A method and system for rapid detection of embankment crack danger of unmanned aerial vehicle

Abstract

The application discloses a kind of unmanned aerial vehicle embankment crack danger rapid detection method and system, method includes: obtaining embankment ground information data;Crack inspection data is collected based on the preset inspection route strategy of unmanned aerial vehicle;Crack inspection data is superimposed with embankment ground information data, establishes embankment three-dimensional image, and in three-dimensional image, key position point cloud data of embankment crack is compared and analyzed based on time sequence, and the deformation damage area of embankment crack is extracted;The at least one crack region containing one embankment crack is obtained by block processing to deformation damage area;Based on the difference between the maximum crack width and the minimum crack width of at least one crack region is divided by time and derivation, the crack change slope is obtained, and the crack danger grade is determined according to the crack change slope.Solved artificial inspection can only perform part of simple detection work and the range of work is more limited, guarantee the unmanned aerial vehicle inspection effect.

Description

Technical Field

[0001] This invention belongs to the field of water conservancy engineering technology, and in particular relates to a method and system for rapid detection of cracks in dikes using unmanned aerial vehicles (UAVs). Background Technology

[0002] With the deepening of high-quality development of water conservancy across the country, people are paying increasing attention to the safety of water conservancy projects. Especially under conditions of abnormal climate and frequent extreme weather events, the development and extension of cracks in dikes are often a precursor to impending dike emergencies. The rate of deformation and failure reflects the deformation and damage characteristics of the dike. Once the rate of crack deformation accelerates, it is highly likely that dike slope failure, landslides, seepage, piping, or even dike collapse will occur, causing disasters to residents outside the dike. Therefore, it is essential to conduct rapid detection of dike cracks.

[0003] Currently, the detection of dike cracks and potential hazards commonly relies on manual inspections. This method requires manual inspection of dike equipment, which is time-consuming, labor-intensive, and lacks timeliness. While there are ongoing explorations into using drone oblique photography and InSAR technology for dike hazard inspection, there is a lack of comparative analysis of the original dike surface topography. The analysis of inspection results and the dissemination of early warning information largely depend on qualitative methods such as expert experience, without considering the mechanism of dike crack deformation and evolution, resulting in low reliability.

[0004] It is evident that existing methods for detecting cracks in dikes suffer from technical drawbacks such as poor timeliness, high cost, and low reliability, and urgently need improvement. Summary of the Invention

[0005] This invention provides a method and system for rapid detection of cracks in dikes using unmanned aerial vehicles (UAVs), which addresses the technical problem that manual inspections can only perform some simple detection tasks and have a limited scope, resulting in low inspection efficiency.

[0006] In a first aspect, the present invention provides a method for rapid detection of levee crack hazards using unmanned aerial vehicles (UAVs), comprising: acquiring levee ground information data; acquiring crack inspection data collected by the UAV based on a preset inspection route strategy; overlaying the crack inspection data with the levee ground information data to establish a three-dimensional image of the levee, and performing comparative analysis on the point cloud data of key locations of levee cracks in the three-dimensional image based on a time series to extract the deformation and damage areas of the levee cracks; dividing the deformation and damage areas into blocks to obtain at least one crack region containing one levee crack; obtaining the crack change slope by dividing the difference between the maximum and minimum crack widths of the at least one crack region by time and taking the derivative, and determining the crack hazard level based on the crack change slope.

[0007] Secondly, the present invention provides a rapid detection system for cracks in levees using unmanned aerial vehicles (UAVs), comprising: a first acquisition module configured to acquire ground information data of the levee; a second acquisition module configured to acquire crack inspection data collected by the UAV based on a preset inspection route strategy; an extraction module configured to overlay the crack inspection data with the ground information data of the levee to establish a three-dimensional image of the levee, and to perform comparative analysis on the point cloud data of key locations of the levee cracks in the three-dimensional image based on a time series to extract the deformation and damage areas of the levee cracks; a processing module configured to divide the deformation and damage areas into blocks to obtain at least one crack region containing one levee crack; and a determination module configured to divide the difference between the maximum and minimum crack widths of the at least one crack region by time and take the derivative to obtain the crack change slope, and to determine the crack hazard level based on the crack change slope.

[0008] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the rapid detection method for levee crack hazards according to any embodiment of the present invention.

[0009] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the rapid detection method for cracks in dikes by unmanned aerial vehicles according to any embodiment of the present invention.

[0010] This application discloses a method and system for rapid detection of cracks in embankments using unmanned aerial vehicles (UAVs). By conducting a UAV-based inspection of the embankment in a zigzag pattern, and considering both orthogonal and oblique photography, the inspection path is executed sequentially to achieve a comprehensive comparison of embankment cracks. This obtains deformation data of the embankment cracks in time and space, improves the adaptability of the UAV inspection system to terrain and environment, and solves the problems of manual inspection, which can only perform some simple detection work and has a limited working range, thus ensuring the effectiveness of UAV-based inspection. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart of a method for rapid detection of cracks in embankments using unmanned aerial vehicles (UAVs) according to an embodiment of the present invention;

[0013] Figure 2 This is a framework diagram of the UAV dike system for a specific embodiment provided by the present invention;

[0014] Figure 3 This is a path map of unmanned aerial photography of dike cracks for a specific embodiment provided by the present invention;

[0015] Figure 4 This is a flowchart for evaluating dike cracks for a specific embodiment provided by the present invention;

[0016] Figure 5 This is a structural block diagram of a rapid detection system for UAV dike crack hazards provided by an embodiment of the present invention;

[0017] Figure 6 This is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Please refer to Figure 1 , which shows a flowchart of a method for rapidly detecting UAV dike crack hazards in the present application.

[0020] As Figure 1 shown, the method for rapidly detecting UAV dike crack hazards specifically includes the following steps:

[0021] Step S101, obtaining dike ground information data.

[0022] In this step, the dike ground information data includes longitude and latitude data, elevation data, length data, width data, formation lithology data, and DEM data.

[0023] Step S102, obtaining crack inspection data collected by the UAV based on a preset inspection route strategy.

[0024] In this step, the inspection route strategy is to set the inspection route along two directions parallel to the dike axis and perpendicular to the dike central axis, and the UAV executes via the route in a "hanging" shape in two directions of oblique photography and orthophoto.

[0025] Step S103: Superimpose the crack inspection data and the embankment ground information data to establish a three-dimensional image of the embankment, and conduct a comparative analysis of the key position point cloud data of the embankment cracks based on the time series in the three-dimensional image to extract the deformation and damage areas of the embankment cracks.

[0026] Step S104: Perform a block processing on the deformation and damage area to obtain at least one crack area containing one embankment crack.

[0027] Step S105: Divide the difference between the maximum crack width and the minimum crack width of the at least one crack area by the time and take the derivative to obtain the crack change slope, and determine the crack danger level according to the crack change slope.

[0028] In this step, the expression for determining the crack danger level is:

[0029]

[0030] In the formula, Δl max and Δl min are the maximum crack width and the minimum crack width respectively, t is the monitoring time, is the crack width change slope.

[0031] In summary, the method of this application, through the "hanging" - shaped inspection of the embankment, takes into account the settings of orthophoto and oblique photography. The inspection path is executed in sequence to achieve a full - range comparison of the embankment cracks, obtain the deformation data of the embankment cracks in time and space, improve the adaptability of the UAV inspection system to the terrain environment, solve the problem that manual inspection can only perform some simple detection work and the working range is relatively limited, and ensure the inspection effect of the UAV inspection.

[0032] In a specific embodiment, before use, prepare the embankment information database, load the DEM data floor of the embankment, and ensure the surface information of the inspection area such as the scope and elevation of the UAV inspection.

[0033] Specifically, please refer to Figure 2 , the rapid detection system for embankment crack danger includes an embankment information database, a crack identification module, an air - ground data fusion module, and an information analysis and release module.

[0034] Constructing the embankment information database includes the basic information of the embankment and its attribute table; the basic information includes data such as name, longitude and latitude, elevation, length, width, formation lithology, and DEM. Use GIS software to superimpose the database and the terrain to process it into the embankment ground information data floor; the attribute table assigns values to each basic information.

[0035] Set the UAV inspection path planning in the crack identification module, perform a block processing on the monitoring area, and plan the optimal flight route.

[0036] Specifically, for drone inspection path planning, see [link to relevant documentation]. Figure 3 As shown, an automatic inspection route adjustment strategy is configured, which includes the following steps:

[0037] The inspection route is set along two directions: parallel to the dike axis and perpendicular to the dike's central axis. The drone will perform the inspection along the route in a zigzag pattern using both oblique and orthophoto photography.

[0038] To conduct parameter inspections of cracks in the dike, a lidar system mounted on a drone is used with oblique photography technology. The laser beam is emitted towards the target, and the signals reflected back from the target are received and calculated together with the emitted signals to obtain point cloud data of the dike ground.

[0039] The crack parameters were processed to the centimeter level using Cloudcomper point cloud processing software.

[0040] The air-ground fusion module overlays crack inspection data obtained by UAVs and airborne radar with the dike information data base plate, and uses Suffer software to create a three-dimensional image of the dike.

[0041] The data base plate and crack inspection data are rendered on the same screen to construct a tilt model and display the three-dimensional point cloud and vector results on the same screen.

[0042] The three-dimensional superimposed data is then compared and analyzed over time using the Suffer software to extract the deformation and damage areas near the cracks and analyze the dynamic change characteristics of the cracks.

[0043] refer to Figure 4 The information analysis and dissemination module includes high-precision reconstruction of ground data, which is sent to the hazard classification system in real time. The DS evidence algorithm is used to fuse and process the crack inspection data. The steps are as follows:

[0044] The software is used to accurately reconstruct ground data from point cloud data, and the data is sent to the hazard classification system in real time.

[0045] Construct a hazard classification system for classifying hazard situations of dike cracks, and establish a threshold matrix table for classifying and classifying hazard situations of dike cracks;

[0046] The crack distribution characteristics and monitoring parameters measured by UAVs are compared and analyzed with the matrix table one by one, and the crack hazard classification is obtained through air-ground data fusion strategy.

[0047] The threshold matrix table for classifying and grading crack risks is used as the basis for judging crack risk classification and grading. The classification basis for dike crack risks includes: the dike importance and the danger of dike instability, which are divided into Class I dike cracks, Class II dike cracks and Class III dike cracks.

[0048] The analysis is based on the derivative of the horizontal displacement rate of the cracks in the dike, combined with the classification of crack hazard.

[0049] When the causes of cracks in the dike are complex, the DS evidence algorithm is used to fuse and process the crack inspection data for calculation.

[0050] The DS evidence algorithm for dike crack hazards includes the following steps:

[0051] Based on the safety and importance of the dikes, dike hazard assessment indicators were selected to construct a dike hazard assessment indicator system and determine the hazard level of each indicator. Each assessment indicator was derived from a comprehensive analysis of dike data, crack deformation rate monitoring data, and expert experience, and was calculated using evidence fusion theory to classify the dike hazard level ranges.

[0052] Based on the DS evidence theory, the measured values ​​of various indicators of dike risk are substituted into the evidence theory calculation formula.

[0053]

[0054] In the formula, m(C) represents the fusion probability of each monitoring data point, and w1 represents the risk assessment index A. i The weights of (such as crack width and crack depth), m1(A) i ) is the evaluation index A i The basic probability, w2 is the risk assessment index B. j The weight of (such as crack width-time displacement velocity, or the slope of the displacement-time curve), m2(B) j ) is the evaluation index B j The basic probability is given by: U is the identification frame, C is the sum of the basic probabilities of all subsets of the levee crack evaluation, and K is the degree of incompatibility between the monitoring data. The formula for calculating K is:

[0055]

[0056] Based on the membership matrix of each parameter index of the hazard obtained from the above calculation, a basic probability allocation is performed on the evaluation index of the levee hazard.

[0057] Based on the above basic probability allocation results, the following formula can be used to transform it into the basic probability allocation of evidence theory:

[0058]

[0059] In the formula: i is the target index of each evaluation indicator (i = 1, 2, ..., α), j is the sub-target index of the evaluation indicator (j = 1, 2, ..., β), s, k, U rs(gij) U s (A k The terms are: language symbol, feature set symbol, expert r's score for indicator g, and expert rating level, respectively.

[0060] Based on the above scoring results, the dynamic weight coefficients of each evaluation indicator are first calculated as follows:

[0061]

[0062] In the formula, w il R represents the dynamic weighting coefficients. i This represents the absolute compatibility of a certain monitoring indicator.

[0063] Furthermore, the static weight coefficients of the evaluation indicators are assigned values ​​using the expert experience method.

[0064] Furthermore, the DS fusion criterion is used to fuse and calculate the dynamic and static weighting coefficients of the aforementioned dike cracks, obtaining the basic probabilities corresponding to each coefficient in the dike crack hazard assessment. The calculated basic probability values ​​are then compared and analyzed, and the highest basic probability value, corresponding to the dike crack hazard level, is selected as the final crack hazard prediction result (see [reference]). Figure 4 ).

[0065] Based on the inertial navigation model of crack deformation development, the point cloud data model of cracks is compared and classified with the model of levee hazard classification, the levee hazard level is calculated with one click, and the data is released in real time on the terminal through narrowband Internet of Things technology.

[0066] Please see Figure 5 The diagram shows a structural block diagram of a rapid detection system for cracks in embankments using unmanned aerial vehicles (UAVs) according to this application.

[0067] like Figure 5 As shown, the UAV-based rapid detection system for cracks in embankments 200 includes a first acquisition module 210, a second acquisition module 220, an extraction module 230, a processing module 240, and a determination module 250.

[0068] The system comprises the following modules: a first acquisition module 210, configured to acquire ground information data of the dike; a second acquisition module 220, configured to acquire crack inspection data collected by a UAV based on a preset inspection route strategy; an extraction module 230, configured to overlay the crack inspection data with the ground information data of the dike to establish a three-dimensional image of the dike, and to perform comparative analysis on the point cloud data of key locations of the dike cracks in the three-dimensional image based on time series to extract the deformation and damage areas of the dike cracks; a processing module 240, configured to divide the deformation and damage areas into blocks to obtain at least one crack area containing a dike crack; and a determination module 250, configured to divide the difference between the maximum and minimum crack widths of the at least one crack area by time and take the derivative to obtain the crack change slope, and to determine the crack hazard level based on the crack change slope.

[0069] It should be understood that Figure 5 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 5 The various modules in the document will not be described in detail here.

[0070] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the rapid detection method for cracks in dikes by unmanned aerial vehicles in any of the above method embodiments.

[0071] In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows:

[0072] Obtain ground information data of the dike;

[0073] Acquire crack inspection data collected by drones based on a preset inspection route strategy;

[0074] The crack inspection data is overlaid with the embankment ground information data to establish a three-dimensional image of the embankment. The point cloud data of key locations of the embankment cracks in the three-dimensional image are compared and analyzed based on time series to extract the deformation and damage areas of the embankment cracks.

[0075] The deformed and damaged area is divided into blocks to obtain at least one crack area containing a levee crack;

[0076] The crack change slope is obtained by dividing the difference between the maximum and minimum crack widths in the at least one crack region by time and taking the derivative, and the crack hazard level is determined based on the crack change slope.

[0077] Computer-readable storage media may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required for at least one function; the data storage area may store data created based on the use of the UAV-based rapid detection system for levee cracks. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely configured relative to a processor, which can be connected to the UAV-based rapid detection system for levee cracks via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0078] Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 6 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 6 Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby realizing the rapid detection method for levee cracks using a drone as described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the rapid detection system for levee cracks using a drone. The output device 340 may include a display screen or other display device.

[0079] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0080] In one implementation, the aforementioned electronic device is applied to a rapid detection system for cracks in levees using unmanned aerial vehicles (UAVs). As a client, it includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0081] Obtain ground information data of the dike;

[0082] Acquire crack inspection data collected by drones based on a preset inspection route strategy;

[0083] The crack inspection data is overlaid with the embankment ground information data to establish a three-dimensional image of the embankment. The point cloud data of key locations of the embankment cracks in the three-dimensional image are compared and analyzed based on time series to extract the deformation and damage areas of the embankment cracks.

[0084] The deformed and damaged area is divided into blocks to obtain at least one crack area containing a levee crack;

[0085] The crack change slope is obtained by dividing the difference between the maximum and minimum crack widths in the at least one crack region by time and taking the derivative, and the crack hazard level is determined based on the crack change slope.

[0086] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for rapid detection of cracks in levees using unmanned aerial vehicles (UAVs), characterized in that, including: Obtain the embankment ground information data; Obtain the crack inspection data collected by the drone based on a preset inspection route strategy. The inspection route strategy is to set the inspection route in two directions, parallel to the embankment axis and perpendicular to the embankment central axis. The drone's route is executed in a "hanging" shape by oblique photography and orthophoto in two directions; Overlay the crack inspection data with the embankment ground information data to establish a three-dimensional stereo image of the embankment, and perform a comparative analysis on the key position point cloud data of the embankment cracks based on time series in the three-dimensional stereo image to extract the deformation and damage areas of the embankment cracks; Perform a block processing on the deformation and damage area to obtain at least one crack area containing one embankment crack; Based on the difference between the maximum crack width and the minimum crack width of the at least one crack area divided by time and taking the derivative, obtain the crack change slope, and determine the crack danger level according to the crack change slope. The expression for determining the crack danger level is: ， In the formula, These are the maximum and minimum crack widths, respectively. For monitoring time, The slope of the crack change.

2. The method for rapid detection of cracks in dikes using unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The embankment ground information data includes longitude and latitude data, elevation data, length data, width data, formation lithology data, and DEM data.

3. A rapid detection system for cracks in levees using unmanned aerial vehicles (UAVs), characterized in that, including: A first acquisition module configured to obtain the embankment ground information data; A second acquisition module configured to obtain the crack inspection data collected by the drone based on a preset inspection route strategy. The inspection route strategy is to set the inspection route in two directions, parallel to the embankment axis and perpendicular to the embankment central axis. The drone's route is executed in a "hanging" shape by oblique photography and orthophoto in two directions; An extraction module configured to overlay the crack inspection data with the embankment ground information data to establish a three-dimensional stereo image of the embankment, and perform a comparative analysis on the key position point cloud data of the embankment cracks based on time series in the three-dimensional stereo image to extract the deformation and damage areas of the embankment cracks; A processing module configured to perform a block processing on the deformation and damage area to obtain at least one crack area containing one embankment crack; A determination module configured to based on the difference between the maximum crack width and the minimum crack width of the at least one crack area divided by time and taking the derivative, obtain the crack change slope, and determine the crack danger level according to the crack change slope. The expression for determining the crack danger level is: ， In the formula, These are the maximum and minimum crack widths, respectively. For monitoring time, The slope of the crack change.

4. An electronic device, characterized in that, including: At least one processor, and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method according to any one of claims 1 to 2.

Images