Multi-polarization radar geological structure analysis method, device and equipment and storage medium

Abstract

The invention relates to a multi-polarization radar geological structure analysis method, device and equipment and a storage medium, and the method comprises the steps: carrying out the detection operation along a target measuring line in a detection region through a multi-polarization radar, so as to obtain the multi-polarization radar data of an underground target body and a geological structure; performing standardization processing on the multi-polarization radar data by using the sample database to obtain an ordered sample data set; performing pixel-level fusion on the multi-polarization radar data according to the ordered sample data set to generate a multi-polarization radar sample data set with the resolution greater than a preset resolution; and inputting the sample data set into a preset pulse neural network to output an intelligent identification result of the underground target body and the geological structure, and extracting categories and potential relationships of the underground target body and the geological structure according to the intelligent identification result. Therefore, the problems that the workload of multi-polarization radar data interpretation analysis is large, the recognition precision and efficiency are low, and the professional ability of employees is excessively depended in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the technical field of multi-polarization radar intelligent analysis, and in particular to a multi-polarization radar geological structure analysis method, device, equipment and storage medium. Background Art

[0002] Ground Penetrating Radar (GPR) is a non-destructive detection technology used to obtain high-resolution images of underground structures. It determines the location, shape and properties of underground objects by sending high-frequency electromagnetic waves underground and receiving the reflected signals.

[0003] In related technologies, multi-polarization geological radar adopts horizontal, vertical and other antenna polarization methods, which can comprehensively utilize signals in different polarization directions and frequency band ranges to achieve more comprehensive and precise imaging and identification of underground targets.

[0004] However, in the related technologies, the traditional multi-polarization radar data interpretation and analysis methods have the following limitations: the manual interpretation method is inefficient and prone to subjective errors; it is difficult to efficiently process complex and diverse multi-polarization radar data; it is too dependent on the professional knowledge and experience of practitioners, and it is difficult for people without relevant professional backgrounds to conduct accurate analysis. A more intelligent and efficient multi-polarization radar intelligent analysis method is urgently needed to use deep learning algorithms to intelligently process and interpret geological radar data. Summary of the invention

[0005] The present application provides a method, device, equipment and storage medium for analyzing geological structures using multi-polarization radar to solve the problems in related technologies such as large workload in interpreting and analyzing multi-polarization radar data, low recognition accuracy and efficiency, and over-reliance on the professional capabilities of practitioners.

[0006] The first aspect of the present application provides a method for analyzing geological structures using a multi-polarization radar, comprising the following steps: using a multi-polarization radar to perform detection operations along a target survey line in a detection area to obtain multi-polarization radar data of underground target bodies and geological structures; using a sample database to standardize the multi-polarization radar data to obtain an ordered sample data set; performing pixel-level fusion on the multi-polarization radar data according to the ordered sample data set to generate a multi-polarization radar sample data set with a resolution greater than a preset resolution; inputting the sample data set into a preset pulse neural network to output intelligent recognition results of the underground target body and the geological structure, and extracting the category and potential relationship of the underground target body and the geological structure based on the intelligent recognition results.

[0007] Optionally, in one embodiment of the present application, the detection operation is performed along the target survey line in the detection area using a multi-polarization radar to obtain multi-polarization radar data of the underground target body and the geological structure, including: using the multi-polarization radar to obtain multi-polarization reflection signals of the underground target body and the geological structure in the horizontal and vertical directions; obtaining at least one multi-polarization signal data of horizontal transmission and horizontal reception, vertical transmission and vertical reception, horizontal transmission and vertical reception, and vertical transmission and horizontal reception according to the multi-polarization reflection signal; extracting and calculating a polarization scattering matrix according to the at least one multi-polarization signal data; and obtaining data information of the underground target body and the geological structure containing anisotropic characteristics according to the polarization scattering matrix.

[0008] Optionally, in one embodiment of the present application, the using a sample database to standardize the multi-polarization radar data to obtain an ordered sample data set includes: using the sample database to perform at least one of data normalization, equalization, feature selection and dimensionality reduction, denoising and consistency verification on the multi-polarization radar data to obtain the ordered sample data set.

[0009] Optionally, in one embodiment of the present application, the pixel-level fusion of the multi-polarization radar data according to the ordered sample data set to generate a sample data set of a multi-polarization radar high-resolution range image includes: extracting at least one feature information of scattering intensity, phase information and polarization characteristics from the multi-polarization radar data based on the ordered sample data set; and processing the at least one feature information to generate the multi-polarization radar sample data set having a resolution greater than the preset resolution.

[0010] Optionally, in one embodiment of the present application, before inputting the sample data set into a preset pulse neural network, it also includes: using an SRM neuron layer to receive a pulse signal of the multi-polarization radar data; performing pulse integration on the pulse signal within a preset time window to generate a pulse response; and processing the SRM neuron model according to the pulse response to obtain the preset pulse neural network.

[0011] Optionally, in one embodiment of the present application, the sample data set is input into a preset pulse neural network to output the intelligent recognition results of the underground target body and the geological structure, including: inputting the calibration category of the sample data set into the preset pulse neural network, and training the deep learning neural network model according to the preset pulse neural network to obtain a multi-polarization radar intelligent analysis model; and intelligently identifying the sample data set according to the multi-polarization radar intelligent analysis model to obtain the intelligent recognition results of the underground target body and the geological structure.

[0012] A second aspect of the present application provides an analysis device for multi-polarization radar geological structure, including: an acquisition module, used to use a multi-polarization radar to perform detection operations along a target survey line in a detection area to obtain multi-polarization radar data of underground target bodies and geological structures; a processing module, used to use a sample database to standardize the multi-polarization radar data to obtain an ordered sample data set; a generation module, used to perform pixel-level fusion of the multi-polarization radar data according to the ordered sample data set to generate a multi-polarization radar sample data set with a resolution greater than a preset resolution; an analysis module, used to input the sample data set into a preset pulse neural network to output an intelligent recognition result of the underground target body and the geological structure, and extract the category and potential relationship of the underground target body and the geological structure according to the intelligent recognition result.

[0013] Optionally, in one embodiment of the present application, the acquisition module includes: an acquisition unit, used to use the multi-polarization radar to acquire multi-polarization reflection signals of the underground target body and the geological structure in the horizontal and vertical directions; a first generation unit, used to obtain at least one multi-polarization signal data of horizontal transmission and horizontal reception, vertical transmission and vertical reception, horizontal transmission and vertical reception, and vertical transmission and horizontal reception according to the multi-polarization reflection signal; a first extraction unit, used to extract and calculate a polarization scattering matrix based on the at least one multi-polarization signal data; and a second generation unit, used to obtain data information of the underground target body and the geological structure containing anisotropic characteristics according to the polarization scattering matrix.

[0014] Optionally, in one embodiment of the present application, the processing module includes: a first processing unit, used to use the sample database to perform at least one of data normalization, equalization, feature selection and dimensionality reduction, denoising and consistency verification on the multi-polarization radar data to obtain the ordered sample data set.

[0015] Optionally, in one embodiment of the present application, the generation module includes: a second extraction unit, used to extract at least one feature information of scattering intensity, phase information and polarization characteristics from the multi-polarization radar data based on the ordered sample data set; a second processing unit, used to process the at least one feature information to generate the multi-polarization radar sample data set with a resolution greater than the preset resolution.

[0016] Optionally, in one embodiment of the present application, it also includes: a receiving module, used to receive the pulse signal of the multi-polarization radar data using the SRM neuron layer before inputting the sample data set into the preset pulse neural network; a generating module, used to perform pulse integration on the pulse signal within a preset time window to generate a pulse response; and a third processing module, used to process the SRM neuron model according to the pulse response to obtain the preset pulse neural network.

[0017] Optionally, in one embodiment of the present application, the analysis module includes: a training unit, used to input the calibration category of the sample data set into the preset pulse neural network, and train the deep learning neural network model according to the preset pulse neural network to obtain a multi-polarization radar intelligent analysis model; an identification unit, used to intelligently identify the sample data set according to the multi-polarization radar intelligent analysis model to obtain the intelligent identification results of the underground target body and the geological structure.

[0018] The third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-polarization radar geological structure analysis method as described in the above embodiment.

[0019] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above multi-polarization radar geological structure analysis method.

[0020] The fifth aspect of the present application provides a computer program product, which stores a computer program that, when executed by a processor, implements the above multi-polarization radar geological structure analysis method.

[0021] The embodiment of the present application can perform detection operations along a predetermined survey line in the detection area by means of technicians operating or drones carrying multi-polarization radars. The multi-polarization radar acquires multi-polarization radar data such as polarization scattering matrices of underground targets and geological structures by sending and receiving radar signals in different polarization directions. The sample database standardizes multi-polarization radar data such as polarization scattering matrices according to task requirements to form an ordered data set. Professional technicians calibrate, classify and verify data such as polarization scattering matrices acquired by the multi-polarization radar to generate sample data sets, and dynamically update the sample database in real time. The data fusion system integrates data such as polarization scattering matrices using a variety of data fusion algorithms, performs data fusion, and generates a sample data set of high-resolution range images of multi-polarization radars. The intelligent analysis module extracts features and performs intelligent recognition analysis on the multi-polarization radar detection sample data to obtain intelligent recognition results of underground targets and geological structures, thereby reducing a large amount of manual operation costs and improving the accuracy of recognition and analysis of multi-polarization radar detection data, providing reliable and accurate geophysical information for engineering practice. This solves the problems in related technologies such as low efficiency and proneness to subjective errors in manual interpretation of multi-polarization radar data, difficulty in efficiently processing complex and diverse multi-polarization radar data, and over-reliance on the professional knowledge and experience of practitioners.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flowchart of a method for analyzing geological structures using multi-polarization radar provided according to an embodiment of the present application;

[0025] Figure 2 A system structure diagram of a method for analyzing geological structures using multi-polarization radar according to an embodiment of the present application;

[0026] Figure 3 A schematic diagram of the structure of a multi-polarization radar geological structure analysis device provided according to an embodiment of the present application;

[0027] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0029] The following describes the analysis method, device, equipment and storage medium of the multi-polarization radar geological structure of the embodiment of the present application with reference to the accompanying drawings. In view of the problems that the traditional multi-polarization radar manual interpretation method is inefficient and prone to subjective errors, it is difficult to efficiently process complex and diverse multi-polarization radar data, it is too dependent on the professional knowledge and experience of practitioners, and it is difficult for people without relevant professional backgrounds to perform accurate analysis, the present application provides a multi-polarization radar geological structure analysis method, in which a multi-polarization radar geological structure intelligent analysis model based on data fusion technology and deep learning neural network algorithm can be used to realize intelligent identification of multi-polarization radar data, save a lot of manpower consumption, improve work efficiency, convenient operation and simple steps, easy for workers to learn and master, short on-site preparation and debugging time, save time, and facilitate popularization. As a result, the problems of large workload, low recognition accuracy and efficiency, and over-reliance on the professional ability of practitioners in the related technology are solved.

[0030] Specifically, Figure 1 A schematic flow chart of a method for analyzing geological structures using multi-polarization radar provided in an embodiment of the present application.

[0031] like Figure 1 As shown, the multi-polarization radar geological structure analysis method includes the following steps:

[0032] In step S101, a multi-polarization radar is used to perform detection along a target survey line in a detection area to obtain multi-polarization radar data of underground target bodies and geological structures.

[0033] It is understandable that the multi-polarization radar in the embodiment of the present application can obtain multi-polarization reflection signals of underground targets and geological structures, accurately reflect the anisotropic characteristics of underground media, and obtain multi-polarization radar data such as polarization scattering matrix of underground targets and geological structures with high resolution. The underground targets and geological structures in the embodiment of the present application include but are not limited to underground targets such as underground pipe galleries and buried cables, and geological structures such as rock interfaces, water-bearing structures, and karst cavities.

[0034] Among them, the embodiment of the present application can divide the target body into three types of target bodies according to different polarization scattering mechanisms, namely single scattering, secondary scattering and volume scattering. The polarization scattering matrix of each type of target body obtained according to different polarization directions can represent the reflection characteristics and scattering mechanism of each target body under different polarization directions, providing a multi-level data perspective for the geological structure intelligent analysis system.

[0035] During the actual implementation process, the embodiments of the present application can perform detection operations along the established survey lines in the detection area through the operation of technicians or by drones, so as to obtain multi-polarization radar data of underground targets and geological structures. Technicians can set the appropriate frequency band range and check the working status to ensure that the multi-polarization radar can accurately detect the detection area.

[0036] The embodiment of the present application uses a multi-polarization radar to receive and detect multi-polarization reflection signals of geological structures, accurately detect the anisotropic characteristics of underground targets, and help meet the needs of different detection tasks.

[0037] Optionally, in one embodiment of the present application, a multi-polarization radar is used to perform detection operations along a target survey line in a detection area to obtain multi-polarization radar data of underground target bodies and geological structures, including: using a multi-polarization radar to obtain multi-polarization reflection signals in horizontal and vertical directions of underground target bodies and geological structures; obtaining at least one multi-polarization signal data of horizontal transmission and horizontal reception, vertical transmission and vertical reception, horizontal transmission and vertical reception, and vertical transmission and horizontal reception based on the multi-polarization reflection signals; extracting and calculating a polarization scattering matrix based on the at least one multi-polarization signal data; and obtaining data information of underground target bodies and geological structures containing anisotropic characteristics based on the polarization scattering matrix.

[0038] It can be understood that the multi-polarization radar in the embodiment of the present application includes: a data storage and transmission module, which can store the multi-polarization radar data of underground targets and geological structures collected and recorded in real time by the multi-polarization radar in the following steps, wherein the storage capacity meets the requirements for the amount of data collected in a complete detection operation task, and at the same time meets the real-time lossless transmission of data during the detection process.

[0039] During the actual implementation process, the embodiment of the present application can use a multi-polarization radar to obtain signals of different polarization directions in the horizontal direction (H) and the vertical direction (V) of the underground target and geological structure, and can obtain VV and HH co-polarization data, as well as VH and HV cross-polarization data. According to the multi-polarization reflection signal, multi-polarization signal data such as horizontal transmission and horizontal reception HH, vertical transmission and vertical reception VV, horizontal transmission and vertical reception HV, and vertical transmission and horizontal reception VH are obtained. According to the multi-polarization signal data, a polarization scattering matrix is ​​extracted and calculated, and according to the polarization scattering matrix, data information of the underground target and geological structure containing anisotropic characteristics is obtained, thereby realizing high-precision detection of the underground target and geological structure.

[0040] In step S102, the multi-polarization radar data is standardized using the sample database to obtain an ordered sample data set.

[0041] It can be understood that the sample database in the embodiment of the present application can store, manage and calibrate multi-polarization radar fusion data. The sample database can standardize the multi-polarization radar data such as the polarization scattering matrix in the above steps to reduce the amount of data and thus improve processing efficiency.

[0042] As a possible implementation method, professional technicians can calibrate, classify and verify the polarization scattering matrix obtained by the multi-polarization radar through the sample database to ensure the accuracy and reliability of the data. And generate a sample data set according to the coordinate sequence, generate a sample database, and dynamically update the sample database in real time, where the coordinate sequence can be a geographic location coordinate, a time series or other ordered indicators.

[0043] Optionally, in one embodiment of the present application, the multi-polarization radar data is standardized using a sample database to obtain an ordered sample data set, including: using the sample database to perform at least one of data normalization, equalization, feature selection and dimensionality reduction, denoising and consistency verification on the multi-polarization radar data to obtain an ordered sample data set.

[0044] It can be understood that the data normalization in the embodiment of the present application can ensure that the data in different polarization directions have similar numerical ranges and distributions, and all data are within a uniform numerical range by adopting methods such as linear transformation (such as minimum-maximum normalization or Z-Score normalization).

[0045] The equalization processing in the embodiment of the present application is used to solve problems such as uneven data distribution that may exist in different polarization directions, by adopting equalization technology (such as histogram equalization or an equalization method based on probability density function) to ensure that data is evenly distributed in different directions.

[0046] The feature selection and dimensionality reduction in the embodiments of the present application are used to perform feature selection or dimensionality reduction after data fusion to reduce the complexity and redundancy of the data and improve the data processing efficiency and the effect of model training.

[0047] The denoising process in the embodiments of the present application is used to solve problems such as noise or outliers in the data, by adopting filtering technology or denoising algorithms (such as median filtering, wavelet denoising, etc.) to improve data quality and accuracy.

[0048] The consistency verification in the embodiment of the present application is as follows: after the standardization processing, the processed data needs to be verified and evaluated for consistency to ensure that the multi-polarization radar data remains consistent and comparable in different fusion methods and different polarization directions, thereby ensuring the validity of the data fusion result.

[0049] In the actual implementation process, the embodiment of the present application can use the sample database to perform data normalization, equalization, feature selection and dimension reduction, denoising and consistency verification on multi-polarization radar data such as polarization scattering matrix, and obtain an ordered sample data set to ensure that the multi-polarization radar data is consistent and comparable in different fusion methods and different polarization directions. Standardization processing helps to further improve the identifiable performance and analysis accuracy of multi-polarization radar data, so that it can play an effective role in various application scenarios.

[0050] In step S103, pixel-level fusion is performed on the multi-polarization radar data according to the ordered sample data set to generate a multi-polarization radar sample data set with a resolution greater than a preset resolution.

[0051] It can be understood that the multi-polarization radar sample data set with a resolution greater than the preset resolution in the embodiment of the present application is a multi-polarization radar high-resolution range image sample data set.

[0052] As a possible implementation method, the embodiment of the present application can perform pixel-level fusion of multi-polarization radar data based on an ordered sample data set, that is, through a data fusion system, the polarization scattering matrices of VV, HH, VH, and HV (where HV represents horizontal transmission and vertical reception, and other definitions are similar) of the same target body detected by the multi-polarization radar, and multiple data fusion algorithms are used to integrate data in different polarization directions, perform data fusion, and generate a multi-polarization radar sample data set with a resolution greater than a preset resolution. The embodiment of the present application uses multiple data fusion algorithms and standardized processing technologies for data such as polarization scattering matrices of different polarization directions and different scattering targets, and comprehensively processes the data obtained by the multi-polarization radar, which can effectively realize differentiated processing and integration of multi-polarization radar data.

[0053] The embodiment of the present application can use the data fusion system to extract a variety of geological structure features, including but not limited to underground rock layers, fractures, and hydrogeology. These features are used to provide input data for the intelligent analysis model to help the model better understand the underground structure, thereby achieving more accurate target identification and geological structure analysis.

[0054] It should be noted that the preset resolution can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0055] Optionally, in one embodiment of the present application, pixel-level fusion is performed on multi-polarization radar data according to an ordered sample data set to generate a multi-polarization radar sample data set with a resolution greater than a preset resolution, including: extracting at least one feature information of scattering intensity, phase information and polarization characteristics from the multi-polarization radar data based on the ordered sample data set; and processing at least one feature information to generate a sample data set of a high-resolution range image of the multi-polarization radar.

[0056] In the actual implementation process, the embodiment of the present application can extract useful feature information from multi-polarization radar data such as polarization scattering matrix based on an ordered sample data set, such as scattering intensity, phase information, polarization characteristics and other feature information, to distinguish different types of underground targets and geological structures, and use multi-polarization radar imaging algorithms to process and analyze the extracted features. Using the data of multiple polarization channels of the multi-polarization radar, a high-resolution range image of the target area is reconstructed, thereby obtaining a high-resolution range image data set of the detection area, which helps to provide effective data input for data fusion in the next step.

[0057] Among them, the data fusion system in the embodiment of the present application can use a variety of technologies applied to the field of image fusion, including but not limited to weighted average fusion, principal component analysis (PCA), Laplacian Pyramid (LP), multi-scale wavelet transform (WT), etc., to perform data fusion and standardization processing on multi-polarization radar detection data.

[0058] The weighted average fusion in the embodiment of the present application is performed by processing the data matrix S obtained by the multi-polarization radar. HH , S VV , S HV , S VH Assign weight coefficients k to balance their contributions HH , k VV , k HV , k VH . Its expression is as follows:

[0059] F = k HH *S HH +k VV *S VV +k HV *S HV +k VH *S VH ,

[0060] Among them, weighted average fusion, as a commonly used multi-polarization radar data fusion method, is the basic part of the training set in the sample database.

[0061] In the embodiment of the present application, principal component analysis (PCA) is used for feature extraction and data dimension reduction of multi-polarization radar signals to facilitate identification of potential relationships in the data.

[0062] Among them, principal component analysis can remove redundant identical parts of the VV, HH, VH, and HV polarization direction data and fuse the parts with different characteristics, which can give full play to the advantages of multi-polarization radar and realize refined detection of the target.

[0063] The Laplacian pyramid (LP) in the embodiment of the present application is used for LP decomposition of the multi-polarization radar image, and can decompose the original image into different frequency band ranges, thereby merging different frequency band components obtained at different decomposition layers.

[0064] Among them, different LP fusion rules are used to fuse the same decomposition layers obtained by decomposing VV, HH, VH, and HV images, and then reconstruct the image. In this way, a fused image with all the detail features of multiple original images can be obtained, thereby realizing the feature fusion and high-precision recognition of multi-polarization data.

[0065] The multi-scale wavelet transform (WT) in the embodiment of the present application can perform low- and high-frequency filtering and image decomposition of VV, HH, VH, and HV to obtain images in different frequency bands, fuse parts of corresponding frequency bands, and reconstruct the fusion result of multi-polarization radar data.

[0066] In step S104, the sample data set is input into a preset pulse neural network to output intelligent recognition results of underground target bodies and geological structures, and the categories and potential relationships of underground target bodies and geological structures are extracted according to the intelligent recognition results.

[0067] During the actual execution process, the embodiment of the present application can input the sample data set into a preset pulse neural network, and use the multi-polarization data intelligent analysis model to intelligently identify and analyze the detection sample data of the multi-polarization radar to output the intelligent identification results of underground target bodies and geological structures, and extract the categories and potential relationships of underground target bodies and geological structures based on the intelligent identification results.

[0068] The embodiment of the present application can utilize the multi-polarization data intelligent analysis model to obtain precise features such as the geological structure type, shape, surface roughness, and directionality of the detection area, thereby enhancing the refined features of the geological structure and providing reliable and accurate geophysical information for engineering practice.

[0069] It should be noted that the preset pulse neural network can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0070] Optionally, in one embodiment of the present application, before inputting the sample data set into a preset pulse neural network, it also includes: using an SRM neuron layer to receive a pulse signal of multi-polarization radar data; performing pulse integration on the pulse signal within a preset time window to generate a pulse response; and processing the SRM neuron model according to the pulse response to obtain a preset pulse neural network.

[0071] Specifically, the embodiment of the present application can build a pulse neural network model based on the SRM neuron model, including: an input layer for receiving data from a multi-polarization radar, the data including the polarization scattering matrix or high-resolution range image of the multi-polarization radar; an SRM neuron layer for receiving pulse signals from the input layer and performing pulse integration within a predefined time window; an output layer for performing further pattern recognition or target classification based on the pulse response generated by the SRM neuron layer. The model can effectively capture and process complex multi-polarization radar data features, thereby improving the accuracy and efficiency of target detection and classification.

[0072] The SRM neuron model in the embodiment of the present application simulates the dynamic changes of multi-polarization radar signals in the form of neural pulses, so that the neuron model learns specific types of radar signal patterns and generates corresponding pulse responses based on the input multi-polarization radar data. It can effectively capture and identify complex features and patterns in multi-polarization radar data, thereby improving the accuracy and robustness of target detection and classification.

[0073] It should be noted that the preset pulse neural network can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0074] Optionally, in one embodiment of the present application, a sample data set is input into a preset pulse neural network to output intelligent recognition results of underground target bodies and geological structures, including: inputting the calibration category of the sample data set into a preset pulse neural network, and training the deep learning neural network model according to the preset pulse neural network to obtain a multi-polarization radar intelligent analysis model; intelligently identifying the sample data set according to the multi-polarization radar intelligent analysis model to obtain intelligent recognition results of underground target bodies and geological structures.

[0075] During the actual execution process, the embodiment of the present application can use the intelligent analysis module to train and test the deep learning neural network model based on the SRM neuron model according to the calibration category of the sample data set, thereby obtaining a multi-polarization radar intelligent analysis model, and intelligently identify the sample data set according to the multi-polarization radar intelligent analysis model, thereby realizing intelligent analysis and identification of the multi-polarization radar detection data, and obtaining intelligent identification results of underground targets and geological structures.

[0076] Among them, the spiking neural network (SNN) imitates the neural dynamics mechanism of high-efficiency biological networks, propagates information in the form of pulse signals between neurons through synapses, and has good time series data processing capabilities. The neuron model Spike Response Model (SRM) can handle the dynamic changes of multi-polarization radar signals in time, and can adjust the intensity and timing characteristics of the response according to the influence of historical inputs, and perform effective time modeling and analysis.

[0077] The neuron model SRM is used to encode and process multipolarized signals. The model efficiently encodes and processes input signals through the firing time of neurons. Specifically, when a spike neuron is stimulated by external stimuli (including input from the external environment and input from the parent synaptic neuron), if the membrane potential of the neuron exceeds the preset threshold, the neuron will generate a spike and send an output signal. This output signal can be further transmitted to other neurons or system components in the neural network, thereby realizing the transmission and processing of information.

[0078] The embodiment of the present application is a pulse learning neural network built based on the SRM neuron model, which simulates the dynamic changes of multi-polarization radar signals in the form of neural pulses, so that the neuron model learns a specific type of radar signal pattern and generates a corresponding pulse response based on the input multi-polarization radar data. It can effectively capture and identify complex features and patterns in multi-polarization radar data, thereby realizing high-precision recognition and intelligent analysis of multi-polarization radar data.

[0079] It should be noted that the preset pulse neural network can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0080] Specifically, it can be combined Figure 2 As shown, the working principle of the multi-polarization radar geological structure analysis method in the embodiment of the present application is described in detail with a specific embodiment.

[0081] like Figure 2As shown, an embodiment of the present application includes a multi-polarization radar, a sample database, a data fusion system and an intelligent analysis module.

[0082] Among them, the multi-polarization radar is used to obtain multi-polarization radar data such as polarization scattering matrix in multiple polarization directions such as VV, HH, VH, HV (where HV means horizontal transmission and vertical reception, and other definitions are similar) of underground targets and geological structures.

[0083] The sample database is used to store, manage and calibrate multi-polarization radar sample data such as polarization scattering matrix of underground targets and geological structures, providing effective data input for data fusion, training and verification of intelligent analysis models in the next step.

[0084] The data fusion system is used to perform pixel-level fusion of multi-polarization radar data such as polarization scattering matrix to obtain a more comprehensive and information-rich multi-polarization radar high-resolution range image.

[0085] The intelligent analysis module is used to analyze and identify the high-resolution range images of multi-polarization radar using deep learning algorithms, and to extract the categories and potential relationships of underground targets.

[0086] In the embodiments of the present application, detection tasks can be performed by technicians operating a vehicle-mounted or unmanned aerial vehicle-mounted multi-polarization radar. Before performing the detection task, the technicians check the working status of the multi-polarization radar and set the frequency band range and parameters, check whether the data storage and transmission modules are working normally, and make the multi-polarization radar reach the detection starting point. The multi-polarization radar is used to perform detection operations, thereby obtaining multi-polarization radar data such as the polarization scattering matrix.

[0087] Next, the embodiment of the present application standardizes multi-polarization radar data such as polarization scattering matrix to reduce the amount of data and improve processing efficiency. At the same time, in the sample database, the processed data can be organized according to the coordinate sequence, and the technical personnel can calibrate, classify and verify the geological structure data obtained by the multi-polarization radar to form an ordered sample data set.

[0088] Secondly, the embodiment of the present application inputs multi-polarization radar detection data such as polarization scattering matrix into the data fusion system, extracts useful feature information from the polarization scattering matrix, and utilizes the multi-polarization radar imaging algorithm and the data of multiple polarization channels of the multi-polarization radar to reconstruct a high-resolution range image of the target area, thereby forming a multi-polarization radar high-resolution range image sample data set.

[0089] Finally, the embodiment of the present application can input the sample data set into the multipolarization data intelligent analysis model to obtain the geological structure multipolarization detection intelligent analysis and identification results. After the task is completed, the results are exported and the storage is cleared.

[0090] According to the multi-polarization radar geological structure analysis method proposed in the embodiment of the present application, the multi-polarization radar geological structure intelligent analysis model based on data fusion technology and deep learning neural network algorithm can realize intelligent identification of multi-polarization radar data, save a lot of manpower consumption, improve work efficiency, convenient operation and simple steps, easy for workers to learn and master, short on-site preparation and debugging time, save time, and facilitate popularization. Therefore, the problems of large workload, low recognition accuracy and efficiency, and over-reliance on the professional ability of practitioners in the related technology of multi-polarization radar data interpretation and analysis are solved.

[0091] Next, the multi-polarization radar geological structure analysis device proposed in the embodiment of the present application is described with reference to the accompanying drawings.

[0092] Figure 3 It is a schematic diagram of the structure of the multi-polarization radar geological structure analysis device of an embodiment of the present application.

[0093] like Figure 3 As shown, the multi-polarization radar geological structure analysis device 10 includes: an acquisition module 100 , a processing module 200 , a generation module 300 and an analysis module 400 .

[0094] Specifically, the acquisition module 100 is used to perform detection operations along the target survey line in the detection area using a multi-polarization radar to obtain multi-polarization radar data of underground target bodies and geological structures.

[0095] The processing module 200 is used to perform standardization processing on the multi-polarization radar data using the sample database to obtain an ordered sample data set.

[0096] The generating module 300 is used to perform pixel-level fusion on the multi-polarization radar data according to the ordered sample data set to generate a multi-polarization radar sample data set with a resolution greater than a preset resolution.

[0097] The analysis module 400 is used to input the sample data set into a preset pulse neural network to output the intelligent recognition results of the underground target body and geological structure, and extract the categories and potential relationships of the underground target body and geological structure according to the intelligent recognition results.

[0098] Optionally, in one embodiment of the present application, the acquisition module 100 includes: an acquisition unit, a first generation unit, a first extraction unit and a second generation unit.

[0099] The acquisition unit is used to acquire multi-polarization reflection signals of underground target bodies and geological structures in horizontal and vertical directions using multi-polarization radar.

[0100] The first generating unit is used to obtain at least one multi-polarization signal data of horizontal transmission and horizontal reception, vertical transmission and vertical reception, horizontal transmission and vertical reception, and vertical transmission and horizontal reception according to the multi-polarization reflected signal.

[0101] The first extraction unit is used to extract and calculate the polarization scattering matrix according to at least one multi-polarization signal data.

[0102] The second generating unit is used to obtain data information of underground target body and geological structure containing anisotropic characteristics according to the polarization scattering matrix.

[0103] Optionally, in one embodiment of the present application, the processing module 200 includes: a first processing unit.

[0104] The first processing unit is used to perform at least one of data normalization, equalization, feature selection and dimension reduction, denoising and consistency verification on the multi-polarization radar data using the sample database to obtain an ordered sample data set.

[0105] Optionally, in one embodiment of the present application, the generating module 300 includes: a second extracting unit and a second processing unit.

[0106] The second extraction unit is used to extract at least one feature information of scattering intensity, phase information and polarization characteristics from the multi-polarization radar data based on the ordered sample data set.

[0107] The second processing unit is used to process at least one item of characteristic information to generate a multi-polarization radar sample data set with a resolution greater than a preset resolution.

[0108] Optionally, in one embodiment of the present application, the multi-polarization radar geological structure analysis device 10 further includes: a receiving module, a generating module and a third processing module.

[0109] Among them, the receiving module is used to receive the pulse signal of the multi-polarization radar data using the SRM neuron layer before inputting the sample data set into the preset pulse neural network.

[0110] The generation module is used to perform pulse integration on the pulse signal within a preset time window to generate an impulse response.

[0111] The third processing module is used to process the SRM neuron model according to the impulse response to obtain a preset pulse neural network.

[0112] Optionally, in one embodiment of the present application, the analysis module 400 includes: a training unit and a recognition unit.

[0113] Among them, the training unit is used to input the calibration category of the sample data set into the preset pulse neural network, and train the deep learning neural network model according to the preset pulse neural network to obtain a multi-polarization radar intelligent analysis model.

[0114] The recognition unit is used to perform intelligent recognition on the sample data set according to the multi-polarization radar intelligent analysis model to obtain intelligent recognition results of underground target bodies and geological structures.

[0115] It should be noted that the above explanation of the embodiment of the multi-polarization radar geological structure analysis method is also applicable to the multi-polarization radar geological structure analysis device of this embodiment, which will not be repeated here.

[0116] According to the multi-polarization radar geological structure analysis device proposed in the embodiment of the present application, the multi-polarization radar geological structure intelligent analysis model based on data fusion technology and deep learning neural network algorithm can realize intelligent identification of multi-polarization radar data, save a lot of manpower consumption, improve work efficiency, convenient operation and simple steps, easy for workers to learn and master, short on-site preparation and debugging time, save time, and facilitate popularization. Therefore, the problems of large workload, low recognition accuracy and efficiency, and over-reliance on the professional ability of practitioners in the related technology of multi-polarization radar data interpretation and analysis are solved.

[0117] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0118] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0119] When the processor 402 executes the program, the multi-polarization radar geological structure analysis method provided in the above embodiment is implemented.

[0120] Furthermore, the electronic device further comprises:

[0121] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0122] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0123] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0124] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0125] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0126] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0127] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above multi-polarization radar geological structure analysis method is implemented.

[0128] The embodiment of the present application also provides a computer program product, on which a computer program is stored, and when the program is executed by a processor, the above multi-polarization radar geological structure analysis method is implemented.

[0129] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0130] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0131] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0132] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0133] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0134] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0135] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0136] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for analyzing geological structures using multi-polarization radar, characterized in that: The following steps are involved: Use multi-polarization radar to conduct detection operations along the target survey line in the detection area to obtain multi-polarization radar data of underground targets and geological structures; The multi-polarization radar data is standardized using a sample database to obtain an ordered sample data set; Performing pixel-level fusion on the multi-polarization radar data according to the ordered sample data set to generate a multi-polarization radar sample data set with a resolution greater than a preset resolution; The sample data set is input into a preset pulse neural network to output intelligent recognition results of the underground target body and the geological structure, and the categories and potential relationships of the underground target body and the geological structure are extracted according to the intelligent recognition results.

2. The method according to claim 1, characterized in that The method of using a multi-polarization radar to perform detection operations along a target survey line in a detection area to obtain multi-polarization radar data of underground target bodies and geological structures includes: Using the multi-polarization radar to obtain multi-polarization reflection signals of the underground target body and the geological structure in horizontal and vertical directions; Obtain at least one multi-polarization signal data of horizontal transmission and horizontal reception, vertical transmission and vertical reception, horizontal transmission and vertical reception, and vertical transmission and horizontal reception according to the multi-polarization reflected signal; Extract and calculate a polarization scattering matrix according to the at least one multi-polarization signal data; Data information of the underground target body and the geological structure containing anisotropic characteristics is obtained according to the polarization scattering matrix.

3. The method according to claim 1, characterized in that: The method of using a sample database to standardize the multi-polarization radar data to obtain an ordered sample data set includes: The sample database is used to perform at least one standardization process of data normalization, equalization, feature selection and dimension reduction, denoising and consistency verification on the multi-polarization radar data to obtain the ordered sample data set.

4. The method according to claim 1, characterized in that The performing pixel-level fusion on the multi-polarization radar data according to the ordered sample data set to generate a multi-polarization radar sample data set with a resolution greater than a preset resolution includes: Based on the ordered sample data set, extract at least one feature information of scattering intensity, phase information and polarization characteristics from the multi-polarization radar data; The at least one item of feature information is processed to generate the multi-polarization radar sample data set having a resolution greater than the preset resolution.

5. The method according to claim 1, characterized in that Before inputting the sample data set into the preset spiking neural network, the method further includes: Utilizing the SRM neuron layer to receive the pulse signal of the multi-polarization radar data; In a preset time window, the pulse signal is pulse-integrated to generate an impulse response; The SRM neuron model is processed according to the impulse response to obtain the preset pulse neural network.

6. The method according to claim 1, characterized in that The step of inputting the sample data set into a preset pulse neural network to output intelligent recognition results of the underground target body and the geological structure includes: Inputting the calibrated categories of the sample data set into the preset spiking neural network, and training the deep learning neural network model according to the preset spiking neural network to obtain a multi-polarization radar intelligent analysis model; The sample data set is intelligently identified according to the multi-polarization radar intelligent analysis model to obtain intelligent identification results of the underground target body and the geological structure.

7. A multi-polarization radar geological structure analysis device, characterized in that: include: An acquisition module is used to perform detection operations along the target survey line in the detection area using a multi-polarization radar to obtain multi-polarization radar data of underground targets and geological structures; A processing module, used for standardizing the multi-polarization radar data using a sample database to obtain an ordered sample data set; A generating module, configured to perform pixel-level fusion on the multi-polarization radar data according to the ordered sample data set to generate a multi-polarization radar sample data set having a resolution greater than a preset resolution; The analysis module is used to input the sample data set into a preset pulse neural network to output intelligent recognition results of the underground target body and the geological structure, and extract the categories and potential relationships of the underground target body and the geological structure based on the intelligent recognition results.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-polarization radar geological structure analysis method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the multi-polarization radar geological structure analysis method as described in any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement the multi-polarization radar geological structure analysis method according to any one of claims 1 to 5.

Images