Shoreline Evolution Monitoring Method and Device Based on Multi-Source Data Fusion

Abstract

The present disclosure provides a beach evolution monitoring method and device based on multi-source data fusion, which relates to the technical field of data processing. The method includes: collecting airborne LiDAR point cloud data and multi-beam bathymetric grid data corresponding to a target beach area; performing terrain zoning on the beach area based on the spatial distribution characteristics in the airborne LiDAR point cloud data and the multi-beam bathymetric grid data; according to the result of the terrain zoning, using a weighted fusion method to perform terrain adaptation fusion on the airborne LiDAR point cloud data and the multi-beam bathymetric grid data to obtain terrain fusion data; constructing a beach evolution prediction model according to the elevation change characteristics and spatial change characteristics; according to the beach evolution prediction model, predicting the beach change trend and generating monitoring and warning information. The technical solution in the present disclosure can improve the monitoring accuracy and processing efficiency of the beach area.

Description

Background Art

[0002] The topographic changes in the beach area are affected by both natural factors and human activities, and its dynamic evolution is of great significance to the ecological environment, disaster prevention and mitigation, and infrastructure safety.

[0003] The existing technologies mainly rely on single measurement means for terrain data collection, such as using single-beam bathymeters or lidar ranging. However, in complex environments, the applicability of such measurement methods is limited, and it is difficult to meet the measurement accuracy requirements of different regions simultaneously. For example, although the observation means based on remote sensing can cover a large area, there are certain limitations in local fine measurement, especially in the land-water interface area. In addition, in terms of real-time monitoring and early warning response, the existing methods mainly rely on manual interpretation or static judgment mechanisms based on fixed thresholds, resulting in insufficient perception ability of sudden beach changes, lagging response speed, and difficulty in accurately identifying abnormal situations in a timely manner and taking corresponding early warning measures.

[0004] In summary, the accuracy and efficiency of beach evolution monitoring in the existing technologies are difficult to guarantee, and cannot meet the high-precision and continuous monitoring requirements for beach topographic changes. Summary of the Invention

[0005] The purpose of the embodiments of the present disclosure is to provide a beach evolution monitoring method and system based on multi-source data fusion, so as to at least to some extent improve the monitoring accuracy and processing efficiency of beach evolution monitoring.

[0006] Other features and advantages of the present disclosure will become apparent through the following detailed description, or be learned in part through the practice of the present disclosure.

[0007] According to the first aspect of the embodiments of the present disclosure, a beach evolution monitoring method based on multi-source data fusion is provided. The method includes: collecting airborne LiDAR point cloud data and multi-beam bathymetric grid data corresponding to the target beach area; performing topographic zoning on the beach area based on the spatial distribution characteristics in the airborne LiDAR point cloud data and multi-beam bathymetric grid data; according to the results of the topographic zoning, using a weighted fusion method to perform topographic adaptation fusion on the airborne LiDAR point cloud data and multi-beam bathymetric grid data to obtain topographic fusion data; based on the topographic fusion data at different time periods, obtaining the elevation change characteristics and spatial change characteristics corresponding to the beach area, and constructing a beach evolution prediction model according to the elevation change characteristics and spatial change characteristics; according to the beach evolution prediction model, predicting the beach change trend and generating monitoring and early warning information.

[0008] According to a second aspect of an embodiment of the present disclosure, a shore evolution monitoring device based on multi-source data fusion is provided, and the device includes: a data acquisition module, which is used to collect airborne LiDAR point cloud data and multi-beam bathymetry grid data corresponding to the target shore area; a terrain partitioning module, which is used to perform terrain partitioning on the shore area based on the spatial distribution characteristics of the airborne LiDAR point cloud data and the multi-beam bathymetry grid data; a data fusion module, which is used to perform terrain adaptation and fusion on the airborne LiDAR point cloud data and the multi-beam bathymetry grid data according to the result of the terrain partitioning, so as to obtain terrain fusion data; a model construction module, which is used to obtain the elevation change characteristics and spatial change characteristics corresponding to the shore area according to the terrain fusion data at different times, and construct a shore evolution prediction model according to the elevation change characteristics and the spatial change characteristics; a model prediction module, which is used to predict the shore change trend and generate monitoring and early warning information according to the shore evolution prediction model.

[0009] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method for monitoring shore evolution based on multi-source data fusion is implemented.

[0010] According to a fourth aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for monitoring shore evolution based on multi-source data fusion is implemented.

[0011] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0012] The shore evolution monitoring method based on multi-source data fusion in the exemplary embodiment of the present disclosure, firstly, can obtain high-precision terrain information in different spatial medium environments through the joint collection of airborne LiDAR point cloud data and multi-beam bathymetric grid data, avoiding the problem of data loss or reduced accuracy that may be caused by a single measurement method in complex shore areas. Terrain zoning is performed based on the spatial distribution characteristics of airborne LiDAR point cloud data and multi-beam bathymetric grid data, so that land areas, water areas and boundary areas can be clearly divided, thereby providing an accurate regional division basis for subsequent data processing, and avoiding the discontinuity problem that may be caused by direct splicing of different measurement data in the boundary area.

[0013] Secondly, based on the terrain zoning, a weighted fusion method is used to perform terrain adaptation and fusion on airborne LiDAR point cloud data and multi-beam bathymetric grid data, which can more accurately characterize the terrain features of the shore beach area under different environmental conditions. Moreover, by extracting the elevation change features and spatial change features from the terrain fusion data of different time periods, the dynamic evolution information of the shore beach area can be presented in the comparison of multi-time period data. Using the elevation change features and spatial change features to construct a shore beach evolution prediction model enables the dynamic change trend of the shore beach area to be modeled based on historical data, so as to continuously optimize the model parameters in long-term monitoring and improve the prediction accuracy. Based on the shore beach evolution prediction model, the future trend is predicted and monitoring and early warning information is generated, so that the changes in the shore beach area can not only be monitored in real time, but also be identified and reasonable early warning prompts can be given in the early stage of trend evolution. Thus, to a certain extent, the monitoring accuracy and processing efficiency of the shore beach area are improved.

[0014] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0016] Figure 1 Schematically shows a flowchart of a shore beach evolution monitoring method based on multi-source data fusion according to some embodiments of the present disclosure.

[0017] Figure 2 Schematically shows a flowchart of a method for terrain zoning of a shore beach area according to some embodiments of the present disclosure.

[0018] Figure 3 Schematically shows a flowchart of a method for constructing a shore beach evolution prediction model according to some embodiments of the present disclosure.

[0019] Figure 4 Schematically shows a block diagram of a shore beach evolution monitoring device based on multi-source data fusion according to some embodiments of the present disclosure.

[0020] Figure 5 Schematically shows a structural diagram of a computer system of an electronic device according to some embodiments of the present disclosure.

[0021] Figure 6A schematic diagram of a computer-readable storage medium according to some embodiments of the present disclosure is schematically shown.

[0022] In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed implementation manners

[0023] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with this specification. On the contrary, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.

[0024] The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit this specification. The singular forms "a", "the", and "said" used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0025] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this specification, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0026] Now, the exemplary embodiments will be described more fully with reference to the drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more complete and comprehensive, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0027] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to give a full understanding of the embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0028] In addition, the attached drawings are only schematic diagrams and are not necessarily drawn to scale. The block diagrams shown in the attached drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0029] The shoreline topography is affected by natural factors and human activities, and its dynamic changes are crucial for the ecological environment, disaster prevention and mitigation, and the safety of infrastructure. Related technologies mainly rely on single measurement methods, such as single-beam bathymeters or lidar ranging, but their applicability is limited in complex environments and it is difficult to meet the measurement accuracy requirements of different regions simultaneously, especially in the land-water interface area. In addition, current monitoring and early warning methods mostly rely on manual interpretation or fixed threshold judgment, resulting in limited perception ability of sudden changes, lagging response, and difficulty in timely identifying and warning abnormal situations.

[0030] To solve some or all of the above technical problems, the present disclosure provides a shoreline evolution monitoring method based on multi-source data fusion. Figure 1 Schematically shows a flow diagram of a shoreline evolution monitoring method based on multi-source data fusion according to some embodiments of the present disclosure. Refer to Figure 1 As shown, the shoreline evolution monitoring method based on multi-source data fusion may include the following steps:

[0031] Step S110, collecting airborne LiDAR point cloud data and multi-beam bathymetric grid data corresponding to the target shoreline area;

[0032] Step S120, based on the spatial distribution characteristics in the airborne LiDAR point cloud data and multi-beam bathymetric grid data, performing terrain zoning on the shoreline area;

[0033] Step S130, according to the result of terrain zoning, using a weighted fusion method to perform terrain adaptation fusion on the airborne LiDAR point cloud data and multi-beam bathymetric grid data to obtain terrain fusion data;

[0034] Step S140, based on the terrain fusion data of different time periods, obtaining the elevation change characteristics and spatial change characteristics corresponding to the shoreline area, and constructing a shoreline evolution prediction model according to the elevation change characteristics and spatial change characteristics;

[0035] Step S150, according to the shoreline evolution prediction model, predicting the shoreline change trend and generating monitoring and early warning information.

[0036] In the actual operation process, first, an airborne LiDAR device is used to scan the target beach area to obtain point cloud data covering the land area, and a multibeam sounding device is used to collect sounding grid data of the water area. After the data collection is completed, the spatial distribution characteristics of the airborne LiDAR point cloud data and the multibeam sounding grid data are analyzed. By calculating the elevation distribution and regional characteristics, the topographic characteristics of the beach area are determined, and the target area is divided into land area, water area, and land-water boundary area accordingly. Then, according to the results of the topographic zoning, a weighted fusion method is used to perform topographic adaptation fusion on the airborne LiDAR point cloud data and the multibeam sounding grid data. Specifically, in the land area, the airborne LiDAR point cloud data is used as the main data source; in the water area, the multibeam sounding grid data is the main; in the land-water boundary area, the weights are dynamically adjusted according to the topographic characteristics, and the two types of data are fused. Then, based on the topographic fusion data of different time periods, the elevation change characteristics and spatial change characteristics are extracted to construct a beach evolution prediction model. During the model training process, it is necessary to optimize the parameter settings based on long-time series data to enable the model to adapt to different types of beach environments. Finally, based on the beach evolution prediction model, the beach change trend is predicted and monitoring and warning information is generated so that relevant personnel can take preventive measures in a timely manner.

[0037] Next, the technical details of the above beach evolution monitoring method based on multi-source data fusion will be introduced in detail in other embodiments of the present disclosure.

[0038] In step S110, the airborne LiDAR point cloud data and the multibeam sounding grid data corresponding to the target beach area are collected. Among them, the target beach area represents the beach range to be monitored and analyzed, including the land area, the water area, and the land-water boundary area. The airborne LiDAR point cloud data can represent a three-dimensional space coordinate data set obtained by an airborne lidar (Light Detection and Ranging, LiDAR) device. This data set is composed of a large number of discontinuous points, and each point can contain elevation information and reflection intensity information. The multibeam sounding grid data can represent the underwater topographic data obtained by a multibeam echo sounder (MBES). This data is based on the principle of acoustic echo, and the underwater area is covered by multiple acoustic beams to generate regular or irregular grid-like water depth information.

[0039] In some embodiments, collecting the airborne LiDAR point cloud data and the multibeam sounding grid data corresponding to the target beach area specifically includes the following technical steps:

[0040] First, use an airborne LiDAR device and a multibeam sounding device to obtain the elevation values corresponding to the target shore area, and construct airborne LiDAR point cloud data and multibeam sounding grid data respectively according to the elevation values. Among them, the elevation value can represent the vertical height information of each measurement point in the target shore area, representing the surface elevation of the land area in airborne LiDAR measurement and the water depth of the underwater terrain in multibeam sounding measurement, expressed as a value relative to the reference plane.

[0041] Then, denoise and perform three-dimensional coordinate transformation on the airborne LiDAR point cloud data and the multibeam sounding grid data to unify the data format. Among them, denoising means that during the data processing process, noise filtering operations are performed on the airborne LiDAR point cloud data and the multibeam sounding grid data, which can include removing abnormal points, mismeasurement points, and non-terrain echo interference to improve the accuracy and reliability of the data. Three-dimensional coordinate transformation can represent a unified spatial transformation of the coordinate systems of the airborne LiDAR point cloud data and the multibeam sounding grid data to align them in the same geographic reference coordinate system to ensure the spatial consistency of different data sources.

[0042] Exemplarily, the following technical steps can be used to denoise and perform three-dimensional coordinate transformation on the airborne LiDAR point cloud data and the multibeam sounding grid data:

[0043] First, perform denoising processing on the airborne LiDAR point cloud data. Denote the airborne LiDAR point cloud data as:

[0044]

[0045] Among them, represents the horizontal coordinate of the th point in the airborne LiDAR point cloud data, represents the vertical coordinate of the th point in the airborne LiDAR point cloud data, represents the elevation value of the th point in the airborne LiDAR point cloud data, represents the total number of points in the airborne LiDAR point cloud data. For , use a denoising method based on density characteristics. Define the point neighborhood density as:

[0046]

[0047] Among them, represents the neighborhood area centered on the th point, represents the Euclidean distance between the airborne LiDAR point and other points in the neighborhood, represents the denoising smoothing coefficient. If is less than the threshold , the corresponding point is determined as a noise point and removed from . Among them, represents the critical value for noise judgment.

[0048] Subsequently, denoising processing is performed on the multi-beam bathymetric grid data. Denote the multi-beam bathymetric grid data as:

[0049]

[0050] Among them, represents the horizontal coordinate of the -th point in the multi-beam bathymetric grid data, represents the vertical coordinate of the -th point in the multi-beam bathymetric grid data, represents the water depth value of the -th point in the multi-beam bathymetric grid data, represents the total number of points in the multi-beam bathymetric grid data. For , local median filtering is used for denoising, and the filtered depth is defined as:

[0051]

[0052] Among them, represents the median operation, represents the filtering window radius. If the difference between the original water depth value and is greater than the threshold , then this point is determined as an abnormal measurement value and removed. Among them, represents the threshold for abnormal removal of multi-beam bathymetric data.

[0053] After completing the denoising operation, three-dimensional coordinate transformation is performed on the airborne LiDAR point cloud data and the multi-beam bathymetric grid data. Assume that the airborne LiDAR point cloud data uses the projection coordinate system , and the multi-beam bathymetric grid data uses the geographic coordinate system . Among them, represents the longitude, represents the latitude, represents the elevation (or depth) relative to the reference base plane. Define the coordinate transformation relationship as:

[0054]

[0055] Among them, represents the horizontal coordinate of the multi-beam bathymetric grid data in the projection plane after transformation, represents the transformed vertical coordinate, represents the transformed elevation value, Represents the transformation matrix from geographic coordinates to projected coordinates. By performing the above transformation on all multi-beam bathymetric grid data points, alignment with the airborne LiDAR point cloud data in the same coordinate system is achieved. Finally, in the unified projected coordinate system the denoised airborne LiDAR point cloud data and multi-beam bathymetric grid data are obtained, making the two consistent in format and coordinate reference.

[0056] In step S120, based on the spatial distribution characteristics in the airborne LiDAR point cloud data and the multi-beam bathymetric grid data, the beach area is divided into terrain zones. Among them, the spatial distribution characteristics represent the spatial distribution law of the airborne LiDAR point cloud data and the multi-beam bathymetric grid data in the target beach area, which may include uniformity, elevation gradient change, regional continuity, and spatial correlation.

[0057] In some embodiments, as shown in Figure 2 based on the spatial distribution characteristics in the airborne LiDAR point cloud data and the multi-beam bathymetric grid data, the beach area is divided into terrain zones, specifically including the following technical steps:

[0058] In the first step, a first elevation function is generated according to the airborne LiDAR point cloud data, and a first complexity index is obtained according to the first elevation function. Among them, the first elevation function can represent a mathematical function established based on the airborne LiDAR point cloud data, which can describe the elevation distribution of the land part in the beach area to a certain extent. The first complexity index can represent a quantitative index of terrain complexity calculated from the first elevation function.

[0059] In some embodiments, generating a first elevation function according to the airborne LiDAR point cloud data and obtaining a first complexity index according to the first elevation function specifically include the following technical steps:

[0060] Generate a first elevation function according to the airborne LiDAR point cloud data , where represents the elevation value obtained by the airborne LiDAR device at the planar coordinate .

[0061] Based on the first elevation function, by:

[0062]

[0063] determine the first elevation gradient field , where represents the elevation change rate of the airborne LiDAR point cloud data in the direction, represents the elevation change rate of the airborne LiDAR point cloud data in the The elevation change rate in the

[0064] Based on the first elevation gradient field, by:

[0065]

[0066] Determine the first complexity index, where represents the local calculation window around the point

[0067] In the second step, generate a second elevation function based on the multibeam sounding grid data, and obtain a second complexity index according to the second elevation function. Among them, the second elevation function can represent a mathematical function established based on the multibeam sounding grid data, which can describe the underwater topographic elevation distribution of the water area to a certain extent. The second complexity index can represent a topographic complexity quantization index calculated from the second elevation function.

[0068] The process of obtaining the second complexity index may include the following technical steps:

[0069] Generate a second elevation function based on the multibeam sounding data , where represents the water depth value of the multibeam sounding device at the planar coordinate , and the negative sign is used to convert the water depth into the elevation form.

[0070] Based on the second elevation function, by:

[0071]

[0072] Determine the second elevation gradient field , where represents the elevation change rate of the multibeam sounding data in the direction, represents the elevation change rate of the multibeam sounding data in the direction.

[0073] Based on the second elevation gradient field, by:

[0074]

[0075] Determine the second complexity index, where represents the local calculation window around the point

[0076] ​​In the third step, determine the elevation difference between the elevation values of the airborne LiDAR and the multi-beam bathymetry on the reference plane. Herein, the reference plane can represent the reference plane used to calculate the elevation difference between the airborne LiDAR point cloud data and the multi-beam bathymetry data. The elevation difference can represent the numerical difference between the elevation value of the airborne LiDAR and the elevation value of the multi-beam bathymetry at the same coordinate point, reflecting the topographic changes in the land-water boundary area.

[0077] Specifically, the elevation difference can be determined based on , where represents the elevation value of the airborne LiDAR point cloud data mapped onto the reference plane , and represents the elevation value of the multi-beam bathymetry data mapped onto the reference plane .

[0078] In the fourth step, based on the elevation difference, the first complexity index, and the second complexity index, divide the beach area into land areas, water areas, and land-water boundary areas through preset elevation difference thresholds and complexity thresholds.

[0079] Specifically, for the elevation difference threshold and the complexity threshold , classify the point set on the beach area. When exists and , and at the same time is less than , the corresponding point belongs to the land area; when exists and , and at the same time is less than , the corresponding point belongs to the water area; when or and at least one of them is greater than , then the corresponding point belongs to the land-water boundary area.

[0080] In step S130, according to the result of the terrain zoning, adopt a weighted fusion method to perform terrain adaptation fusion on the airborne LiDAR point cloud data and the multi-beam bathymetry grid data to obtain terrain fusion data. Herein, the weighted fusion method can represent a method that, based on the spatial distribution characteristics of the airborne LiDAR point cloud data and the multi-beam bathymetry grid data, dynamically allocates data weights according to the regional division and performs operations on the two types of data to generate unified terrain data. The terrain fusion data can represent the data set processed by the weighted fusion method, which combines the advantages of the land area of the airborne LiDAR point cloud data and the underwater topographic survey advantages of the multi-beam bathymetry grid data, and can accurately characterize the topographic change characteristics of the beach area.

[0081] In some embodiments, according to the results of terrain zoning, a weighted fusion method is used to perform terrain adaptation and fusion on airborne LiDAR point cloud data and multibeam bathymetric grid data to obtain terrain fusion data. The specific technical steps are as follows:

[0082] First, based on the first elevation gradient field and the second elevation gradient field, by:

[0083]

[0084]

[0085] Determine the first weight and the second weight , where represents the weighting parameter that controls the influence of the multibeam bathymetric gradient, represents the weighting parameter that controls the influence of the airborne LiDAR gradient, represents the second elevation gradient field mapped onto the reference plane, represents the first elevation gradient field mapped onto the reference plane. When is located in the land area, is 1. When is located in the water area, is 0. This weighting strategy can be adaptively adjusted according to different regions of terrain zoning, ensuring that in the land area, it mainly relies on airborne LiDAR point cloud data, in the water area, it mainly relies on multibeam bathymetric data, and in the land-water boundary area, it makes a smooth transition based on the elevation gradient, effectively solving the measurement error problem that may exist in the boundary area of different measurement methods. In addition, by calculating the weights through an exponential function, the weighting process is made smoother, avoiding the fusion instability caused by data mutations, and at the same time enhancing the continuity of the land-water boundary area.

[0086] Then, using the first weight and the second weight, fuse the airborne LiDAR elevation matrix and the multibeam bathymetric elevation matrix to obtain terrain fusion data. The fused elevation value can be defined as:

[0087]

[0088] where represents the elevation value of the airborne LiDAR point cloud data at the reference plane coordinates (X,Y), represents the elevation value of the multibeam bathymetric data at the reference plane coordinates (X,Y), and generate terrain fusion data based on the fused elevation value.

[0089] In addition, in other embodiments of the present disclosure, in order to ensure the continuity and consistency of the transition region, after the fusion is completed, local smoothing processing can also be performed on the fused elevation values. Specifically, set the smoothing window size and the smoothing parameter , define the local smoothing weight , , where and respectively represent the offsets in the and directions, represents the parameter controlling the smoothing degree. Perform local smoothing on through the following weighted average formula:

[0090]

[0091] Obtain the terrain fusion data after local smoothing processing , where k represents half of the size of the smoothing window.

[0092] In step S140, based on the terrain fusion data of different time periods, obtain the elevation change characteristics and spatial change characteristics corresponding to the beach area, and construct a beach evolution prediction model according to the elevation change characteristics and spatial change characteristics. Among them, the elevation change characteristics can represent the spatio-temporal characteristics extracted through the change amount, change rate, and change mode of the elevation values between the terrain fusion data of different time periods. The spatial change characteristics can represent the spatial morphological changes of the beach area in the terrain data of different time periods. The beach evolution prediction model can represent a prediction framework constructed based on the elevation change characteristics and spatial change characteristics of different time periods, using statistical methods or machine learning models, for inferring the future evolution trend of the beach terrain.

[0093] In some embodiments, based on the terrain fusion data of different time periods, obtaining the elevation change characteristics and spatial change characteristics corresponding to the beach area specifically includes the following technical steps:

[0094] First step, select adjacent observation times, and obtain an elevation change matrix based on the terrain fusion data of different time periods. Among them, the adjacent observation times can represent two adjacent time points used to calculate the terrain change. The elevation change matrix can represent a matrix formed by calculating the elevation differences of the same coordinate points between the terrain fusion data at adjacent observation times.

[0095] Specifically, first, set the discrete time series , where , on the plane coordinate system , record the terrain fusion data at each moment.

[0096] Among them, , represents the fused elevation value obtained at time at coordinates . represents the total number of discrete points.

[0097] Then, select adjacent observation times , and define the elevation change matrix as:

[0098]

[0099] Among them, represents the fused elevation value obtained at time , represents the fused elevation value obtained at time .

[0100] In the second step, select the time difference and obtain the rate change matrix according to the elevation change matrix. Among them, the rate change matrix can represent the matrix calculated based on the elevation change matrix and the time difference, and the element value represents the elevation change rate of the corresponding coordinate point.

[0101] Specifically, set the time difference , and define the change rate matrix as:

[0102]

[0103] represents the time interval between adjacent observation times.

[0104] In the third step, according to the elevation change matrix, obtain the centroid coordinates of the change region and generate the spatial centroid matrix. The spatial centroid matrix can represent the matrix composed of the centroid coordinates of the change region at multiple observation times, and its element values are the centroid coordinate data at different times, which are used to analyze the terrain change trend, morphological migration characteristics and overall evolution direction of the beach area.

[0105] In some embodiments, according to the elevation change matrix, obtaining the centroid coordinates of the change region and generating the spatial centroid matrix specifically includes the following technical steps:

[0106] According to the elevation change matrix , through:

[0107]

[0108] obtain the centroid coordinates of the change region, represents the centroid coordinate of the elevation change region at the Represents The centroid coordinates of the elevation change area in the Y-axis direction Represents the set of coordinates of the area where elevation changes occur on the reference plane . Generate a spatial centroid matrix based on the centroid coordinates of the change area .

[0109] In some embodiments, referring to Figure 3 As shown, construct a beach evolution prediction model based on the elevation change characteristics and spatial change characteristics, specifically including the following technical steps:

[0110] Step S310, construct a time series input sequence based on the elevation change characteristics and spatial change characteristics corresponding to multiple observation times. Among them, the time series input sequence can represent the terrain change data arranged in chronological order, including elevation change characteristics and spatial change characteristics, etc., as the input data of the prediction model

[0111] Based on the elevation change characteristics and spatial change characteristics corresponding to multiple observation times Integrate to construct a time series input sequence , where Represents the elevation difference at time , Represents the elevation change rate at time , And Represents the centroid coordinates of the change area at time .

[0112] Step S320, input the time series input sequence into the hidden state vector of the prediction model in sequence, and generate a prediction output according to the trainable parameters of the model. Among them, the hidden state vector can represent the internal state variable of the model for storing time series information, used to memorize and update historical information. The trainable parameters can represent the parameters in the prediction model that can be optimized through the learning process, including weight matrices, bias terms, etc

[0113] Exemplarily, in order to describe the correlation of beach terrain changes in the time series, an update chain of the hidden state vector can be established in the model, defined as follows:

[0114] ,

[0115] Represents the hidden state vector updated after the th time series input, used to store the internal memory of the model in time Represents the hidden state after the previous time series input Represent the weight matrices of the hidden state, input sequence and output layer respectively respectively represent the bias vectors of the hidden layer and the output layer, is the activation function, represents the predicted output, which is used to estimate the topographic change amount or elevation value at a future time . Through this recursive formula of time series, each time a new feature vector is input, it can combine the previous hidden state to predict the trend of beach topography change at a future time.

[0116] Step S330: Evaluate the difference between the predicted output and the true fused elevation data at different times, and adjust the trainable parameters of the model according to the difference value. Specifically, the loss function can be used for difference evaluation, and the loss function L can be defined as:

[0117]

[0118] where, represents the total number of sample points on the plane coordinate , represents the value of the predicted output at the coordinate , represents the true fused elevation value obtained at the time . In order to minimize , the gradient descent method is used to optimize the trainable parameters.

[0119] Step S340: After completing the time series input and difference evaluation for a preset number of times, output the beach evolution prediction model including the hidden state and the trainable parameters. Specifically, after the training process iterates to the maximum number of loops or meets the set accuracy threshold, the final beach evolution prediction model is obtained.

[0120] In step S150, according to the beach evolution prediction model, predict the beach change trend and generate monitoring and early warning information. Specifically, the above process may include the following technical steps:

[0121] First, input the real-time collected terrain fusion data into the beach evolution prediction model to obtain the predicted beach change data. Specifically, match the terrain fusion data collected at the current time with the historical observation data, and calculate the elevation change trend, spatial movement trend and change rate at a future time based on the hidden state vector and trainable parameters of the model, so as to generate a prediction data matrix.

[0122] Then, according to the pre-set elevation change threshold and rate threshold, it is judged whether the predicted beach change data reaches the warning condition. Specifically, multiple warning thresholds are set, where the elevation change threshold is used to evaluate the amplitude of terrain change, the rate threshold is used to measure the change rate, and the predicted data is classified based on different threshold intervals. If the elevation change amount of the predicted data exceeds the set threshold and the change rate exceeds the safe range, it is determined that there is an abnormal risk in the beach evolution trend.

[0123] Finally, in response to meeting the warning condition, monitoring warning information of the corresponding level is generated. Specifically, according to the matching result of the warning threshold, the warning level is determined, and the corresponding monitoring warning mechanism is automatically triggered. For low-risk warnings, the trend information can be recorded and displayed through data storage and visualization means; for medium-high risk warnings, an alarm signal can be sent to the relevant management system, and visual analysis data of the prediction result can be provided so that the management personnel can take protective measures in advance. In addition, to improve the accuracy of the warning information, the current prediction result can be corrected by combining historical data to ensure the reliability of the monitoring warning information.

[0124] The beach evolution monitoring method based on multi-source data fusion in the above embodiments improves the accuracy and efficiency of beach evolution monitoring by fusing data from different observation means. The terrain is partitioned based on the spatial distribution characteristics of the data, enabling subsequent processing to adopt different strategies for different terrain regions. In the data fusion process, the data from different measurement means are adaptively weighted and fused for terrain through a weighted fusion method, so that the final terrain fusion data can fully retain the advantages of each data source, reduce measurement errors, and improve the continuity and consistency of the terrain data. Especially in the land-water boundary region, the elevation gradient information is used to adaptively weight the data, avoiding the problems of data mutation or unstable fusion in traditional methods.

[0125] The elevation change characteristics and spatial change characteristics are extracted from the terrain fusion data at different time periods, and a beach evolution prediction model is constructed, enabling the monitoring system to dynamically analyze the change trend of the beach. By constructing a time series input sequence and combining the hidden state vector and trainable parameters of the prediction model, the terrain changes at different observation times are modeled, which can effectively mine the change patterns in the time series data and improve the prediction ability of the long-term evolution trend of the beach. In addition, the centroid coordinates of the change region are calculated based on the elevation change matrix and rate change matrix, and a spatial centroid matrix is generated, enabling the spatial characteristics of the beach change to be quantitatively described, thus providing more intuitive terrain evolution information for subsequent analysis. In terms of monitoring and warning, combined with the output result of the prediction model, the beach evolution trend is classified based on the elevation change threshold and rate threshold, and monitoring warning information is generated according to different levels of change trends, thereby improving the response ability of the monitoring system. Thus, to a certain extent, the monitoring accuracy and processing efficiency of the beach area are improved.

[0126] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0127] Secondly, in an exemplary embodiment of the present disclosure, a beach evolution monitoring device based on multi-source data fusion is also provided. Referring to Figure 4 as shown, the beach evolution monitoring device 400 based on multi-source data fusion may be composed of a data acquisition module 401, a terrain zoning module 402, a data fusion module 403, a model construction module 404, and a model prediction module 405. Among them, the data acquisition module 401 may be used to acquire the airborne LiDAR point cloud data and multi-beam bathymetric grid data corresponding to the target beach area; the terrain zoning module 402 may be used to zone the terrain of the beach area based on the spatial distribution characteristics in the airborne LiDAR point cloud data and multi-beam bathymetric grid data; the data fusion module 403 may be used to perform terrain adaptation fusion on the airborne LiDAR point cloud data and multi-beam bathymetric grid data by using a weighted fusion method according to the result of terrain zoning to obtain terrain fusion data; the model construction module 404 may be used to obtain the elevation change characteristics and spatial change characteristics corresponding to the beach area according to the terrain fusion data at different times, and construct a beach evolution prediction model according to the elevation change characteristics and spatial change characteristics; the model prediction module 405 may be used to predict the beach change trend and generate monitoring and warning information according to the beach evolution prediction model.

[0128] It should be noted that the specific details of each part in the above-mentioned beach evolution monitoring device based on multi-source data fusion have been described in detail in the implementation manner of the beach evolution monitoring method based on multi-source data fusion. The details not disclosed can be seen in the implementation manner of the method part, and thus will not be elaborated here.

[0129] It should be noted that although several modules or units of the beach evolution monitoring device based on multi-source data fusion are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of the two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided and embodied by multiple modules or units.

[0130] In addition, in the exemplary embodiments of the present disclosure, an electronic device capable of implementing the above-mentioned beach evolution monitoring method based on multi-source data fusion is also provided.

[0131] Those skilled in the art of the present technology can understand that various aspects of the present disclosure can be implemented as a system, a method, or a program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuits", "modules", or "systems" here.

[0132] The following refers to Figure 5 to describe the electronic device 500 according to the above embodiments of the present disclosure. Figure 5 The illustrated electronic device 500 is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0133] As Figure 5 shown, the electronic device 500 is presented in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: the at least one processing unit 510 mentioned above, the at least one storage unit 520 mentioned above, a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510), and a display unit 540.

[0134] Among them, the storage unit stores program codes, and the program codes can be executed by the processing unit 510, so that the processing unit 510 executes the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification. The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 521 and / or a cache storage unit 522, and may further include a read-only storage unit (ROM) 523.

[0135] The storage unit 520 may further include a program / utilities 524 having a set (at least one) of program modules 525. Such program modules 525 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0136] The bus 530 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0137] The electronic device 500 can also communicate with one or more external devices 570 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 500, and / or communicate with any device that enables the electronic device 500 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 550. Moreover, the electronic device 500 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 560. As shown in the figure, the network adapter 560 communicates with other modules of the electronic device 500 through the bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0138] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or can be implemented by the way of software combined with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0139] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0140] Reference Figure 6 As shown, a program product 600 for implementing the above shoreline evolution monitoring method based on multi-source data fusion according to the embodiments of the present disclosure is described. It can adopt a portable compact disc read-only memory (CD-ROM) and includes program code, and can run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.

[0141] The program product may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the readable storage medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0142] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0143] The program code contained on the readable medium may be transmitted with any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, electromagnetic wave, etc., or any suitable combination of the foregoing.

[0144] The program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0145] In addition, the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, rather than for limiting purposes. It is easy to understand that the processes shown in the above-mentioned drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easy to understand that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0146] From the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (such as a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0147] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed by the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0148] It should be understood that the present disclosure is not limited to the exact structures already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A beach evolution monitoring method based on multi-source data fusion, characterized in that, Including: Collecting airborne LiDAR point cloud data and multi-beam bathymetric grid data corresponding to the target beach area; Based on the spatial distribution characteristics in the airborne LiDAR point cloud data and multi-beam bathymetric grid data, performing terrain zoning on the beach area; According to the result of terrain zoning, using a weighted fusion method to perform terrain adaptation fusion on the airborne LiDAR point cloud data and multi-beam bathymetric grid data to obtain terrain fusion data; Based on the terrain fusion data at different time periods, obtaining the spatial change characteristics corresponding to the beach area, and constructing a time series input sequence based on the spatial change characteristics corresponding to multiple observation times; sequentially inputting the time series input sequence into the hidden state vector of the prediction model, and generating a prediction output according to the trainable parameters of the prediction model; performing difference evaluation on the prediction output and the true fusion elevation data at different times, and adjusting the trainable parameters of the prediction model according to the difference value; After completing the time series input and difference evaluation for a preset number of times, outputting a beach evolution prediction model including hidden states and trainable parameters; According to the beach evolution prediction model, predicting the beach change trend and generating monitoring and warning information; The obtaining the spatial change characteristics corresponding to the beach area based on the terrain fusion data at different time periods includes: selecting adjacent observation times, and obtaining an elevation change matrix based on the terrain fusion data at different time periods; selecting a time difference, and obtaining a rate change matrix according to the elevation change matrix; according to the elevation change matrix, obtaining the centroid coordinates of the change area and generating a spatial centroid matrix; The timing input sequence is , where represents the elevation difference at time , represents the elevation change rate at time , and represent the centroid coordinates of the change area at time , represents the reference plane coordinates.

2. The shoreline evolution monitoring method based on multi-source data fusion according to claim 1, characterized in that, The collecting the airborne LiDAR point cloud data and multi-beam bathymetric grid data corresponding to the target beach area includes: Using an airborne LiDAR device and a multi-beam bathymetric device to obtain elevation values corresponding to the target beach area, and respectively constructing the airborne LiDAR point cloud data and the multi-beam bathymetric grid data according to the elevation values; Denosing and performing three-dimensional coordinate transformation on the airborne LiDAR point cloud data and the multi-beam bathymetric grid data to unify the data format.

3. The beach evolution monitoring method based on multi-source data fusion according to claim 1, characterized in that The performing terrain zoning on the beach area based on the spatial distribution characteristics in the airborne LiDAR point cloud data and multi-beam bathymetric grid data includes: Generating a first elevation function according to the airborne LiDAR point cloud data, and obtaining a first complexity index according to the first elevation function; Generating a second elevation function according to the multi-beam bathymetric grid data, and obtaining a second complexity index according to the second elevation function; Determining the elevation difference between the airborne LiDAR elevation value and the multi-beam bathymetric elevation value at different coordinates on the reference plane; Based on the elevation difference, the first complexity index and the second complexity index, dividing the beach area into a land area, a water area and a land-water boundary area through preset elevation difference thresholds and complexity thresholds.

4. The shoreline evolution monitoring method based on multi-source data fusion according to claim 3, wherein The generating a first elevation function according to the airborne LiDAR point cloud data, and obtaining a first complexity index according to the first elevation function includes: Generate a first elevation function based on the airborne LiDAR point cloud data , where represents the elevation value obtained by the airborne LiDAR device at the planar coordinates ; Based on the first elevation function, by: Determine the first elevation gradient field , where represents the elevation change rate of the airborne LiDAR point cloud data in the direction, and represents the elevation change rate of the airborne LiDAR point cloud data in the direction; Based on the first elevation gradient field, by: Determine the first complexity metric, where represents a local computation window around the point surrounding.

5. The beach evolution monitoring method based on multi-source data fusion according to claim 4, characterized in that According to the results of terrain zoning, a weighted fusion method is used to perform terrain adaptation fusion on the airborne LiDAR point cloud data and the multibeam bathymetric grid data to obtain terrain fusion data, including: Based on the first elevation gradient field and the second elevation gradient field, by: Determine the first weight and the second weight , where represents a weighting parameter for controlling the influence of multi-beam sounding gradient, represents a weighting parameter for controlling the influence of airborne LiDAR gradient, represents the second elevation gradient field mapped onto the reference plane, represents the first elevation gradient field mapped onto the reference plane. When is located in the land area, is 1. When is located in the water area, is 0; Using the first weight and the second weight, the airborne LiDAR elevation matrix and the multibeam bathymetric elevation matrix are fused to obtain the terrain fusion data.

6. The shoreline evolution monitoring method based on multi-source data fusion according to claim 1, characterized in that According to the elevation change matrix, obtaining the centroid coordinates of the change region and generating a spatial centroid matrix includes: According to the elevation change matrix , by: Obtain the centroid coordinates of the changed area, denote the centroid coordinates of the elevation change area at time X in the axis direction, denote Y the centroid coordinates of the elevation change area at time in the axis direction; represent the coordinate set of the area where the elevation change occurs on the reference plane Generating a spatial centroid matrix according to the centroid coordinates of the change region.

7. The shoreline evolution monitoring method based on multi-source data fusion according to claim 1, characterized in that According to the beach evolution prediction model, predicting the beach change trend and generating monitoring and early warning information includes: Inputting the terrain fusion data collected in real time into the beach evolution prediction model to obtain the predicted beach change data; Judging whether the predicted beach change data meets the early warning conditions according to a preset elevation change threshold and rate threshold; In response to meeting the early warning conditions, generating monitoring and early warning information of the corresponding level.

8. A beach evolution monitoring device based on multi-source data fusion, characterized in that, For implementing the beach evolution monitoring method based on multi-source data fusion according to any one of claims 1-7, the device includes: A data acquisition module for acquiring the airborne LiDAR point cloud data and the multibeam bathymetric grid data corresponding to the target beach area; A terrain zoning module for zoning the beach area based on the spatial distribution characteristics in the airborne LiDAR point cloud data and the multibeam bathymetric grid data; A data fusion module for performing terrain adaptation fusion on the airborne LiDAR point cloud data and the multibeam bathymetric grid data by using a weighted fusion method according to the results of terrain zoning to obtain terrain fusion data; A model construction module for obtaining the spatial change characteristics corresponding to the beach area according to the terrain fusion data at different times, and constructing a time series input sequence based on the spatial change characteristics corresponding to multiple observation times; sequentially inputting the time series input sequence into the hidden state vector of the prediction model, and generating a prediction output according to the trainable parameters of the prediction model; evaluating the difference between the prediction output and the real fusion elevation data at different times, and adjusting the trainable parameters of the prediction model according to the difference value; after completing the preset number of times of time series input and difference evaluation, outputting a beach evolution prediction model including the hidden state and the trainable parameters; A model prediction module for predicting the beach change trend and generating monitoring and early warning information according to the beach evolution prediction model.

Images