Ground Penetrating Radar C-scan Inversion Method and System

Abstract

The present invention discloses a ground penetrating radar C-scan inversion method and system, including obtaining XZ slice, YZ slice and XY slice data of a target to be inverted and preprocessing them to construct a training data set; constructing an initial ground penetrating radar slice data inversion model based on convolutional layers, linear layers, Patch Merging layers, Patch Expanding layers, projection layers, residual connections and skip connections, and training to obtain a ground penetrating radar slice data inversion model; inputting detection data obtained in an actual three-dimensional detection scenario into the ground penetrating radar slice data inversion model for processing to obtain inverted slice data; splicing and three-dimensional reconstructing the obtained inverted slice data to complete the C-scan inversion of the ground penetrating radar. The present invention processes the detection data of XZ slices, YZ slices and XY slices by using the constructed inversion model, and combines splicing and three-dimensional reconstruction, not only realizing the C-scan inversion of the ground penetrating radar, but also having higher reliability, better accuracy and higher efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of geological exploration, and particularly relates to a ground penetrating radar C-scan inversion method and system. Background Art

[0002] A ground penetrating radar is a commonly used non-destructive testing device. It detects internal defects of a structure by transmitting and receiving electromagnetic waves, thereby inferring the internal condition of the structure. Ground penetrating radar inversion can intuitively and clearly reflect the shape, size and position distribution of the detected object, and transform the interpretation of the radar profile into the analysis of the dielectric parameter image, which is beneficial to analyzing the shape information of the target. Therefore, the inversion scheme of the ground penetrating radar is of great significance to the ground penetrating radar.

[0003] At present, the traditional two-dimensional inversion methods of ground penetrating radar mainly include the RTM imaging algorithm and two-dimensional full waveform inversion (FWI). RTM was first applied to seismic wave inversion. Due to the similar kinematic and dynamic characteristics of the electromagnetic waves of the ground penetrating radar, it has gradually been introduced into the field of ground penetrating radar. Two-dimensional FWI is a quantitative inversion technique, which was initially applied to seismic wave inversion. In recent years, with the improvement of computing power, it has been introduced into the inversion of ground penetrating radar data. In addition, through deep learning technology, the analysis and processing ability of ground penetrating radar data has been significantly improved. For example, the method based on a deep neural network takes the B-scan data of the ground penetrating radar as input and realizes the inversion of the dielectric constant of the detection area.

[0004] However, the above ground penetrating radar inversion schemes are mainly for two-dimensional inversion; for a three-dimensional scenario with higher complexity, the existing schemes usually jointly analyze multiple B-scan images, form a three-dimensional C-scan from multiple two-dimensional B-scans, and directly map the C-scan to a three-dimensional spatial structure through a three-dimensional inversion network. However, the network parameter quantity of such schemes is extremely large and the system efficiency is low; moreover, due to the different input dimensions, the two-dimensional inversion network with fewer parameter quantities cannot be applied to three-dimensional inversion. Summary of the Invention

[0005] One of the purposes of the present invention is to provide a ground penetrating radar C-scan inversion method with high reliability, good accuracy and high efficiency.

[0006] Another purpose of the present invention is to provide a system for implementing the ground penetrating radar C-scan inversion method.

[0007] The ground penetrating radar C-scan inversion method provided by the present invention includes the following steps:

[0008] S1. In a three-dimensional detection scenario, obtain the XZ slice, YZ slice and XY slice data of the target to be inverted from the ground penetrating radar C-scan data;

[0009] S2. Preprocess the three-view detection data obtained in step S1 to construct a training data set;

[0010] S3. Based on convolutional layers, linear layers, Patch Merging layers, Patch Expanding layers, projection layers, residual connections, and skip connections, construct an initial model for ground-penetrating radar slice data inversion;

[0011] The constructed initial model for ground-penetrating radar slice data inversion includes an embedding layer, an encoder, a decoder, and a projection layer; the embedding layer adjusts the channels of the input data; the encoder is used to perform feature extraction and downsampling operations on the input data with adjusted channels; the decoder is used to perform feature decoding and upsampling operations on the features output by the encoder; the projection layer is used to recover the features output by the decoder;

[0012] S4. Use the training data set obtained in step S2 to train the initial model for ground-penetrating radar slice data inversion constructed in step S3 to obtain a ground-penetrating radar slice data inversion model;

[0013] S5. Input the detection data obtained in the actual three-dimensional detection scene into the ground-penetrating radar slice data inversion model obtained in step S4 for processing to obtain inverted slice data;

[0014] S6. Stitch and three-dimensionally reconstruct the inverted slice data obtained in step S5 to complete the C-scan inversion of the ground-penetrating radar.

[0015] The described step S1 specifically includes the following steps:

[0016] In a three-dimensional detection scene, set a number of parallel detection lines on the OXZ plane where the ground surface is located;

[0017] Based on the set parallel detection lines, collect several groups of B-scan data to form C-scan data;

[0018] In the B-scan data collected at the first parallel detection line, select the scattering curve region of the potential target to be inverted and use it as the target to be tracked;

[0019] Use a tracking algorithm to track the target to be tracked in the B-scans collected at subsequent parallel detection lines to obtain the target box of the target scattering curve region in the B-scan; the length of the target box is and the width of the target box is The coordinates of the upper left corner point of the target box are The target box is represented as ; The B-scan data corresponds to the XY slice data;

[0020] Slice perspectives of different dimensions to obtain XZ slice data and YZ slice data:

[0021] In the Top-scan data, the length of the target box is , the width of the target box is N, and the coordinates of the upper left corner point of the target box are , and the coordinates of the lower right corner point of the target box are , and the target box is represented as , where the Top-scan data corresponds to the XZ slice data;

[0022] In the Crossline-scan data, the length of the target box is N, and the width of the target box is , the coordinates of the upper left corner point of the target box are , and the coordinates of the lower right corner point of the target box are , and the target box is represented as , where the Crossline-scan data corresponds to the YZ slice data.

[0023] The step S2 specifically includes the following steps:

[0024] Adjust the XZ slice data, YZ slice data, and XY slice data obtained in step S1 to a set size through image size operations , where A is the side length of the square of the set size; the image size operations include padding, cropping, and scaling;

[0025] First, calculate the expansion parameter p as ; then calculate the side length L of the square area to be cropped as ; next, calculate the scaling factor s as ;

[0026] When cropping, judge whether it exceeds the boundary of the data according to the center position and side length information of the target:

[0027] If it exceeds the boundary of the data, the exceeded part is filled with the average pixel value of the picture;

[0028] If it does not exceed the boundary of the data, no filling is performed;

[0029] Adjust the size of the square area to the set size according to the scaling factor s ;

[0030] Slice the three-dimensional spatial structure model of the target based on the positions of each survey line; to ensure that the size of the target model remains unchanged, set a matrix with a set size, align the center of the sliced data with the label matrix, assign the sliced data to the label matrix correspondingly, and at the same time set the value of the target area in the label matrix to 1 and the value of the background area in the label matrix to 0; finally, use the label matrix as the inversion label.

[0031] The step S3 described above includes the following steps:

[0032] Use the Patch Embedding layer as the embedding layer to adjust the channels of the input data;

[0033] Based on the linear layer, Patch Merging layer and residual connection, construct an encoder to perform feature extraction and downsampling operations on the input data;

[0034] Based on the Patch Expanding layer and linear layer, construct a decoder to perform feature decoding and upsampling operations on the features output by the encoder; use skip connections between the encoder and the decoder;

[0035] The projection layer is used to recover the features output by the decoder.

[0036] The initial model for the inversion of ground penetrating radar sliced data includes the following:

[0037] The input of the model includes preprocessed XZ sliced data, YZ sliced data, and XY sliced data;

[0038] The preprocessed XZ sliced data, YZ sliced data, and XY sliced data are input to the encoder after being processed by their respective Patch Embedding layers;

[0039] The encoder includes an XZ sliced data sub-encoder, a YZ sliced data sub-encoder, and an XY sliced data sub-encoder; the structures of the XZ sliced data sub-encoder, YZ sliced data sub-encoder, and XY sliced data sub-encoder are the same; the input of the XZ sliced data sub-encoder is the XZ sliced data processed by the Patch Embedding layer, the input of the YZ sliced data sub-encoder is the YZ sliced data processed by the Patch Embedding layer, and the input of the XY sliced data sub-encoder is the XY sliced data processed by the Patch Embedding layer;

[0040] The processing process of the sub-encoder includes: after the input slice data is processed by the first feature extraction module, the first Patch Merging layer, and the first linear layer, the first sub-feature is obtained; after the first sub-feature is processed by the second feature extraction module, the second Patch Merging layer, and the second linear layer, the second sub-feature is obtained; after the second sub-feature is processed by the third feature extraction module, the third Patch Merging layer, and the third linear layer, the third sub-feature is obtained; after the third sub-feature is processed by the fourth feature extraction module, the fourth sub-feature is obtained; among them, both the Patch Merging layer and the linear layer are used for downsampling operations;

[0041] After adding the fourth sub-feature of the XZ slice data, the fourth sub-feature of the YZ slice data, and the fourth sub-feature of the XY slice data output by the encoder, it is used as the input of the decoder;

[0042] The processing process of the decoder includes: after the input of the decoder is processed by the fifth feature extraction module, it is added to the third sub-feature of the XZ slice data, the third sub-feature of the YZ slice data, and the third sub-feature of the XY slice data output by the encoder to obtain the fifth sub-feature; after the fifth sub-feature is processed by the sixth Patch Expanding layer, the sixth linear layer, and the sixth feature extraction module, it is added to the second sub-feature of the XZ slice data, the second sub-feature of the YZ slice data, and the second sub-feature of the XY slice data output by the encoder to obtain the sixth sub-feature; after the sixth sub-feature is processed by the seventh Patch Expanding layer, the seventh linear layer, and the seventh feature extraction module, it is added to the first sub-feature of the XZ slice data, the first sub-feature of the YZ slice data, and the first sub-feature of the XY slice data output by the encoder to obtain the seventh sub-feature; the seventh sub-feature is processed by the eighth Patch Expanding layer, the eighth linear layer, and the eighth feature extraction module to obtain the output of the encoder; among them, both the Patch Expanding layer and the linear layer are used for upsampling operations;

[0043] The output of the encoder is processed by the projection layer to restore the feature channels, and finally the inverted slice data is obtained.

[0044] The structures of the first feature extraction module to the eighth feature extraction module are the same; the processing process of the feature extraction module includes the following steps:

[0045] The input feature data is processed by the normalization layer and then divided into G channels;

[0046] Each channel of data is subjected to feature extraction through the feature extraction sub-module;

[0047] The G-channel feature extraction data obtained is concatenated, and then processed by the normalization layer and the linear layer to obtain the feature extraction module.

[0048] The processing procedure of the feature extraction sub-module includes the following steps:

[0049] After the input feature data is processed by the first normalization layer, it is divided into two paths:

[0050] The first path of data is processed by the first linear layer and the first activation function layer to obtain the first branch data;

[0051] The second path of data is sequentially processed by the second linear layer, the depthwise separable convolution layer, the two-dimensional selective scanning module SS2D and the second normalization layer to obtain the second branch data;

[0052] After the first branch data and the second branch data are multiplied element by element, they are then processed by the third linear layer to obtain the third branch data;

[0053] The third branch data and the feature data input to the feature extraction sub-module are added together as the output of the feature extraction sub-module.

[0054] The training described in step S4 specifically includes the following steps:

[0055] The following formula is used as the loss function for the training process: In the formula, L is the value of the loss function; n is the number of samples; is the actual label of the i-th sample; is the predicted label of the i-th sample.

[0056] The 3D reconstruction described in step S6 specifically includes the following steps:

[0057] For the data obtained after splicing, the Marching Cubes algorithm is used for 3D reconstruction.

[0058] The present invention also provides a system for implementing the GPR C-scan inversion method, including a data acquisition module, a data processing module, a model construction module, a model training module, a model inversion module, and a three-dimensional reconstruction module; the data acquisition module, the data processing module, the model construction module, the model training module, the model inversion module, and the three-dimensional reconstruction module are connected in series in sequence; the data acquisition module is used to obtain the XZ slice, YZ slice, and XY slice data of the target to be inverted from the GPR C-scan data in a three-dimensional detection scenario, and upload the data information to the data processing module; the data processing module is used to perform data preprocessing on the acquired three-view detection data according to the received data information to construct a training data set, and upload the data information to the model construction module; the model construction module is used to construct an initial model for inverting GPR slice data based on the received data information, a convolutional layer, a linear layer, a Patch Merging layer, a Patch Expanding layer, a projection layer, a residual connection, and a skip connection, and upload the data information to the model training module; the constructed initial model for inverting GPR slice data includes an embedding layer, an encoder, a decoder, and a projection layer; the embedding layer adjusts the channels of the input data; the encoder is used to perform feature extraction and downsampling operations on the input data with adjusted channels; the decoder is used to perform feature decoding and upsampling operations on the features output by the encoder; the projection layer is used to restore the features output by the decoder; the model training module is used to train the constructed initial model for inverting GPR slice data using the obtained training data set according to the received data information to obtain a model for inverting GPR slice data, and upload the data information to the model inversion module; the model inversion module is used to input the detection data obtained in the actual three-dimensional detection scenario into the obtained model for inverting GPR slice data for processing according to the received data information to obtain inverted slice data, and upload the data information to the three-dimensional reconstruction module; the three-dimensional reconstruction module is used to splice and perform three-dimensional reconstruction on the obtained inverted slice data according to the received data information to complete the C-scan inversion of the GPR.

[0059] The GPR C-scan inversion method and system provided by the present invention process the detection data of the XZ slice, YZ slice, and XY slice using the constructed inversion model, and combine splicing and three-dimensional reconstruction, not only realizing the inversion of the GPR C-scan, but also greatly reducing the number of parameters of the inversion network and having higher efficiency. Description of the Drawings

[0060] Figure 1 It is a schematic flowchart of the method of the present invention.

[0061] Figure 2 It is a schematic diagram of three-view data for extracting potential targets of the method of the present invention.

[0062] Figure 3 Schematic diagram of the detection scenario in the method embodiment of the present invention.

[0063] Figure 4 Schematic diagrams of each frame of the C-scan in the method embodiment of the present invention, Figure 4 (1)~ Figure 4 (20) are schematic diagrams of the data of 20 groups of B-scans that make up the C-scan.

[0064] Figure 5 Schematic diagram of the tracking result of the B-scan in the method embodiment of the present invention, Figure 5 (1)~ Figure 5 (20) are schematic diagrams of the data of 20 groups of B-scans.

[0065] Figure 6 Schematic diagram of the tracking result of the Top-scan in the method embodiment of the present invention, Figure 6 (1)~ Figure 6 (20) are schematic diagrams of the data of 20 groups of Top-scans.

[0066] Figure 7 Schematic diagram of the tracking result of the Crossline-scan in the method embodiment of the present invention, Figure 7 (1)~ Figure 7 (20) are schematic diagrams of the data of 20 groups of Crossline-scans.

[0067] Figure 8 Schematic diagram of the three-dimensional reconstruction result in the method embodiment of the present invention, where Figure 8 (1) is a schematic diagram of the model label of the high-resolution STL file, Figure 8 (2) is a schematic diagram of the low-resolution label (the label corresponding to the inversion network) composed of the splicing and reconstruction of the target slices at each survey line, Figure 8 (3) is a schematic diagram of the inversion result of the three-dimensional reconstruction of the present invention, Figure 8 (4) is a schematic diagram of the comparison effect of the three-dimensional inversion result after reconstruction of the present invention stacked with the high-resolution label.

[0068] Figure 9 Schematic diagram of the functional modules of the system of the present invention. Detailed implementation manners

[0069] As Figure 1 shown is the schematic diagram of the method flow of the method of the present invention: The ground penetrating radar C-scan inversion method disclosed in the present invention includes the following steps:

[0070] S1. In a three-dimensional detection scenario, obtain the XZ slice, YZ slice, and XY slice data of the target to be inverted from the ground penetrating radar C-scan data; specifically, it includes the following steps:

[0071] The data from the three perspectives are as Figure 2 shown, namely the XZ slice (Top-scan), the YZ slice (Crossline-scan), and the XY slice (B-scan); where Top-scan is sliced in the depth dimension, Crossline-scan is the slice survey line perpendicular to the radar scanning direction, and B-scan is the slice along the radar detection survey line direction;

[0072] In a three-dimensional detection scenario, set several parallel detection lines in the OXZ plane where the ground surface is located;

[0073] Based on the set parallel detection lines, collect several groups of B-scan data to form C-scan data;

[0074] In the B-scan data collected at the first parallel detection line, select the scattering curve region of the potential target to be inverted and use it as the target to be tracked;

[0075] Adopt a tracking algorithm (such as the KCF algorithm) to track the target to be tracked in the B-scan collected at the subsequent parallel detection lines, and obtain the target box of the target scattering curve region in the B-scan; the length of the target box is and the width of the target box is ; the coordinates of the upper left corner point of the target box are ; the target box is represented as ; the B-scan data corresponds to the XY slice data;

[0076] Slice the perspectives of different dimensions to obtain the XZ slice data and the YZ slice data:

[0077] Since when collecting and obtaining C-scan, it is usually sparse in the Z-axis direction, and all are included in the target box range in this perspective in this axis direction. Therefore, in the Top-scan data, the length of the target box is ; the width of the target box is N, the coordinates of the upper left corner point of the target box are ; the coordinates of the lower right corner point of the target box are ; the target box is represented as ; where the Top-scan data corresponds to the XZ slice data;

[0078] In the Crossline-scan data, the length of the target box is N, the width of the target box is ; the coordinates of the upper left corner point of the target box are , the coordinates of the lower right corner point of the target box are , the target box is represented as , where the Crossline-scan data corresponds to the YZ slice data.

[0079] S2. Perform data preprocessing on the three-view detection data obtained in step S1 to construct a training dataset; specifically, it includes the following steps:

[0080] Adjust the XZ slice data, YZ slice data, and XY slice data obtained in step S1 to a set size through image size operations , A is the side length of the square of the set size (preferably taking the value of 255); the image size operations include padding, cropping, and scaling;

[0081] First, calculate the expansion parameter p as ; then calculate the side length L of the square area to be cropped as ; next, calculate the scaling factor s as ;

[0082] According to the center position and side length information of the target, judge whether it exceeds the boundary of the data:

[0083] If it exceeds the boundary of the data, the exceeded part is filled with the average pixel value of the picture;

[0084] If it does not exceed the boundary of the data, no filling is performed;

[0085] Adjust the size of the square area to the set size according to the scaling factor s ;

[0086] Slice the three-dimensional spatial structure model of the target based on the positions of each survey line; to ensure that the size of the target model remains unchanged, set a matrix of a set size (preferably ), align the center of the slice data with the label matrix, assign the slice data to the label matrix correspondingly, and at the same time set the value of the target area in the label matrix to 1 and the value of the background area in the label matrix to 0; finally, use the label matrix as the label of the data.

[0087] S3. Based on the convolutional layer, linear layer, Patch Merging layer, Patch Expanding layer, projection layer, residual connection, and skip connection, construct an initial model for ground penetrating radar slice data inversion;

[0088] The initially constructed inversion model for ground penetrating radar slice data includes an embedding layer, an encoder, a decoder, and a projection layer; the embedding layer adjusts the channels of the input data; the encoder is used to perform feature extraction and downsampling operations on the input data after channel adjustment; the decoder is used to perform feature decoding and upsampling operations on the features output by the encoder; the projection layer is used to recover the features output by the decoder.

[0089] Specifically, the implementation includes the following steps:

[0090] Use the Patch Embedding layer as the embedding layer to adjust the channels of the input data;

[0091] Based on the linear layer, Patch Merging layer, and residual connection, construct an encoder to perform feature extraction and downsampling operations on the input data;

[0092] Based on the Patch Expanding layer and linear layer, construct a decoder to perform feature decoding and upsampling operations on the features output by the encoder; a skip connection is used between the encoder and the decoder;

[0093] The projection layer is used to recover the features output by the decoder.

[0094] Among them, the initially constructed inversion model for ground penetrating radar slice data includes the following:

[0095] The input of the model includes preprocessed XZ slice data, YZ slice data, and XY slice data;

[0096] The preprocessed XZ slice data, YZ slice data, and XY slice data are input to the encoder after being processed by their respective Patch Embedding layers;

[0097] The encoder includes a sub-encoder for XZ slice data, a sub-encoder for YZ slice data, and a sub-encoder for XY slice data; the structures of the sub-encoder for XZ slice data, the sub-encoder for YZ slice data, and the sub-encoder for XY slice data are the same; the input of the sub-encoder for XZ slice data is the XZ slice data processed by the Patch Embedding layer, the input of the sub-encoder for YZ slice data is the YZ slice data processed by the Patch Embedding layer, and the input of the sub-encoder for XY slice data is the XY slice data processed by the Patch Embedding layer;

[0098] The processing process of the sub-encoder includes: after the input slice data is processed by the first feature extraction module, the first Patch Merging layer, and the first linear layer, the first sub-feature is obtained; after the first sub-feature is processed by the second feature extraction module, the second Patch Merging layer, and the second linear layer, the second sub-feature is obtained; after the second sub-feature is processed by the third feature extraction module, the third Patch Merging layer, and the third linear layer, the third sub-feature is obtained; after the third sub-feature is processed by the fourth feature extraction module, the fourth sub-feature is obtained; among them, both the Patch Merging layer and the linear layer are used for downsampling operations;

[0099] After adding the fourth sub-feature of the XZ slice data, the fourth sub-feature of the YZ slice data, and the fourth sub-feature of the XY slice data output by the encoder, it is used as the input of the decoder;

[0100] The processing process of the decoder includes: after the input of the decoder is processed by the fifth feature extraction module, it is added to the third sub-feature of the XZ slice data, the third sub-feature of the YZ slice data, and the third sub-feature of the XY slice data output by the encoder to obtain the fifth sub-feature; after the fifth sub-feature is processed by the sixth Patch Expanding layer, the sixth linear layer, and the sixth feature extraction module, it is added to the second sub-feature of the XZ slice data, the second sub-feature of the YZ slice data, and the second sub-feature of the XY slice data output by the encoder to obtain the sixth sub-feature; after the sixth sub-feature is processed by the seventh Patch Expanding layer, the seventh linear layer, and the seventh feature extraction module, it is added to the first sub-feature of the XZ slice data, the first sub-feature of the YZ slice data, and the first sub-feature of the XY slice data output by the encoder to obtain the seventh sub-feature; the seventh sub-feature is processed by the eighth Patch Expanding layer, the eighth linear layer, and the eighth feature extraction module to obtain the output of the encoder; among them, both the Patch Expanding layer and the linear layer are used for upsampling operations;

[0101] The output of the encoder is processed by the projection layer to restore the feature channels, and finally the inversion slice data is obtained.

[0102] The structures of the first feature extraction module to the eighth feature extraction module are the same; the processing process of the feature extraction module includes the following steps:

[0103] The input feature data is processed by the normalization layer and then divided into G channels;

[0104] Each channel of data is subjected to feature extraction through the feature extraction sub-module;

[0105] The G channels of feature extraction data obtained are concatenated, and then processed by the normalization layer and the linear layer to obtain the feature extraction module;

[0106] In traditional solutions, the number of channels, the size of the SSM state dimension, the size of the internal 1D convolution kernel, the projection expansion multiplier, and the rank of the stride all affect the parameters, and the influence of the number of channels is explosive. Therefore, in this feature extraction module proposed by the present invention, based on the idea of grouping (corresponding to dividing into G-way data for feature extraction), the feature extraction is realized; through the idea of grouping, the problem of the sharp increase in the number of parameters of the inversion network caused by the increase in the number of channels can be better avoided, and the number of parameters of the inversion model is greatly reduced.

[0107] The processing process of the feature extraction sub-module includes the following steps:

[0108] After the input feature data is processed by the first normalization layer, it is divided into two paths:

[0109] The first path of data is processed by the first linear layer and the first activation function layer to obtain the first branch data;

[0110] The second path of data is successively processed by the second linear layer, the depthwise separable convolution layer, the two-dimensional selective scanning module SS2D, and the second normalization layer to obtain the second branch data;

[0111] After the first branch data and the second branch data are multiplied element by element, they are then processed by the third linear layer to obtain the third branch data;

[0112] The third branch data and the feature data input to the feature extraction sub-module are added as the output of the feature extraction sub-module;

[0113] This feature extraction sub-module provided by the present invention is more efficient than Transformer and has a linear time complexity; compared with the CNN network, this feature extraction sub-module provided by the present invention can capture long-term dependencies.

[0114] S4. Using the training data set obtained in step S2, train the initial model for inverting the ground penetrating radar slice data constructed in step S3 to obtain a ground penetrating radar slice data inversion model;

[0115] During specific training, it includes the following steps:

[0116] Use the following formula as the loss function during the training process: In the formula, L is the value of the loss function; n is the number of samples; is the actual label of the i-th sample; is the predicted label of the i-th sample.

[0117] S5. Input the detection data obtained from the actual three-dimensional detection scene into the ground penetrating radar slice data inversion model obtained in step S4 for processing to obtain the inverted slice data.

[0118] S6. Stitch and three-dimensionally reconstruct the inversion slice data obtained in step S5 to complete the C-scan inversion of the ground penetrating radar; wherein, during the three-dimensional reconstruction, the Marching Cubes algorithm is used for the three-dimensional reconstruction of the data obtained after stitching.

[0119] The method of the present invention can directly perform three-dimensional shape inversion on C-scan data using a two-dimensional inversion network, greatly alleviating the problem of the huge number of parameters in the three-dimensional inversion network. Therefore, the method of the present invention has a lower running memory occupancy rate; at the same time, the method of the present invention designs a method for extracting three-view data of potential targets, and uses the three-view data to provide more prior information for the two-dimensional inversion network, thus greatly improving the accuracy of shape inversion.

[0120] The method of the present invention is further described below in conjunction with an embodiment:

[0121] This embodiment is carried out on a workstation equipped with a 13th Gen Intel(R) Core(TM) i9-13900K CPU, 32 GB of RAM, and a GTX 4090 GPU; the method of the present invention is implemented based on the Python and PyTorch frameworks, and RMSprop is used as the weight optimization algorithm, with the learning rate set to 1e-5.

[0122] First, a three-dimensional target model was randomly generated using 3DsMax software and saved as an STL format file; subsequently, when creating the input file, a dielectric constant model with a size of 2.0 m in length and 1 m in depth was constructed, and the shape of the three-dimensional model slice corresponding to the survey line was selected as the target at the survey line; the transmitter and receiver of the ground penetrating radar were set at a height of 0.9 m from the ground and continuously moved from left to right along the scanning trajectory to obtain B-scan data; the antenna was emitted using a Ricker wavelet with a center frequency of 500 MHz, the distance between the transmitter and the receiver was set to 0.02 m, and the antenna moved 0.02 m per step, and the sampling time window length was 26 ns. The finally generated GPR B-scan data was a matrix with a size of In the FDTD forward simulation, the spatial spacing of the grid was 0.01 m, and 10 grid points were set around each side as the perfectly matched layer (PML) absorption boundary condition, and each dielectric constant model contained grid points; finally, a simulation data set was generated using the finite-difference time-domain (FDTD) algorithm through Gprmax software.

[0123] As Figure 3The model diagram of the detection scenario of the embodiment of the present invention is shown. In this example, two targets are used as an example. There are two cylindrical targets in the detection scenario. 20 horizontal survey lines are set in the Z-axis direction to detect the B-scan data of the XY plane scenario. The 20 groups of B-scan data are as Figure 4 shown. Among the B-scan data obtained on the first survey line, it can be found that there are 2 hyperbolic targets. In this example, the area where the scattering curve on the right is located is selected as the initial tracking target, as Figure 4 shown by the dotted box in (1); then the subsequent B-scan is tracked by the KCF algorithm to obtain the position information of the area where the target scattering curve is located in each frame of the C-scan, and then cropping and extraction are performed based on the target position information. According to the above steps, the data of the area where the tracking target is located in each B-scan can be obtained. For the convenience of the training of the subsequent inversion algorithm, the data of the target scattering curve area needs to undergo operations such as filling, cropping, and scaling before being input into the inversion network to ensure that the aspect ratio of the selected potential target does not change.

[0124] After the area where the target scattering curve is located in the B-scan undergoes operations such as filling, cropping, and scaling, the result is as Figure 5 shown; then slices are taken from different-dimensional perspectives to obtain data of three perspectives. After undergoing operations such as filling, cropping, and scaling in the Top-scan, the result is as Figure 6 shown; after undergoing operations such as filling, cropping, and scaling in the Crossline-scan, the result is as Figure 7 shown;

[0125] Then, the label of the inversion network is constructed, and after passing through the inversion network, the shape slices of the selected target at each survey line are spliced to obtain volume data. Finally, Marching cubes is used to perform three-dimensional reconstruction on the slice data, and the result is as Figure 8 shown;

[0126] In addition, the similarity between the two is evaluated by calculating the error value of ICP registration and the slope distance between them. The calculation process of the ICP registration error is to first convert the surface point data into a point cloud format, find the best rigid body transformation (rotation and translation) between the two point sets, so that the coincidence degree of the registered point cloud in space is maximized. Finally, the error value between the two is obtained. The smaller the error value, the more similar the appearance shapes are. In Figure 8 it is Figure 8 shown that the normalized ICP value between the three-dimensional inversion results after reconstruction of (1) and Figure 8 (4) is 0.02152. The theoretical maximum value of the normalized ICP index is , the larger the value, the farther the distance, and the less similar the two shapes are. This embodiment shows that there is a high similarity between the 3D inversion result of the present invention and the label.

[0127] In addition, by calculating the inclined plane distance to judge the similarity of the 3D model, traverse the two vertex sets bidirectionally, and calculate the average minimum adjacent distance using the following formula: This formula calculates the mean of the nearest point distances from each point x in the set to , and then calculates the corresponding mean of the distances from each point y in to in the reverse direction. Finally, the sum of the two is used as the similarity measure. Figure 8 (1) The calculated value of the normalized inclined plane distance between the reconstructed 3D inversion results of Figure 8 and (4) is 0.0332. The theoretical maximum value of the normalized inclined plane distance index is 3. The larger the value, the farther the distance, and the less similar the two shapes are. Through this index, it can be shown that the present invention can use a 2D inversion network to achieve shape inversion of the target.

[0128] Such as Figure 9The following is a schematic diagram of the functional modules of the system of the present invention: The system for implementing the ground penetrating radar C-scan inversion method disclosed in the present invention includes a data acquisition module, a data processing module, a model construction module, a model training module, a model inversion module, and a three-dimensional reconstruction module; the data acquisition module, the data processing module, the model construction module, the model training module, the model inversion module, and the three-dimensional reconstruction module are connected in series in sequence; the data acquisition module is used to obtain the XZ slice, YZ slice, and XY slice data of the target to be inverted from the ground penetrating radar C-scan data in a three-dimensional detection scenario, and upload the data information to the data processing module; the data processing module is used to perform data preprocessing on the obtained three-view detection data according to the received data information to construct a training data set, and upload the data information to the model construction module; the model construction module is used to construct an initial model for inverting the ground penetrating radar slice data based on the convolutional layer, linear layer, Patch Merging layer, Patch Expanding layer, projection layer, residual connection, and skip connection according to the received data information, and upload the data information to the model training module; the constructed initial model for inverting the ground penetrating radar slice data includes an embedding layer, an encoder, a decoder, and a projection layer; the embedding layer adjusts the channels of the input data; the encoder is used to perform feature extraction and downsampling operations on the input data after channel adjustment; the decoder is used to perform feature decoding and upsampling operations on the features output by the encoder; the projection layer is used to restore the features output by the decoder; the model training module is used to train the constructed initial model for inverting the ground penetrating radar slice data using the obtained training data set according to the received data information to obtain a model for inverting the ground penetrating radar slice data, and upload the data information to the model inversion module; the model inversion module is used to input the detection data obtained in the actual three-dimensional detection scenario into the obtained model for inverting the ground penetrating radar slice data for processing according to the received data information to obtain inverted slice data, and upload the data information to the three-dimensional reconstruction module; the three-dimensional reconstruction module is used to splice and perform three-dimensional reconstruction on the obtained inverted slice data according to the received data information to complete the C-scan inversion of the ground penetrating radar.

Claims

1. A ground penetrating radar C-scan inversion method, characterized in that It includes the following steps: S1. In a three-dimensional detection scenario, obtain the XZ slice, YZ slice, and XY slice data of the target to be inverted from the ground penetrating radar C-scan data; S2. Perform data preprocessing on the three-view detection data obtained in step S1 to construct a training dataset; S3. Based on convolutional layers, linear layers, Patch Merging layers, Patch Expanding layers, projection layers, residual connections, and skip connections, construct an initial model for inverting ground penetrating radar slice data; The constructed initial model for inverting ground penetrating radar slice data includes an embedding layer, an encoder, a decoder, and a projection layer; the embedding layer adjusts the channels of the input data; the encoder is used to perform feature extraction and downsampling operations on the input data after channel adjustment; The decoder is used to perform feature decoding and upsampling operations on the features output by the encoder; the projection layer is used to recover the features output by the decoder; S4. Use the training dataset obtained in step S2 to train the initial model for inverting ground penetrating radar slice data constructed in step S3 to obtain an inverting model for ground penetrating radar slice data; S5. Input the detection data obtained in the actual three-dimensional detection scenario into the inverting model for ground penetrating radar slice data obtained in step S4 for processing to obtain inverted slice data; S6. Stitch and three-dimensionally reconstruct the inverted slice data obtained in step S5 to complete the C-scan inversion of the ground penetrating radar.

2. The ground penetrating radar C-scan inversion method according to claim 1, wherein The specific steps of step S1 are as follows: In a three-dimensional detection scenario, set a number of parallel detection lines on the OXZ plane where the ground surface is located; Based on the set parallel detection lines, collect several groups of B-scan data to form C-scan data; In the B-scan data collected at the first parallel detection line, select the scattering curve region of the potential target to be inverted and use it as the target to be tracked; Using a tracking algorithm, in the B-scan collected at subsequent parallel detection lines, track the target to be tracked to obtain the target box in the target scattering curve region in the B-scan; the length of the target box is , the width of the target box is , the coordinates of the upper left corner point of the target box are , and the target box is represented as ; The B-scan data corresponds to the XY slice data; Slice the perspectives of different dimensions to obtain XZ slice data and YZ slice data: In the Top-scan data, the length of the target box is , the width of the target box is N, and the coordinates of the upper-left corner point of the target box are , and the coordinates of the lower-right corner point of the target box are , and the target box is represented as , where the Top-scan data corresponds to the XZ slice data; In the Crossline-scan data, the length of the target box is N, and the width of the target box is , the coordinates of the upper left corner point of the target box are , the coordinates of the lower right corner point of the target box are , the target box is represented as , where the Crossline-scan data corresponds to the YZ slice data.

3. The ground penetrating radar C-scan inversion method according to claim 2, wherein The specific steps of step S2 are as follows: After performing image size operations on the XZ slice data, YZ slice data, and XY slice data obtained in step S1, adjust them to the set size. , where A is the side length of the square with the set size; the image size operations include padding, cropping, and scaling. First, calculate the expansion parameter p as ; then calculate the side length L of the square region to be cut out as ; Next, the calculated scaling factor s is ; During cropping, judge whether it exceeds the boundary of the data according to the center position and side length information of the target; If it exceeds the boundary of the data, the exceeded part is filled with the average pixel value of the picture; If it does not exceed the boundary of the data, no filling is performed; Adjust the size of the square area to the set size according to the scaling factor s ; Slice the three-dimensional space structure model of the target based on the positions of each survey line; to ensure that the size of the target model remains unchanged, set a matrix with a set size, align the center of the sliced data with the label matrix, assign the sliced data to the label matrix correspondingly, and at the same time set the value of the target area in the label matrix to 1 and the value of the background area in the label matrix to 0; finally, use the label matrix as the inversion label.

4. The ground penetrating radar C-scan inversion method according to claim 3, characterized in that The steps of step S3 include the following steps: Use the Patch Embedding layer as the embedding layer to adjust the channels of the input data; Based on linear layers, Patch Merging layers, and residual connections, construct an encoder to perform feature extraction and downsampling operations on the input data; Based on the Patch Expanding layer and the linear layer, a decoder is constructed to perform feature decoding and upsampling operations on the features output by the encoder; a skip connection is adopted between the encoder and the decoder; The projection layer is used to recover the features output by the decoder.

5. The ground penetrating radar C-scan inversion method according to claim 4, wherein The initial model for the inversion of ground penetrating radar slice data includes the following: The input of the model includes the preprocessed XZ slice data, YZ slice data, and XY slice data; The preprocessed XZ slice data, YZ slice data, and XY slice data are input to the encoder after being processed by their respective Patch Embedding layers; The encoder includes an XZ slice data sub-encoder, a YZ slice data sub-encoder, and an XY slice data sub-encoder; the structures of the XZ slice data sub-encoder, YZ slice data sub-encoder, and XY slice data sub-encoder are the same; the input of the XZ slice data sub-encoder is the XZ slice data processed by the Patch Embedding layer, the input of the YZ slice data sub-encoder is the YZ slice data processed by the Patch Embedding layer, and the input of the XY slice data sub-encoder is the XY slice data processed by the Patch Embedding layer; The processing process of the sub-encoder includes: the input slice data is processed by the first feature extraction module, the first Patch Merging layer, and the first linear layer to obtain the first sub-feature; the first sub-feature is processed by the second feature extraction module, the second Patch Merging layer, and the second linear layer to obtain the second sub-feature; the second sub-feature is processed by the third feature extraction module, the third Patch Merging layer, and the third linear layer to obtain the third sub-feature; the third sub-feature is processed by the fourth feature extraction module to obtain the fourth sub-feature; among them, the Patch Merging layer and the linear layer are both used for downsampling operations; The fourth sub-features of the XZ slice data, YZ slice data, and XY slice data output by the encoder are added together and used as the input of the decoder; The processing process of the decoder includes: after the input of the decoder is processed by the fifth feature extraction module, it is added to the third sub-feature of the XZ slice data, the third sub-feature of the YZ slice data, and the third sub-feature of the XY slice data output by the encoder to obtain the fifth sub-feature; after the fifth sub-feature is processed by the sixth Patch Expanding layer, the sixth linear layer, and the sixth feature extraction module, it is added to the second sub-feature of the XZ slice data, the second sub-feature of the YZ slice data, and the second sub-feature of the XY slice data output by the encoder to obtain the sixth sub-feature; after the sixth sub-feature is processed by the seventh Patch Expanding layer, the seventh linear layer, and the seventh feature extraction module, it is added to the first sub-feature of the XZ slice data, the first sub-feature of the YZ slice data, and the first sub-feature of the XY slice data output by the encoder to obtain the seventh sub-feature; the seventh sub-feature is processed by the eighth Patch Expanding layer, the eighth linear layer, and the eighth feature extraction module to obtain the output of the encoder; among them, both the Patch Expanding layer and the linear layer are used for upsampling operations; The output of the encoder is processed by the projection layer to restore the feature channels, and finally the inverted slice data is obtained.

6. The ground penetrating radar C-scan inversion method according to claim 5, wherein The structures of the first feature extraction module to the eighth feature extraction module are all the same; the processing process of the feature extraction module includes the following steps: The input feature data is processed by the normalization layer and then divided into G channels; Each channel of data is subjected to feature extraction through the feature extraction sub-module; The G channels of feature extraction data obtained are concatenated, and then processed by the normalization layer and the linear layer to obtain the feature extraction module.

7. The ground penetrating radar C-scan inversion method according to claim 6, characterized in that the feature The processing process of the extraction sub-module includes the following steps: The input feature data is processed by the first normalization layer and then divided into two channels: The first channel of data is processed by the first linear layer and the first activation function layer to obtain the first branch data; The second channel of data is successively processed by the second linear layer, the depthwise separable convolution layer, the two-dimensional selective scanning module SS2D, and the second normalization layer to obtain the second branch data; After the first branch data and the second branch data are multiplied element by element, they are then processed by the third linear layer to obtain the third branch data; The third branch data and the feature data input to the feature extraction sub-module are added together as the output of the feature extraction sub-module.

8. The ground penetrating radar C-scan inversion method according to claim 7, characterized in that The training described in step S4 specifically includes the following steps: The following formula is used as the loss function in the training process: where L is the value of the loss function; n is the number of samples; is the actual label of the i-th sample; is the predicted label of the i-th sample.

9. The ground penetrating radar C-scan inversion method according to claim 8, wherein The three-dimensional reconstruction described in step S6 specifically includes the following steps: For the data obtained after splicing, the Marching Cubes algorithm is used for three-dimensional reconstruction.

10. A system for implementing the ground penetrating radar C-scan inversion method according to any one of claims 1 to 9, characterized in that It includes a data acquisition module, a data processing module, a model construction module, a model training module, a model inversion module, and a three-dimensional reconstruction module; the data acquisition module, the data processing module, the model construction module, the model training module, the model inversion module, and the three-dimensional reconstruction module are connected in series in sequence; the data acquisition module is used to obtain the XZ slice, YZ slice, and XY slice data of the target to be inverted from the ground penetrating radar C-scan data in the three-dimensional detection scene, and upload the data information to the data processing module; The data processing module is used to perform data preprocessing on the acquired three-view detection data according to the received data information to construct a training dataset, and upload the data information to the model construction module; The model construction module is used to construct an initial model for ground penetrating radar slice data inversion based on the convolutional layer, linear layer, Patch Merging layer, Patch Expanding layer, projection layer, residual connection, and skip connection according to the received data information, and upload the data information to the model training module; The constructed initial model for ground penetrating radar slice data inversion includes an embedding layer, an encoder, a decoder, and a projection layer; the embedding layer adjusts the channels of the input data; the encoder is used to perform feature extraction and downsampling operations on the input data with adjusted channels; The decoder is used to perform feature decoding and upsampling operations on the features output by the encoder; the projection layer is used to restore the features output by the decoder; The model training module is used to train the constructed initial model for ground penetrating radar slice data inversion using the obtained training dataset according to the received data information to obtain a ground penetrating radar slice data inversion model, and upload the data information to the model inversion module; The model inversion module is used to input the detection data obtained in the actual three-dimensional detection scenario into the obtained ground penetrating radar slice data inversion model for processing according to the received data information to obtain inverted slice data, and upload the data information to the three-dimensional reconstruction module; the three-dimensional reconstruction module is used to splice and perform three-dimensional reconstruction on the obtained inverted slice data according to the received data information to complete the C-scan inversion of the ground penetrating radar.

Images