Pile position deviation detection method and device, electronic equipment and storage medium

Abstract

The invention provides a pile position deviation detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the point cloud data of a to-be-detected region scanned by an unmanned aerial vehicle, and enabling the to-be-detected region to be internally provided with a plurality of sinking piles installed on the water; performing feature extraction on the point cloud data to obtain original point cloud data of each sinking pile; determining a first initial value according to the original point cloud data, and applying first random disturbance to the first initial value according to a preset first objective function to iteratively update the first initial value to obtain a first output value; applying second random disturbance to the first output value according to a preset second objective function, and iteratively updating the first output value to obtain a second output value; and performing pile position deviation detection on the sunk pile according to the second output value. According to the invention, the pile sinking position detection efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of radar point cloud technology, and in particular to a pile position deviation detection method, device, electronic device and storage medium. Background Art

[0002] At present, the application of water engineering is very extensive. The construction of hydraulic structures such as bridge piers, revetments, and docks cannot be separated from underwater pile driving. Underwater pile driving refers to a construction technology that uses a specific construction process to sink prefabricated piles (such as prestressed concrete pipe piles, steel pipe piles, etc.) into the designed depth of the underwater foundation in a water environment to meet the bearing requirements of engineering structures such as docks and bridges.

[0003] Due to disturbances such as wind, waves, tides, and currents, the position of underwater piles may shift. Related technologies use on-water test piles to detect the position deviation of each underwater pile. However, this method is labor-intensive and inefficient, and manual inspections can lead to omissions or misjudgments, resulting in low accuracy in detecting pile position deviations. Summary of the Invention

[0004] In view of this, the present application provides a pile position deviation detection method, device, electronic device and storage medium, which can improve the efficiency and accuracy of pile position detection.

[0005] A first aspect of an embodiment of the present application provides a pile position deviation detection method, comprising: obtaining point cloud data within a test area scanned by a drone, wherein a plurality of sunken piles installed on water are provided in the test area; performing feature extraction on the point cloud data to obtain original point cloud data of each sunken pile; for each sunken pile, determining a first initial value according to the original point cloud data, and applying a first random disturbance to the first initial value according to a preset first objective function, so as to obtain a first output value after iteratively updating the first initial value; applying a second random disturbance to the first output value according to a preset second objective function, so as to obtain a second output value after iteratively updating the first output value, wherein the second random disturbance is smaller than the first random disturbance, and the first initial value, the first output value and the second output value are all used to characterize the state of the sunken pile; and performing pile position deviation detection on the sunken pile according to the second output value.

[0006] Compared with the related art, the embodiment of the present application has at least the following advantages: since the point cloud data scanned by the drone contains other objects in the area to be tested, the original point cloud data of each pile is obtained by extracting features from the point cloud data, thereby improving the accuracy of pile position deviation detection. A first initial value is obtained based on the original point cloud data of the pile, and a first random perturbation is first applied to the first initial value for preliminary processing to obtain a more accurate first output value. A second random perturbation is then applied to the first output value for secondary processing. Since the second random perturbation is smaller than the first random perturbation, a more accurate second output value can be obtained through a smaller perturbation. Since the second output value represents the state of the pile, the pile position deviation can be accurately detected by the second output value. In addition, the above-mentioned pile position deviation detection method does not require manual measurement. The pile position deviation detection of each pile in the area to be tested can be achieved by controlling the drone to scan the point cloud data of the area to be tested, thereby reducing labor costs and improving detection efficiency.

[0007] In a possible implementation, the first objective function and the second objective function are both constructed based on a simulated annealing algorithm; a first random perturbation is applied to the first initial value according to a preset first objective function to obtain a first output value after iteratively updating the first initial value, including: taking the first initial value as the first current parameter optimal solution of the first objective function, applying a first random perturbation to the first current parameter optimal solution to generate a first new parameter solution; comparing the first objective function value corresponding to the first new parameter solution and the first current parameter optimal solution to determine whether to update the first parameter optimal solution of the first objective function; repeating the previous step until the set first objective function condition is met, and obtaining the first objective function The optimal solution of the first objective parameter is the first output value; the second random perturbation is applied to the first output value according to the preset second objective function to iteratively update the first output value to obtain the second output value, including: taking the first output value as the second current parameter optimal solution of the second objective function, applying the second random perturbation to the second current parameter optimal solution to generate a second new parameter solution; comparing the second new parameter solution and the second current parameter optimal solution corresponding to the second objective function value to determine whether to update the second parameter optimal solution of the second objective function; repeating the previous step until the set second objective function condition is met, and obtaining the second objective parameter optimal solution of the second objective function, which is the second output value.

[0008] In a possible implementation, determining the first initial value based on the original point cloud data includes: calculating a point cloud bounding box of the original point cloud data, where the point cloud bounding box is the first initial value.

[0009] In a possible implementation, before extracting features from the point cloud data, the method further includes: preprocessing the point cloud data to obtain target point cloud data from which noise data and outlier data are removed; and extracting features from the point cloud data includes: extracting features from the target point cloud data.

[0010] In one possible implementation, the preprocessing of the point cloud data to obtain target point cloud data with noise data and outlier data removed includes: inputting the point cloud data into a point cloud outlier removal filter to obtain intermediate point cloud data with outlier data removed; and inputting the intermediate point cloud data into a radius outlier filter to obtain the target point cloud data with noise data removed.

[0011] In one possible implementation, the sunken pile is cylindrical; the feature extraction of the point cloud data to obtain the original point cloud data of each sunken pile includes: performing cylindrical segmentation on the point cloud data to extract the cylindrical point cloud in the point cloud data; and performing monomerization processing on the cylindrical point cloud to obtain the original point cloud data of each sunken pile.

[0012] In one possible implementation, the method further includes: during the process of the drone scanning the area to be measured, controlling the turning speed of the drone to not exceed 3 m / s, the attitude angle of the drone to not exceed 20°, and the ascent and descent speeds of the drone to not exceed 8 m / s.

[0013] In the second aspect, an embodiment of the present application also provides a pile position deviation detection device, including: an acquisition module, an extraction module, a processing module and a detection module; the acquisition module is used to acquire point cloud data in a test area scanned by a drone, and a plurality of sinking piles installed on water are provided in the test area; the extraction module is used to perform feature extraction on the point cloud data to obtain the original point cloud data of each sinking pile; for each sinking pile, the processing module is used to determine a first initial value according to the original point cloud data, and apply a first random disturbance to the first initial value according to a preset first objective function, so as to obtain a first output value after iteratively updating the first initial value; the processing module is also used to apply a second random disturbance to the first output value according to a preset second objective function, so as to obtain a second output value after iteratively updating the first output value, wherein the second random disturbance is smaller than the first random disturbance, and the first initial value, the first output value and the second output value are all used to characterize the state of the sinking pile; the detection module is used to perform pile position deviation detection on the sinking pile according to the second output value.

[0014] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the pile position deviation detection method as described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application further provides a storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the pile position deviation detection method as described in the first aspect.

[0016] The technical effects obtained in the above-mentioned second, third and fourth aspects are similar to the technical effects obtained by the corresponding technical means in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of the steps of a pile position deviation detection method provided in one embodiment of the present application.

[0018] Figure 2 This is a schematic diagram of the effect of the second output value obtained based on the second objective function provided in one embodiment of the present application.

[0019] Figure 3 Another step flow chart of the pile position deviation detection method provided in one embodiment of the present application.

[0020] Figure 4 This is a functional module diagram of a pile position deviation detection device provided in one embodiment of the present application.

[0021] Figure 5 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to more clearly understand the above-mentioned objectives, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features therein can be combined with each other in the absence of conflict.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present application. The described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application pertains. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0025] It should be further noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0026] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A alone, A and B together, and B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," and so on (if any) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or precedence.

[0027] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0028] To facilitate understanding, some illustrations of concepts related to the embodiments of the present application are given for reference.

[0029] Cylinder segmentation: Segmenting specific geometric shapes is a common task in point cloud processing. Cylinder segmentation is a key application, widely used in industrial inspection, robotic vision, and other fields. By using the RANSAC algorithm in PCL, combined with a cylinder model, points that conform to the cylinder model can be extracted from complex point cloud data for further processing and analysis.

[0030] Individualization: This is a key technology for segmenting objects (such as buildings and trees) in 3D point cloud data into individual entities. Its core lies in improving data segmentation and management capabilities. Deep learning models (such as the SECOND architecture) can be used to achieve object detection and segmentation in complex scenarios based on the spatial distribution and geometric characteristics of point clouds.

[0031] Simulated annealing algorithm: Starting from a high initial temperature, the simulated annealing algorithm continuously decreases the temperature parameter, combining probabilistic jump characteristics to randomly search for the global optimal solution of the objective function in the solution space. This means that it can probabilistically jump out of the local optimal solution and ultimately converge to the global optimal solution. Simulated annealing is a general optimization algorithm that theoretically possesses probabilistic global optimization performance. It has been widely used in engineering fields such as VLSI, production scheduling, control engineering, machine learning, neural networks, and signal processing.

[0032] A point cloud bounding box is the smallest rectangular box that describes the outer boundaries of point cloud data in three-dimensional space. It is used to accurately describe an object's size, position, orientation, and other information. When processing 3D data, calculating the bounding box effectively simplifies geometric operations such as collision detection, scaling, and rotation. Principal component analysis techniques can be used to construct a point cloud bounding box based on the principal axis orientation of the point cloud, ensuring that the orientation of the point cloud bounding box more closely matches the object's geometry, thereby improving space utilization efficiency.

[0033] Please refer to Figure 1 , Figure 1 This is a flowchart of the steps in one embodiment of the pile position deviation detection method of the present application. Depending on different needs, the order of the steps in this flowchart can be changed, and some steps can be omitted. The pile position deviation detection method of the present application can be applied to a pile position deviation detection device, but is not limited thereto, and the embodiments of the present application are not limited thereto.

[0034] The specific process of this embodiment is as follows Figure 1 As shown, the following steps are included: Step 101: obtaining point cloud data of a test area scanned by a drone, wherein a plurality of submerged piles installed on water are provided in the test area.

[0035] In some embodiments, by obtaining the area shape information of the area to be measured, determining the flight route information of the drone based on the area shape information, and finally controlling the flight of the drone based on the flight route information, the drone can scan the point cloud data in the area to be measured.

[0036] By determining the flight route information of the drone based on the regional shape information of the area to be tested, it is ensured that after the drone flies based on the flight route information, it can scan all the piles in the area to be tested, thereby ensuring that pile position deviation detection can be performed on each pile in the area to be tested subsequently, thereby improving the reliability of the pile position deviation detection method.

[0037] In some embodiments, the region shape information can be obtained by measuring the length and width of the region to be measured. It is understood that this embodiment does not specifically limit the method for obtaining the region shape information.

[0038] In some embodiments, the flight route information includes the flight route and route direction of the drone.

[0039] It is worth noting that in order to further ensure that the drone can scan the complete point cloud data of the area to be measured, the drone's route can also be optimized according to the following methods: 1. There must be a certain degree of overlap between flight strips. The lateral overlap of flight strips should be between 35% and 45%, the lateral overlap of images should be above 45%, and the heading overlap should be above 80%.

[0040] 2. When the drone is flying in a straight line, the inertial sensor will drift and accumulate errors. The design limit for continuous straight-line flight is 2 minutes. If the operation requires a continuous straight-line flight of more than 2 minutes, you can add a waypoint at the 2-minute mark, decelerate, and then increase the flight speed to achieve better accuracy.

[0041] 3. The direction of the route is determined according to the shape of the survey area. Each end of the route should extend about 30m beyond the area to be measured for the UAV to adjust its head and ensure that the UAV enters the survey area route smoothly to ensure the quality of the survey area data; point cloud data during acceleration, deceleration, turning, change of route, takeoff and landing will be deleted.

[0042] 4. Use a small aircraft to conduct a test flight, and then adjust the route according to the test flight results, which not only ensures the accuracy of the point cloud data obtained subsequently, but also ensures the safety of the operation.

[0043] In some embodiments, in the process of controlling the flight of the drone according to the flight route information, the turning speed of the drone is controlled not to exceed 3m / s, the attitude angle of the drone is not to exceed 20°, and the ascent and descent speeds of the drone are not to exceed 8m / s.

[0044] In some embodiments, before controlling the drone to fly according to the flight route information, the drone is also controlled to fly in the air for a period of time so that the condition of the drone can be observed, so that if any abnormality is found in the drone, the operation of the drone can be stopped immediately.

[0045] In some embodiments, after the drone obtains the point cloud data in the area to be measured, the integrity of the point cloud data is immediately checked. If the point cloud data quality meets the requirements, the field work can be terminated. Otherwise, the point cloud data collection continues until the data quality meets the requirements.

[0046] Step 102: extract features from the point cloud data to obtain original point cloud data of each pile.

[0047] In some embodiments, the pile is cylindrical in shape. Feature extraction is performed on the point cloud data by: performing cylinder segmentation on the point cloud data to extract cylindrical point clouds from the point cloud data; and performing monomer processing on the cylindrical point clouds to obtain original point cloud data for each pile.

[0048] In some embodiments, the drone's processor has built-in cylinder segmentation and individualization functions. This allows the drone to automatically extract features from point cloud data, ensuring that the data sent by the drone to the pile position deviation detection device is the original point cloud data, thereby improving the data processing efficiency of the pile position deviation detection device.

[0049] Step 103 : for each pile sinking, determine a first initial value according to the original point cloud data, and apply a first random perturbation to the first initial value according to a preset first objective function, so as to obtain a first output value after iteratively updating the first initial value.

[0050] Step 104: Apply a second random disturbance to the first output value according to a preset second objective function to iteratively update the first output value to obtain a second output value, wherein the second random disturbance is smaller than the first random disturbance, and the first initial value, the first output value, and the second output value are all used to characterize the state of pile driving.

[0051] Regarding step 103 and step 104, specifically, the first objective function and the second objective function are both constructed based on the simulated annealing algorithm; a first random perturbation is applied to the first initial value according to the preset first objective function to obtain a first output value after iteratively updating the first initial value, including: taking the first initial value as the first current parameter optimal solution of the first objective function, applying a first random perturbation to the first current parameter optimal solution to generate a first new parameter solution; comparing the first objective function value corresponding to the first new parameter solution and the first current parameter optimal solution to determine whether to update the first parameter optimal solution of the first objective function; repeating the previous step until the set first objective function condition is met, and obtaining the first objective function. The optimal solution of the first objective parameter of the target function is the first output value; a second random perturbation is applied to the first output value according to a preset second objective function to iteratively update the first output value to obtain a second output value, including: taking the first output value as the second current parameter optimal solution of the second objective function, applying a second random perturbation to the second current parameter optimal solution to generate a second new parameter solution; comparing the second objective function value corresponding to the second new parameter solution and the second current parameter optimal solution to determine whether to update the second parameter optimal solution of the second objective function; repeating the previous step until the set second objective function condition is met, and obtaining the second objective parameter optimal solution of the second objective function, which is the second output value.

[0052] It should be noted that, in this embodiment, the point cloud bounding box of the original point cloud data is calculated, and the point cloud bounding box is the first initial value.

[0053] Please refer to Figure 2, which is a schematic diagram of the effect of the second output value provided in an embodiment of the present application. A first random perturbation is first applied to the point cloud bounding box (i.e., the first initial value) for preliminary processing to obtain a relatively accurate first output value. A second random perturbation is then applied to the first output value for secondary processing. Because the second random perturbation is smaller than the first random perturbation, a more accurate second output value can be obtained with a smaller perturbation.

[0054] Step 105: Perform pile position deviation detection on the pile according to the second output value.

[0055] Compared with the related art, the embodiment of the present application has at least the following advantages: since the point cloud data scanned by the drone contains other objects in the area to be tested, the original point cloud data of each pile is obtained by extracting features from the point cloud data, thereby improving the accuracy of pile position deviation detection. A first initial value is obtained based on the original point cloud data of the pile, and a first random perturbation is first applied to the first initial value for preliminary processing to obtain a more accurate first output value. A second random perturbation is then applied to the first output value for secondary processing. Since the second random perturbation is smaller than the first random perturbation, a more accurate second output value can be obtained through a smaller perturbation. Since the second output value represents the state of the pile, the pile position deviation can be accurately detected by the second output value. In addition, the above-mentioned pile position deviation detection method does not require manual measurement. The pile position deviation detection of each pile in the area to be tested can be achieved by controlling the drone to scan the point cloud data of the area to be tested, thereby reducing labor costs and improving detection efficiency.

[0056] Please refer to Figure 3 , Figure 3 This is a flowchart of the steps of one embodiment of the pile position deviation detection method of the present application. Depending on different needs, the order of the steps in this flowchart can be changed, and some steps can be omitted. This pile position deviation detection method can be applied to the aforementioned pile position deviation detection device, but is not limited thereto, and this embodiment of the present application is not limited thereto.

[0057] This embodiment is a further improvement on the previous embodiment. Specifically, before feature extraction, the point cloud data is preprocessed to obtain target point cloud data that has been freed of noise and outliers. This further improves the accuracy of the pile position deviation detection method.

[0058] The specific process of this embodiment is as follows Figure 3 As shown, the following steps are included: Step 201: obtaining point cloud data of a test area scanned by a drone, wherein a plurality of submerged piles installed on water are provided in the test area.

[0059] Step 202 : pre-process the point cloud data to obtain target point cloud data from which noise data and outlier data are removed.

[0060] In some embodiments, the point cloud data is input into a point cloud outlier removal filter to obtain intermediate point cloud data from which outlier data is removed; and the intermediate point cloud data is input into a radius outlier filter to obtain target point cloud data from which noise data is removed.

[0061] Understandably, point cloud data inevitably contains noise due to factors such as scanning equipment accuracy, environmental factors, electromagnetic wave diffraction characteristics, and variations in the surface properties of the measured object. Furthermore, due to external factors such as line of sight obstructions and obstacles, outliers often exist that are far from the target point cloud. Noise and outliers can severely impact the accuracy of calculating local point cloud features (such as surface normals and curvature), thereby affecting the results of point cloud processing models such as point cloud registration, object extraction, and model reconstruction.

[0062] Therefore, this embodiment uses a point cloud outlier removal filter to remove outliers and a radius outlier filter to remove noise points, thereby improving the accuracy of the obtained target point cloud data.

[0063] Specifically, the point cloud outlier removal filter identifies outliers by calculating the density of points within the input point cloud. The denser the point cloud, the higher the density, and vice versa. The density is measured by defining the average distance between each point and its k neighbors as a density metric. If a point cloud falls below a certain density threshold, it is considered an outlier and removed.

[0064] The Radius Outlier Filter uses radius as a discriminant, removing all query points that do not have a sufficient number of neighboring points within a certain range of the input point cloud. Set the neighborhood threshold to N and define a sphere of radius d centered around the current point. Calculate the number of neighboring points within the sphere. If the number is greater than N, the point is retained; otherwise, it is removed.

[0065] Step 203: extract features from the target point cloud data to obtain original point cloud data of each pile.

[0066] Step 204 : for each pile sinking, determine a first initial value based on the original point cloud data, and apply a first random perturbation to the first initial value according to a preset first objective function, so as to obtain a first output value after iteratively updating the first initial value.

[0067] Step 205: Apply a second random disturbance to the first output value according to a preset second objective function to iteratively update the first output value to obtain a second output value, wherein the second random disturbance is smaller than the first random disturbance, and the first initial value, the first output value and the second output value are all used to characterize the state of pile driving.

[0068] Step 206: Perform pile position deviation detection on the pile according to the second output value.

[0069] Compared with the related art, the embodiment of the present application has at least the following advantages: since the point cloud data scanned by the drone contains other objects in the area to be tested, the original point cloud data of each pile is obtained by extracting features from the point cloud data, thereby improving the accuracy of pile position deviation detection. A first initial value is obtained based on the original point cloud data of the pile, and a first random perturbation is first applied to the first initial value for preliminary processing to obtain a more accurate first output value. A second random perturbation is then applied to the first output value for secondary processing. Since the second random perturbation is smaller than the first random perturbation, a more accurate second output value can be obtained through a smaller perturbation. Since the second output value represents the state of the pile, the pile position deviation can be accurately detected by the second output value. In addition, the above-mentioned pile position deviation detection method does not require manual measurement. The pile position deviation detection of each pile in the area to be tested can be achieved by controlling the drone to scan the point cloud data of the area to be tested, thereby reducing labor costs and improving detection efficiency.

[0070] Based on the same concept as the pile position deviation detection method in the above embodiment, the present application also provides a pile position deviation detection device, which can be used to perform the above pile position deviation detection method. For ease of explanation, the structural diagram of the embodiment of the pile position deviation detection device only shows the parts related to the embodiment of the present application. Those skilled in the art will understand that the illustrated structure does not constitute a limitation of the device, and the device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0071] like Figure 4 As shown, the pile position deviation detection device 400 includes an acquisition module 401, an extraction module 402, a processing module 403, and a detection module 404. In some embodiments, these modules may be programmable software instructions stored in a memory and executed by a processor. It is understood that in other embodiments, these modules may also be program instructions or firmware embedded in the processor.

[0072] An acquisition module 401 is configured to acquire point cloud data within a test area scanned by a drone, wherein a plurality of submerged piles installed above water are provided within the test area; An extraction module 402 is used to perform feature extraction on the point cloud data to obtain original point cloud data of each pile; For each of the piles, the processing module 403 is configured to determine a first initial value based on the original point cloud data, and apply a first random perturbation to the first initial value according to a preset first objective function, so as to iteratively update the first initial value to obtain a first output value; The processing module 404 is further configured to apply a second random perturbation to the first output value according to a preset second objective function, so as to iteratively update the first output value to obtain a second output value, wherein the second random perturbation is smaller than the first random perturbation, and the first initial value, the first output value, and the second output value are all used to represent the state of the pile driving; The detection module 406 is configured to perform pile position deviation detection on the pile according to the second output value.

[0073] Please refer to Figure 5 , Figure 5 This is a schematic diagram of an embodiment of an electronic device of the present application.

[0074] The electronic device 100 includes a memory 20, a processor 30, and a computer program 40 stored in the memory 20 and executable on the processor 30. When the processor 30 executes the computer program 40, the steps in the above-mentioned pile position deviation detection method embodiment are implemented, for example Figure 1 Steps 101 to 105 are shown.

[0075] For example, the computer program 40 can also be divided into one or more modules / units, one or more modules / units being stored in the memory 20 and executed by the processor 30. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 40 in the electronic device 100. For example, it can be divided into the acquisition module 401, determination module 402, processing module 403, and detection module 404 shown.

[0076] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 100 and does not constitute a limitation on the electronic device 100. The electronic device 100 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 100 may also include input and output devices, network access devices, buses, etc.

[0077] The processor 30 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, a single-chip microcomputer, or the processor 30 may be any conventional processor, etc.

[0078] The memory 20 can be used to store computer programs 40 and / or modules / units. The processor 30 implements various functions of the electronic device 100 by running or executing the computer programs and / or modules / units stored in the memory 20 and accessing data stored in the memory 20. The memory 20 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated during the use of the electronic device 100 (such as audio data). Furthermore, the memory 20 may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0079] If the modules / units integrated into the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a storage medium, and when executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The storage medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content contained in the storage medium can be appropriately increased or decreased according to the requirements of patent practice. For example, according to patent practice, the storage medium does not include electric carrier signal and telecommunication signal.

[0080] The above is a detailed introduction to the pile position deviation detection method, device, electronic device and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A pile position deviation detection method, characterized in that: include: Acquire point cloud data of a test area scanned by a drone, wherein a plurality of submerged piles installed above water are provided in the test area; Performing feature extraction on the point cloud data to obtain original point cloud data of each pile; For each of the piles, determining a first initial value based on the original point cloud data, and applying a first random perturbation to the first initial value according to a preset first objective function, so as to obtain a first output value after iteratively updating the first initial value; applying a second random perturbation to the first output value according to a preset second objective function to iteratively update the first output value to obtain a second output value, wherein the second random perturbation is smaller than the first random perturbation, and the first initial value, the first output value, and the second output value are all used to characterize the state of the pile driving; The pile position deviation of the pile is detected according to the second output value.

2. The pile position deviation detection method according to claim 1, characterized in that: The first objective function and the second objective function are both constructed based on a simulated annealing algorithm; Applying a first random disturbance to the first initial value according to a preset first objective function to iteratively update the first initial value to obtain a first output value, including: Taking the first initial value as a first current parameter optimal solution of the first objective function, applying a first random perturbation to the first current parameter optimal solution to generate a first new parameter solution; Comparing the first objective function value corresponding to the first new parameter solution and the first current parameter optimal solution, and determining whether to update the first parameter optimal solution of the first objective function; Repeat the previous step until the set first objective function condition is met, and the optimal solution of the first objective parameter of the first objective function is obtained, which is the first output value; Applying a second random disturbance to the first output value according to a preset second objective function to iteratively update the first output value to obtain a second output value includes: Taking the first output value as a second current parameter optimal solution of the second objective function, applying a second random perturbation to the second current parameter optimal solution to generate a second new parameter solution; Comparing the second objective function value corresponding to the second new parameter solution and the second current parameter optimal solution, and determining whether to update the second parameter optimal solution of the second objective function; Repeat the previous step until the set second objective function condition is met, and the optimal solution of the second objective parameter of the second objective function is obtained, which is the second output value.

3. The pile position deviation detection method according to claim 1 or 2, characterized in that: The determining of the first initial value according to the original point cloud data includes: A point cloud bounding box of the original point cloud data is calculated, where the point cloud bounding box is the first initial value.

4. The pile position deviation detection method according to claim 1, characterized in that: Before extracting features from the point cloud data, the method further includes: Preprocessing the point cloud data to obtain target point cloud data after removing noise data and outlier data; The feature extraction of the point cloud data includes: Feature extraction is performed on the target point cloud data.

5. The pile position deviation detection method according to claim 4, characterized in that: The preprocessing of the point cloud data to obtain target point cloud data with noise data and outlier data removed includes: Inputting the point cloud data into a point cloud outlier removal filter to obtain intermediate point cloud data from which outlier data has been removed; The intermediate point cloud data is input into a radius outlier filter to obtain the target point cloud data after noise data is removed.

6. The pile position deviation detection method according to claim 1, characterized in that: The pile is cylindrical; the feature extraction of the point cloud data to obtain the original point cloud data of each pile includes: Performing cylinder segmentation on the point cloud data to extract cylindrical point clouds from the point cloud data; The cylindrical point cloud is singulated to obtain the original point cloud data of each of the piles.

7. The pile position deviation detection method according to any one of claims 1 to 6, characterized in that: The method further comprises: During the process of the drone scanning the area to be measured, the turning speed of the drone is controlled not to exceed 3 m / s, the attitude angle of the drone is controlled not to exceed 20°, and the ascent and descent speeds of the drone are controlled not to exceed 8 m / s.

8. A pile position deviation detection device, characterized in that: include: Acquisition module, extraction module, processing module and detection module; The acquisition module is used to acquire point cloud data within the area to be measured scanned by the drone, wherein a plurality of submerged piles installed on water are provided in the area to be measured; The extraction module is used to extract features from the point cloud data to obtain original point cloud data of each pile; For each of the piles, the processing module is used to determine a first initial value based on the original point cloud data, and apply a first random perturbation to the first initial value according to a preset first objective function, so as to obtain a first output value after iteratively updating the first initial value; The processing module is further configured to apply a second random perturbation to the first output value according to a preset second objective function, so as to obtain a second output value after iteratively updating the first output value, wherein the second random perturbation is smaller than the first random perturbation, and the first initial value, the first output value, and the second output value are all used to characterize the state of the pile driving; The detection module is used to perform pile position deviation detection on the pile according to the second output value.

9. An electronic device comprising a processor and a memory, characterized in that: The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the pile position deviation detection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the pile position deviation detection method according to any one of claims 1 to 7.

Images