A method and system for calculating the thickness of road surface structural layers based on ground penetrating radar

Abstract

This invention discloses a method and system for calculating pavement structural layer thickness based on ground-penetrating radar (GPR), belonging to the field of road engineering pavement maintenance technology. The method includes: acquiring road radar maps and identifying pavement structural layers using a YOLOv8 model; calculating the structural layer thickness using OpenCV; extracting corresponding electromagnetic data and tracking the maximum amplitude point within the layer range for locations with thickness anomalies, and correcting the thickness value using DBSCAN clustering; importing the thickness results for the entire road section into post-processing software to generate continuous layer surfaces, and statistically analyzing the average thickness data for different length sections. The system executes the above steps. This invention solves the problems of low efficiency in traditional core drilling sampling and high cost of manual radar data processing, realizing automated non-destructive detection and anomaly correction of pavement thickness, and providing accurate data support for maintenance design.

Description

Technical Field

[0001] This invention belongs to the field of road engineering pavement maintenance technology, specifically relating to a method and system for calculating the thickness of pavement structural layers based on ground penetrating radar. Background Technology

[0002] In the field of road pavement maintenance, accurate detection of asphalt structural layer thickness is a core indicator for evaluating construction quality and developing maintenance plans. Currently, the industry mainly employs two types of technical solutions:

[0003] Traditional core sampling method: This method involves physically drilling core samples from the road surface to directly measure the thickness. This method has significant drawbacks:

[0004] The detection efficiency is low, making it difficult to meet the needs of large-scale road inspections;

[0005] The sampling points are not representative enough and cannot reflect the overall thickness distribution of the road section;

[0006] Damaging the integrity of the road surface structure may lead to secondary diseases.

[0007] Ground-penetrating radar (GPR) non-destructive testing technology, as a non-destructive method, has been widely used in road defect diagnosis, structural layer thickness detection, and moisture content determination. However, with the increase in testing mileage, this technology has revealed the following bottlenecks:

[0008] Data processing is highly dependent on manual labor: specialized engineers are needed to interpret radar images, which consumes a lot of human resources;

[0009] The result lacks standardization: the interpretation process is influenced by subjective experience, and the output results of different operators are inconsistent.

[0010] Long-distance detection efficiency is limited: When faced with massive amounts of radar data (such as 320 electromagnetic data points generated in a single detection), manual processing makes it difficult to achieve efficient batch analysis.

[0011] The aforementioned problems mean that existing technologies cannot meet the demands for automation, standardization, and high efficiency in road thickness detection during road maintenance. Summary of the Invention

[0012] This invention provides a method and system for calculating the thickness of road surface structure layers based on ground penetrating radar. It automatically identifies road surface structure layers in radar images using the YOLOv8 algorithm and automatically calculates the thickness using OpenCV, completely replacing the traditional method of manually interpreting radar data. This significantly reduces labor costs and processing time, and is especially suitable for large-scale road inspection projects, thereby effectively solving at least one of the technical problems mentioned in the background art.

[0013] To achieve the above objectives, the technical solution of the present invention is as follows:

[0014] A method for calculating the thickness of road surface structural layers based on ground-penetrating radar includes the following steps:

[0015] Step S1: Obtain the radar map and corresponding electromagnetic data generated by the ground penetrating radar for road detection;

[0016] Step S2: Use the YOLOv8 model to identify the road surface structure layers in the radar map;

[0017] Step S3: Determine the size reference object based on the known thickness in the radar image;

[0018] Step S4: Calculate the pixel size of each structural layer in the radar image using OpenCV, and convert the actual thickness value by combining it with the size reference object.

[0019] Step S5: Perform anomaly handling for abnormal thickness identification locations:

[0020] Step S51: Extract the electromagnetic data corresponding to the abnormal location;

[0021] Step S52: Track the point with the maximum absolute value of the amplitude of a single electromagnetic wave within the stratigraphic depth range;

[0022] Step S53: Perform DBSCAN clustering on the layer locations of the 320 electromagnetic waves;

[0023] Step S54: Calculate the actual thickness at the abnormal locations based on the clustering results;

[0024] Step S6: Integrate all thickness identification results to generate a continuous layer surface.

[0025] Optionally, step S2 may also include:

[0026] Collect road radar detection data to create a thickness recognition dataset;

[0027] The optimal weight model is obtained by training the dataset using the YOLOv8s model.

[0028] Optionally, in step S4, the size reference is the known road surface thickness marked in the radar image.

[0029] Optionally, in step S52:

[0030] The depth range of the stratum is determined by back-calculation of the adjacent normal thickness values ​​at the abnormal location. The calculation formula is as follows:

[0031] Tracking range = [min-20, max+20];

[0032] Where min and max are the number of depth points corresponding to adjacent normal thicknesses, respectively.

[0033] Optionally, step S6 may include the following:

[0034] The average thickness is calculated by dividing the material into segments of a preset length, where the segment lengths include 5m, 10m, 100m, and 1000m.

[0035] Generate thickness variation curves and result files.

[0036] The present invention also provides a system for calculating the thickness of road surface structure layers based on ground penetrating radar, for performing the method described, including:

[0037] The data acquisition module is used to collect radar images and electromagnetic data;

[0038] The layer identification module, equipped with a YOLOv8 model, is used to identify structural layers in radar images.

[0039] The thickness calculation module uses OpenCV to calculate the actual thickness based on a dimensional reference object.

[0040] The exception handling module is configured as follows:

[0041] Extract electromagnetic data from abnormal locations;

[0042] Track the point where the absolute value of electromagnetic wave amplitude is the maximum within the stratigraphic depth range;

[0043] DBSCAN clustering was performed on 320 layer sites and the thickness was calculated;

[0044] The output module integrates thickness data to generate continuous layer surfaces and segmented statistical reports.

[0045] Optionally, the output module is further configured as follows:

[0046] The average thickness was calculated in segments of 5m, 10m, 100m, and 1000m length.

[0047] Output the thickness variation curve and the corresponding result file.

[0048] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method.

[0049] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described.

[0050] The beneficial effects of this invention are as follows:

[0051] 1. This invention automatically identifies road surface structure layers in radar maps using the YOLOv8 algorithm and automatically calculates thickness using OpenCV, completely replacing the traditional method of manually interpreting radar data. This significantly reduces labor costs and processing time, and is especially suitable for large-scale road inspection projects.

[0052] 2. This invention uses ground-penetrating radar non-destructive testing technology to avoid physical damage to the road surface caused by core sampling, while overcoming the defects of poor representativeness and sparse detection points in core sampling, and realizing continuous thickness analysis of the entire road section.

[0053] 3. This invention addresses layer identification anomalies (such as outliers or unidentified layers): by tracking the maximum amplitude point of the electromagnetic signal within the layer range, the boundary of the structural layer is accurately located; combined with the DBSCAN clustering algorithm, outlier correction is performed on 320 data points, effectively eliminating interference and ensuring the stability of the thickness calculation results (the example shows an error of only 0.2%~1.1%).

[0054] 4. This invention imports the identification results into post-processing software to generate a continuous thickness layer surface, which intuitively displays the spatial changes of the pavement structure; it supports multi-scale thickness statistical analysis such as 5m, 10m, 100m, and 1000m, and outputs data files and change curves to accurately guide the formulation of maintenance plans (such as the location of weak road sections).

[0055] 5. In the embodiments of the present invention, the OpenCV calculation results deviate from the actual core measurement values ​​by less than 1.1%, and are highly consistent with the results of radar post-processing software, confirming the reliability and applicability of the method in engineering scenarios. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0057] Figure 1 A flowchart illustrating a method for calculating the thickness of road surface structure layers based on ground-penetrating radar, provided by this invention;

[0058] Figure 2 The radar spectrum provided by this invention;

[0059] Figure 3 This is a schematic diagram of the road surface structure layer division provided by the present invention. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0061] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0062] Furthermore, in this invention, descriptions involving "first," "second," etc., are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0063] In this invention, unless otherwise explicitly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0064] Furthermore, the technical solutions of the various embodiments of the present invention can be combined with each other, but only if they are feasible for those skilled in the art. If the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0065] Please see Figure 1 As shown, this embodiment of the invention provides a method for calculating the thickness of road surface structure layers based on ground-penetrating radar, including the following steps:

[0066] Step S1: Obtain the radar map and corresponding electromagnetic data generated by the ground penetrating radar for road detection;

[0067] Step S2: Use the YOLOv8 model to identify the road surface structure layers in the radar map;

[0068] Step S3: Determine the size reference object based on the known thickness in the radar image;

[0069] Step S4: Calculate the pixel size of each structural layer in the radar image using OpenCV, and convert the actual thickness value by combining it with the size reference object.

[0070] Step S5: Perform anomaly handling for abnormal thickness identification locations:

[0071] Step S51: Extract the electromagnetic data corresponding to the abnormal location;

[0072] Step S52: Track the point with the maximum absolute value of the amplitude of a single electromagnetic wave within the stratigraphic depth range;

[0073] Step S53: Perform DBSCAN clustering on the layer locations of the 320 electromagnetic waves;

[0074] Step S54: Calculate the actual thickness at the abnormal locations based on the clustering results;

[0075] Step S6: Integrate all thickness identification results to generate a continuous layer surface.

[0076] Step S2 also includes:

[0077] Collect road radar detection data to create a thickness recognition dataset;

[0078] The optimal weight model is obtained by training the dataset using the YOLOv8s model.

[0079] In step S4, the size reference is the known road surface thickness marked in the radar map.

[0080] In step S52:

[0081] The depth range of the stratum is determined by back-calculation of the adjacent normal thickness values ​​at the abnormal location. The calculation formula is as follows:

[0082] Tracking range = [min-20, max+20];

[0083] Where min and max are the number of depth points corresponding to adjacent normal thicknesses, respectively.

[0084] Step S6 is followed by:

[0085] The average thickness is calculated by dividing the material into segments of a preset length, where the segment lengths include 5m, 10m, 100m, and 1000m.

[0086] Generate thickness variation curves and result files.

[0087] The present invention also provides a road surface structure layer thickness calculation system based on ground penetrating radar for executing the method described, including a data acquisition module, a layer identification module, a thickness calculation module, and an anomaly handling module.

[0088] The data acquisition module is used to collect radar spectra and electromagnetic data.

[0089] The layer identification module is equipped with a YOLOv8 model to identify structural layers in the radar map.

[0090] The thickness calculation module uses OpenCV to convert the actual thickness based on a size reference.

[0091] The exception handling module is configured as follows:

[0092] Extract electromagnetic data from abnormal locations;

[0093] Track the point where the absolute value of electromagnetic wave amplitude is the maximum within the stratigraphic depth range;

[0094] DBSCAN clustering was performed on 320 layer sites and the thickness was calculated;

[0095] The output module integrates thickness data to generate continuous layer surfaces and segmented statistical reports.

[0096] The output module is further configured as follows:

[0097] The average thickness was calculated in segments of 5m, 10m, 100m, and 1000m length.

[0098] Output the thickness variation curve and the corresponding result file.

[0099] The following detailed description of the method for calculating the thickness of road surface structure layers based on ground penetrating radar provided by the present invention will be based on specific embodiment 1.

[0100] Example 1

[0101] Example 1 provides a method for calculating the thickness of road surface structure layers based on ground penetrating radar, including the following steps:

[0102] Step S1: Obtain the radar map generated by ground-penetrating radar for road detection (see...) Figure 2 (as shown) and the corresponding electromagnetic data;

[0103] Step S2: Use the YOLOv8 model to identify the road surface structure layers in the radar image (see...). Figure 3 (as shown)

[0104] Step S3: Determine the size reference object based on the known thickness in the radar image;

[0105] Step S4: The pixel dimensions of each structural layer in the radar image are calculated using OpenCV, and the actual thickness values ​​are calculated based on a size reference. The structural layer thicknesses from top to bottom are 7.4 in, 14.6 in, and 23.0 in, which translate to 18.79 cm, 37.08 cm, and 58.42 cm, respectively. Post-processing software results are 19 cm, 37 cm, and 59 cm, respectively. Verification was performed using core samples taken on-site. The actual core sample thickness was 19 cm for the surface layer, 37 cm for the upper layer, and 58 cm for the lower layer. The OpenCV-based calculation results deviate from the actual thicknesses of the surface layer, upper layer, and lower layer by 1.1%, 0.2%, and 0.7%, respectively.

[0106] Step S5: Perform anomaly handling for abnormal thickness identification locations:

[0107] Step S51: Extract the electromagnetic data corresponding to the abnormal location;

[0108] Step S52: Track the point with the maximum absolute value of the amplitude of a single electromagnetic wave within the stratigraphic depth range;

[0109] Step S53: Perform DBSCAN clustering on the layer locations of the 320 electromagnetic waves;

[0110] Step S54: Calculate the actual thickness at the abnormal locations based on the clustering results;

[0111] Step S6: Integrate all thickness identification results to generate a continuous layer surface.

[0112] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A method for calculating the thickness of road surface structural layers based on ground-penetrating radar, characterized in that, Includes the following steps: Step S1: Obtain the radar map and corresponding electromagnetic data generated by the ground penetrating radar for road detection; Step S2: Use the YOLOv8 model to identify the road surface structure layers in the radar map; Step S3: Determine the size reference object based on the known thickness in the radar image; Step S4: Calculate the pixel size of each structural layer in the radar image using OpenCV, and convert the actual thickness value by combining it with the size reference object. Step S5: Perform anomaly handling for abnormal thickness identification locations: Step S51: Extract the electromagnetic data corresponding to the abnormal location; Step S52: Track the point with the maximum absolute value of the amplitude of a single electromagnetic wave within the stratigraphic depth range; Step S53: Perform DBSCAN clustering on the layer locations of the 320 electromagnetic waves; Step S54: Calculate the actual thickness at the abnormal locations based on the clustering results; Step S6: Integrate all thickness identification results to generate a continuous layer surface.

2. The method according to claim 1, characterized in that, Step S2 also includes: Collect road radar detection data to create a thickness recognition dataset; The optimal weight model is obtained by training the dataset using the YOLOv8s model.

3. The method according to claim 1, characterized in that, In step S4, the size reference is the known road surface thickness marked in the radar map.

4. The method according to claim 1, characterized in that, In step S52: The depth range of the stratum is determined by back-calculation of the adjacent normal thickness values ​​at the abnormal location. The calculation formula is as follows: Tracking range = [min-20, max+20]; Where min and max are the number of depth points corresponding to adjacent normal thicknesses, respectively.

5. The method according to claim 1, characterized in that, Step S6 is followed by: The average thickness is calculated by dividing the material into segments of a preset length, where the segment lengths include 5m, 10m, 100m, and 1000m. Generate thickness variation curves and result files.

6. A system for calculating the thickness of road surface structure layers based on ground-penetrating radar, used to execute the method as described in any one of claims 1-5, characterized in that, include: The data acquisition module is used to collect radar images and electromagnetic data; The layer identification module, equipped with a YOLOv8 model, is used to identify structural layers in radar images. The thickness calculation module uses OpenCV to calculate the actual thickness based on a dimensional reference object. The exception handling module is configured as follows: Extract electromagnetic data from abnormal locations; Track the point where the absolute value of electromagnetic wave amplitude is the maximum within the stratigraphic depth range; DBSCAN clustering was performed on 320 layer sites and the thickness was calculated; The output module integrates thickness data to generate continuous layer surfaces and segmented statistical reports.

7. The system according to claim 6, characterized in that, The output module is further configured as follows: The average thickness was calculated in segments of 5m, 10m, 100m, and 1000m length. Output the thickness variation curve and the corresponding result file.

Images