Pavement performance evaluation method and system based on joint judgment

Abstract

The invention relates to the technical field of pavement evaluation, and discloses a pavement performance evaluation method and system based on joint judgment, and the method comprises the steps: collecting the multi-section image data of a pavement based on a corresponding collection strategy, generating a base crack image data set, carrying out the independent judgment, and carrying out the joint judgment based on the independent judgment. The system corresponds to the method. According to the method, the collection strategy is selected according to the road surface basic information and the signal quality, and the road surface data more fitting the reality is obtained; the data enhancement technology increases the diversity and reliability of the data, so that the generated base crack image data set is more representative; based on an identification and joint judgment mechanism of a YOLOv5 series model, the identification accuracy of the base layer crack is effectively improved, and misjudgment is reduced; therefore, the accuracy of pavement performance evaluation is comprehensively improved, a scientific basis is provided for road maintenance and repair, the service life of a road is prolonged, and traffic safety is guaranteed.

Description

Technical Field

[0001] This application relates to the technical field of pavement evaluation, and specifically, to a pavement performance evaluation method and system based on joint judgment. Background Technique

[0002] With the acceleration of the urbanization process, the scale of road construction has been continuously expanding, and it has become crucial to accurately and efficiently evaluate pavement performance. By accurately grasping the pavement performance status, potential diseases can be detected in a timely manner, maintenance work can be reasonably arranged, the service life of the road can be extended, and traffic safety can be ensured.

[0003] Currently, pavement performance evaluation technologies mainly rely on manual detection and traditional non-destructive detection technologies. Manual detection has low efficiency, strong subjectivity, and it is difficult to detect hidden diseases inside the pavement. Traditional non-destructive detection technologies, such as ground penetrating radar (GPR), although they can obtain information about the internal structure of the pavement, there are many problems in data processing and disease identification. In existing research, the processing of pavement GPR image data mainly relies on professional personnel to interpret frame by frame, which is not only time-consuming and laborious, but also difficult to guarantee accuracy, restricting the large-scale application of radar technology. At the same time, in the existing deep learning algorithms for GPR image disease identification, affected by factors such as similar echo characteristics of different diseases, non-uniformity of pavement materials, and electromagnetic noise interference, the recognition accuracy is limited.

[0004] Chinese Patent with the application number CN119314021A discloses a research on the automatic recognition of GPR echo characteristics images of semi-rigid base cracks based on deep learning. The selected YOLOv5 series models have weak small target detection capabilities, are prone to false detections, and have insufficient pertinence in feature extraction and fusion. Further, in terms of model deployment, it is only tested on workstations and does not consider the real-time detection requirements of mobile devices. These deficiencies make it difficult for this technology to meet the requirements of accuracy and efficiency in actual pavement performance evaluation and urgently need improvement.

[0005] In summary, there is an urgent need for a new technical solution for pavement performance evaluation based on joint judgment to solve the above technical problems. Summary of the Invention

[0006] The purpose of this application is to provide a pavement performance evaluation method and system based on joint judgment to solve the technical problems proposed in the above background technique.

[0007] To achieve the above purpose, this application discloses the following technical solutions: In the first aspect, this application discloses a pavement performance evaluation method based on joint judgment, and this method includes the following steps: S1: Use 3D ground penetrating radar technology to adopt different acquisition strategies for different road surfaces, and collect multi-profile image data of the road surface based on the corresponding acquisition strategies. Among them, the adoption of the acquisition strategy is selected based on the road surface basic information and the road surface signal quality. The multi-profile image data includes longitudinal section image data and horizontal section image data. S2: Use data enhancement technology, combined with the acquisition strategy, to process the longitudinal section image data and the horizontal section image data to generate a base crack image dataset. Among them, combining the acquisition strategy is to perform enhancement based on data characteristics on the data obtained by processing the longitudinal section image data and the horizontal section image data using data enhancement technology based on the data characteristics corresponding to the acquisition strategy. S3: Use the recognition model pre-constructed based on the YOLOv5 series models to independently judge the base crack image dataset, and perform joint judgment based on the independent judgment. Among them, the independent judgment is to judge the base cracks in the longitudinal section image data or the horizontal section image data.

[0008] It should be noted that in this embodiment, the existing YOLOv5 series models are used to construct the recognition model.

[0009] Preferably, the use of 3D ground penetrating radar technology to adopt different acquisition strategies for different road surfaces includes: The road surface basic information includes the road surface material type and the structural layer thickness. The road surface signal quality includes the signal strength and the signal-to-noise ratio. Different combinations of acquisition parameters are selected as the acquisition strategy based on the road surface material type, the structural layer thickness, the signal strength, and the signal-to-noise ratio. The acquisition parameters include the antenna center frequency, the two-way travel time, the dwell time, and the sampling interval, and the acquisition parameters correspond to the road surface basic information and the road surface signal quality. Among them, when selecting the acquisition strategy, the road surface evaluation is calculated using the road surface evaluation formula, and the corresponding acquisition parameters are matched based on the road surface evaluation. The road surface evaluation formula is: Among them, is the comprehensive change rate of the road surface material type and the structural layer thickness, is the change rate of the signal strength, is the change rate of the signal-to-noise ratio, is the calculated road surface evaluation.

[0010] Preferably, the collection of the multi-profile image data of the road surface based on the corresponding acquisition strategy includes: Calibrate the 3D ground penetrating radar equipment before collection; After setting the acquisition parameters based on the selected acquisition strategy, make the 3D ground penetrating radar travel along the road surface at a constant speed, and synchronously collect the longitudinal section image data and the horizontal section image data. During the acquisition process, a high-precision positioning system is used to record the location information of each acquisition point.

[0011] Preferably, using data augmentation techniques and combining with acquisition strategies to process the longitudinal section image data and horizontal section image data includes: Using data augmentation techniques to process the longitudinal section image data and the horizontal section image data to generate first augmented data, and this processing is carried out based on the following steps: Adopting GPR numerical simulation technology to generate simulated images of subgrade cracks with different depths, sizes and moisture states, and fusing them with the original longitudinal section image data and horizontal section image data; Adjust the gain of the image to enhance the contrast and brightness of the image; Perform a scaling operation on the image to change the size and proportion of the image; Introduce simulated interference signals and add random noise to simulate the interference situations that may be encountered during the actual acquisition process.

[0012] Preferably, using data augmentation techniques and combining with acquisition strategies to process the longitudinal section image data and the horizontal section image data further includes: Processing the first augmented data based on the acquisition strategy to generate second augmented data, and this processing is carried out based on the following steps: When the data feature corresponding to the acquisition strategy is that the resolution of the image data does not meet the preset resolution threshold, perform super-resolution reconstruction processing on the first augmented data; When the data feature corresponding to the acquisition strategy is that the noise of the image data does not meet the preset noise threshold, perform noise reduction processing on the first augmented data; When the data feature corresponding to the acquisition strategy is that the feature distribution of the image data does not meet the preset feature distribution threshold, perform histogram equalization on the first augmented data to adjust the feature distribution of the image.

[0013] Preferably, generating the subgrade crack image dataset includes: Sort and annotate the second augmented data, and this annotation is to annotate the location, size and category of the subgrade cracks in the image; Divide the annotated image data into a training set, a validation set and a test set based on a preset ratio; where: the training set is used to train the recognition model, the validation set is used to evaluate the recognition model and adjust the hyperparameters during the training process, and the test set is used to finally evaluate the accuracy and generalization ability of the recognition model.

[0014] Preferably, using the recognition model pre-constructed based on the YOLOv5 series models to make an independent judgment on the subgrade crack image dataset includes: Use the recognition model to independently judge the longitudinal section image data in the base crack image dataset, and this independent judgment is carried out based on the following steps: Input the longitudinal section image data into the recognition model; Preprocess the longitudinal section image data, adjust the image size and maintain the original aspect ratio; Use a multi-layer convolutional neural network to extract multi-dimensional features of the base cracks in the image; Based on bounding box regression, class prediction, and confidence prediction, determine the location, size, and class of the base cracks in the image; Adopt non-maximum suppression processing to remove overlapping prediction boxes and output the results of independent judgment.

[0015] Preferably, when using the recognition model pre-constructed based on the YOLOv5 series model to independently judge the base crack image dataset, it further includes: Use the recognition model to independently judge the horizontal section image data in the base crack image dataset, and this independent judgment is carried out based on the following steps: Input the horizontal section image data into the recognition model; Preprocess the horizontal section image data, adjust the image size and maintain the original aspect ratio; Use a multi-layer convolutional neural network to extract multi-dimensional features of the base cracks in the image; Based on bounding box regression, class prediction, and confidence prediction, determine the location, size, and class of the base cracks in the image; Adopt non-maximum suppression processing to remove overlapping prediction boxes and output the results of independent judgment.

[0016] Preferably, the joint judgment based on the independent judgment includes: Compare the independent judgment results of the longitudinal section image data and the horizontal section image data; When the crack echo features at the same position are determined to be base cracks in both the recognition results of the longitudinal section image data and the horizontal section image data, it is determined that there are base cracks at this position; When it is determined to be a base crack only in the recognition result of the image data of a certain section, the image data at this position needs to be manually rechecked; Based on the results of the joint judgment, comprehensively evaluate the pavement performance and determine the type, location, and severity of the pavement diseases.

[0017] In a second aspect, the present application discloses a pavement performance evaluation system based on joint judgment. This system is applicable to the pavement performance evaluation method based on joint judgment as described above, and this system includes: The dynamic acquisition module is used to adopt different acquisition strategies for different road surfaces by using three-dimensional ground penetrating radar technology, and collect multi-profile image data of the road surface based on the corresponding acquisition strategies. Among them, the adoption of the acquisition strategy is selected based on the road surface basic information and road surface signal quality, and the multi-profile image data includes longitudinal section image data and horizontal section image data; The image enhancement module is used to use data enhancement technology and combine the acquisition strategy to process the longitudinal section image data and the horizontal section image data to generate a base crack image data set. Among them, combining the acquisition strategy is to perform enhancement based on data characteristics on the data after processing the longitudinal section image data and the horizontal section image data by using the data enhancement technology, based on the data characteristics corresponding to the acquisition strategy; The joint judgment module is used to independently judge the base crack image data set by using the recognition model pre-constructed based on the YOLOv5 series models, and perform joint judgment based on the independent judgment. Among them, the independent judgment is to judge the base cracks in the longitudinal section image data or the horizontal section image data.

[0018] Beneficial effects: The road surface performance evaluation method and system based on joint judgment of the present application obtain more practical road surface data by selecting the acquisition strategy according to the road surface basic information and signal quality; the data enhancement technology increases the diversity and reliability of the data, making the generated base crack image data set more representative; and the recognition and joint judgment mechanism based on the YOLOv5 series models effectively improves the recognition accuracy of base cracks and reduces misjudgment; thus comprehensively improving the accuracy of road surface performance evaluation, providing a scientific basis for road maintenance and repair, extending the service life of the road, and ensuring traffic safety. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a flowchart of the road surface performance evaluation method based on joint judgment provided by the embodiment of the present application; Figure 2 It is a structural block diagram of the road surface performance evaluation system based on joint judgment provided by the embodiment of the present application. Detailed Embodiments

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0022] In this article, the term "including" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or device. Without more limitations, the elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article or device including the said elements.

[0023] The first aspect of this embodiment discloses a pavement performance evaluation method based on joint judgment as Figure 1 shown, and this method includes the following steps: S1: Using three-dimensional ground penetrating radar technology, different acquisition strategies are adopted for different road surfaces, and multi-profile image data of the road surface is acquired based on the corresponding acquisition strategies; among them, the adoption of the acquisition strategy is selected based on the road surface basic information and the road surface signal quality, and the multi-profile image data includes longitudinal section image data and horizontal section image data; S2: Using data enhancement technology, combined with the acquisition strategy, to process the longitudinal section image data and the horizontal section image data to generate a base crack image data set; among them, combining the acquisition strategy is to perform enhancement based on data characteristics on the data obtained by processing the longitudinal section image data and the horizontal section image data using the data enhancement technology according to the data characteristics corresponding to the acquisition strategy; S3: Using an identification model pre-constructed based on the YOLOv5 series of models to independently judge the base crack image data set, and perform joint judgment based on the independent judgment; among them, the independent judgment is to judge the base cracks for the longitudinal section image data or the horizontal section image data.

[0024] Through the above, in this embodiment, the three-dimensional ground penetrating radar technology is used to formulate different acquisition strategies for different road surfaces, combined with data enhancement technology to process the collected multi-profile image data, and an independent judgment and joint judgment are carried out with the help of an identification model pre-constructed based on the YOLOv5 series of models, realizing a more accurate and efficient evaluation of the road surface performance. Among them, by selecting the acquisition strategy according to the road surface basic information and signal quality, road surface data that is more in line with the actual situation is obtained. The data enhancement technology increases the diversity and reliability of the data, making the generated base crack image data set more representative. The identification and joint judgment mechanism based on the YOLOv5 series of models effectively improves the identification accuracy of base cracks and reduces misjudgment. Combining these technical means comprehensively improves the accuracy of road surface performance evaluation, provides a scientific basis for road maintenance and repair, extends the service life of the road, and ensures traffic safety.

[0025] Specifically, the three-dimensional ground penetrating radar technology is used to adopt different acquisition strategies for different road surfaces, including: The road surface basic information includes the road surface material type and the structural layer thickness, and the road surface signal quality includes the signal strength and the signal-to-noise ratio. Different acquisition parameter combinations are selected as the acquisition strategy based on the road surface material type, the structural layer thickness, the signal strength, and the signal-to-noise ratio. The acquisition parameters include the antenna center frequency, the two-way travel time, the dwell time, and the sampling interval, and the acquisition parameters correspond to the road surface basic information and the road surface signal quality; among them, when selecting the acquisition strategy, the road surface evaluation is calculated using the road surface evaluation formula, and the corresponding acquisition parameters are matched based on the road surface evaluation. The road surface evaluation formula is: Among them, is the comprehensive change rate of the road surface material type and the structural layer thickness, is the change rate of the signal strength, is the change rate of the signal-to-noise ratio, is the calculated road surface evaluation.

[0026] It can be understood that in practical applications, the change of acquisition parameters occurs when the road surface changes. Therefore, the analysis of road surface changes is more valuable than directly analyzing the road surface. The road surface material type and the structural layer thickness are the inherent properties of the road surface, and their changes will affect signal propagation. In this implementation, the comprehensive change rate is obtained by weighted summation of the change rate of the road surface material type and the change rate of the structural layer thickness. The change rate of the road surface material type is the change of the road surface material with respect to time, and the corresponding data can be obtained by any one of the existing technologies. The change rate of the structural layer thickness is the change of the structural layer thickness with respect to time, and the corresponding data can be obtained by any one of the existing technologies. The signal strength and the signal-to-noise ratio directly reflect the quality of the acquired signal and are related to the accurate judgment of the road surface condition. These factors jointly determine the road surface evaluation. Further, based on weight allocation and fusion, the changes in different road surface evaluations brought about by different changes are highlighted. Specifically: It shows that when the comprehensive change rate of the road surface material type and the structural layer thickness is small, the weight of the signal strength change rate in the road surface evaluation is relatively large. Because at this time, the road surface structure is relatively stable, and the signal strength is more critical for the evaluation. Complementary to the previous part, when the comprehensive change rate of the road surface material type and the structural layer thickness is large, it can reflect the combined effect of these two factors and the signal strength change rate on the road surface evaluation. And Added separately as an item to the formula, it shows that the signal-to-noise ratio change rate plays an independent and important role in the road surface evaluation, and its change will directly affect the final road surface evaluation result. Based on this design, the finally obtained road surface evaluation can comprehensively reflect the overall situation of the road surface basic information and the signal quality. When the change rates of each factor are in different states, the road surface evaluation will change accordingly. Furthermore, the appropriate acquisition parameters can be matched according to this value, providing a basis for the data acquisition of subsequent road surface performance evaluation.

[0027] Through the above, this embodiment selects different combinations of acquisition parameters as acquisition strategies by using multiple factors such as pavement material type, structural layer thickness, signal strength, and signal-to-noise ratio, achieving the refinement of the acquisition strategy. In practical applications, since the pavement materials and the thicknesses of the structural layers are different, the electromagnetic wave propagation characteristics are different. By selecting appropriate parameters such as the antenna center frequency, the acquired signals can be clearer and more accurate. The signal strength and signal-to-noise ratio reflect the quality of the acquisition environment. Based on these, the parameters are adjusted to improve the data quality. In a simple example, for a pavement with uniform pavement materials, a relatively thin structural layer, and good signal quality, a higher antenna center frequency, a shorter two-way travel time, a shorter dwell time, and a smaller sampling interval are selected; for a pavement with complex pavement materials, a relatively thick structural layer, and poor signal quality, a lower antenna center frequency, a longer two-way travel time, a longer dwell time, and a larger sampling interval are selected. This acquisition strategy customized according to multiple factors effectively improves the quality and accuracy of the acquired data, provides a reliable data basis for subsequent pavement performance evaluation, and enhances the credibility of the evaluation results.

[0028] Specifically, collecting multi-profile image data of the pavement based on the corresponding acquisition strategy includes: Calibrating the three-dimensional ground penetrating radar equipment before acquisition; After setting the acquisition parameters based on the selected acquisition strategy, making the three-dimensional ground penetrating radar travel along the pavement at a constant speed, and synchronously collecting longitudinal section image data and horizontal section image data; During the acquisition process, using a high-precision positioning system to record the position information of each acquisition point.

[0029] Through the above, this embodiment uses GPR numerical simulation technology to fuse images, gain adjustment, scaling operations, and introduce interference signals and noise, achieving the preliminary enhancement of data. GPR numerical simulation generates images of base layer cracks in different states and fuses them with the original data, enriching the data samples and increasing the diversity of crack features. Gain adjustment highlights the crack details in the image, facilitating subsequent identification. The scaling operation simulates the image effects at different detection distances and angles, improving the adaptability of the model to cracks of different scales. Introducing interference and noise simulates the actual detection environment and enhances the anti-interference ability of the model. Thus, the stability of crack identification in a complex electromagnetic environment is improved, the practicality of the data and the reliability of model training are enhanced, and it helps to improve the accuracy of pavement performance evaluation.

[0030] Specifically, using data enhancement technology and combining with the acquisition strategy to process the longitudinal section image data and the horizontal section image data further includes: Processing the first enhanced data based on the acquisition strategy to generate the second enhanced data, and this processing is carried out based on the following steps: When the data feature corresponding to the acquisition strategy is that the resolution of the image data does not meet the preset resolution threshold, perform super-resolution reconstruction processing on the first enhanced data; When the data feature corresponding to the acquisition strategy is that the noise of the image data does not meet the preset noise threshold, perform noise reduction processing on the first enhanced data; When the data feature corresponding to the acquisition strategy is that the feature distribution of the image data does not meet the preset feature distribution threshold, perform histogram equalization on the first enhanced data to adjust the feature distribution of the image.

[0031] Through the above, in this embodiment, according to the data feature corresponding to the acquisition strategy, super-resolution reconstruction, noise reduction processing, and histogram equalization are performed on the first enhanced data, realizing secondary enhancement of the data. In this embodiment, super-resolution reconstruction, noise reduction processing, and histogram equalization are all any one of the existing technologies. Based on super-resolution reconstruction, when the image resolution is insufficient, super-resolution reconstruction improves the image clarity, making the crack details more clearly distinguishable, which helps the model accurately identify the crack features. Facing the noise problem, noise reduction processing removes the interference signal and improves the image quality, avoiding the influence of noise on crack identification. Histogram equalization adjusts the feature distribution, making the overall contrast of the image more reasonable and enhancing the distinction between the crack and the background. For example, for an image with uneven feature distribution caused by acquisition parameters, after processing, the model is more likely to identify the crack. These operations further optimize the data, improve the quality of the grass-roots crack image dataset, and enhance the accuracy of pavement performance evaluation.

[0032] Specifically, generating a grass-roots crack image dataset includes: Sort and label the second enhanced data, and the label is to label the position, size, and category of the grass-roots cracks in the image; Based on a preset ratio, divide the labeled image data into a training set, a validation set, and a test set; where: the training set is used to train the recognition model, the validation set is used to evaluate the recognition model and adjust the hyperparameters during the training process, and the test set is used to finally evaluate the accuracy and generalization ability of the recognition model.

[0033] Through the above, in this embodiment, by sorting and annotating the second enhanced data and dividing it into a training set, a validation set, and a test set according to a preset ratio, the standardized management of the subgrade crack image dataset is achieved. In a simple example, the preset ratio is 7:1:2. The position, size, and category of the subgrade cracks in the image provide clear learning objectives for model training, enabling the model to learn the characteristics and laws of the cracks. By reasonably dividing the dataset, the training set is used for model learning, the validation set is used to adjust hyperparameters to prevent overfitting, and the test set is used to evaluate the model performance, ensuring that the model is effectively trained and evaluated at different stages. For example, during the training process, the model is continuously optimized through the validation set, making the model perform better on the test set. This standardized management improves the efficiency and accuracy of model training and lays a foundation for accurately evaluating the pavement performance.

[0034] Specifically, using the recognition model pre-constructed based on the YOLOv5 series of models to independently judge the subgrade crack image dataset, including: Using the recognition model to independently judge the longitudinal section image data in the subgrade crack image dataset, and this independent judgment is carried out based on the following steps: Input the longitudinal section image data into the recognition model; Preprocess the longitudinal section image data, adjust the image size and maintain the original aspect ratio; Use a multi-layer convolutional neural network to extract multi-dimensional features of the subgrade cracks in the image; Based on bounding box regression, class prediction, and confidence prediction, determine the position, size, and category of the subgrade cracks in the image; Adopt non-maximum suppression processing to remove overlapping prediction boxes and output the results of independent judgment.

[0035] Specifically, using the recognition model pre-constructed based on the YOLOv5 series of models to independently judge the subgrade crack image dataset, also includes: Using the recognition model to independently judge the horizontal section image data in the subgrade crack image dataset, and this independent judgment is carried out based on the following steps: Input the horizontal section image data into the recognition model; Preprocess the horizontal section image data, adjust the image size and maintain the original aspect ratio; Use a multi-layer convolutional neural network to extract multi-dimensional features of the subgrade cracks in the image; Based on bounding box regression, class prediction, and confidence prediction, determine the position, size, and category of the subgrade cracks in the image; Adopt non-maximum suppression processing to remove overlapping prediction boxes and output the results of independent judgment.

[0036] Through the above, this embodiment uses an identification model to input, preprocess, extract features, predict, and perform non-maximum suppression processing on the longitudinal section image data and the horizontal section image data, achieving accurate identification of the base layer cracks in the longitudinal section and the horizontal section.

[0037] Specifically, a combined judgment is performed based on independent judgments, including: Comparing the independent judgment results of the longitudinal section image data and the horizontal section image data; When the crack echo features at the same position are determined to be base layer cracks in the identification results of both the longitudinal section image data and the horizontal section image data, it is determined that there is a base layer crack at that position; When it is determined to be a base layer crack only in the identification result of the image data of a certain section, the image data at that position needs to be manually rechecked; Based on the result of the combined judgment, a comprehensive evaluation of the pavement performance is carried out to determine the type, location, and severity of the pavement diseases.

[0038] Through the above, this embodiment compares the independent judgment results of the longitudinal section and the horizontal section image data, performs a combined judgment and a pavement performance evaluation based on the judgment results, and achieves a more accurate pavement disease assessment. Determining the type, location, and severity of the pavement diseases based on the result of the combined judgment can comprehensively evaluate the pavement performance. For example, judging the severity of the disease according to the characteristics such as the width and length of the cracks, providing accurate information for road maintenance, guiding the reasonable arrangement of maintenance work, improving the pertinence and effectiveness of road maintenance, and ensuring the safe use of the road.

[0039] In the second aspect of this embodiment, there is disclosed a Figure 2 pavement performance evaluation system based on combined judgment as shown. This system is applicable to the pavement performance evaluation method based on combined judgment as described above. The system includes: A dynamic acquisition module, which is used to use three-dimensional ground penetrating radar technology to adopt different acquisition strategies for different pavements, and acquire multi-section image data of the pavement based on the corresponding acquisition strategies; among them, the adoption of the acquisition strategy is selected based on the pavement basic information and the pavement signal quality, and the multi-section image data includes longitudinal section image data and horizontal section image data; An image enhancement module, which is used to use data enhancement technology and combine the acquisition strategy to process the longitudinal section image data and the horizontal section image data to generate a base layer crack image dataset; among them, combining the acquisition strategy is to perform enhancement based on the data characteristics on the data obtained by processing the longitudinal section image data and the horizontal section image data based on the data enhancement technology according to the data characteristics corresponding to the acquisition strategy; The joint judgment module is used to independently judge the dataset of base course crack images by using the recognition model pre-built based on the YOLOv5 series models, and perform joint judgment based on the independent judgment; wherein, the independent judgment is to judge the base course cracks for the longitudinal section image data or the horizontal section image data.

[0040] It should be noted that the pavement performance evaluation system based on joint judgment in this embodiment corresponds to the aforementioned pavement performance evaluation method based on joint judgment. Therefore, the content not specifically described in the pavement performance evaluation system based on joint judgment in this embodiment, such as, but not limited to, function definition, working principle, and technical effect, etc., can refer to the description of the aforementioned pavement performance evaluation method based on joint judgment, and will not be elaborated herein.

[0041] In a specific application, the YOLOv5 model is selected as the YOLOv5x model. The overall precision rate P, recall rate R, and mAP@0.5 value of using the YOLOv5x model to detect the echo features of base course cracks (the longitudinal section base course crack echo feature Crack-V and the horizontal section base course crack echo feature Crack-H) are 0.808, 0.876, and 87.5% respectively, all not exceeding 88%, and the overall detection accuracy is not high; the AP@0.5 values of the YOLOv5x model for separately detecting Crack-V and Crack-H are 82.6% and 92.4% respectively. The detection accuracy of the longitudinal section base course crack echo feature Crack-V in the GPR is relatively high, which is 9.8% higher than Crack-H in the horizontal section GPR map. Based on the above data, it shows that the echo features of some base course cracks cannot be simultaneously recognized in both the longitudinal section and horizontal section GPR images. It is necessary to jointly determine the recognition results of the base course crack echo features (Crack-V and Crack-H) in the horizontal section and longitudinal section GPR images. If the echo features of the same crack can be recognized in both the longitudinal section and horizontal section GPR maps, it is determined that there must be a base course crack at that position and no recheck is required; if the echo features of the same crack can only be recognized in the GPR map of a certain section (longitudinal section or horizontal section), manual recheck is required to determine the base course crack. After the above joint determination, the precision rate P, recall rate R, and mAP@0.5 value of the recognition of the base course crack echo features (Crack-V and Crack-H) in the test set GPR images are 0.896, 0.914, and 93.1% respectively, which are increased by 0.088, 0.038, and 5.6% respectively compared with the previous ones, indicating that this joint determination method can effectively achieve the accurate recognition of the base course crack echo features in the GPR images.

[0042] In summary, the pavement performance evaluation method and system based on joint judgment in this embodiment obtain more practical pavement data by selecting acquisition strategies according to pavement basic information and signal quality; the data enhancement technology increases the diversity and reliability of the data, making the generated base crack image dataset more representative; and the recognition and joint judgment mechanism based on the YOLOv5 series models effectively improves the recognition accuracy of base cracks and reduces misjudgment; thereby comprehensively improving the accuracy of pavement performance evaluation, providing a scientific basis for road maintenance and repair, extending the service life of the road, and ensuring traffic safety.

[0043] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, or other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be completed by a computer program instructing the relevant hardware. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transfer of a computer program from one place to another. The storage media can be any available medium that can be accessed by a computer. The computer-readable storage medium can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0044] Finally, it should be noted that the above are only the preferred embodiments of the present application and are not used to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A road performance evaluation method based on joint judgment, characterized in that: The method comprises the following steps: S1: using 3D ground penetrating radar technology to adopt different acquisition strategies for different road surfaces, and to acquire multi-section image data of the road surface based on the corresponding acquisition strategies; wherein the acquisition strategy is selected based on the basic information of the road surface and the road surface signal quality, and the multi-section image data includes longitudinal section image data and horizontal section image data; S2: Using data enhancement technology and combining with acquisition strategy, processing longitudinal section image data and horizontal section image data, generating a base crack image data set; wherein combining with acquisition strategy is based on the data features corresponding to the acquisition strategy, the longitudinal section image data and horizontal section image data processed by data enhancement technology are enhanced based on data features; S3: Use the recognition model pre-built based on the YOLOv5 series model to make independent judgments on the base crack image dataset, and make joint judgments based on the independent judgments; wherein the independent judgment is to make base crack judgments on the longitudinal section image data or the horizontal section image data.

2. The pavement performance evaluation method based on joint judgment according to claim 1 is characterized in that: The three-dimensional ground penetrating radar technology adopts different acquisition strategies for different road surfaces, including: The basic road surface information includes the road surface material type and the thickness of the structural layer, and the road surface signal quality includes the signal strength and the signal-to-noise ratio. Different acquisition parameter combinations are selected as acquisition strategies based on the road surface material type, the structural layer thickness, the signal strength and the signal-to-noise ratio. The acquisition parameters include the antenna center frequency, the two-way travel time, the dwell time and the sampling interval, and the acquisition parameters correspond to the basic road surface information and the road surface signal quality. When selecting the acquisition strategy, the road surface evaluation formula is used to calculate the road surface evaluation, and the corresponding acquisition parameters are matched based on the road surface evaluation. The road surface evaluation formula is: in, is the comprehensive change rate of pavement material type and structural layer thickness, is the rate of change of signal strength, is the rate of change of the signal-to-noise ratio, The calculated pavement evaluation.

3. The pavement performance evaluation method based on joint judgment according to claim 2 is characterized in that: The collecting of multi-section image data of the road surface based on the corresponding collection strategy includes: Calibrate the 3D GPR equipment before acquisition; After setting the acquisition parameters based on the selected acquisition strategy, the 3D ground penetrating radar is driven along the road surface at a uniform speed to synchronously acquire longitudinal section image data and horizontal section image data; During the collection process, a high-precision positioning system is used to record the location information of each collection point.

4. The pavement performance evaluation method based on joint judgment according to claim 1 is characterized in that: The method of using data enhancement technology in combination with acquisition strategies to process longitudinal section image data and horizontal section image data includes: The longitudinal section image data and the horizontal section image data are processed by using a data enhancement technique to generate first enhanced data, and the processing is performed based on the following steps: GPR numerical simulation technology is used to generate simulated images of base cracks of different depths, sizes and moisture conditions, and then merged with the original longitudinal section image data and horizontal section image data; Adjust the image gain to enhance the image contrast and brightness; Scaling the image to change its size and proportion; Simulated interference signals and random noise are introduced to simulate the interference conditions that may be encountered during the actual acquisition process.

5. The pavement performance evaluation method based on joint judgment according to claim 4 is characterized in that: The method of processing the longitudinal image data and the horizontal slice image data by using the data enhancement technology in combination with the acquisition strategy also includes: The first enhanced data is processed based on the acquisition strategy to generate second enhanced data, and the processing is performed based on the following steps: When the data feature corresponding to the acquisition strategy is that the resolution of the image data does not meet a preset resolution threshold, performing super-resolution reconstruction processing on the first enhanced data; When the data feature corresponding to the acquisition strategy is that the noise of the image data does not meet a preset noise threshold, performing noise reduction processing on the first enhanced data; When the data feature corresponding to the acquisition strategy is that the feature distribution of the image data does not meet a preset feature distribution threshold, histogram equalization is performed on the first enhanced data to adjust the feature distribution of the image.

6. The pavement performance evaluation method based on joint judgment according to claim 5 is characterized in that: The step of generating a base layer crack image dataset comprises: Arranging and marking the second enhanced data, wherein the marking is to mark the location, size and category of the base crack in the image; The labeled image data is divided into a training set, a validation set and a test set based on a preset ratio; wherein: the training set is used to train the recognition model, the validation set is used to evaluate the recognition model and adjust hyperparameters during the training process, and the test set is used to finally evaluate the accuracy and generalization ability of the recognition model.

7. The pavement performance evaluation method based on joint judgment according to claim 1 is characterized in that: The method of independently judging the base crack image dataset by using the recognition model pre-built based on the YOLOv5 series model includes: The recognition model is used to independently judge the longitudinal section image data in the base crack image data set, and the independent judgment is performed based on the following steps: Inputting longitudinal section image data into the recognition model; Preprocessing the longitudinal section image data, adjusting the image size and maintaining the original aspect ratio; A multi-layer convolutional neural network is used to extract the multi-dimensional features of the base cracks in the image; Determine the location, size and category of the base layer cracks in the image based on bounding box regression, category prediction and confidence prediction; Non-maximum suppression processing is used to remove overlapping prediction boxes and output independent judgment results.

8. The pavement performance evaluation method based on joint judgment according to claim 7 is characterized in that: The method of independently judging the base crack image dataset using a recognition model pre-built based on the YOLOv5 series model also includes: The recognition model is used to independently judge the horizontal section image data in the base crack image data set, and the independent judgment is performed based on the following steps: Inputting horizontal section image data into the recognition model; Preprocessing the horizontal slice image data, adjusting the image size and maintaining the original aspect ratio; A multi-layer convolutional neural network is used to extract the multi-dimensional features of the base cracks in the image; Determine the location, size and category of the base layer cracks in the image based on bounding box regression, category prediction and confidence prediction; Non-maximum suppression processing is used to remove overlapping prediction boxes and output independent judgment results.

9. The pavement performance evaluation method based on joint judgment according to claim 8, characterized in that: As stated above and based on independent judgment, joint judgment is made, including: Compare the independent judgment results of longitudinal section image data and horizontal section image data; When the crack echo characteristics at the same position are determined to be base cracks in the identification results of the longitudinal section image data and the horizontal section image data, it is determined that there are base cracks at the position; If only one section of the image data is identified as a base crack, the image data at that location needs to be manually reviewed; Based on the results of the joint judgment, the pavement performance is comprehensively evaluated to determine the type, location and severity of pavement defects.

10. A road performance evaluation system based on joint judgment, the system being applicable to the road performance evaluation method based on joint judgment as claimed in any one of claims 1 to 9, characterized in that: The system includes: A dynamic acquisition module, which is used to adopt different acquisition strategies for different road surfaces using three-dimensional ground penetrating radar technology, and to acquire multi-section image data of the road surface based on the corresponding acquisition strategies; wherein the acquisition strategy is selected based on the basic information of the road surface and the signal quality of the road surface, and the multi-section image data includes longitudinal section image data and horizontal section image data; The image enhancement module is used to utilize data enhancement technology and combine with acquisition strategy to process longitudinal section image data and horizontal section image data to generate a base crack image data set; wherein, combining with acquisition strategy is based on the data features corresponding to the acquisition strategy, and the longitudinal section image data and horizontal section image data are processed based on the data enhancement technology, and then enhanced based on the data features; The joint judgment module is used to make independent judgments on the base crack image data set using a recognition model pre-built based on the YOLOv5 series model, and to make joint judgments based on the independent judgments; wherein the independent judgment is to make base crack judgments on the longitudinal section image data or the horizontal section image data.

Images