Visual displacement correction method and system based on target mutual reference and correlation analysis

Abstract

The invention relates to the technical field of computer vision, in particular to a visual displacement correction method and system based on target mutual reference and correlation analysis. According to the method, during target displacement calculation, the displacement correlation between any two targets is calculated, the two targets with the highest displacement correlation are selected firstly, and the stability of the targets is considered to be the best; the higher the displacement correlation is, the displacement is mainly derived from errors, so that the displacement errors of other targets can be corrected by performing differential calculation on the displacement of the other targets and the displacement of the reference target, self-benchmark correction is realized, and the bottleneck of stable benchmark dependence is broken through.

Description

Technical Field

[0001] This invention relates to the field of computer vision technology, and in particular to a visual displacement correction method and system based on target cross-reference and correlation analysis. Background Technology

[0002] In computer vision-based engineering structure displacement monitoring technology, the physical displacement of a target in the real world is calculated by analyzing the pixel motion of the target relative to a reference image in a sequence of images. However, this conversion process is highly susceptible to various interference factors, among which slight camera shake (caused by wind load, vibrations from surrounding construction, or deformation of the support structure) and optical refraction effects caused by light passing through non-uniform media (such as air temperature gradients, dust, or water vapor) are the most prominent. These factors can cause nonlinear overall drift or local distortion of the image coordinate system, resulting in significant errors in the target displacement vector directly calculated from the image, severely affecting the reliability and accuracy of the monitoring data.

[0003] To address the aforementioned issues, the mainstream correction strategy in current engineering practice involves deploying one or more reference targets deemed absolutely stable or with known displacements within the monitoring field of view. These reference targets are typically installed at stable reference points far from the deformation zone. By calculating the displacement of the measured target relative to these reference targets, the shared errors can be largely offset, thereby separating the true displacement of the measured target. The core of this method lies in treating the displacement of the reference targets (theoretically zero or a known value) as the "observation value" of the error, and then performing differential correction on other measuring points.

[0004] In computer vision-based displacement monitoring technology, the target displacement directly obtained from images often contains significant errors due to factors such as camera shake and optical refraction. Therefore, in engineering practice, relatively stable reference targets are often deployed to correct the visual displacement measurement results. However, in complex construction environments such as foundation pits, setting up such reference targets is often very difficult.

[0005] However, in complex and dynamic construction environments such as foundation pits, slopes, and tunnel faces, establishing an ideal reference benchmark often faces significant challenges or is even infeasible. On the one hand, the construction site itself is constantly deforming and disturbed, making it difficult to find an absolutely stable location to install the reference target. On the other hand, the monitoring field of view may be frequently obstructed by large machinery, temporary structures, or material stockpiles, or limited by narrow spaces, making it impossible to find a stable benchmark point that simultaneously allows a view of all measuring points. Furthermore, in monitoring tall structures or ultra-long linear projects, even if a stable point exists, it may be too far away to be kept within the same effective field of view as all measuring targets. This practical dilemma of "no stable benchmark available" limits the application of correction methods relying on traditional reference targets, necessitating the development of a self-calibrating displacement monitoring technology that does not depend on external stable reference objects. Summary of the Invention

[0006] (a) Technical problems to be solved The main objective of this invention is to provide a visual displacement correction method and system based on target cross-reference and correlation analysis, so as to solve the technical problem that the application of correction methods that rely on traditional reference targets is limited in the prior art.

[0007] (II) Technical Solution To achieve the above objectives, this invention provides a visual displacement correction method based on target cross-reference and correlation analysis, comprising the following steps: S1, Obtain displacement information of at least three targets deployed within the monitoring area; S2, Calculate the displacement correlation between any two targets. ;in, n is the number of targets, and the total number of combinations between any two targets is... Group; S3, Select the displacement correlation calculated in step S2. The two highest targets should be used as relative reference benchmarks; S4, using the two selected relative reference benchmarks, perform reference correction on the other target displacements; S5, calculate the displacement in the visual image of the monitoring area based on the corrected target position.

[0008] Preferably, step S2 includes: S21, Based on the original displacement data of all the targets, the displacement data in the image coordinate system or the object coordinate system are converted and calculated respectively; S22, calculate the displacement correlation between any two targets in the image-space coordinate system or the object-space coordinate system respectively. .

[0009] Preferably, step S22 includes: S221, in the corresponding coordinate system, using the Spearman rank correlation coefficient calculation method, the correlation coefficient of displacement between any two targets is traversed and calculated. The calculation formula is: Wherein, any two targets are recorded as target x and target y, and m represents the number of displacement samples of the two targets x and y in the corresponding coordinate system. The displacement of target x is expressed as follows: The displacement of the target y is expressed as: , This represents the Spearman rank correlation coefficient between target x and target y, calculated as follows. d j This represents the rank difference between the j-th sample and the two displacements; S222, taking target x and target y as two targets in the i-th group, and adjusting the weight of their displacement correlation considering the relative distance between target x and target y. And calculate the displacement correlation between the target x and the target y. .

[0010] Preferably, the weights in step S222 The calculation formula is: S i This represents the relative distance between the two targets in the i-th group.

[0011] Preferably, the correlation between the displacements of target x and target y in step S22 The calculation formula is: .

[0012] Preferably, in step S4, the displacement error of other targets is corrected by performing a differential calculation between the displacement of other targets and the displacement of the reference target, which serves as a relative reference benchmark.

[0013] Preferably, in step S3, the displacement correlation between any two targets calculated in step S2 in the image-space coordinate system or the object-space coordinate system is selected. The two highest targets are used as relative reference benchmarks.

[0014] Preferably, in step S3, the correlation calculated in step S2 is selected. The two highest targets are used as relative reference benchmarks.

[0015] The present invention also provides a visual displacement correction system based on target cross-reference and correlation analysis, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the visual displacement correction method based on target cross-reference and correlation analysis described above.

[0016] (III) Beneficial Effects This application proposes a visual displacement correction method and system based on target cross-reference and correlation analysis. Compared with the prior art, the present invention has the following advantages: (1) When calculating the target displacement, the two targets with the highest displacement correlation are selected first, and it is considered that their stability is the best. Since the higher the displacement correlation, the more the displacement is caused by error, it can be considered that the displacement of the reference target is entirely caused by error. Therefore, the displacement of other targets and the displacement of the reference target are calculated by difference, and the displacement error of other targets can be corrected. This achieves "self-reference" correction and breaks through the bottleneck of stability reference dependence.

[0017] (2) To ensure the accuracy and reliability of displacement correlation calculation, a mutual verification mechanism combining image coordinate system and object coordinate system is proposed, which enhances the adaptability and robustness of complex dynamic environment.

[0018] (3) When assessing the correlation, the relative distance between targets is introduced as an auxiliary weight index. The closer the two targets are, the higher their actual displacement correlation may be, which will interfere with the accurate assessment of error correlation. By introducing the relative distance between targets to adjust the weight of their correlation, the influence of relative distance can be eliminated.

[0019] (3) Using the two selected targets as relative reference benchmarks, the displacement measurement results of the remaining measurement targets are corrected for errors, and finally high-precision visual displacement monitoring is achieved, which is more flexible in deployment and lower in engineering implementation cost. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of a visual displacement correction method based on target cross-reference and correlation analysis provided in this embodiment.

[0021] Figure 2 This is a schematic diagram illustrating the principle of pinhole imaging in a camera.

[0022] Figure 3 for Figure 1 A schematic diagram of the sub-process of step S2.

[0023] Figure 4 for Figure 3 A schematic diagram of the sub-process of step S22.

[0024] Figure 5This is a schematic diagram of the hardware structure of a visual displacement correction system based on target cross-reference and correlation analysis provided in this embodiment. Detailed Implementation

[0025] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0027] The visual displacement correction method and system based on target cross-reference and correlation analysis in this invention are based on the following assumptions: The displacement errors of all measured targets within the camera's field of view are highly correlated, while the actual displacements of each target are less correlated. This is because errors such as camera instability and light bending have a consistent impact on each target, while the actual displacements of the targets due to positional differences do not exhibit significant correlation.

[0028] Please combine them together Figure 1 and Figure 5 Based on the above assumptions, this embodiment provides a visual displacement correction method based on target cross-reference and correlation analysis, including the following steps: S1, Obtain displacement information of at least three targets deployed within the monitoring area; S2, Calculate the displacement correlation between any two targets. ;in, n is the number of targets, and the total number of combinations between any two targets is... Group; S3, Select the displacement correlation calculated in step S2. The two highest targets should be used as relative reference benchmarks; S4, using the two selected relative reference benchmarks, perform reference correction on the other target displacements; S5, calculate the displacement in the visual image of the monitoring area based on the corrected target position.

[0029] When calculating the target displacement, the two targets with the highest displacement correlation are selected first, as they are considered to have the best stability. Since the higher the displacement correlation, the more the displacement is caused by error, it can be assumed that the displacement of the reference target is entirely caused by error. Therefore, by performing differential calculation between the displacement of other targets and the displacement of the reference target, the displacement error of other targets can be corrected, thus realizing "self-reference" correction and breaking through the bottleneck of stability reference dependence.

[0030] Preferably, step S2 includes: S21, Based on the original displacement data of all the targets, the displacement data in the image coordinate system or the object coordinate system are converted and calculated respectively; S22, calculate the displacement correlation between any two targets in the image-space coordinate system or the object-space coordinate system respectively. .

[0031] Specifically, to ensure the accuracy and reliability of displacement correlation calculation, a mutual verification mechanism combining image-space coordinate system and object-space coordinate system is proposed, which enhances the adaptability and robustness in complex dynamic environments.

[0032] Please combine them together Figure 2 Image coordinate system is the image coordinate system, with pixels as the unit; object coordinate system is the physical coordinate system, which is based on the pinhole imaging principle of a camera and converts pixel units into physical units (such as millimeters).

[0033] Depend on Figure 2 The following transformation relationship can be obtained from the principle: In the formula, f represents the camera focal length, Z represents the distance from the center of the lens to the object being measured, D is the actual size of the object, and d is the size of the object in the image (in pixels). The conversion relationship between D and d can be obtained from the formula.

[0034] To calculate the correlation between targets, a full search (exhaustive search) strategy is required, which involves traversing the two coordinate systems and calculating the correlation coefficient between the displacements of any two targets.

[0035] Those skilled in the art should understand that the correlation coefficient between the displacements of any two targets can also be calculated in a single coordinate system. This simply reduces the mutual verification mechanism.

[0036] Preferably, step S22 includes steps S221 and S222.

[0037] Step S221 includes: in the corresponding coordinate system, using the Spearman rank correlation coefficient calculation method, traversing and calculating the correlation coefficient of displacement between any two targets, the calculation formula is: Wherein, any two targets are recorded as target x and target y, and m represents the number of displacement samples of the two targets x and y in the corresponding coordinate system. The displacement of target x is expressed as follows: The displacement of the target y is expressed as: , This represents the Spearman rank correlation coefficient between target x and target y, calculated as follows. d j Let represent the rank difference between the j-th sample and the two displacements.

[0038] The Spearman rank correlation coefficient can be used to calculate correlation. The Spearman rank correlation coefficient is a non-parametric statistical method used to measure the strength and direction of the monotonic relationship between two variables. It is particularly suitable for handling displacement data with non-linear scaling or monotonic transformations.

[0039] The relative distance between targets should be considered when adjusting the weight of their correlation. The closer two targets are, the higher their actual displacement correlation may be, which can interfere with the accurate assessment of error correlation. Therefore, the closer the targets are, the lower their correlation weight should be.

[0040] S222, taking target x and target y as two targets in the i-th group, and adjusting the weight of their displacement correlation considering the relative distance between target x and target y. And calculate the displacement correlation between the target x and the target y. .

[0041] Taking a monitoring scenario with n measurement targets as an example, the total relative distances between the n measurement targets are... Groups, the relative distance between each group is denoted as S. i , .

[0042] Preferably, the weights in step S222 The calculation formula is: S i This represents the relative distance between the two targets in the i-th group.

[0043] Since the correlation is inversely proportional to the weight of the distance, preferably, the correlation of the displacements between the target x and the target y in step S22 is... The calculation formula is: .

[0044] Preferably, in step S3, the displacement correlation between any two targets calculated in step S2 in the image-space coordinate system or the object-space coordinate system is selected. The two highest targets are used as relative reference benchmarks.

[0045] Preferably, in step S3, the correlation calculated in step S2 is selected. The two highest targets are used as relative reference benchmarks.

[0046] Preferably, in step S4, the displacement errors of other targets are corrected by calculating the difference between the displacements of other targets and the displacement of the reference target, which serves as a relative reference benchmark. After determining the reference target, it can be assumed that all the displacements of the reference target are caused by errors. Therefore, by calculating the difference between the displacements of other targets and the displacement of the reference target, the displacement errors of other targets can be corrected.

[0047] like Figure 5 As shown, this application also provides a visual displacement correction system based on target cross-reference and correlation analysis, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a visual displacement correction method based on target cross-reference and correlation analysis as described in any of the above claims.

[0048] Figure 5 This is a schematic diagram of the hardware structure for running a visual displacement correction method based on target cross-reference and correlation analysis, provided by an embodiment of the present invention. Figure 5 As shown, this embodiment / computer 6 includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60, such as a program for running a visual displacement correction method based on target cross-reference and correlation analysis. When the processor 60 executes the computer program 62, it implements the steps in the various embodiments of running a visual displacement correction method based on target cross-reference and correlation analysis. Alternatively, when the processor 60 executes the computer program 62, it implements the functions of each module / unit in the various device embodiments described above.

[0049] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the computer 6.

[0050] The computer 6 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The computer 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 5This is merely an example of computer 6 and does not constitute a limitation on computer 6. It may include more or fewer components than shown, or combine certain components, or different components. For example, computer 6 may also include input / output devices, network access devices, buses, etc.

[0051] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0052] The memory 61 can be an internal storage unit of the computer 6, such as a hard drive or memory. The memory 61 can also be an external storage device of the computer 6, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device. Furthermore, the memory 61 can include both internal storage units and external storage devices of the computer 6. The memory 61 is used to store the computer program and other programs and data required by the terminal device. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0053] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0054] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0055] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0056] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0057] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0058] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0059] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0060] The above are merely specific application examples of the present invention and do not constitute any limitation on the scope of protection of the present invention. In addition to the above embodiments, the present invention may have other implementations. All technical solutions formed by equivalent substitution or equivalent transformation fall within the scope of protection claimed by the present invention.

Claims

1. A visual displacement correction method based on target inter-reference and correlation analysis, characterized in that, The method comprises the steps of: S1, acquiring displacement information of at least three targets arranged in a monitoring area; S2, calculating the displacement correlation between any two of the targets ; wherein, n is the number of targets, and there are groups of combinations between any two targets. S3, selecting the displacement correlation calculated in step S2 the highest at least two targets as a relative reference S4, using two selected relative reference bases to correct the displacement of other targets; S5, calculating the displacement in the visual image of the monitoring area according to the positions of the corrected targets.

2. The visual displacement correction method based on target inter-reference and correlation analysis according to claim 1, wherein, The step S2 comprises: S21, respectively converting and calculating displacement data in the image coordinate system or the object coordinate system according to the original displacement data of all the targets; S22, calculate the displacement correlation between any two of the targets in the image coordinate system or the object coordinate system, respectively .

3. The visual displacement correction method based on target inter-reference and correlation analysis according to claim 2, wherein, The step S22 comprises: S221, in the corresponding coordinate system, using the calculation method of Spearman rank correlation coefficient, traversing and calculating the correlation coefficient of the displacement between any two targets, the calculation formula is: ; wherein, any two target records are target x and target y, m represents the number of displacement samples of the two targets of target x and target y in the corresponding coordinate system, the displacement of target x is respectively represented as , the displacement of target y is respectively represented as , P xy indicates the Spearman rank correlation coefficient between target x and target y calculated, , d j indicates the rank difference of the jth sample in the two displacements; S222, considering the relative distance between target x and target y, adjusting the weight of the displacement correlation between target x and target y as the two targets of the ith group , and calculating the displacement correlation between the target x and the target y .

4. The visual displacement correction method based on target inter-reference and correlation analysis according to claim 3, wherein, The weight in the step S222 The calculation formula is: , S i represents the relative distance between two targets of the i-th group.

5. The visual displacement correction method based on target inter-reference and correlation analysis according to claim 4, wherein, The correlation of the displacement between the target x and the target y in the step S22 The calculation formula is .

6. The visual displacement correction method based on target inter-reference and correlation analysis according to claim 1, wherein, In the step S4, the displacement errors of other targets are corrected by differentiating the displacement of other targets from the displacement of the reference targets as the relative reference bases.

7. The visual displacement correction method based on target inter-reference correlation analysis according to any one of claims 2-5, characterized in that, In the step S3, the displacement correlation between any two of the targets calculated in the step S2 in the image coordinate system or the object coordinate system is selected The highest at least two targets are taken as the relative reference datum.

8. The visual displacement correction method based on target inter-reference and correlation analysis according to claim 7, wherein, In the step S3, the correlation calculated in the step S2 is selected The two highest targets serve as a relative reference.

9. A visual displacement correction system based on target inter-reference and correlation analysis, comprising a memory, a processor, a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the steps of the visual displacement correction method based on target mutual reference and correlation analysis according to any one of claims 1 to 8 when executing the computer program.

Images