes a building settlement monitoring device, which includes: a building settlement monitoring device, a memory, a processor, and a building settlement monitoring program stored in the memory and executable on the processor, wherein the building settlement monitoring program is configured to implement the steps of the building settlement monitoring method described above, and the building settlement monitoring device includes:

[0017] a center signal acquisition module configured to obtain a center sedimentation pixel time course signal based on a center monitoring video, wherein the center monitoring video is a video shot with a preset marker as the center of the field of view;

[0018] a scale determination module configured to determine a scale factor according to the central settlement pixel time course signal;

[0019] an overall signal module configured to obtain an overall settlement pixel time course signal based on an overall monitoring video, wherein the overall monitoring video is a video shot with the building as the center of the field of view;

[0020] The target signal module is configured to obtain a target building settlement time-course signal according to the proportional factor and the overall settlement pixel time-course signal.

[0021] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a building settlement monitoring program is stored. When the building settlement monitoring program is executed by a processor, the steps of the building settlement monitoring method described above are implemented.

[0022] This application obtains a central settlement pixel time-course signal based on the central monitoring video, then determines a proportional factor based on the central settlement pixel time-course signal, and then obtains an overall settlement pixel time-course signal based on the overall monitoring video, and finally obtains a target building settlement time-course signal based on the proportional factor and the overall settlement pixel time-course signal. This application obtains a central settlement pixel time-course signal and an overall settlement pixel time-course signal by analyzing videos shot with a preset marker as the center of the field of view and with a building as the center of the field of view, respectively, and obtains a proportional factor through the central settlement pixel time-course signal, thereby achieving high-precision calibration of the proportional factor. Furthermore, the target building settlement time-course signal is obtained through the proportional factor and the overall settlement pixel time-course signal, thereby improving the monitoring accuracy of building settlement. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] FIG1 is a schematic diagram of the structure of a building settlement monitoring device according to a hardware operating environment of an embodiment of the present application;

[0024] FIG2 is a flow chart of an embodiment of a method for monitoring building settlement according to the present application;

[0025] FIG3 is a flow chart of an embodiment of a method for monitoring building settlement according to the present application;

[0026] FIG4 is a schematic diagram of a sub-process in an embodiment of a building settlement monitoring method of the present application;

[0027] FIG5 is a schematic diagram of another sub-process in an embodiment of the building settlement monitoring method of the present application;

[0028] FIG6 is a schematic diagram of another sub-process in an embodiment of the building settlement monitoring method of the present application;

[0029] FIG7 is a schematic diagram of another sub-process in an embodiment of the building settlement monitoring method of the present application;

[0030] FIG8 is a schematic diagram of another sub-process in an embodiment of the building settlement monitoring method of the present application;

[0031] FIG9 is a structural block diagram of an embodiment of a building settlement monitoring device of the present application.

[0032] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0033] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0034] Refer to Figure 1, which is a schematic diagram of the structure of a building settlement monitoring device in the hardware operating environment involved in an embodiment of the present application.

[0035] As shown in Figure 1, the building settlement monitoring device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may include a standard wired interface and a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0036] Those skilled in the art will understand that the structure shown in FIG1 does not constitute a limitation on the building settlement monitoring equipment, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0037] As shown in FIG1 , the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a building settlement monitoring program.

[0038] In the building settlement monitoring device shown in Figure 1, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the building settlement monitoring device of the present application can be set in the building settlement monitoring device, and the building settlement monitoring device calls the building settlement monitoring program stored in the memory 1005 through the processor 1001, and executes the building settlement monitoring method provided in the embodiment of the present application.

[0039] An embodiment of the present application provides a method for monitoring building settlement. Referring to FIG. 2 , FIG. 2 is a flow chart of an embodiment of the method for monitoring building settlement of the present application.

[0040] In this embodiment, the building settlement monitoring method includes the following steps:

[0041] Step S1: obtaining a central sedimentation pixel time course signal based on a central monitoring video, wherein the central monitoring video is a video shot with a preset marker as the center of the field of view;

[0042] It should be noted that the execution subject of the method of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a mobile phone, tablet computer, personal computer, etc., or other electronic devices capable of performing the same or similar functions. The building settlement monitoring device described above is used here to specifically illustrate the building settlement monitoring method provided in this embodiment and the following embodiments.

[0043] Specifically, the center monitoring video is captured with a preset marker as the center of the camera's field of view and the camera is relatively close to the preset marker (compared to the distance between the building and the camera in the overall monitoring video). The camera's field of view refers to the range of view that the camera can monitor at its current position and angle (i.e., the range covered by the lens). The center settlement pixel time-course signal refers to the pixel time-course signal of the settlement change of the preset marker.

[0044] Furthermore, by recording and observing the changes in markers, the stability and safety of the building can be analyzed and predicted. In practical applications, different preset markers can be set according to different building structure types and building materials.

[0045] By analyzing the video shot with the preset marker as the center of the camera's field of view, the pixel time-course signal of the preset marker's settlement change is obtained, which is conducive to the subsequent determination of the accurate proportional factor, and thus helps to improve the efficiency and effectiveness of building settlement monitoring.

[0046] Step S2: determining a scaling factor according to the central subsidence pixel time course signal;

[0047] Specifically, the scale factor refers to a physical quantity conversion parameter used when calculating settlement monitoring for actual building structures. Compared to traditional building monitoring methods, calculating the scale factor allows cameras to detect building settlement without direct contact with the object being measured, increasing the monitoring distance and reducing monitoring costs.

[0048] Furthermore, the scaling factor is determined based on the time-course signal of the central settlement pixel, making the building settlement monitoring more accurate.

[0049] Step S3: obtaining an overall settlement pixel time course signal based on the overall monitoring video, wherein the overall monitoring video is a video shot with the building as the center of the field of view;

[0050] Specifically, the overall monitoring video is a video shot with the building as the center of the field of view (the building includes preset markers), and the overall settlement pixel time-series signal refers to the settlement change pixel time-series signal of the building (the building includes preset markers).

[0051] Furthermore, by analyzing the video shot with the building as the center of the field of view, the pixel time-course signal of the building's settlement change is obtained, which facilitates the subsequent prediction and further analysis of the building's settlement.

[0052] Step S4: obtaining a target building settlement time-history signal according to the scale factor and the overall settlement pixel time-history signal;

[0053] Specifically, based on the precise proportional factor and the building's settlement change pixel time-series signal, a more precise building settlement change pixel time-series signal (target building settlement time-series signal) can be determined. By analyzing the target building settlement time-series signal, the precise building settlement situation can be obtained, thereby realizing accurate monitoring of building settlement.

[0054] Furthermore, the target building settlement time history signal can be expressed as: f(t) = ΔH(t) × SF true

[0055] Where f(t) represents the time-history signal of the target building settlement, ΔH(t) is the time-history signal of the preset marker, and SF true is the scale factor.

[0056] This application obtains a central settlement pixel time-course signal based on the central monitoring video, then determines a proportional factor based on the central settlement pixel time-course signal, and then obtains an overall settlement pixel time-course signal based on the overall monitoring video, and finally obtains a target building settlement time-course signal based on the proportional factor and the overall settlement pixel time-course signal. This application obtains a central settlement pixel time-course signal and an overall settlement pixel time-course signal by analyzing the video shot with a preset marker as the center of the field of view and the video shot with the building as the center of the field of view respectively, obtains the proportional factor through the central settlement pixel time-course signal, and realizes high-precision calibration of the proportional factor. Then, the target building settlement time-course signal is obtained through the proportional factor and the overall settlement pixel time-course signal, thereby improving the monitoring accuracy of building settlement and realizing accurate monitoring of building settlement.

[0057] Please refer to FIG3 , which is a flow chart of an embodiment of a building settlement monitoring method of the present application.

[0058] Based on the above embodiment, in this embodiment, before step S1, the following steps are further included:

[0059] S1a: Determining the pixel size of the preset marker according to the short video of the marker, wherein the short video of the marker is a dynamic video of the preset marker within a short period of time;

[0060] S1b: determining a range of the scale factor according to the actual size of the preset marker and the pixel size of the preset marker;

[0061] Specifically, a pre-set marker is attached to the surface of a building, and a short video of the marker is taken from a distance from the building to obtain a short video of the marker. It should be noted that a short time refers to a few tens of seconds, which can be 10s or 20s, and there is no specific limitation here.

[0062] Furthermore, the actual size of the preset marker is known. Based on the short video of the marker, the pixel size of the preset marker can be measured, and then the numerical range of the scale factor can be determined according to the scale factor formula. The specific calculation formula of the scale factor is as follows:

[0063] Where D is the actual size of the feature marker, I is the pixel size of the feature marker, and SF is the scale factor.

[0064] Then determine the numerical range of the scale factor: [SF lower ,SF upper ].

[0065] in,

[0066] Furthermore, by presetting the actual size and pixel size of the marker and determining the range of the scale factor, it is beneficial to further determine the precise value of the scale factor, thereby improving the accuracy of building settlement monitoring.

[0067] Please refer to FIG4 , which is a schematic diagram of a sub-process in an embodiment of the building settlement monitoring method of the present application;

[0068] Based on the above embodiment, in this embodiment, step S1 includes:

[0069] S11: Frame the central monitoring video to obtain a central frame set, wherein the frames in the central frame set are arranged in chronological order;

[0070] S12: sequentially obtaining frames in the central frame set as central tracking templates, and removing the central tracking templates from the central frame set to obtain a central matching video;

[0071] S13: Normalizing the center tracking template and the center matching video respectively to obtain multiple normalized center templates and multiple normalized center videos;

[0072] S14: constructing multiple center mapping matrices according to the multiple normalized center templates and the multiple normalized center videos;

[0073] S15: selecting a maximum value corresponding to each center mapping matrix from the plurality of center mapping matrices to obtain a first maximum value set, and obtaining the center subsidence pixel time course signal based on the first maximum value set;

[0074] Specifically, step a: for a video shot with a preset marker as the center of the field of view, use the first frame of the time sequence image as the center tracking template T, and perform normalization processing on T and the remaining time sequence images I to obtain T' and I':

[0075] Step b, calculate the mapping relationship matrix R: the normalized center template T' slides from left to right and from top to bottom on the normalized center video I', moving one pixel position each time and calculating the mapping value of the position, and finally calculating the mapping matrix R of the preset marker area:

[0076] Where: (x, y) is the coordinate of a point on the normalized central video; (x', y') is the coordinate of the normalized central template image; T(x, y) is the central tracking template, and a point (x, y) on the mapping matrix R(x, y) represents the correlation between the image sub-block with (x, y) as the upper left corner point in the normalized central video I' and the same size as the central tracking template image T(x, y) and T(x, y).

[0077] Step c: Select the position with the maximum value of the mapping matrix as the matching result, and repeat the above steps ac for all frames in the center monitoring video. Finally, the center subsidence pixel time course signal f(t) is obtained.

[0078] Furthermore, by normalizing each frame in the central monitoring video with the remaining frames to construct multiple mapping matrices, the central settlement pixel time-series signal is obtained (the maximum value corresponding to each mapping matrix represents a point on the central settlement pixel time-series signal), which facilitates the subsequent determination of the accurate value of the proportional factor and improves the accuracy of building settlement monitoring.

[0079] Please refer to FIG5 , which is a schematic diagram of another sub-process in an embodiment of the building settlement monitoring method of the present application.

[0080] Based on the above embodiment, in this embodiment, step S2 includes:

[0081] S21: determining the displacement range of the preset marker in the direction of gravity according to the range of the scale factor;

[0082] S22: Obtaining a time displacement change curve according to the displacement range of the preset marker in the gravity direction;

[0083] S23: Comparing the central subsidence pixel time course signal with the time displacement change curve to obtain a subsidence change value, and using the absolute value of the subsidence change value as the proportional factor;

[0084] Step S23 includes:

[0085] S231: traversing the central subsidence pixel time course signal, obtaining the moment when the first pixel change amount in the central subsidence pixel time course signal reaches a preset pixel value, and using the moment as the initial moment;

[0086] S232: determining the displacement corresponding to the initial moment in the time displacement change curve, taking the displacement corresponding to the initial moment as the settlement change value, and taking the absolute value of the settlement change value as the scale factor;

[0087] Specifically, the preset marker is attached to the preset calibration device, which is then bonded to the original marker location / settlement monitoring point. The preset calibration device is a tool for measuring building settlement, ensuring that the measured object remains horizontal or vertical, providing high measurement accuracy.

[0088] Follow these steps to determine the scale factor:

[0089] Step A: According to the range of the scale factor determined in the above embodiment, determine the displacement change of the preset marker in the direction of gravity controlled by the preset calibration device: [0, SF upper -SF lower ].

[0090] Step B: Control the preset calibration device to gradually fine-tune the displacement change of the preset marker in the direction of gravity from 0 to SFupper-SFlower, and record the time and displacement change value of each fine-tuning to obtain the time-displacement change curve.

[0091] Step C: traverse and search the initial moment K of the settlement in which the pixel change value is 1 in the central settlement pixel time course signal f(t) t By comparing it with the time displacement change curve, we can get the K when one pixel changes. t The settlement change value corresponding to the moment, the absolute value of this value is the exact value of the proportional factor SF true .

[0092] Furthermore, the present application determines the displacement of a preset marker in the direction of gravity through the range of a proportional factor, and then obtains a time displacement change curve based on this displacement, thereby achieving a quantitative assessment of building settlement through pixel size changes in video images, thereby improving the convenience and accuracy of building settlement monitoring. The present application uses the absolute value of the displacement corresponding to the initial moment in the time displacement change curve as the proportional factor, making the value of the proportional factor more accurate, thereby making the subsequent target building settlement signal more precise, thereby improving the accuracy of building settlement monitoring.

[0093] Please refer to FIG6 , which is a schematic diagram of another sub-process in an embodiment of the building settlement monitoring method of the present application.

[0094] Based on the above embodiment, in this embodiment, step S3 includes:

[0095] S31: Divide the entire detection video into frames to obtain an entire frame set, wherein the frames in the entire frame set are arranged in chronological order;

[0096] S32: sequentially acquiring frames in the overall frame set as an overall tracking template, and removing the overall tracking template from the overall frame set to obtain an overall matching video;

[0097] S33: performing normalization processing on the overall tracking template and the overall matching video respectively to obtain multiple normalized overall templates and multiple normalized overall videos;

[0098] S34: determining a plurality of overall mapping matrices according to the plurality of normalized overall templates and the plurality of normalized overall videos;

[0099] S35: selecting a maximum value corresponding to each overall mapping matrix from the plurality of overall mapping matrices to obtain a second maximum value set, and obtaining the overall sedimentation pixel time course signal based on the second maximum value set;

[0100] In one embodiment, as shown in FIG7 , FIG7 is a schematic diagram of another sub-process in one embodiment of the building settlement monitoring method of the present application, step S34 includes:

[0101] S341: constructing multiple similarity matrices according to the multiple normalized overall templates and the multiple normalized overall videos;

[0102] S342: reconstructing the plurality of similarity matrices according to a preset reconstruction method to obtain a plurality of reconstructed matrices, and using the plurality of reconstructed matrices as the plurality of overall mapping matrices;

[0103] It should be noted that the overall detection video is a video shot of the building from the far end of the building.

[0104] As shown in FIG8 , FIG8 is a schematic diagram of another sub-process in an embodiment of the building settlement monitoring method of the present application, and the steps of the overall settlement pixel time course signal are as follows:

[0105] Sa1: Select the first beam image frame of the overall detection video and use it as the overall tracking template T. The remaining frames of the overall detection video are used as the original image I.

[0106] Sa2: Normalize the overall tracking template T and the original image I to obtain T' and I':

[0107] Among them, w1, h1 are the sizes of the overall tracking template, w2, h2 are the image sizes of the original video; T′ and I′ are the normalized overall tracking template and the original video, respectively.

[0108] Step Sa3: T′ slides on I′ from left to right and from top to bottom, moving one pixel position each time and calculating the mapping value of the position, and finally calculating the similarity matrix R:

[0109] Where: (x, y) is the coordinate of a point on the normalized overall video; (x', y') is the coordinate of the overall tracking template image; T(x, y) is the overall tracking template image, with an image size of w×h; a point (x, y) on the mapping matrix R(x, y) represents the correlation between the image sub-block with (x, y) as the upper left corner point in the normalized overall video I' and the same size as the overall tracking template image T(x, y) and T(x, y).

[0110] Step Sa4: Perform matrix reconstruction processing on the mapping matrix R(x, y) to obtain a reconstructed matrix R'(x, y).

[0111] (1) Decompose the coordinates (x, y) into the integer parts x0, y0 and the decimal parts dx, dy. The following relationship holds: x = x0 + dx, y = y0 + dy

[0112] (2) Take 16 adjacent pixels centered at (x0, y0) and mark them as I(x i ,y i ), where i, j = 0, 1, 2, 3.

[0113] (3) Reconstruct the mapping relationship matrix:

[0114] in, a is a parameter to be determined.

[0115] Step Sa5: Select the position of the maximum value of the mapping matrix as the matching result, output the position index of the matching result as the vibration position tracking result, and repeat the above matching process for all frames in the entire detection video. Calculate the overall sedimentation pixel time course signal

[0116] Step Sa6: Calculate the overall sedimentation pixel time course signal:

[0117] Where n is the number of image frames, Hi and Li are the width position and height position of the vibration position tracking result output of the i-th frame image, respectively.

[0118] In this embodiment, by normalizing each frame in the overall monitoring video with the remaining frames to construct multiple mapping matrices, the overall settlement pixel time-course signal is obtained (the maximum value corresponding to each mapping matrix represents a point on the overall settlement pixel time-course signal). This improves the accuracy of the overall settlement pixel time-course signal, thereby improving the accuracy of building settlement monitoring. By constructing a similarity matrix and performing matrix reconstruction, the overall mapping matrix is ​​made more accurate, thereby improving the accuracy of the overall settlement pixel time-course signal, thereby improving the accuracy of building settlement monitoring.

[0119] This application obtains a central settlement pixel time-course signal based on the central monitoring video, then determines a proportional factor based on the central settlement pixel time-course signal, and then obtains an overall settlement pixel time-course signal based on the overall monitoring video, and finally obtains a target building settlement time-course signal based on the proportional factor and the overall settlement pixel time-course signal. This application obtains a central settlement pixel time-course signal and an overall settlement pixel time-course signal by analyzing videos shot with a preset marker as the center of the field of view and with a building as the center of the field of view, respectively, and obtains a proportional factor through the central settlement pixel time-course signal, thereby achieving high-precision calibration of the proportional factor. Furthermore, the target building settlement time-course signal is obtained through the proportional factor and the overall settlement pixel time-course signal, thereby improving the monitoring accuracy of building settlement.

[0120] In addition, an embodiment of the present application further proposes a storage medium, on which a building settlement monitoring program is stored. When the building settlement monitoring program is executed by a processor, the steps of the building settlement monitoring method described above are implemented.

[0121] Refer to FIG. 9 , which is a structural block diagram of an embodiment of a building settlement monitoring device of the present application.

[0122] The building settlement monitoring device includes:

[0123] The center signal acquisition module 701 is used to obtain a center sedimentation pixel time course signal based on a center monitoring video, wherein the center monitoring video is a video shot with a preset marker as the center of the field of view;

[0124] A scale determination module 702 is configured to determine a scale factor based on the central subsidence pixel time course signal;

[0125] The overall signal module 703 is used to obtain an overall settlement pixel time course signal based on the overall monitoring video, wherein the overall monitoring video is a video shot with the building as the center of the field of view;

[0126] The target signal module 704 is configured to obtain a target building settlement time-history signal according to the scale factor and the overall settlement pixel time-history signal.

[0127] The central signal acquisition module 701 includes:

[0128] a central frame division unit, configured to divide the central monitoring video into frames to obtain a central frame set, wherein the frames in the central frame set are arranged in chronological order;

[0129] a center matching unit, configured to sequentially obtain frames from the center frame set as center tracking templates, and remove the center tracking templates from the center frame set to obtain a center matching video;

[0130] a center normalization unit, configured to perform normalization processing on the center tracking template and the center matching video respectively, to obtain a plurality of normalized center templates and a plurality of normalized center videos;

[0131] A center mapping unit, configured to construct a plurality of center mapping matrices according to the plurality of normalized center templates and the plurality of normalized center videos;

[0132] The central signal unit is configured to select a maximum value corresponding to each central mapping matrix from the plurality of central mapping matrices to obtain a first maximum value set, and obtain the central subsidence pixel time course signal based on the first maximum value set.

[0133] The ratio determination module 702 includes:

[0134] a displacement determining unit, configured to determine a displacement range of the preset marker in the direction of gravity according to a range of the scale factor;

[0135] a curve determining unit, configured to obtain a time displacement variation curve according to a displacement range of the preset marker in the direction of gravity;

[0136] The factor determination unit is used to compare the central sedimentation pixel time course signal with the time displacement change curve to obtain a sedimentation change value, and use the absolute value of the sedimentation change value as the proportional factor.

[0137] The overall signal module 703 includes:

[0138] an overall framing unit, configured to frame the overall detection video to obtain an overall frame set, wherein the frames in the overall frame set are arranged in chronological order;

[0139] an overall matching unit, configured to sequentially obtain frames from the overall frame set as overall tracking templates, and remove the overall tracking templates from the overall frame set to obtain an overall matching video;

[0140] an overall normalization unit, configured to perform normalization processing on the overall tracking template and the overall matching video respectively, to obtain a plurality of normalized overall templates and a plurality of normalized overall videos;

[0141] an overall mapping unit, configured to determine a plurality of overall mapping matrices according to the plurality of normalized overall templates and the plurality of normalized overall videos;

[0142] The overall signal unit is used to select the maximum value corresponding to each overall mapping matrix in the multiple overall mapping matrices to obtain a second maximum value set, and obtain the overall sedimentation pixel time course signal according to the second maximum value set.

[0143] In one embodiment, the central signal acquisition module 701 is further used to determine the pixel size of the preset marker based on the short video of the marker, wherein the short video of the marker is a dynamic video of the preset marker in a short period of time; and determine the range of the proportional factor based on the actual size of the preset marker and the pixel size of the preset marker.

[0144] In one embodiment, the proportion determination module 702 is also used to traverse the central sedimentation pixel time series signal, obtain the moment when the initial pixel change in the central sedimentation pixel time series signal is a preset pixel value, and use it as the initial moment; determine the displacement corresponding to the initial moment in the time displacement change curve, and use the displacement corresponding to the initial moment as the sedimentation change value, and use the absolute value of the sedimentation change value as the proportional factor.

[0145] In one embodiment, the overall signal module 703 is further used to construct multiple similarity matrices based on the multiple normalized overall templates and the multiple normalized overall videos; reconstruct the multiple similarity matrices according to a preset reconstruction method to obtain multiple reconstructed matrices, and use the multiple reconstructed matrices as the multiple overall mapping matrices.

[0146] This application obtains a central settlement pixel time-course signal based on the central monitoring video, then determines a proportional factor based on the central settlement pixel time-course signal, and then obtains an overall settlement pixel time-course signal based on the overall monitoring video, and finally obtains a target building settlement time-course signal based on the proportional factor and the overall settlement pixel time-course signal. This application obtains a central settlement pixel time-course signal and an overall settlement pixel time-course signal by analyzing videos shot with a preset marker as the center of the field of view and with a building as the center of the field of view, respectively, and obtains a proportional factor through the central settlement pixel time-course signal, thereby achieving high-precision calibration of the proportional factor. Furthermore, the target building settlement time-course signal is obtained through the proportional factor and the overall settlement pixel time-course signal, thereby improving the monitoring accuracy of building settlement.

[0147] Other embodiments or specific implementation methods of the building settlement monitoring device of the present application can refer to the above-mentioned method embodiments and will not be repeated here.

[0148] 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.

[0149] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0150] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0151] The above are merely optional embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A building settlement monitoring method, wherein, The building settlement monitoring method includes: Obtaining a central settlement pixel time - history signal based on a central monitoring video, where the central monitoring video is a video taken with a preset marker as the visual center; Determining a scale factor according to the central settlement pixel time - history signal; Framing an overall monitoring video to obtain an overall frame set, where the frames in the overall frame set are arranged in chronological order, and the overall monitoring video is a video taken with a building as the visual center; Sequentially obtaining the frames in the overall frame set as overall tracking templates, and removing the overall tracking templates from the overall frame set to obtain an overall matching video; Performing normalization processing on the overall tracking templates and the overall matching video respectively to obtain a plurality of normalized overall templates and a plurality of normalized overall videos; Determining a plurality of overall mapping matrices according to the plurality of normalized overall templates and the plurality of normalized overall videos; Selecting the maximum value corresponding to each overall mapping matrix in the plurality of overall mapping matrices to obtain a second maximum value set, and obtaining an overall settlement pixel time - history signal according to the second maximum value set; Obtaining a target building settlement time - history signal according to the scale factor and the overall settlement pixel time - history signal.

2. The building settlement monitoring method according to claim 1, wherein, Before obtaining the central settlement pixel time - history signal based on the central monitoring video, it further includes: Determining the pixel size of the preset marker according to a marker short - video, where the marker short - video is a dynamic video of the preset marker in a short period of time; Determining the range of the scale factor according to the actual size and the pixel size of the preset marker.

3. The building settlement monitoring method according to claim 2, wherein, The obtaining of the central settlement pixel time - history signal based on the central monitoring video includes: Framing the central monitoring video to obtain a central frame set, where the frames in the central frame set are arranged in chronological order; Sequentially obtaining the frames in the central frame set as central tracking templates, and removing the central tracking templates from the central frame set to obtain a central matching video; Performing normalization processing on the central tracking templates and the central matching video respectively to obtain a plurality of normalized central templates and a plurality of normalized central videos; Constructing a plurality of central mapping matrices according to the plurality of normalized central templates and the plurality of normalized central videos; and Selecting the maximum value corresponding to each central mapping matrix in the plurality of central mapping matrices to obtain a first maximum value set, and obtaining the central settlement pixel time - history signal according to the first maximum value set.

4. The building settlement monitoring method according to claim 3, wherein, The determining of the scale factor according to the central settlement pixel time - history signal includes: Determining the displacement range of the preset marker in the gravity direction according to the range of the scale factor; Obtaining a time - displacement change curve according to the displacement range of the preset marker in the gravity direction; and Comparing the central settlement pixel time - history signal with the time - displacement change curve to obtain a settlement change value, and taking the absolute value of the settlement change value as the scale factor.

5. The building settlement monitoring method according to claim 4, wherein, Comparing the central settlement pixel time - history signal with the time - displacement change curve to obtain a settlement change value, and taking the absolute value of the settlement change value as the scale factor, includes: Traversing the central settlement pixel time - history signal to obtain the moment when the initial pixel change amount in the central settlement pixel time - history signal is a preset pixel value, and taking it as the initial moment; Determining the displacement amount corresponding to the initial moment in the time - displacement change curve, taking the displacement amount corresponding to the initial moment as the settlement change value, and taking the absolute value of the settlement change value as the scale factor.

6. The building settlement monitoring method according to claim 1, wherein, The step of determining multiple overall mapping matrices according to the multiple normalized overall templates and the multiple normalized overall videos includes: Constructing multiple similarity matrices according to the multiple normalized overall templates and the multiple normalized overall videos; Reconstructing the multiple similarity matrices according to a preset reconstruction method to obtain multiple reconstruction matrices, and taking the multiple reconstruction matrices as the multiple overall mapping matrices.

7. The building settlement monitoring method according to claim 1, wherein, The step of obtaining the central settlement pixel time - history signal according to the central monitoring video further includes: For the video taken with a preset marker as the visual field center, using the first - frame time - series picture as the central tracking template, and performing normalization processing on the central tracking template and the other time - series pictures respectively; Calculating the mapping matrix of the preset marker area; and Selecting the position with the maximum value of the mapping matrix as the matching result, and repeating the above steps for all frames in the central monitoring video to obtain the central settlement pixel time - history signal.

8. The building settlement monitoring method according to claim 5, wherein, The preset marker is installed on a preset calibration device, the preset calibration device is bonded to the original preset marker pasting position or the settlement monitoring point, and the preset calibration device is a measurement tool for building settlement, configured to keep the measured object horizontal or vertical.

9. A building settlement monitoring device, wherein, The computer device includes a building settlement monitoring device, a memory, a processor, and a computer program stored on the memory and executable on the processor. The building settlement monitoring device is configured to implement a building settlement monitoring method, and the method includes: Obtaining a central settlement pixel time - history signal according to a central monitoring video, where the central monitoring video is a video taken with a preset marker as the visual field center; Determining a scale factor according to the central settlement pixel time - history signal; Obtaining an overall settlement pixel time - history signal according to an overall monitoring video, where the overall monitoring video is a video taken with a building as the visual field center; Obtaining a target building settlement time - history signal according to the scale factor and the overall settlement pixel time - history signal.

10. The building settlement monitoring device according to claim 9, wherein, The building settlement monitoring device includes: A central signal acquisition module, configured to obtain a central settlement pixel time - history signal according to a central monitoring video, where the central monitoring video is a video taken with the preset marker as the visual field center; A scale determination module, configured to determine a scale factor according to the central settlement pixel time - history signal; An overall signal module, configured to obtain an overall settlement pixel time - history signal according to an overall monitoring video, where the overall monitoring video is a video taken with a building as the visual field center; The target signal module is configured to obtain the target building settlement time history signal according to the scale factor and the overall settlement pixel time history signal.

11. The building settlement monitoring device according to claim 10, wherein, Before the central signal acquisition module is configured to obtain the central settlement pixel time history signal according to the central monitoring video, it is further configured to: Determine the pixel size of the preset marker according to the marker short video, where the marker short video is a dynamic video of the preset marker within a short period of time; Determine the range of the scale factor according to the actual size and the pixel size of the preset marker.

12. The building settlement monitoring device according to claim 11, wherein, The central signal acquisition module is further configured to: Frame the central monitoring video to obtain a central frame set, where the frames in the central frame set are arranged in chronological order; Successively obtain the frames in the central frame set as the central tracking template, and remove the central tracking template from the central frame set to obtain the central matching video; Normalize the central tracking template and the central matching video respectively to obtain a plurality of normalized central templates and a plurality of normalized central videos; Construct a plurality of central mapping matrices according to the plurality of normalized central templates and the plurality of normalized central videos; Select the maximum value corresponding to each central mapping matrix in the plurality of central mapping matrices to obtain a first maximum value set, and obtain the central settlement pixel time history signal according to the first maximum value set.

13. The building settlement monitoring device according to claim 11, wherein, The ratio determination module is further configured to: Determine the displacement range of the preset marker in the gravity direction according to the range of the scale factor; Obtain the time-displacement change curve according to the displacement range of the preset marker in the gravity direction; Compare the central settlement pixel time history signal with the time-displacement change curve to obtain the settlement change value, and take the absolute value of the settlement change value as the scale factor.

14. The building settlement monitoring device according to claim 13, wherein, The ratio determination module is further configured to: Traverse the central settlement pixel time history signal to obtain the moment when the initial pixel change amount in the central settlement pixel time history signal is the preset pixel value, and use it as the initial moment; Determine the displacement amount corresponding to the initial moment in the time-displacement change curve, and use the displacement amount corresponding to the initial moment as the settlement change value, and take the absolute value of the settlement change value as the scale factor.

15. The building settlement monitoring device according to claim 10, wherein, The overall signal module is further configured to: Frame the overall detection video to obtain an overall frame set, where the frames in the overall frame set are arranged in chronological order; Successively obtain the frames in the overall frame set as the overall tracking template, and remove the overall tracking template from the overall frame set to obtain the overall matching video; and Normalize the overall tracking template and the overall matching video respectively to obtain a plurality of normalized overall templates and a plurality of normalized overall videos.

16. The building settlement monitoring device according to claim 15, wherein, The overall signal module is further configured to: Determine a plurality of overall mapping matrices according to the plurality of normalized overall templates and the plurality of normalized overall videos; and Select the maximum value corresponding to each of the multiple overall mapping matrices to obtain a second maximum value set, and obtain the overall settlement pixel time history signal according to the second maximum value set.

17. The building settlement monitoring device according to claim 15, wherein, The overall signal module is further configured to: Construct a plurality of similarity matrices according to the plurality of normalized overall templates and the plurality of normalized overall videos; Reconstruct the plurality of similarity matrices according to a preset reconstruction method to obtain a plurality of reconstructed matrices, and use the plurality of reconstructed matrices as the plurality of overall mapping matrices.

18. The building settlement monitoring device according to claim 10, wherein, The central signal acquisition module is further configured to: For a video captured with a preset marker as the center of the field of view, use the first frame of the time-series image as the central tracking template, and perform normalization processing on the central tracking template and the remaining time-series images respectively; Calculate the mapping matrix of the preset marker area; And Select the position of the maximum value of the mapping matrix as the matching result, and repeat the above steps for all frames in the central monitoring video to obtain the central settlement pixel time history signal.

19. The building settlement monitoring device according to claim 14, wherein, The preset marker is installed on a preset calibration device, the preset calibration device is adhered to the original preset marker pasting position or the settlement monitoring point, and the preset calibration device is a measurement tool for building settlement, configured to keep the object to be measured horizontal or vertical.

20. A computer-readable storage medium, wherein, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, a building settlement monitoring method is implemented, and the method includes: Obtain a central settlement pixel time history signal according to a central monitoring video, where the central monitoring video is a video captured with a preset marker as the center of the field of view; Determine a scale factor according to the central settlement pixel time history signal; Obtain an overall settlement pixel time history signal according to an overall monitoring video, where the overall monitoring video is a video captured with a building as the center of the field of view; Obtain a target building settlement time history signal according to the scale factor and the overall settlement pixel time history signal.

Images