Multi-dimensional display method and system based on three-dimensional geological radar data intelligent analysis

Abstract

The invention belongs to the technical field of geoscience information, and relates to a multi-dimensional display method and system based on three-dimensional geological radar data intelligent analysis, and the method comprises the steps: firstly converting three-dimensional geological radar data into an image, building an accurate mapping relation between image pixels and actual physical dimensions, and achieving the crossing of intelligent recognition from image abnormal region interpretation to quantitative analysis; secondly, based on a multi-dimensional collaborative visual interface, synchronously displaying a multi-channel vertical section, a multi-depth horizontal slice and a synchronous video frame in the same view, integrating and splitting data dimensions through a space-time synchronous linkage mechanism, and then utilizing a target identification model trained by multi-modal data to identify a target object; fusion feature extraction analysis is carried out on a multi-channel vertical section, a multi-depth horizontal slice and a synchronous video frame, the earth surface feature correlation degree is used as a key basis for judging confidence, underground anomalies are proved or eliminated, the false alarm rate of a traditional single image analysis method is greatly reduced, and radar recognition accuracy and reliability are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of geosciences information technology, and in particular, relates to a multi-dimensional display method and system based on intelligent analysis of three-dimensional geological radar data. BACKGROUND

[0002] As a non-destructive, fast and intuitive detection technology, geological radar has shown broad application prospects and important value in urban underground space survey, underground disease body and pipeline detection, road structure defect analysis, archaeological detection and many other fields.

[0003] Among them, three-dimensional geological radar can simultaneously obtain vertical profile data of multiple channels through its unique acquisition method, and generate horizontal slice maps of different depths by fusing data at the same horizontal position, providing more comprehensive underground information, and having the characteristics of multi-channel vertical profile and horizontal slice map at each depth, greatly expanding the interpretation dimension and reference basis of geological radar data.

[0004] However, the prior art has significant deficiencies in the processing and display of three-dimensional geological radar data, which are specifically manifested in: 1. Although the prior art can generate radar images, it generally fails to establish a high-precision mapping relationship between image pixels and actual physical dimensions, resulting in that the interpretation result can only stay at the image anomaly level, and the real geometric size of the underground target body cannot be directly and accurately calculated, making it difficult for data analysis to move from qualitative to quantitative, and unable to meet the needs of precise evaluation and engineering decision-making.

[0005] 2. The existing software usually displays multi-channel vertical profiles, multi-depth horizontal slices and synchronous video data in different windows or modules in isolation, and there is no spatio-temporal correlation and interactive response between views, so the analyst needs to manually correlate and compare a large number of isolated data based on experience, which is extremely inefficient, and key information is easily missed, and the advantages of three-dimensional data in multiple dimensions and high information quantity cannot be converted into advantages in interpretation efficiency.

[0006] 3. Most of the existing automatic identification methods of geological anomalies only analyze radar image signals, completely ignoring the ground surface environment features recorded by synchronous video, and are difficult to distinguish between real signals generated by underground anomalies and false anomalies caused by ground surface interference, resulting in high false positive rate, and the reliability and accuracy of the identification result cannot be guaranteed. SUMMARY

[0007] In view of this, in order to solve the problems raised in the background art, a multi-dimensional display method and system based on intelligent analysis of three-dimensional geological radar data is proposed.

[0008] The technical scheme adopted by the present application to solve its technical problems is: in the first aspect, the present application provides a multi-dimensional display method based on intelligent analysis of three-dimensional geological radar data, comprising: collecting original three-dimensional geological radar data, synchronous video data and positioning data.

[0009] The original three-dimensional geological radar data is preprocessed, and the positioning data is combined to give spatial coordinate information, generating a geological radar data sequence carrying spatial position attributes.

[0010] The synchronous video data is timestamp aligned to generate a video frame sequence time-synchronized with the geological radar data sequence.

[0011] Based on the geological radar data sequence, a multi-channel vertical profile data set and a multi-depth horizontal slice data set are constructed, and a mapping relationship between image pixels and actual physical dimensions is established.

[0012] A multi-dimensional collaborative visualization interface is constructed, which synchronously displays the multi-channel vertical profile, multi-depth horizontal slice and synchronous video frame in the same view, and supports timestamp and spatial coordinate-based linkage response.

[0013] The multi-channel vertical profile, multi-depth horizontal slice and synchronous video frame are intelligently fused and analyzed to identify geological anomaly bodies and calculate their physical dimensions.

[0014] A detection report containing abnormal body physical size and spatial position information is output, and the three-dimensional position of the abnormal body is labeled in the geographic space platform.

[0015] In the second aspect, the present application provides a multi-dimensional display system based on intelligent analysis of three-dimensional geological radar data, comprising: a data acquisition module, a radar data processing module, a video data alignment module, an image conversion module, a multi-dimensional display module, an intelligent identification module and a detection output module.

[0016] The data acquisition module is connected with the radar data processing module and the video data alignment module respectively, the radar data processing module is connected with the image conversion module, the image conversion module and the video data alignment module are connected with the multi-dimensional display module, the multi-dimensional display module is connected with the intelligent identification module, and the intelligent identification module is connected with the detection output module.

[0017] The data acquisition module collects original three-dimensional geological radar data, synchronous video data and positioning data.

[0018] The radar data processing module pre-processes the original three-dimensional geological radar data, combines the positioning data to give spatial coordinate information, and generates a geological radar data sequence carrying spatial position attributes.

[0019] The video data alignment module performs timestamp alignment processing on the synchronized video data to generate a video frame sequence time-synchronized with the GPR data sequence.

[0020] The image conversion module constructs a multi-channel vertical profile data set and a multi-depth horizontal slice data set based on the GPR data sequence, and establishes a mapping relationship between image pixels and actual physical dimensions.

[0021] The multi-dimensional display module constructs a multi-dimensional collaborative visualization interface that synchronously displays the multi-channel vertical profile, multi-depth horizontal slice, and synchronized video frame in the same view, and supports time-stamp and spatial coordinate-based linkage response.

[0022] The intelligent identification module performs intelligent fusion analysis on the multi-channel vertical profile, multi-depth horizontal slice, and synchronized video frame, identifies geological anomaly bodies, and calculates their physical dimensions.

[0023] The detection output module outputs a detection report containing anomaly body physical dimension and spatial position information, and labels the three-dimensional position of the anomaly body in the geographic space platform.

[0024] Compared with the prior art, the embodiments of the present application have at least the following advantages or beneficial effects: (1) The present application converts three-dimensional GPR data into images and establishes an accurate mapping relationship between image pixels and actual physical dimensions in length, width, and depth directions, so that the intelligent identification result is no longer limited to the abnormal area in the image layer, realizing a leap from image interpretation to quantitative analysis, and effectively improving the accuracy and engineering value of data analysis.

[0025] (2) The present application constructs a multi-dimensional collaborative visualization interface that synchronously displays multi-channel vertical profiles, multi-depth horizontal slices, and synchronized video frames in the same view and establishes a time-space synchronization linkage mechanism, integrates the originally fragmented data dimensions into an organic whole, and makes it possible to perform integrated and intuitive analysis of complex underground space.

[0026] (3) The present application uses a target recognition model trained by multi-modal data to perform fusion feature extraction and analysis on radar images and synchronized video frames, and uses the correlation degree with surface features as a key basis for determining confidence, effectively uses surface context information to support or exclude underground anomalies, greatly overcomes the high false alarm rate of traditional single image analysis methods, and makes the identification result more accurate and reliable. BRIEF DESCRIPTION OF DRAWINGS

[0027] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the method flow provided in the first embodiment of the present invention.

[0029] Figure 2 This is a schematic diagram of radar data zero-point correction according to the first embodiment of the present invention.

[0030] Figure 3 This is a system module connection diagram provided for the second embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Example 1

[0033] like Figure 1 As shown, the first embodiment of the present invention provides a multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data, including: S01. Acquiring raw three-dimensional ground-penetrating radar data, synchronous video data and positioning data.

[0034] It should be noted that the original three-dimensional ground-penetrating radar data is a multi-dimensional data set parsed from ground-penetrating radar data files. Its dimensional information includes at least the number of channels, the number of sampling points per radar data channel, the acquisition timestamp, the amplitude sequence, the survey line number, the sampling frequency, and the channel spacing. The number of channels is used to characterize the total amount of data collected along the radar survey line direction. The number of sampling points per radar data channel is used to characterize the total amount of data sampled by the radar in the depth direction. The amplitude sequence records the original electromagnetic response of the radar signal propagating and reflecting in the medium. The survey line number is used to identify the detection line to which the data belongs. The sampling frequency determines the resolution on the time axis, and its reciprocal corresponds to the size of the time window. The time window defines the maximum time interval from radar signal transmission to reception to determine the maximum detection depth. The channel spacing is the physical distance between adjacent detection channels.

[0035] The synchronous video data specifically refers to the surface video images recorded continuously by the geological radar detection area. Through the time stamp synchronization mechanism with the geological radar master control unit, the camera ensures that each frame of video image can be accurately associated to the corresponding radar scanning position. The frame rate of the video image should be matched or in an integer multiple relationship with the scanning frequency of the geological radar to ensure the synchronization accuracy.

[0036] The positioning data is global positioning system coordinate data or position data generated based on an encoder.

[0037] S02. Preprocessing the original three-dimensional geological radar data, combining the positioning data to give spatial coordinate information, and generating a geological radar data sequence carrying spatial position attributes.

[0038] In a preferred embodiment of the present application, preprocessing the original three-dimensional geological radar data includes: performing data format type analysis on the original three-dimensional geological radar data, loading a corresponding preprocessing procedure according to the analyzed data format type, and the preprocessing procedure at least includes background noise removal, gain processing, filtering processing, and data zero point correction.

[0039] It should be noted that the above data format type analysis is configured with a data file interface module, which communicates with the data storage medium through a preset interface protocol. When receiving the original three-dimensional geological radar data file, the file content analysis procedure is started. This procedure first reads the specific byte sequence and field structure in the file header area to identify the file magic number, version identifier, data block layout, and internal encoding scheme. The WEB cloud built-in data format registry is called, which predefines the characteristic signatures of various common geological radar data formats including but not limited to GSSI DZT format, Mala*.rad format, Sensors&Software DZC / DZT format, and data formats conforming to SEG-Y standard, etc. The data file interface module compares the file header information according to the analysis in the data format registry to automatically determine the specific format type of the current geological radar data file.

[0040] The above background noise removal eliminates the constant background noise unrelated to the underground target through the sliding average or linear fitting method.

[0041] The gain processing compensates for the echo signal strength through exponential gain or time gain method according to the attenuation characteristics of electromagnetic waves in underground medium to enhance the visibility of deep targets.

[0042] The filtering processing uses a digital filter such as a Butterworth filter or a Gaussian filter to remove high-frequency random noise and low-frequency system drift in the radar signal, and retains the signals within the effective frequency band.

[0043] AsFigure 2 The data zero point correction is performed by searching for a specific signal feature in each radar data channel within a preset starting time window, determining the actual signal zero point of each radar data channel, cutting off or setting to zero the data of the sampling points before the actual signal zero point, and performing time offset and resampling on the remaining data, so that the signal zero points of all radar data channels are aligned in the time dimension, and a radar data volume with consistent depth direction is generated.

[0044] It should be noted that the specific signal feature searched by the above data zero point correction refers to searching for a high-amplitude or high-gradient signal that first appears within a preset time window after the radar signal is transmitted from the antenna, which usually corresponds to the propagation of the radar direct wave between the antennas or the reflection when the radar pulse first contacts the medium surface, wherein high amplitude or high gradient can exemplarily refer to more than 3 times the standard deviation of the average value of the corresponding parameters within the preset time window.

[0045] It should be noted that the reason for the data zero point correction is that in the actual geological radar operation process, due to factors such as surface undulation, detection environment noise interference, and radar equipment self-coupling effect, it is impossible to ensure that the zero point position in the original data waveform of each survey line is completely consistent with the theoretical medium surface position. The zero point position is the starting time point of the radar signal transmission and propagation, in order to eliminate this systematic error in the depth direction and ensure the alignment and consistency of the data in the depth dimension.

[0046] In a preferred embodiment of the present application, the geological radar data sequence carrying spatial position attributes generation process comprises: analyzing the positioning data to obtain the time stamp and latitude and longitude coordinates of each positioning point.

[0047] Extract the acquisition time stamp of each radar data channel in the original three-dimensional geological radar data.

[0048] Match each radar data channel with multiple adjacent positioning points based on the time stamp, and calculate the spatial coordinates of each radar data channel through an interpolation algorithm.

[0049] It should be noted that the specific process of obtaining the spatial coordinates of each radar data channel is as follows: for a radar data channel whose acquisition time stamp is located in the time interval between two consecutive positioning points, a linear interpolation algorithm is used to calculate the accurate spatial coordinates of the data channel on the line connecting the two consecutive positioning points according to the relative position of the acquisition time stamp of the data channel in the time interval.

[0050] The generation of the geological radar data sequence carrying spatial position attributes is a key link to ensure the accuracy of geological exploration results, and its core significance is derived from the problem of collection frequency difference caused by the physical characteristics of the equipment: in the actual exploration scene, the positioning equipment is limited by physical conditions such as hardware response speed and signal receiving interval, and the data collection frequency is much lower than the sampling frequency of the geological radar host. Under normal circumstances, within the time interval of each spatial coordinate point recorded by the positioning equipment, the geological radar has completed the collection of hundreds of radar data, and this frequency difference directly leads to the fact that most of the radar data channels lack positioning information synchronized with the accurate time. If a simple processing method of nearest neighbor allocation is used, that is, the radar data channel without synchronization positioning is directly matched to the nearest positioning point, it will cause significant sawtooth errors in the spatial position of the radar profile. This error is not a random disturbance, but a periodic position jump feature, which not only distorts the actual spatial distribution form of the underground target body, but also may cover up the real position information of small geological anomalies, and ultimately seriously affects the accuracy of geological interpretation, and even leads to deviation of the exploration conclusion.

[0051] The calculated spatial coordinates are associated with the corresponding radar data channels as attribute information to form a geological radar data sequence carrying spatial position attributes.

[0052] S03. Time stamp alignment processing is performed on the synchronization video data to generate a video frame sequence time-synchronized with the geological radar data sequence.

[0053] S04. Based on the geological radar data sequence, a multi-channel vertical profile graph data set and a multi-depth horizontal slice graph data set are constructed, and a mapping relationship between image pixels and actual physical size is established.

[0054] In a preferred embodiment of the present application, the multi-channel vertical profile graph data set construction process includes: taking the radar data of each detection channel as input, determining the image width according to the number of channels, and determining the image height according to the number of sampling points, and constructing a two-dimensional image pixel grid.

[0055] Single-column pixel mapping is performed on each radar data channel, and the amplitude value sequence of the data channel is matched to the longitudinal coordinate position of the corresponding image column pixel based on the amplitude value collection sequence.

[0056] Each sampling point amplitude value is independently converted into a corresponding RGB color value through a predetermined color mapping mechanism, and filled into the mapped pixel position, thereby generating a vertical profile graph image of each channel. The color mapping mechanism includes normalizing the amplitude value and applying a pseudo-color or grayscale mapping table.

[0057] In a preferred embodiment of the present application, the multi-depth horizontal slice map data set construction process comprises: determining the actual depth corresponding to each sampling point according to the radar wave velocity and the sampling frequency parameters.

[0058] It should be noted that the detection principle of the geological radar is to emit high-frequency electromagnetic pulses to the underground through the transmitting antenna, and the wave will be reflected when encountering different medium interfaces, and the reflected wave is received by the receiving antenna. The above actual depth calculation process is based on this physical process: the ratio of the sampling point index to the sampling frequency is taken as the reflection wave propagation time, the product of the radar wave velocity and the reflection wave propagation time is taken as the radar wave double-path length, and the radar wave single-path length is taken as the actual depth.

[0059] For each target depth, the pixel row corresponding to the depth is extracted from the vertical profile map image of all channels.

[0060] The extracted rows of pixels are spliced according to the physical space position of the corresponding channel to generate a horizontal slice image representing the depth layer structure distribution.

[0061] In a preferred embodiment of the present application, the mapping relationship between the image pixels and the actual physical size comprises: determining the physical length value corresponding to the pixels of the image in the detection direction based on the channel spacing.

[0062] Based on the sampling frequency, the radar wave velocity and the number of sampling points, the physical depth value corresponding to the pixels of the image in the depth direction is determined.

[0063] It should be noted that the physical depth value corresponding to the pixels of the image in the depth direction specifically refers to the actual depth quantified by the sampling frequency and the radar wave velocity, and the ratio operation result of the number of sampling points.

[0064] Based on the number of channels and the channel spacing, the physical width value corresponding to the pixels of the image in the width direction is determined.

[0065] It should be noted that the physical width value corresponding to the pixels of the image in the width direction is specifically the difference between the number of channels and 1, and the multiplication operation result of the channel spacing.

[0066] According to the determined physical size mapping relationship, corresponding physical scales are generated and added to the vertical profile map image and the horizontal slice map image.

[0067] The embodiments of the present application convert three-dimensional geological radar data into images, and establish accurate mapping relationship between image pixels and actual physical size in length, width and depth directions, so that the intelligent recognition result is no longer limited to the abnormal area in the image layer, realizes the leap from image interpretation to quantitative analysis, and effectively improves the accuracy and engineering value of data analysis.

[0068] S05. Construct a multi-dimensional collaborative visualization interface that synchronously displays the multi-channel vertical profile, multi-depth horizontal slice and synchronous video frame in the same view, and supports linkage response based on timestamps and spatial coordinates.

[0069] In a preferred embodiment of the present application, the multi-dimensional collaborative visualization interface comprises:

[0070] A vertical profile display area, a horizontal slice display area and a video playback area are set up for displaying the selected vertical profile, the horizontal slice at a specific depth level and the synchronous video frame, respectively.

[0071] A spatiotemporal linkage mechanism is established among the three areas to synchronously update the display content in the remaining areas in response to user interaction in any area.

[0072] The linkage mechanism specifically implements the following synchronization: i. According to the vertical position selected on the vertical profile, the horizontal slice display area is synchronously updated to the slice at the corresponding depth, and the video playback area is controlled to jump to the video frame at the corresponding time.

[0073] ii. According to the horizontal position selected on the horizontal slice, the vertical profile display area is synchronously switched to the vertical profile passing through the position, and the video playback area is controlled to jump to the video frame at the corresponding time.

[0074] iii. According to the adjustment of the video playback progress, the vertical profile and horizontal slice display areas are synchronously updated to the radar image corresponding to the time and position of the current video frame.

[0075] It should be noted that the above multi-dimensional collaborative visualization interface also supports data linkage review function, and the user can input a specific channel number or travel distance, and the interface will automatically position all views to the position for display.

[0076] The embodiment of the present application synchronously displays the multi-channel vertical profile, multi-depth horizontal slice and synchronous video frame in the same view by constructing a multi-dimensional collaborative visualization interface, and establishes a spatiotemporal synchronization linkage mechanism among them, integrates the originally fragmented data dimensions into an organic whole, and interpreters do not need to manually switch and compare among multiple windows. Any operation on a dimension can trigger global linkage update, making it possible to analyze complex underground space in an integrated and intuitive manner.

[0077] S06. Intelligent fusion analysis is performed on the multi-channel vertical profile, multi-depth horizontal slice and synchronous video frame to identify geological anomalies and calculate their physical dimensions.

[0078] In a preferred embodiment of the present application, the geological anomaly body identification process comprises: training a multi-modal deep learning network based on a geological radar sample data set labeled with anomaly body types, boundary information and their corresponding surface environment features, to obtain a target identification model.

[0079] The multi-channel vertical profile, multi-depth horizontal slice and synchronous video frame are input into the target identification model, which performs fusion feature extraction and analysis to identify potential abnormal targets in the image, and outputs the type and confidence of each identification result.

[0080] It should be noted that in the geological anomaly identification process, the feature extraction network of the target identification model is used to extract depth features representing the reflection structure of the underground medium from the multi-channel vertical profile and the multi-depth horizontal slice, and to extract visual features representing the surface environment and scene from the synchronous video frame.

[0081] Through the feature fusion unit built-in the model, the extracted radar depth features and visual features are cross-modal associated and fused to generate a unified feature identifier that integrates underground information and surface context.

[0082] Based on the unified feature identifier, the classification and region proposal network of the model decodes: generates multiple candidate boxes of different sizes and proportions at each location of the image, extracts the unified feature identifier subset corresponding to each candidate box, obtains the probability that the unified feature identifier subset in the candidate box belongs to each anomaly body type, and if the maximum probability value is greater than the preset class probability threshold, the class corresponding to the maximum probability value is preliminarily determined as the target class.

[0083] The gradient of the target class relative to the radar depth features in the candidate box is calculated, and the gradient information is reversely mapped to the original radar image to quantify the contrast deviation of the candidate box relative to the background, which is used as the saliency of the abnormal target in the radar image.

[0084] For the candidate box identified as the target class, the cosine similarity between its visual feature vector and the typical sample feature vector in the target class predefined positive sample feature vector library is calculated, which is used as the association degree of the abnormal target and the surface features in the video frame.

[0085] The confidence is determined based on the output probability of the classification layer in the target identification model, the saliency of the abnormal target in the radar image, and the association degree of the abnormal target and the surface features in the video frame.

[0086] It should be noted that the above confidence can be calculated by linearly weighted fusion, and the allocation of linear weights is the optimal weight learned by the target identification model through a series of correct decision samples.

[0087] The recognition result with the confidence reaching the preset threshold is determined as a valid anomaly body.

[0088] In a preferred embodiment of the present application, the physical size calculation process comprises: performing boundary sketching on the recognized anomaly body based on the anomaly body boundary information output by the target recognition model.

[0089] The pixel numbers of the boundary sketched region in the length direction, the width direction and the depth direction on the vertical profile graph and the horizontal slice graph are respectively counted.

[0090] The pixel numbers are respectively multiplied by corresponding unit pixel physical values in combination with the mapping relationship between image pixels and actual physical sizes, so as to calculate the actual length, the actual width and the actual depth of the anomaly body.

[0091] In the embodiment of the present application, the target recognition model trained by multi-modal data is adopted to perform fusion feature extraction and analysis on radar images and synchronous video frames, and the correlation degree with the ground features is taken as a key basis for determining the confidence, so that the context information on the ground is effectively utilized to prove or exclude underground anomalies, the disadvantages of high false alarm rate of traditional single image analysis method are greatly overcome, and the recognition result is more accurate and reliable.

[0092] S07. Output a detection report containing the physical size and spatial position information of the anomaly body, and mark the three-dimensional position of the anomaly body in the geographic space platform.

[0093] Embodiment Two

[0094] As shown in Figure 3 The second embodiment of the present application provides a multi-dimensional display system based on intelligent analysis of three-dimensional geological radar data, which comprises a data acquisition module, a radar data processing module, a video data alignment module, an image conversion module, a multi-dimensional display module, an intelligent recognition module and a detection output module.

[0095] The data acquisition module is connected with the radar data processing module and the video data alignment module, the radar data processing module is connected with the image conversion module, the image conversion module and the video data alignment module are connected with the multi-dimensional display module, the multi-dimensional display module is connected with the intelligent recognition module, and the intelligent recognition module is connected with the detection output module.

[0096] The data acquisition module acquires original three-dimensional geological radar data, synchronous video data and positioning data.

[0097] The radar data processing module pre-processes the original three-dimensional geological radar data, and combines with the positioning data to give spatial coordinate information, thereby generating a geological radar data sequence carrying spatial position attributes.

[0098] A video data alignment module performs timestamp alignment processing on the synchronized video data to generate a video frame sequence time-synchronized with the GPR data sequence.

[0099] An image conversion module constructs a multi-channel vertical profile data set and a multi-depth horizontal slice data set based on the GPR data sequence, and establishes a mapping relationship between image pixels and actual physical dimensions.

[0100] A multi-dimensional display module constructs a multi-dimensional collaborative visualization interface that synchronously displays the multi-channel vertical profile, multi-depth horizontal slice, and synchronized video frame in the same view, and supports linkage response based on timestamps and spatial coordinates.

[0101] An intelligent identification module performs intelligent fusion analysis on the multi-channel vertical profile, multi-depth horizontal slice, and synchronized video frame, identifies a geological anomaly body, and calculates its physical dimensions.

[0102] A detection output module outputs a detection report containing the physical dimensions and spatial position information of the anomaly body, and labels the three-dimensional position of the anomaly body in a geographic space platform.

[0103] The multi-dimensional display system based on intelligent analysis of three-dimensional GPR data provided by the embodiments of the present application has the same implementation principle and technical effects as the foregoing method embodiments. For brevity of description, the system embodiment part is not mentioned in the foregoing method embodiment part, and the corresponding content in the foregoing method embodiment part can be referred to.

[0104] The above content is merely an example and description of the structure of the present application. Those skilled in the art of the present technology can make various modifications or supplements to the described specific embodiments or adopt similar ways to replace them, as long as they do not deviate from the structure of the present application or exceed the scope defined by the present application, and all of them shall fall within the protection scope of the present application.

Claims

1. A multi-dimensional display method based on intelligent analysis of 3D ground-penetrating radar data, characterized in that, include: Collect raw 3D ground-penetrating radar data, synchronous video data, and positioning data; The original three-dimensional ground-penetrating radar data is preprocessed and combined with the positioning data to assign spatial coordinate information, thereby generating a ground-penetrating radar data sequence carrying spatial location attributes. The synchronized video data is timestamped to generate a video frame sequence that is time-synchronized with the ground-penetrating radar data sequence. Based on the aforementioned ground-penetrating radar data sequence, a multi-channel vertical profile dataset and a multi-depth horizontal slice dataset were constructed, and a mapping relationship between image pixels and actual physical dimensions was established. A multi-dimensional collaborative visualization interface is constructed, which synchronously displays the multi-channel vertical profile, multi-depth horizontal slice, and synchronous video frames in the same view, and supports linkage response based on timestamp and spatial coordinates; Intelligent fusion analysis is performed on the multi-channel vertical profile, multi-depth horizontal slice, and synchronous video frames to identify geological anomalies and calculate their physical dimensions. Output a detection report containing the physical size and spatial location information of the anomaly, and mark the three-dimensional location of the anomaly in the geospatial platform.

2. The multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data according to claim 1, characterized in that, The raw 3D ground-penetrating radar data is preprocessed, including: The raw 3D ground-penetrating radar data is parsed for data format type, and the corresponding preprocessing process is loaded according to the parsed data format type. The preprocessing process includes at least background noise removal, gain processing, filtering processing, and data zero-point correction. The data zero-point correction involves retrieving specific signal characteristics of each radar data channel within a preset start time window to determine the actual signal zero point of each radar data channel. The sampling point data before the actual signal zero point is then cut off or zeroed out, and the remaining data is time-shifted and resampled to align the signal zero points of all radar data channels in the time dimension, generating a radar data volume with consistent depth direction.

3. The multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data according to claim 1, characterized in that, The process of generating the ground-penetrating radar data sequence carrying spatial location attributes includes: Parse the location data to obtain the timestamp and latitude / longitude coordinates of each location point; Extract the acquisition timestamp of each radar data channel from the original three-dimensional ground-penetrating radar data; Each radar data channel is matched with multiple neighboring positioning points based on timestamps, and the spatial coordinates of each radar data channel are calculated using an interpolation algorithm. The calculated spatial coordinates are used as attribute information and associated with the corresponding radar data channels to form a geological radar data sequence carrying spatial location attributes.

4. The multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data according to claim 1, characterized in that, The process of constructing the multi-channel vertical profile dataset includes: Using radar data from each detection channel as input, the image width is determined based on the number of channels, and the image height is determined based on the number of sampling points, thus constructing a pixel grid for a two-dimensional image; For each radar data channel, perform single-column pixel mapping, and match the amplitude value sequence of the data channel to the vertical axis coordinate position of the corresponding image column pixel one by one, based on the acquisition order of the amplitude value of the data channel. By using a predetermined color mapping mechanism, the amplitude value of each sampling point is independently converted into the corresponding RGB color value and filled into its mapped pixel position, thereby generating a vertical profile spectrum image of each channel. The color mapping mechanism includes normalizing the amplitude value and applying a pseudo-color or grayscale mapping table.

5. The multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data according to claim 4, characterized in that, The process of constructing the multi-depth horizontal slice map dataset includes: The actual depth corresponding to each sampling point is determined based on the radar wave velocity and sampling frequency parameters. For each target depth, extract the pixel row corresponding to that depth from the vertical profile atlas image of all channels; The extracted pixels in each row are stitched together according to their corresponding channel's physical spatial location to generate a horizontal slice image representing the structural distribution of that depth level.

6. The multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data according to claim 5, characterized in that, The process of establishing the mapping relationship between image pixels and actual physical dimensions includes: The physical length value of the pixel in the detection direction is determined based on the channel spacing. The physical depth value of each pixel in the depth direction of the image is determined based on the sampling frequency, radar wave velocity, and number of sampling points. The physical width value of the pixel in the width direction of the image is determined based on the number of channels and the channel spacing. Based on the determined physical size mapping relationship, corresponding physical scales are generated and added to the vertical profile atlas image and the horizontal slice atlas image.

7. The multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data according to claim 1, characterized in that, The construction of the multi-dimensional collaborative visualization interface includes: Set up a vertical profile display area, a horizontal slice display area, and a video playback area to display the selected vertical profile, a horizontal slice at a specific depth, and a synchronized video frame, respectively. Establish a spatiotemporal linkage mechanism among the three regions, and respond to user interaction operations in any region to synchronously update the displayed content in the other regions; The linkage mechanism specifically achieves the following synchronization: i. Based on the vertical position selected on the vertical profile, the horizontal slice display area is synchronously updated to the slice at the corresponding depth and the video playback area is controlled to jump to the video frame at the corresponding time. ii. Based on the horizontal position selected on the horizontal slice map, synchronously switch the vertical profile display area to the vertical profile passing through that position and control the video playback area to jump to the video frame at the corresponding time. iii. Based on the adjustment of the video playback progress, synchronously update the vertical profile and horizontal slice display areas to the radar image corresponding to the current video frame time and position.

8. The multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data according to claim 1, characterized in that, The geological anomaly identification process includes: Based on a geological radar sample dataset labeled with anomaly types, boundary information and corresponding surface environment features, a multimodal deep learning network is trained to obtain a target recognition model. The multi-channel vertical profile, multi-depth horizontal slice, and synchronous video frames are input into the target recognition model. The model performs fusion feature extraction and analysis to identify potential abnormal targets in the image and outputs the type and confidence level corresponding to each recognition result. The confidence level is determined based on the output probability of the classification layer in the target recognition model, the salience of the abnormal target in the radar image, and its correlation with the surface features in the video frame. Identification results that reach a preset confidence threshold are judged as valid anomalies.

9. The multi-dimensional display method based on intelligent analysis of three-dimensional ground-penetrating radar data according to claim 8, characterized in that, The physical dimension calculation process includes: Based on the boundary information of the abnormal body output by the target recognition model, the boundary of the identified abnormal body is delineated; The number of pixels occupied by the boundary delineation area along the length, width, and depth directions in the vertical cross-sectional view and the horizontal slice view are counted respectively. By combining the pre-established mapping relationship between image pixels and actual physical size, the number of pixels is multiplied by the corresponding physical value per unit pixel to calculate the actual length, actual width, and actual depth of the anomaly.

10. A multi-dimensional display system based on intelligent analysis of three-dimensional ground-penetrating radar data, characterized in that: include: The data acquisition module collects raw 3D ground-penetrating radar data, synchronous video data, and positioning data; The radar data processing module preprocesses the original three-dimensional ground-penetrating radar data, combines it with the positioning data to assign spatial coordinate information, and generates a ground-penetrating radar data sequence carrying spatial location attributes. The video data alignment module performs timestamp alignment processing on the synchronized video data to generate a video frame sequence that is time-synchronized with the ground-penetrating radar data sequence. The image conversion module, based on the ground-penetrating radar data sequence, constructs a multi-channel vertical profile dataset and a multi-depth horizontal slice dataset, and establishes a mapping relationship between image pixels and actual physical dimensions. The multi-dimensional display module constructs a multi-dimensional collaborative visualization interface, which synchronously displays the multi-channel vertical profile, multi-depth horizontal slice, and synchronous video frames in the same view, and supports linkage response based on timestamps and spatial coordinates. The intelligent recognition module performs intelligent fusion analysis on the multi-channel vertical profile, multi-depth horizontal slice, and synchronous video frames to identify geological anomalies and calculate their physical dimensions. The detection output module outputs a detection report containing the physical size and spatial location information of the anomaly, and marks the three-dimensional location of the anomaly in the geospatial platform.

Images