A reference point processing method and apparatus
By using settlement monitoring results and a benchmark discrete point judgment model to select benchmark points, the problem of large settlement deformation errors at benchmark points was solved, improving measurement accuracy and efficiency while reducing costs.
Patent Information
- Application Number
- CN202611308975.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-27
- Publication Date
- 2026-11-17
AI Technical Summary
In railway track measurement with longitudinal uneven settlement, existing technologies suffer from large errors in benchmark settlement deformation and low measurement accuracy, especially in long subway tunnels where measurement efficiency is low and costs are high.
By analyzing the settlement monitoring results, benchmark points that have not settled are identified. The optimal combination of target benchmark points is selected using a benchmark discrete point judgment model, avoiding the use of level instruments or satellite systems and improving the efficiency and accuracy of benchmark point selection.
This improved the efficiency of benchmark selection, reduced costs, and enhanced the accuracy of benchmark selection, ensuring the precision of measurement results.
Smart Images

Figure CN123111191A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of camera measurement technology, specifically relating to a reference point processing method and apparatus. Background Technology
[0002] Longitudinal uneven settlement is one of the core hidden dangers to railway track safety. In recent years, the serial-parallel camera network video measurement method based on image measurement has unique advantages in measuring the static and dynamic deformation of large-scale engineering structures. However, it also suffers from drawbacks such as high cost, difficult maintenance, and low measurement efficiency in long subway tunnels. Under these circumstances, mobile camera network video measurement can solve these problems. Dynamic network measurement of cameras on a mobile vehicle platform can significantly improve the detection efficiency of track subgrade settlement deformation in long subway tunnels. In the mobile camera network video measurement method, the measurement results of settlement deformation at the measuring points are only accurate under a unified coordinate system. Therefore, when carrying out settlement measurement tasks, it is usually necessary to connect benchmark points to establish a unified measurement coordinate system. However, in actual engineering situations, due to various external environmental interferences, such as unpredictable collisions, vibrations and disturbances caused by vehicles or construction, the benchmark points may also experience settlement deformation like the measuring points. This results in a large error in the measured settlement of the monitoring points, leading to low measurement accuracy. Summary of the Invention
[0003] This application provides a benchmark point processing method and apparatus, which determines benchmark points that have not settled by analyzing settlement monitoring results alone, without the need for a level or satellite system. This improves the efficiency and reduces the cost of benchmark point selection. At the same time, it uses a benchmark discrete point judgment model to determine abnormal benchmark points that have not settled, which is not limited by the selection of monitoring points on the target structure and improves the accuracy of benchmark point selection.
[0004] In a first aspect, embodiments of this application provide a reference point processing method, the method comprising: Acquire benchmark point information for monitoring the settlement and deformation of the target structure, wherein the benchmark point information includes benchmark point location information and encoding information; Based on the reference point information, multiple reference point combinations are determined; Determine the settlement monitoring results corresponding to each combination of benchmark points; Based on the multiple settlement monitoring results of the multiple benchmark point combinations and the benchmark discrete point judgment model, the optimal target benchmark point combination is determined.
[0005] In one possible example, determining the optimal target benchmark point combination based on multiple settlement monitoring results and a benchmark discrete point judgment model of the multiple benchmark point combinations includes: The standard combination is defined by taking a single reference point combination from a plurality of reference point combinations and the other reference point combinations from the plurality of reference point combinations excluding the standard combination as reference combinations, and the degree of overlap between the results of the standard combination and the reference combination is determined. Based on the overlap of the results and the preset threshold, determine the interior point rate when each reference point combination is used as a standard combination; The combination of reference points with the highest interior point ratio is taken as the optimal target reference point combination.
[0006] In one possible example, the result overlap includes a first linear correlation value and a mean absolute error; the step of determining the result overlap between the standard combination and the reference combination by sequentially using a single reference point combination from a plurality of reference point combinations as the standard combination and other reference point combinations from a plurality of reference point combinations besides the standard combination as reference combinations includes: The first linear correlation value is determined sequentially based on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination; The mean absolute error is determined sequentially based on the settlement monitoring results of the standard combination and the reference combination.
[0007] In one possible example, determining the first linear correlation value based sequentially on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination includes: The following operations were performed on the settlement monitoring results of the standard combination and each reference combination to obtain the first linear correlation value: Formula for obtaining Pearson correlation coefficient; Determine the first average settlement from multiple settlement measurements in the settlement monitoring results of the standard combination; The second average settlement of multiple settlement values in the settlement monitoring results of the reference combination is determined separately; The first linear correlation value is determined based on the Pearson correlation coefficient formula, the first average settlement, the second average settlement, multiple settlement values from the settlement monitoring results of the standard combination, and multiple settlement values from the settlement monitoring results of the reference combination.
[0008] In one possible example, determining the mean absolute error based sequentially on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination includes: The following operations were performed on the settlement monitoring results of the standard combination and each reference combination to obtain the mean absolute error: The difference between the settlement amount of each standard combination and the settlement amount corresponding to the reference combination currently being treated is determined to obtain multiple first differences; Determine the absolute value of each first difference to obtain multiple first values; The mean absolute error is obtained by determining the average of multiple first values.
[0009] In one possible example, determining multiple combinations of reference points based on the reference point information includes: Multiple reference point regions are determined based on the reference point location information, and each reference point region includes at least one reference point. Determine the initial number of reference points to be selected for each region; Based on the first quantity and the encoding information, reference points are selected from the reference point region to obtain multiple reference point combinations.
[0010] In one possible example, determining the settlement monitoring results corresponding to each combination of reference points includes: Acquire a settlement monitoring algorithm for the target structure; Identify multiple monitoring points on the target structure; The settlement amount of each monitoring point is determined based on the settlement monitoring algorithm and the combination of the reference points, and the settlement monitoring results are obtained.
[0011] Secondly, embodiments of this application provide a reference point processing apparatus, which includes an acquisition unit and a determination unit; wherein, The acquisition unit is used to acquire reference point information for monitoring the settlement and deformation of the target structure. The reference point information includes reference point location information and encoding information. The determining unit is used to determine multiple reference point combinations based on the reference point information; The determining unit is also used to determine the settlement monitoring results corresponding to each combination of reference points; The determining unit is also used to determine the optimal target benchmark combination based on the multiple settlement monitoring results of the multiple benchmark combination and the benchmark discrete point judgment model.
[0012] A third aspect of this application provides an electronic device including: a processor and a memory; and one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for some or all of the steps as described in the first aspect.
[0013] A fourth aspect of this application provides a computer-readable storage medium for storing a computer program that causes a computer to perform some or all of the steps described in the first aspect of this application.
[0014] A fifth aspect of this application provides a computer program product, comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of this application. This computer program product may be a software installation package.
[0015] As can be seen, in this embodiment, the benchmark information for monitoring the settlement deformation of the target structure can be obtained first. The benchmark information includes benchmark location information and encoding information. Then, based on the benchmark information, multiple benchmark combinations are determined. Next, the settlement monitoring results corresponding to each benchmark combination are determined. Finally, based on the multiple settlement monitoring results of the multiple benchmark combinations and the benchmark discrete point judgment model, the optimal target benchmark combination is determined. By analyzing the settlement monitoring results alone to determine benchmarks that have not experienced settlement, there is no need for manual settlement measurement using a level or satellite measurement. This improves the efficiency and reduces the cost of benchmark selection. Furthermore, using the benchmark discrete point judgment model to determine abnormal benchmarks that have not experienced settlement is not limited by the selection of monitoring points on the target structure, thus improving the accuracy of benchmark selection. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 This is a schematic diagram of the architecture of a reference point processing system provided in an embodiment of this application; Figure 2 This is a schematic flowchart of a reference point processing method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the distribution of reference point locations provided in an embodiment of this application; Figure 4 This is a schematic diagram of a process for determining a combination of target reference points according to an embodiment of this application; Figure 5 This is a flowchart illustrating the result overlap provided in an embodiment of this application; Figure 6 This is a schematic diagram of a process for determining a first linear correlation value provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 8 This is a block diagram of the functional units of a reference point processing device provided in an embodiment of this application. Detailed Implementation
[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.
[0019] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.
[0020] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0021] In the embodiments of this application, "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone; A and B exist simultaneously; B exists alone. Among them, A and B can be singular or plural.
[0022] In this embodiment, the symbol " / " can indicate that the preceding and following objects are in an "or" relationship. Alternatively, the symbol " / " can also represent a division sign, i.e., performing a division operation. For example, A / B can mean A divided by B.
[0023] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.
[0024] In the embodiments of this application, "equal to" can be used with "greater than" and is applicable to technical solutions used when "greater than" is used; it can also be used with "less than" and is applicable to technical solutions used when "less than" is used. When "equal to" is used with "greater than", it is not used with "less than"; when "equal to" is used with "less than", it is not used with "greater than".
[0025] To better understand the solutions of the embodiments of this application, the electronic devices, related concepts and background that may be involved in the embodiments of this application will be introduced below.
[0026] The electronic device in this application embodiment is a device with wireless communication capabilities, and may be referred to as a terminal, user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal device, vehicle-mounted terminal device, industrial control terminal device, UE unit, UE station, mobile station, remote station, remote terminal device, mobile device, UE terminal device, wireless communication device, UE agent, or UE device, etc. The terminal device can be fixed or mobile. It should be noted that the terminal device can support at least one wireless communication technology, such as LTE, New Radio (NR), Wideband Code Division Multiple Access (WCDMA), etc. For example, terminal devices can be mobile phones, tablets, desktop computers, laptops, all-in-one computers, in-vehicle terminals, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, electronic devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in future mobile communication networks, or terminal devices in future evolved public land mobile networks (PLMNs), etc.
[0027] Please see Figure 1 , Figure 1 This is a schematic diagram of the architecture of a reference point processing system provided in an embodiment of this application. The reference point processing system 1 includes a vehicle-mounted mobile platform 10, a measuring camera 20 mounted on the vehicle-mounted mobile platform 10, and a processing device 30.
[0028] Among them, the vehicle-mounted mobile platform 10 is used to drive the measuring camera 20 to capture monitoring points at different locations on the target structure.
[0029] The target structure can be a large-scale engineering structure that can experience longitudinal settlement, such as subway tunnels, highway tunnels, roadbeds, and bridges. There are no restrictions on the location of monitoring points on different large-scale engineering structures, nor on the location of the benchmark point.
[0030] The processing device 30 is connected to the measuring camera 20. The processing device 30 can acquire image data of the monitoring points captured by the measuring camera 20, and analyze the image data to determine the settlement monitoring results of the monitoring points. Furthermore, based on the settlement monitoring results, it can screen and identify abnormal benchmark points where settlement has occurred.
[0031] In one possible example, the processing device 30 can first acquire benchmark point information from the measurement camera 20 for target structure settlement deformation monitoring. This benchmark point information includes benchmark point location information and encoding information. Then, based on this benchmark point information, the processing device 30 determines multiple benchmark point combinations. Next, the processing device 30 determines the settlement monitoring results corresponding to each benchmark point combination. Finally, based on the multiple settlement monitoring results of multiple benchmark point combinations and a benchmark discrete point judgment model, the processing device 30 determines the optimal target benchmark point combination. By analyzing settlement monitoring results alone to identify benchmark points that have not experienced settlement, manual settlement measurement using a level or satellite system is unnecessary. This improves the efficiency and reduces the cost of benchmark point selection. Furthermore, using a benchmark discrete point judgment model to identify abnormal benchmark points that have not experienced settlement is not limited by the selection of monitoring points on the target structure, thus improving the accuracy of benchmark point selection.
[0032] Please see Figure 2 , Figure 2 This is a flowchart illustrating a reference point processing method provided in an embodiment of this application, specifically including the following steps: Step S201: Obtain the benchmark point information for monitoring the settlement and deformation of the target structure. The benchmark point information includes benchmark point location information and encoding information.
[0033] When measuring the monitoring points of the target structure, a reference point should be selected, and a unified measurement coordinate system, namely the world coordinate system, should be established based on the reference point.
[0034] To ensure measurement accuracy, benchmark points can be set up in different areas, with multiple benchmark points set up in each area. Then, benchmark points are selected from each area for measurement. During the measurement, at least one benchmark point must be selected in each area.
[0035] For example, see Figure 3Assuming that in the initial setup, there are four reference points in each of the two regions at the left and right ends, the four reference points at the left end are numbered 1, 2, 3 and 4, and the four reference points at the right end are numbered 5, 6, 7 and 8.
[0036] Step S202: Determine multiple reference point combinations based on the reference point information.
[0037] One example of selecting a reference point is as follows: select a reference point from the left end and a reference point from the right end. This will result in multiple reference point combinations. A single reference point combination includes the reference point from the left end and the reference point from the right end.
[0038] Step S203: Determine the settlement monitoring results corresponding to each combination of benchmark points.
[0039] Specifically, a reference coordinate system is established sequentially using the reference points of each reference point combination, and the settlement amounts of multiple monitoring points on the target structure measured under that reference point combination are determined, which are the settlement monitoring results.
[0040] Step S204: Determine the optimal target benchmark combination based on the multiple settlement monitoring results of the multiple benchmark combination and the benchmark discrete point judgment model.
[0041] The benchmark discrete point judgment model utilizes the denoising idea of random sample sampling to determine consistency. It selects a certain result overlap standard and performs pairwise matching of settlement monitoring results. If the result overlap standard is met, the two sets of settlement monitoring results are considered the same in actual work. This process is repeated until all results have been processed. Since "abnormal benchmark points" are discrete, the deformation and settlement results of monitoring points obtained from selecting different "abnormal benchmark points" will also be discrete. Only the selected benchmark points that have not undergone deformation will have the largest solution set. That is, this benchmark point combination is used as the standard combination, and other benchmark point combinations are used as reference combinations. The settlement monitoring results of the standard combination and the reference combinations are matched. The combination that meets the result overlap standard has the most solutions, and this standard combination is the optimal target benchmark point combination.
[0042] As can be seen, in this embodiment, the benchmark information for monitoring the settlement deformation of the target structure can be obtained first. The benchmark information includes benchmark location information and encoding information. Then, based on the benchmark information, multiple benchmark combinations are determined. Next, the settlement monitoring results corresponding to each benchmark combination are determined. Finally, based on the multiple settlement monitoring results of the multiple benchmark combinations and the benchmark discrete point judgment model, the optimal target benchmark combination is determined. By analyzing the settlement monitoring results alone to determine benchmarks that have not experienced settlement, there is no need for manual settlement measurement using a level or satellite measurement. This improves the efficiency and reduces the cost of benchmark selection. Furthermore, using the benchmark discrete point judgment model to determine abnormal benchmarks that have not experienced settlement is not limited by the selection of monitoring points on the target structure, thus improving the accuracy of benchmark selection.
[0043] Please see Figure 4 In determining the optimal combination of target reference points based on multiple settlement monitoring results and a reference discrete point judgment model, the above method may include the following steps: Step S401: Sequentially, a single reference point combination from multiple reference point combinations is used as a standard combination, and a reference point combination other than the standard combination from multiple reference point combinations is used as a reference combination, and the degree of overlap between the standard combination and the reference combination is determined.
[0044] In this process, a single reference point combination is used as the standard combination, and other reference point combinations among multiple reference point combinations other than the standard combination are used as reference combinations. Then, the standard combination and the reference combination are matched in pairs to determine the degree of overlap between the settlement monitoring results of the two combinations.
[0045] Step S402: Based on the result overlap and the preset threshold, determine the interior point rate when each reference point combination is used as a standard combination.
[0046] If the result overlap meets the preset result overlap standard, i.e. the preset threshold, then the two settlement monitoring results are regarded as the same solution in actual engineering, and the reference combination is the interior point of the standard combination.
[0047] The interior point ratio is calculated as: (Number of interior points in the standard combination) / (Total number of all benchmark combinations).
[0048] Each reference point combination can be used as a standard combination in turn, and its interior point ratio can be determined accordingly.
[0049] Step S403: Select the combination of reference points with the highest interior point rate as the optimal target reference point combination.
[0050] Among them, the benchmark point combination with the highest internal point ratio is the benchmark point combination that has not experienced any settlement deformation. This benchmark point combination can be used as the optimal target benchmark point combination. When measuring the monitoring points using this target benchmark point combination, the measurement error is minimized.
[0051] As can be seen, in this example, by analyzing the degree of overlap between the settlement monitoring results of the benchmark point combinations in pairs, and further analyzing the in-point rate of the benchmark point combinations, the benchmark point combination with the highest in-point rate is selected as the optimal target benchmark point combination, which helps to improve the accuracy of benchmark point selection.
[0052] Please see Figure 5 The result overlap includes a first linear correlation value and a mean absolute error; regarding the determination of the result overlap between the standard combination and the reference combination by sequentially using a single reference point combination from a plurality of reference point combinations as the standard combination and other reference point combinations from a plurality of reference point combinations besides the standard combination as the reference combination, the above method may include the following steps: Step S501: Determine the first linear correlation value based on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination. Among them, Pearson correlation coefficient and mean absolute error were selected as the standards for the overlap of analysis results.
[0053] The first linear correlation value is the Pearson correlation coefficient, which is a statistical measure of the strength and direction of the linear correlation between two continuous variables.
[0054] Step S502: Determine the mean absolute error based on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination.
[0055] Among them, mean absolute error is the core indicator for measuring the average level of the deviation between the values of two curves. The smaller the mean absolute error, the closer the values of the two curves are and the greater the overlap. The larger the mean absolute error, the more the values of the two curves deviate and the lower the overlap.
[0056] As can be seen, in this example, using the Pearson correlation coefficient and mean absolute error as the criteria for judging the overlap of results, and taking the benchmark point represented by the group with the highest inlier rate as the optimal benchmark point, is beneficial to improving the accuracy of benchmark point selection.
[0057] Please see Figure 6 In determining the first linear correlation value based sequentially on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination, the above method may include the following steps: Step S601: Perform the following operations on the settlement monitoring results of the standard combination and each reference combination to obtain the first linear correlation value: obtain the Pearson correlation coefficient formula.
[0058] The formula for the Pearson correlation coefficient is as follows:
[0059] Where n represents the number of monitoring points, This represents the settlement at the monitoring points corresponding to the standard combination. This indicates the settlement at the monitoring point corresponding to the reference combination. This represents the average settlement at all monitoring points corresponding to the standard combination. This represents the average settlement value across all monitoring points corresponding to the reference combination.
[0060] Step S602: Determine the first average settlement of multiple settlement values in the settlement monitoring results of the standard combination.
[0061] Among them, the first average settlement is .
[0062] Step S603: Determine the second average settlement of multiple settlement values in the settlement monitoring results of the reference combination.
[0063] Among them, the second average settlement is .
[0064] Step S604: Determine the first linear correlation value based on the Pearson correlation coefficient formula, the first average settlement, the second average settlement, multiple settlement values in the settlement monitoring results of the standard combination, and multiple settlement values in the settlement monitoring results of the reference combination.
[0065] The Pearson correlation coefficient is obtained by substituting the first average settlement, the second average settlement, multiple settlement values from the settlement monitoring results of the standard combination, and multiple settlement values from the settlement monitoring results of the reference combination into the Pearson correlation coefficient formula. This Pearson correlation coefficient is the first linear correlation value.
[0066] The preset threshold may include a first preset threshold corresponding to the linear correlation value. The first preset threshold can be set manually or by system default, and is not limited here.
[0067] As can be seen in this example, the average settlement corresponding to the standard combination and the average settlement corresponding to the reference combination can be determined respectively. Then, based on the multiple settlement values, average settlement values and Pearson correlation coefficient formula of the settlement monitoring results, the first linear correlation value can be determined, which is beneficial to the subsequent determination of the degree of overlap of the results and to improving the accuracy of the benchmark selection.
[0068] In one possible example, regarding the determination of the mean absolute error based on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination, the above method may include the following steps: performing the following operations on the settlement monitoring results of the standard combination and the settlement monitoring results of each reference combination respectively to obtain the mean absolute error: determining the difference between each settlement amount of the standard combination and the settlement amount corresponding to the currently processed reference combination, obtaining a plurality of first differences; determining the absolute value of each first difference, obtaining a plurality of first values; determining the average value of the plurality of first values, obtaining the mean absolute error.
[0069] Wherein, the first difference = settlement at the same monitoring point of the standard combination - settlement at the same monitoring point of the reference combination.
[0070] Among them, the smaller the mean absolute error, the higher the overlap between the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination; the larger the mean absolute error, the lower the overlap between the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination.
[0071] The preset threshold includes a second preset threshold corresponding to the mean absolute error. The second preset threshold can be set manually or by system default, and is not limited here.
[0072] For example, for a set of standard combinations and reference combinations, if the determined mean absolute error is less than or equal to a second preset threshold and the first linear correlation value is greater than or equal to a first preset threshold, then the reference combination and the standard combination are determined to meet the result overlap criterion, and the reference combination is an interior point of the standard combination. The number of interior points and the interior point rate of the standard combination can be further calculated.
[0073] As can be seen, in this example, the mean absolute error can be determined based on the settlement monitoring results of the standard combination and the reference combination. Using the mean absolute error as one of the results overlap standards is beneficial to improving the accuracy of benchmark selection.
[0074] In one possible example, regarding the determination of multiple reference point combinations based on the reference point information, the above method may include the following steps: determining multiple reference point regions based on the reference point location information, each reference point region including at least one reference point; determining a first number of reference points to be selected from each region; and selecting reference points from the reference point regions respectively based on the first number and the encoding information to obtain multiple reference point combinations.
[0075] The reference point region includes at least two reference points, each reference point region includes at least one reference point, and at least one reference point is selected for each region.
[0076] For an example, please refer to Figure 3 , Figure 3The diagram shows two regions, left and right. The four reference points in the left region are numbered 1, 2, 3, and 4, and the four reference points in the right region are numbered 5, 6, 7, and 8. Taking the selection of one reference point in the left region and one reference point in the right region as an example, there are a total of... There are several combinations; taking two reference points selected in the left region and one reference point selected in the right region as an example, then there are a total of There are several combinations; and so on, a total of hundreds of combinations can be obtained, and each combination will determine a set of settlement monitoring results.
[0077] As can be seen in this example, by selecting different combinations of benchmark points, multiple sets of actual settlement and discrete settlement results caused by incorrect benchmark point selection can be obtained. This is beneficial for subsequent similarity judgment of each set of results and helps to improve the accuracy of benchmark point selection.
[0078] In one possible example, the above method may include the following steps in determining the settlement monitoring results corresponding to each combination of reference points: obtaining a settlement monitoring algorithm for the target structure; determining multiple monitoring points on the target structure; determining the settlement amount of each monitoring point according to the settlement monitoring algorithm and the combination of reference points, and obtaining the settlement monitoring results.
[0079] The settlement monitoring algorithm is a purely visual algorithm that uses the coordinate system of a reference point and images of the monitoring points captured by a camera to determine the displacement of the monitoring points, including the longitudinal settlement. Specifically, as a purely visual algorithm, the settlement monitoring algorithm first pre-constructs a global world coordinate system with a stable reference point as its core. By defining a fixed combination of reference point indices and calibrating the camera's intrinsic and extrinsic parameters and pose transformation matrix, the absolute anchoring of the reference coordinate system is completed. Then, a camera placed on a moving platform continuously acquires a sequence of images of monitoring points deployed on the target structure. Image feature extraction and matching algorithms are used to track the changes in pixel coordinates of the monitoring points in different frames. The coordinate transformation is completed by combining the camera imaging model and the reference coordinate system. By constructing an overdetermined linear equation system that includes the displacement of the monitoring points and the motion of the camera platform, the longitudinal settlement in the vertical direction is finally accurately separated from the calculated three-dimensional spatial displacement of the monitoring points.
[0080] The settlement monitoring results include the settlement amount at each monitoring point on the target structure under the benchmark point combination setting.
[0081] As can be seen, in this example, the settlement amount of each monitoring point can be determined based on the settlement monitoring algorithm, which is beneficial for subsequent similarity judgment of the results of each group and for improving the accuracy of benchmark point selection.
[0082] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 7 As shown, the electronic device includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs are configured to be executed by the processor according to the following instructions: Acquire benchmark point information for monitoring the settlement and deformation of the target structure, wherein the benchmark point information includes benchmark point location information and encoding information; Based on the reference point information, multiple reference point combinations are determined; Determine the settlement monitoring results corresponding to each combination of benchmark points; Based on the multiple settlement monitoring results of the multiple benchmark point combinations and the benchmark discrete point judgment model, the optimal target benchmark point combination is determined.
[0083] As can be seen, in this embodiment of the application, the electronic device determines the benchmark points that have not settled by analyzing the data of the settlement monitoring results. There is no need to use a level to manually measure the settlement or use a satellite system for measurement. This is beneficial to improving the efficiency of benchmark point selection and reducing the cost of benchmark point selection. At the same time, the benchmark discrete point judgment model is used to determine the abnormal benchmark points that have not settled. It is not limited by the selection of monitoring points on the target structure, which is beneficial to improving the accuracy of benchmark point selection.
[0084] In one possible example, regarding the determination of the optimal target reference point combination based on multiple settlement monitoring results and a reference discrete point judgment model of the multiple reference point combinations, the above procedure includes instructions for performing the following steps: The standard combination is defined by taking a single reference point combination from a plurality of reference point combinations and the other reference point combinations from the plurality of reference point combinations excluding the standard combination as reference combinations, and the degree of overlap between the results of the standard combination and the reference combination is determined. Based on the overlap of the results and the preset threshold, determine the interior point rate when each reference point combination is used as a standard combination; The combination of reference points with the highest interior point ratio is taken as the optimal target reference point combination.
[0085] In one possible example, the result overlap includes a first linear correlation value and a mean absolute error; regarding the determination of the result overlap between the standard combination and the reference combination by sequentially using a single combination of multiple reference points as the standard combination and other combinations of reference points (excluding the standard combination) as reference combinations, the above procedure includes instructions for performing the following steps: The first linear correlation value is determined sequentially based on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination; The mean absolute error is determined sequentially based on the settlement monitoring results of the standard combination and the reference combination.
[0086] In one possible example, regarding the determination of the first linear correlation value based sequentially on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination, the above procedure includes instructions for performing the following steps: The following operations were performed on the settlement monitoring results of the standard combination and each reference combination to obtain the first linear correlation value: Formula for obtaining Pearson correlation coefficient; Determine the first average settlement from multiple settlement measurements in the settlement monitoring results of the standard combination; The second average settlement of multiple settlement values in the settlement monitoring results of the reference combination is determined separately; The first linear correlation value is determined based on the Pearson correlation coefficient formula, the first average settlement, the second average settlement, multiple settlement values from the settlement monitoring results of the standard combination, and multiple settlement values from the settlement monitoring results of the reference combination.
[0087] In one possible example, in determining the mean absolute error based sequentially on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination, the above procedure also includes instructions for performing the following steps: The following operations were performed on the settlement monitoring results of the standard combination and each reference combination to obtain the mean absolute error: The difference between the settlement amount of each standard combination and the settlement amount corresponding to the reference combination currently being treated is determined to obtain multiple first differences; Determine the absolute value of each first difference to obtain multiple first values; The mean absolute error is obtained by determining the average of multiple first values.
[0088] In one possible example, regarding the determination of multiple reference point combinations based on the reference point information, the above procedure further includes instructions for performing the following steps: Multiple reference point regions are determined based on the reference point location information, and each reference point region includes at least one reference point. Determine the initial number of reference points to be selected for each region; Based on the first quantity and the encoding information, reference points are selected from the reference point region to obtain multiple reference point combinations.
[0089] In one possible example, regarding the determination of the settlement monitoring results corresponding to each set of reference points, the above procedure also includes instructions for performing the following steps: Acquire a settlement monitoring algorithm for the target structure; Identify multiple monitoring points on the target structure; The settlement amount of each monitoring point is determined based on the settlement monitoring algorithm and the combination of the reference points, and the settlement monitoring results are obtained.
[0090] The above primarily describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware 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 implementation should not be considered beyond the scope of this application.
[0091] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.
[0092] When dividing each function into modules according to its corresponding function. Figure 8 This is a functional unit block diagram of a reference point processing device provided in an embodiment of this application, such as... Figure 8 As shown, the reference point processing device includes an acquisition unit 801 and a determination unit 802; wherein, The acquisition unit 801 is used to acquire reference point information for monitoring the settlement and deformation of the target structure. The reference point information includes reference point location information and encoding information. The determining unit 802 is used to determine multiple reference point combinations based on the reference point information; The determining unit 802 is also used to determine the settlement monitoring results corresponding to each combination of reference points; The determining unit 802 is further configured to determine the optimal target benchmark combination based on the multiple settlement monitoring results of the multiple benchmark combination and the benchmark discrete point judgment model.
[0093] As can be seen, in this embodiment, the benchmark processing device first acquires benchmark information for monitoring the settlement deformation of the target structure. This benchmark information includes benchmark location information and encoding information. Then, based on this benchmark information, multiple benchmark combinations are determined. Next, the settlement monitoring results corresponding to each benchmark combination are determined. Finally, based on the multiple settlement monitoring results of the multiple benchmark combinations and the benchmark discrete point judgment model, the optimal target benchmark combination is determined. By analyzing the settlement monitoring results alone to identify benchmarks that have not experienced settlement, there is no need for manual settlement measurement using a level or satellite measurement. This improves the efficiency and reduces the cost of benchmark selection. Furthermore, using the benchmark discrete point judgment model to identify abnormal benchmarks that have not experienced settlement is not limited by the selection of monitoring points on the target structure, thus improving the accuracy of benchmark selection.
[0094] In one possible example, regarding the determination of the optimal target reference point combination based on multiple settlement monitoring results and a reference discrete point judgment model according to the combination of the multiple reference points, the determining unit 802 is specifically used for: The standard combination is defined by taking a single reference point combination from a plurality of reference point combinations and the other reference point combinations from the plurality of reference point combinations excluding the standard combination as reference combinations, and the degree of overlap between the results of the standard combination and the reference combination is determined. Based on the overlap of the results and the preset threshold, determine the interior point rate when each reference point combination is used as a standard combination; The combination of reference points with the highest interior point ratio is taken as the optimal target reference point combination.
[0095] In one possible example, regarding the determination of the degree of overlap between the results obtained by sequentially using a single reference point combination from a plurality of reference point combinations as a standard combination and other reference point combinations from a plurality of reference point combinations besides the standard combination as reference combinations, the determining unit 802 is specifically used for: The first linear correlation value is determined sequentially based on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination; The mean absolute error is determined sequentially based on the settlement monitoring results of the standard combination and the reference combination.
[0096] In one possible example, in determining the first linear correlation value based sequentially on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination, the determining unit 802 is specifically used for: The following operations were performed on the settlement monitoring results of the standard combination and each reference combination to obtain the first linear correlation value: Formula for obtaining Pearson correlation coefficient; Determine the first average settlement from multiple settlement measurements in the settlement monitoring results of the standard combination; The second average settlement of multiple settlement values in the settlement monitoring results of the reference combination is determined separately; The first linear correlation value is determined based on the Pearson correlation coefficient formula, the first average settlement, the second average settlement, multiple settlement values from the settlement monitoring results of the standard combination, and multiple settlement values from the settlement monitoring results of the reference combination.
[0097] In one possible example, in determining the mean absolute error based sequentially on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination, the determining unit 802 is further specifically used for: The following operations were performed on the settlement monitoring results of the standard combination and each reference combination to obtain the mean absolute error: The difference between the settlement amount of each standard combination and the settlement amount corresponding to the reference combination currently being treated is determined to obtain multiple first differences; Determine the absolute value of each first difference to obtain multiple first values; The mean absolute error is obtained by determining the average of multiple first values.
[0098] In one possible example, in determining the combination of multiple reference points based on the reference point information, the determining unit 802 is further specifically configured to: Multiple reference point regions are determined based on the reference point location information, and each reference point region includes at least one reference point. Determine the initial number of reference points to be selected for each region; Based on the first quantity and the encoding information, reference points are selected from the reference point region to obtain multiple reference point combinations.
[0099] In one possible example, in determining the settlement monitoring results corresponding to each set of reference points, the determining unit 802 is further specifically used for: Acquire a settlement monitoring algorithm for the target structure; Identify multiple monitoring points on the target structure; The settlement amount of each monitoring point is determined based on the settlement monitoring algorithm and the combination of the reference points, and the settlement monitoring results are obtained.
[0100] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.
[0101] The electronic device provided in this embodiment is used to execute the above-described reference point processing method, and therefore can achieve the same effect as the above-described implementation method.
[0102] When using integrated units, the electronic device may include a processing module, a storage module, and a communication module. The processing module can be used to control and manage the actions of the electronic device; for example, it can support the electronic device in executing the steps performed by the aforementioned functional units. The storage module can support the electronic device in executing stored program code and data. The communication module can support communication between the electronic device and other devices.
[0103] The processing module can be a processor or a controller. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory. The communication module can specifically be a radio frequency circuit, a Bluetooth chip, a Wi-Fi chip, or other devices that interact with other electronic devices.
[0104] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.
[0105] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer includes a control platform.
[0106] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0107] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0108] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above 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 or other forms.
[0109] The units described above 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.
[0110] Furthermore, the functional units in the various embodiments of this application 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.
[0111] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0112] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.
[0113] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A reference point processing method, characterized in that, include: Acquire benchmark point information for monitoring the settlement and deformation of the target structure, wherein the benchmark point information includes benchmark point location information and encoding information; Based on the reference point information, multiple reference point combinations are determined; Determine the settlement monitoring results corresponding to each combination of benchmark points; Based on the multiple settlement monitoring results of the multiple benchmark point combinations and the benchmark discrete point judgment model, the optimal target benchmark point combination is determined.
2. The method according to claim 1, characterized in that, The step of determining the optimal target reference point combination based on multiple settlement monitoring results and a reference discrete point judgment model for the combination of multiple reference points includes: The standard combination is defined by taking a single reference point combination from a plurality of reference point combinations and the other reference point combinations from the plurality of reference point combinations excluding the standard combination as reference combinations, and the degree of overlap between the results of the standard combination and the reference combination is determined. Based on the overlap of the results and the preset threshold, determine the interior point rate when each reference point combination is used as a standard combination; The combination of reference points with the highest interior point ratio is taken as the optimal target reference point combination.
3. The method according to claim 2, characterized in that, The result overlap includes the first linear correlation value and the mean absolute error; the step of sequentially using a single reference point combination from multiple reference point combinations as the standard combination and other reference point combinations from multiple reference point combinations (excluding the standard combination) as reference combinations, and determining the result overlap between the standard combination and the reference combination, includes: The first linear correlation value is determined sequentially based on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination; The mean absolute error is determined sequentially based on the settlement monitoring results of the standard combination and the reference combination.
4. The method according to claim 3, characterized in that, The determination of the first linear correlation value based on the settlement monitoring results of the standard combination and the reference combination includes: The following operations were performed on the settlement monitoring results of the standard combination and each reference combination to obtain the first linear correlation value: Formula for obtaining Pearson correlation coefficient; Determine the first average settlement from multiple settlement measurements in the settlement monitoring results of the standard combination; Determine the second average settlement of multiple settlement values in the settlement monitoring results of the reference combination; The first linear correlation value is determined based on the Pearson correlation coefficient formula, the first average settlement, the second average settlement, multiple settlement values from the settlement monitoring results of the standard combination, and multiple settlement values from the settlement monitoring results of the reference combination.
5. The method according to claim 4, characterized in that, The mean absolute error is determined sequentially based on the settlement monitoring results of the standard combination and the settlement monitoring results of the reference combination, including: The following operations were performed on the settlement monitoring results of the standard combination and each reference combination to obtain the mean absolute error: The difference between the settlement amount of each standard combination and the settlement amount corresponding to the reference combination currently being treated is determined to obtain multiple first differences; Determine the absolute value of each first difference to obtain multiple first values; The mean absolute error is obtained by determining the average of multiple first values.
6. The method according to claim 1, characterized in that, The step of determining multiple reference point combinations based on the reference point information includes: Multiple reference point regions are determined based on the reference point location information, and each reference point region includes at least one reference point. Determine the initial number of reference points to be selected for each region; Based on the first quantity and the encoding information, reference points are selected from the reference point region to obtain multiple reference point combinations.
7. The method according to claim 1, characterized in that, The determination of the settlement monitoring results corresponding to each combination of benchmark points includes: Acquire a settlement monitoring algorithm for the target structure; Identify multiple monitoring points on the target structure; The settlement amount of each monitoring point is determined based on the settlement monitoring algorithm and the combination of the reference points, and the settlement monitoring results are obtained.
8. A reference point processing device, characterized in that, The reference point processing device includes an acquisition unit and a determination unit; wherein... The acquisition unit is used to acquire reference point information for monitoring the settlement and deformation of the target structure. The reference point information includes reference point location information and encoding information. The determining unit is used to determine multiple reference point combinations based on the reference point information; The determining unit is also used to determine the settlement monitoring results corresponding to each combination of reference points; The determining unit is further configured to determine the optimal target benchmark combination based on the multiple settlement monitoring results of the multiple benchmark combination and the benchmark discrete point judgment model.
9. An electronic device, characterized in that, It includes a processor and a memory, the memory being used to store one or more programs and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, A computer program for storing electronic data interchange, wherein the computer program causes a computer to perform the method as described in any one of claims 1-7.
