A photographic monitoring method for building deformation used in construction engineering

Abstract

The present application relates to the field of photogrammetry technology, and specifically to a method for photographic monitoring of building deformation for construction engineering, the method comprising: obtaining the spatial coordinates and grayscale values ​​of each load-bearing structure point of the building under multiple sampling rounds, and recording the load-bearing structure point as a target point; determining the comprehensive deviation of each target point under the current sampling round based on the change of the distance between the spatial coordinates of each target point under all adjacent sampling rounds, combined with the change of the grayscale value under all sampling rounds; determining the correlation transmission difference of each target point under the current sampling round based on the distribution characteristics of the spatial coordinates of each target point and multiple neighboring target points under the current sampling round; determining the correlation credibility of each target point under the current sampling round based on the comprehensive deviation and the correlation transmission difference of each target point; further determining the true deformation of each target point, and monitoring the deformation of the target point. The present application aims to improve the accuracy of building deformation measurement.

Description

Technical Field

[0001] The present application relates to the technical field of photogrammetry, and in particular to a method for photographic monitoring of building deformation used in construction projects. Background Art

[0002] In construction projects, buildings are affected by external factors, such as the construction stage, foundation conditions, natural disasters, etc., which cause a certain degree of deformation. Monitoring the deformation of buildings is not only related to the safety and service life of the building itself, but also involves the safety of personnel and the stability of the surrounding environment. However, with the acceleration of urbanization, the increase in high-rise buildings and complex structures has made it more difficult to monitor the deformation of buildings.

[0003] In the deformation monitoring of buildings, in addition to monitoring small and complex deformations, the cost of monitoring buildings also needs to be considered. Among them, UAV oblique photography is a monitoring method with high acquisition accuracy and low monitoring cost. It mainly uses oblique photography to triangulate each load-bearing structure point on the building, obtain the spatial information of the load-bearing structure point, and judge the deformation of the building through the spatial information of the load-bearing structure point in adjacent acquisition cycles. However, in the actual process, when using drones to measure the load-bearing structure points, it may be affected by factors such as ambient light and building occlusion, resulting in a deviation between the measured position and the actual position of the load-bearing structure point. At this time, when directly using the collected data to monitor the deformation of the building, it is easy to cause large errors in the measurement of building deformation. Summary of the invention

[0004] In view of the above, it is necessary to provide a building deformation photographic monitoring method for construction engineering, which improves the accuracy of building deformation measurement compared with traditional building deformation photographic monitoring methods.

[0005] The present invention discloses a method for monitoring building deformation through photography for construction projects using the following technical solutions:

[0006] An embodiment of the present application provides a method for photographic monitoring of building deformation for construction engineering, the method comprising the following steps:

[0007] Obtain the spatial coordinates and grayscale values ​​of each load-bearing structure point of the building under multiple sampling rounds, and record the load-bearing structure point as the target point;

[0008] Based on the change of the distance between the spatial coordinates of each target point in all adjacent sampling rounds and the change of the gray value in all sampling rounds, the comprehensive deviation of each target point in the current sampling round is determined;

[0009] Based on the distribution characteristics of the spatial coordinates of each target and multiple neighboring targets in the current sampling round, the correlation transfer difference of each target in the current sampling round is determined;

[0010] Determining the association credibility of each target in the current sampling round based on the comprehensive deviation and the association transfer difference of each target;

[0011] Based on the distance between the spatial coordinates of each target point in the current sampling round and the preset standard spatial coordinates, combined with the association credibility, the actual deformation amount of each target point is determined to perform target deformation monitoring.

[0012] In one embodiment, the comprehensive deviation is determined as follows:

[0013] The distance between the spatial coordinates of each target point in any two adjacent sampling rounds is used as the deformation amount of each target point between the two adjacent sampling rounds, and all deformation amounts corresponding to each target point are arranged in time sequence to form each deformation sequence;

[0014] Based on the difference between the grayscale values ​​of each target point in the current sampling round and the remaining sampling rounds, the grayscale trust weight of each target point in the current sampling round is determined;

[0015] For each target point, based on the change trend of the data in the deformation sequence of the target point, combined with the difference between the corresponding deformation of the target point in the current sampling round and the remaining deformations in the deformation sequence, the deformation deviation value of each target point in the current sampling round is determined;

[0016] The fusion result of the grayscale credible weight and deformation deviation value of each target in the current sampling round is used as the comprehensive deviation of each target in the current sampling round.

[0017] In one embodiment, the grayscale trustworthy weight is determined as follows:

[0018] Arrange the grayscale values ​​of each target point in all sampling rounds in time sequence to form each photometric sequence;

[0019] Calculate the mean of all data in the photometric sequence of each target point except the grayscale value in the current sampling round;

[0020] Calculate the difference between the grayscale value of each target point in the current sampling round and the mean value, and record it as the grayscale difference;

[0021] Based on the grayscale difference, the grayscale credible weight of each target in the current sampling round is obtained.

[0022] In one embodiment, the grayscale credible weight of each target point in the current sampling round is the reciprocal of the sum of the grayscale difference of each target point and a preset value greater than 0.

[0023] In one embodiment, the process of determining the deformation deviation value is as follows:

[0024] Calculate the difference between the deformation amount corresponding to each target point in the deformation sequence in the current sampling round and the mean of the remaining deformation amounts, which is recorded as the deformation difference;

[0025] The product of the trend strength of the deformation sequence of each target point and the deformation difference is taken as the deformation deviation value of each target point in the current sampling round.

[0026] In one embodiment, the process of determining the association transfer difference is:

[0027] For any target point, the spatial coordinates of the target point and multiple neighboring target points in the current sampling round form a displacement set of the target point;

[0028] Obtain a fitting straight line of all spatial coordinates in the displacement set of any target point, and use the distance between the spatial coordinate of any target point in the current sampling round and the fitting straight line as the association transfer difference of any target point in the current sampling round.

[0029] In one embodiment, any one target point and a plurality of neighboring target points are on the same column structure.

[0030] In one embodiment, the process of determining the association credibility is:

[0031] The cumulative value of the association transfer difference of each target point and a preset value greater than 0 is calculated, and the ratio of the comprehensive deviation to the cumulative value is used as the association credibility of each target point in the current sampling round.

[0032] In one embodiment, the process of determining the actual deformation is as follows:

[0033] Calculate the distance between the spatial coordinates of each target point in the current sampling round and the preset standard spatial coordinates, and record it as the measured deformation;

[0034] The product of the normalized value of the associated credibility of each target point and the measured deformation amount is taken as the actual deformation amount of each target point.

[0035] In one embodiment, the method for monitoring target deformation is as follows: obtaining a deformation threshold corresponding to each target point according to the building structure design specification, marking a target whose actual deformation is greater than or equal to the deformation threshold as a deformed target point, otherwise, marking it as a normal target point.

[0036] This application has at least the following beneficial effects:

[0037] This application adopts the UAV tilt measurement technology and uses triangulation to obtain the spatial position information and texture information of each target on the building, comprehensively analyzes the changes in the spatial coordinates and texture information of a single target under different sampling rounds, and obtains the comprehensive deviation to reflect the authenticity of the current deformation of the target;

[0038] Furthermore, according to the transmission characteristics of the deformation on the mechanical structure, combined with the distribution characteristics of the local target in space under a single sampling round, the correlation credibility is obtained to reflect the credibility of the target deformation;

[0039] Furthermore, the spatial coordinates of each target point during the design and planning of the building are combined to obtain the actual displacement of the target point, thereby measuring the deformation of the building. This solves the problem of low deformation measurement accuracy caused by external interference when directly using drone measurement data to analyze the deformation of the building in the traditional way. This application is mainly based on the photometric consistency assumption, the gradual change characteristics of the deformation of the building target point over time, and the transmission characteristics of the target point deformation in the structure, to achieve the adjustment of the measured deformation of each target point, so that it can more accurately reflect the real deformation of the building and improve the accuracy of the building deformation measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A flowchart of the steps of a building deformation photography monitoring method for construction engineering provided in this application;

[0042] Figure 2 This is a schematic diagram of the grayscale trust weight determination process;

[0043] Figure 3 The figure is a flow chart of determination of comprehensive deviation;

[0044] Figure 4 Schematic diagram of the process of obtaining the actual deformation. DETAILED DESCRIPTION

[0045] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. It should be understood that, unless otherwise specified, " / " means or.

[0047] It should also be noted that the terms "first" and "second" in the present application are used to distinguish similar objects rather than to describe a specific order or sequence.

[0048] The following is a detailed description of a specific scheme of a building deformation photographic monitoring method for construction engineering provided by the present application in conjunction with the accompanying drawings.

[0049] An embodiment of the present application provides a method for monitoring building deformation through photographing for construction projects. Specifically, the following method for monitoring building deformation through photographing for construction projects is provided. Figure 1 , the method comprises the following steps:

[0050] Step 1: Obtain the spatial coordinates and grayscale values ​​of each load-bearing structure point of the building under multiple sampling rounds, and record the load-bearing structure point as the target point.

[0051] The oblique photography method of drones is used to realize photographic monitoring of building deformation.

[0052] In one embodiment of the present application, a DJI Mavic Air2 is used as a drone platform, equipped with a multi-camera system, and the camera has automatic exposure control. A single lens of the camera is not less than 50 million pixels, and a single exposure can reach 200 million pixels.

[0053] In one embodiment of the present application, during the oblique photography of a drone, the load-bearing structure points in the building are marked by laser, and the load-bearing structure points are recorded as targets. The flight plan of the drone is set to: the flight altitude is 1.5 times the maximum height of the building to be measured, the heading overlap is 85%, and the lateral overlap is 75%. The spatial position information of each target point is obtained by triangulating each target point at different flight angles, wherein the spatial position information is the spatial coordinates of each target point in the world coordinate system, and the texture information of each target point is obtained at the same time, wherein the texture information is the average of the grayscale values ​​of each target point at all viewing angles, and the average of the grayscale values ​​of each target point at all viewing angles is recorded as the grayscale value of each target point.

[0054] In one embodiment of the present application, the sampling interval of the drone oblique photography is set to 1d, that is, the information of the building target is collected once at a fixed time every day, for example, 8 o'clock in the morning, and the number of samplings is 15. The values ​​of the sampling interval and the number of samplings are preset manually, and the implementer can set them according to the actual situation. This application does not impose any special restrictions.

[0055] Step 2: Based on the change in the distance between the spatial coordinates of each target point in all adjacent sampling rounds and the change in the grayscale value in all sampling rounds, the comprehensive deviation of each target point in the current sampling round is determined.

[0056] In construction projects, the target points on the building structure, that is, the load-bearing structure points, are the points where the building structures intersect. They mainly bear the weight of the structure and transfer it to the foundation, such as beams, columns, and plates. The deformation of the target point is a micro-gradient process, so the change in the spatial position of a single target point has a certain time extension. In addition, during the oblique photography of drones, the spatial measurement of a single target point is based on the photometric consistency assumption, that is, the texture information of the same target point remains consistent at all viewing angles. Therefore, ideally, the texture difference of a single target point over a time span should be small.

[0057] Therefore, the distance between the spatial coordinates of each target point in any two adjacent sampling rounds is used as the deformation of each target point between the two adjacent sampling rounds, and all deformations corresponding to each target point are arranged in time sequence to form each deformation sequence. The grayscale values ​​of each target point in all sampling rounds are arranged in time sequence to form each photometric sequence.

[0058] In one embodiment of the present application, the distance between the spatial coordinates under two sampling rounds is the Euclidean distance. As other implementation methods, on the basis of being able to measure the distance between the spatial coordinates under two sampling rounds, the implementer may adopt other existing technologies to measure the distance between the spatial coordinates under two sampling rounds, such as DTW distance, Manhattan distance, etc., and the present application does not impose any special restrictions.

[0059] Based on the changes in the data in the deformation sequence and photometric sequence of each target point, the comprehensive deviation of each target point in the current sampling round is determined. The specific steps are:

[0060] Step 2.1, based on the difference between the grayscale values ​​of each target in the current sampling round and the remaining sampling rounds, determine the grayscale trust weight of each target in the current sampling round.

[0061] Calculate the mean of all data in the photometric sequence of each target point except the grayscale value in the current sampling round;

[0062] Calculate the difference between the grayscale value of each target point in the current sampling round and the mean value, and record it as the grayscale difference;

[0063] The reciprocal of the sum of the grayscale difference and a preset value greater than 0 is used as the grayscale credible weight of each target point in the current sampling round;

[0064] In one embodiment of the present application, the grayscale difference is the absolute value of the difference between the two. As other implementation methods, on the basis of being able to describe the difference between the two, the difference can be calculated in other ways, such as a ratio relationship, etc., and the implementer can define it according to the actual situation.

[0065] The calculation formula of the grayscale credible weight of each target in the current sampling round is:

[0066] ; In the formula, represents the grayscale trust weight of the i-th target in the current sampling round, Represents the gray value of the i-th target in the current sampling round, It represents the mean of all data in the photometric sequence of the i-th target except the grayscale value in the current sampling round. α represents a preset value greater than 0. The purpose is to avoid the denominator being 0. The value of α is preset manually and can be set by the implementer. In one embodiment of the present application, the value of α is 0.1.

[0067] It should be noted that: if the target is disturbed by environmental factors when using drone oblique photography to collect relevant data of the target, the grayscale value collected for the target in the current sampling round will be significantly different from the grayscale value in other sampling rounds, and the grayscale trust weight of the target in the current sampling round is small, indicating that the relevant data of the target in the current sampling round is not trustworthy. The flow chart of determining the grayscale trust weight is as follows: Figure 2 shown.

[0068] Step 2.2, for each target point, based on the change trend of the data in the deformation sequence of the target point, combined with the difference between the corresponding deformation of the target point in the current sampling round and the remaining deformations in the deformation sequence, determine the deformation deviation value of each target point in the current sampling round.

[0069] The calculation formula for the deformation deviation value of each target point in the current sampling round is:

[0070] ; In the formula, It represents the deformation deviation value of the i-th target in the current sampling round. represents the trend strength of the deformation sequence of the i-th target, The difference between the deformation amount corresponding to the i-th target point in the deformation sequence in the current sampling round and the mean of the remaining deformation amounts is recorded as the deformation difference, wherein the calculation of the trend strength is a well-known technology and will not be described in detail in this application.

[0071] In one embodiment of the present application, the deformation difference is the absolute value of the difference between the two. As other implementation methods, on the basis of being able to describe the difference between the two, the difference can be calculated in other ways, such as a ratio relationship, etc. The implementer can define it according to the actual situation.

[0072] It should be noted that: since the deformation of the target is a gradual process, if the target is an interference point without deformation, the deformation of the target between the current sampling round and the previous sampling round is only caused by external interference. At this time, the data in the deformation sequence is basically zero, and there is no obvious trend growth. The value of the trend intensity is small, and the deformation deviation value of the target in the current sampling round is small.

[0073] Step 2.3, based on the grayscale credible weight and deformation deviation value of each target point in the current sampling round, determine the comprehensive deviation of each target point in the current sampling round.

[0074] The fusion result of the grayscale credible weight and deformation deviation value of each target in the current sampling round is used as the comprehensive deviation of each target in the current sampling round.

[0075] It should be understood that fusion refers to combining multiple independent variables in a way that enhances the overall effect, such as additive relationship, multiplicative relationship, etc. Implementers can define it according to actual conditions.

[0076] In one embodiment of the present application, the product of the grayscale credible weight and the deformation deviation value of each target point in the current sampling round is used as the comprehensive deviation of each target point in the current sampling round.

[0077] In another embodiment of the present application, the sum of the grayscale credible weight and the deformation deviation value of each target point in the current sampling round is used as the comprehensive deviation of each target point in the current sampling round.

[0078] It should be noted that: if the target point is the real deformation point of the building, the change of the spatial coordinates of the target point is a gradual process. Therefore, there is a certain growth trend in the deformation between adjacent sampling rounds, and the deformation deviation value of the target point in the current sampling round is relatively large; at the same time, if the target point is less disturbed by the outside world during the current round of oblique photography monitoring, the texture color of the target point remains basically consistent, indicating that the higher the credibility of the relevant data of the target point in the current sampling round, the greater the value of the comprehensive deviation of the target point in the current sampling round. The schematic diagram of the comprehensive deviation determination process is as follows Figure 3 shown.

[0079] Step 3, based on the distribution characteristics of the spatial coordinates of each target point and multiple neighboring target points in the current sampling round, combined with the comprehensive deviation of each target point, determine the association credibility of each target point in the current sampling round.

[0080] The comprehensive deviation of each target in the current sampling round can reflect the authenticity of the current deformation of the target. However, if the grayscale value of the real deformed target is not collected accurately, resulting in a large difference in grayscale between different sampling rounds, the value of the comprehensive deviation may be small and cannot accurately reflect the deformation of the target. Therefore, further analysis is required in combination with the situation of the target.

[0081] The real role of the target in the building structure is to bear the overall weight of the building and realize mechanical transmission. Therefore, the deformation of the target does not change independently, but has certain transmission characteristics in the mechanical structure. Generally, it is transmitted from bottom to top in the building structure, that is, when a single target on the building is deformed, it will cause the deformation of the mechanical transmission target above it.

[0082] Step 3.1, based on the distribution characteristics of the spatial coordinates of each target and multiple neighboring targets in the current sampling round, determine the association transfer difference of each target in the current sampling round.

[0083] In today's construction process, columns are generally vertical components that bear vertical loads from the upper structure. Therefore, for any target point, the targets on the column structure where the target point is located are arranged in ascending order according to the Euclidean distance between the target point and the target point, and the spatial coordinates of the previous preset number of targets and the target point in the current sampling round form the displacement set of the target point.

[0084] Obtaining a fitting straight line of all spatial coordinates in the displacement set of any target point, and taking the distance between the spatial coordinate of any target point in the current sampling round and the fitting straight line as the association transfer difference of any target point in the current sampling round;

[0085] In one embodiment of the present application, the value of the preset number is 10. The value of the preset number is preset manually and can be set by the implementer according to actual conditions. This application does not impose any special restrictions.

[0086] In one embodiment of the present application, the least squares method is used to obtain the fitting straight line. As other implementation methods, on the basis of being able to obtain the fitting straight line, the implementer may use other existing technologies to obtain the fitting straight line, such as the gradient descent method, etc., and the present application does not make any special restrictions.

[0087] Step 3.2, based on the comprehensive deviation and the association transfer difference of each target, determine the association credibility of each target in the current sampling round.

[0088] The calculation formula for the association credibility of each target in the current sampling round is:

[0089] ; In the formula, represents the association credibility of the i-th target in the current sampling round, and They respectively represent the comprehensive deviation and associated transfer difference of the ith target in the current round. α represents a preset value greater than 0 in order to avoid the denominator being 0. The value of α is preset manually and can be set by the implementer. In an embodiment of the present application, the value of α is 0.1.

[0090] It should be noted that: if the target is a real deformation target, based on the correlation characteristics of building deformation in mechanical structure, the deformation of the target in the vertical structure basically presents a linear distribution, that is, with the increase of height, the deformation of the target gradually increases, which is reflected in the spatial coordinates of the target. The target presents a linear distribution. Therefore, the closer the distance between the target and the fitting straight line, the more likely the target is a real deformation target, and the smaller the value of the correlation transfer difference.

[0091] If the target is greatly disturbed by environmental factors in the current sampling round, the credibility of the relevant data of the target in the current sampling round is not high, and the value of the comprehensive deviation is small; at the same time, the deviation between the target and the local target fitting line in the vertical direction is large, and the value of the associated transfer difference is large, then the associated credibility of the target in the current sampling round is small. If the target is a real deformation point, but is greatly disturbed by environmental factors during tilt measurement, the value of the comprehensive deviation of the target in the current sampling round is smaller than that of the normal deformation target, but due to the transferability of the target in the mechanical structure, the deviation between the target and the local target fitting line is small, and the value of the associated transfer difference is small, then the value of the associated credibility is large.

[0092] Step 4: Based on the distance between the spatial coordinates of each target point in the current sampling round and the preset standard spatial coordinates, combined with the association credibility, determine the actual deformation of each target point and perform target deformation monitoring.

[0093] The association credibility reflects the credibility of the spatial coordinates of the target point, and is further combined with the preset standard spatial coordinates to determine the actual displacement of each target point of the building in the current sampling round:

[0094] The distance between the spatial coordinates of each target point in the current sampling round and the preset standard spatial coordinates is calculated and recorded as the measured deformation. The product of the normalized value of the associated credibility of each target point in the current sampling round and the measured deformation is taken as the actual deformation of each target point.

[0095] Among them, the preset standard spatial coordinates of each target point are the spatial coordinates of each target point during building design and planning, which are obtained through the three-dimensional model of building design and planning.

[0096] In one embodiment of the present application, the distance between the spatial coordinates and the preset standard spatial coordinates is the Euclidean distance. As other implementation methods, based on the measurable distance between the spatial coordinates and the preset standard spatial coordinates, the implementer may use other existing technologies to measure the distance between the spatial coordinates and the preset standard spatial coordinates, such as DTW distance, Manhattan distance, etc. This application does not impose any special restrictions.

[0097] It should be noted that: if the target is a real deformation target, the normalized value of the associated credibility of the target is large and close to 1. At this time, the real deformation is close to the measured deformation, which can represent the real deformation information of the target; if the target is an interference target that is greatly disturbed by environmental factors, the normalized value of the associated credibility of the target is small, thereby reducing the measured deformation and reflecting the real deformation information of the target. The schematic diagram of the process of obtaining the real deformation is shown in the figure. Figure 4 shown.

[0098] According to the building structure design manual, the deformation threshold corresponding to each target point is obtained, and the target points whose actual deformation is greater than or equal to the deformation threshold are marked as deformed targets. Otherwise, they are marked as normal targets, and the deformed targets are fed back to the monitoring technicians to provide data support for their subsequent in-depth analysis.

[0099] In summary, this application adopts the UAV tilt measurement technology, uses triangulation to obtain the spatial position information and texture information of each target on the building, and comprehensively analyzes the changes in the spatial coordinates and texture information of a single target under different sampling rounds to obtain the comprehensive deviation, reflecting the authenticity of the current deformation of the target;

[0100] Furthermore, according to the transmission characteristics of the deformation on the mechanical structure, combined with the distribution characteristics of the local target in space under a single sampling round, the correlation credibility is obtained to reflect the credibility of the target deformation;

[0101] Furthermore, the spatial coordinates of each target point during the design and planning of the building are combined to obtain the actual displacement of the target point, thereby measuring the deformation of the building. This solves the problem of low deformation measurement accuracy caused by external interference when directly using drone measurement data to analyze the deformation of the building in the traditional way. This application is mainly based on the photometric consistency assumption, the gradual change characteristics of the deformation of the building target point over time, and the transmission characteristics of the target point deformation in the structure, to achieve the adjustment of the measured deformation of each target point, so that it can more accurately reflect the real deformation of the building and improve the accuracy of the building deformation measurement.

[0102] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0103] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive.

Claims

1. A building deformation photographic monitoring method for construction engineering, characterized in that: The method comprises the following steps: Obtain the spatial coordinates and grayscale values ​​of each load-bearing structure point of the building under multiple sampling rounds, and record the load-bearing structure point as the target point; Based on the change of the distance between the spatial coordinates of each target point in all adjacent sampling rounds and the change of the gray value in all sampling rounds, the comprehensive deviation of each target point in the current sampling round is determined; Based on the distribution characteristics of the spatial coordinates of each target and multiple neighboring targets in the current sampling round, the correlation transfer difference of each target in the current sampling round is determined; Determining the association credibility of each target in the current sampling round based on the comprehensive deviation and the association transfer difference of each target; Based on the distance between the spatial coordinates of each target point in the current sampling round and the preset standard spatial coordinates, combined with the correlation credibility, the actual deformation amount of each target point is determined to monitor the deformation of the target point; The determination process of the comprehensive deviation is: The distance between the spatial coordinates of each target point in any two adjacent sampling rounds is used as the deformation amount of each target point between the two adjacent sampling rounds, and all deformation amounts corresponding to each target point are arranged in time sequence to form each deformation sequence; Based on the difference between the grayscale values ​​of each target point in the current sampling round and the remaining sampling rounds, the grayscale trust weight of each target point in the current sampling round is determined; For each target point, based on the change trend of the data in the deformation sequence of the target point, combined with the difference between the corresponding deformation of the target point in the current sampling round and the remaining deformations in the deformation sequence, the deformation deviation value of each target point in the current sampling round is determined; The fusion result of the grayscale credible weight and deformation deviation value of each target point in the current sampling round is used as the comprehensive deviation of each target point in the current sampling round; The determination process of the grayscale credible weight is as follows: Arrange the grayscale values ​​of each target point in all sampling rounds in time sequence to form each photometric sequence; Calculate the mean of all data in the photometric sequence of each target point except the grayscale value in the current sampling round; Calculate the difference between the grayscale value of each target point in the current sampling round and the mean value, and record it as the grayscale difference; Based on the grayscale difference, the grayscale credible weight of each target point in the current sampling round is obtained; The grayscale credible weight of each target point in the current sampling round is the reciprocal of the sum of the grayscale difference of each target point and a preset value greater than 0.

2. A method for monitoring building deformation by photographing for construction engineering as claimed in claim 1, characterized in that: The process of determining the deformation deviation value is as follows: Calculate the difference between the deformation amount corresponding to each target point in the deformation sequence in the current sampling round and the mean of the remaining deformation amounts, which is recorded as the deformation difference; The product of the trend strength of the deformation sequence of each target point and the deformation difference is taken as the deformation deviation value of each target point in the current sampling round.

3. A building deformation photographic monitoring method for construction engineering as claimed in claim 1, characterized in that: The determination process of the association transfer difference is: For any target point, the spatial coordinates of the target point and multiple neighboring target points in the current sampling round form a displacement set of the target point; Obtain a fitting straight line of all spatial coordinates in the displacement set of any target point, and use the distance between the spatial coordinate of any target point in the current sampling round and the fitting straight line as the association transfer difference of any target point in the current sampling round.

4. A building deformation photographic monitoring method for construction engineering as claimed in claim 3, characterized in that: Any target point and multiple neighboring target points are on the same column structure.

5. A method for monitoring building deformation by photographing for construction engineering as claimed in claim 1, characterized in that: The process of determining the association credibility is as follows: The cumulative value of the association transfer difference of each target point and a preset value greater than 0 is calculated, and the ratio of the comprehensive deviation to the cumulative value is used as the association credibility of each target point in the current sampling round.

6. A method for monitoring building deformation by photography for construction engineering as claimed in claim 1, characterized in that: The process of determining the true deformation is as follows: Calculate the distance between the spatial coordinates of each target point in the current sampling round and the preset standard spatial coordinates, and record it as the measured deformation; The product of the normalized value of the associated credibility of each target point and the measured deformation amount is taken as the actual deformation amount of each target point.

7. A method for monitoring building deformation by photography for construction engineering as claimed in claim 1, characterized in that: The method for monitoring target deformation is as follows: according to the building structure design manual, the deformation threshold corresponding to each target point is obtained, and the target point whose actual deformation is greater than or equal to the deformation threshold is marked as a deformed target point, otherwise, it is marked as a normal target point.

Images