A traffic engineering pavement quality detection method

Abstract

The application provides a traffic engineering pavement quality detection method, and relates to the field of traffic engineering.The traffic engineering pavement quality detection method comprises the following steps: collecting pavement image data, collecting pavement images and surface height data through a high-definition camera and a laser scanner installed on a special detection vehicle, and constructing a three-dimensional model of pavement flatness to ensure the detection accuracy of surface micro-unevenness; processing image data and height data, performing denoising, segmentation and feature extraction processing on the collected pavement image data through image processing software, identifying the defects of cracks and potholes of the pavement, and using the height data collected by the laser scanner to calculate the pavement flatness, and evaluating the area and degree of pavement surface unevenness through an algorithm.Through the collaborative work of intelligent sensors and a data processing system, the automation level of pavement quality detection is greatly improved, the demand for manual intervention is reduced, and the work efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of traffic engineering technology, specifically to a method for detecting the quality of road surfaces in traffic engineering. Background Technology

[0002] With the continuous development of transportation and the advancement of urbanization, roads, as one of the important infrastructures, bear a large number of transportation tasks. The safety, comfort, and durability of roads directly affect traffic flow and the safety of drivers and passengers. However, as the service life of roads increases and the traffic load intensifies, road surface quality gradually deteriorates, and road surface defects such as cracks, ruts, and potholes occur frequently. These problems not only affect driving safety but may also cause traffic accidents. Therefore, how to effectively and accurately monitor and assess road surface conditions has become an urgent problem for traffic management departments to solve.

[0003] Traditional road surface inspection methods rely heavily on manual inspections and periodic testing of vehicle-mounted equipment. While these methods can detect road surface defects to some extent, they suffer from drawbacks such as significant human error, incomplete data, and low inspection efficiency. Manual inspections are not only time-consuming and labor-intensive but also prone to overlooking minor road surface issues. Furthermore, with the continuous expansion of road scale, the workload of traditional inspection methods is also showing a sharp upward trend, further exacerbating the difficulties of inspection and maintenance. Therefore, those skilled in the art provide a road surface quality inspection method for traffic engineering to solve the problems mentioned in the background art. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] To address the shortcomings of existing technologies, this invention provides a method for detecting the quality of road surfaces in traffic engineering, which solves the problems of errors, incomplete data, and low inspection efficiency in traditional road surface detection methods.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for detecting the quality of road surface in traffic engineering, comprising:

[0008] Road surface image data is collected using a high-definition camera and laser scanner mounted on a dedicated inspection vehicle. This data includes road surface images and surface height data, which are then used to construct a three-dimensional model of the road surface smoothness. The laser scanner should have an accuracy of no less than millimeters to ensure the accuracy of detecting minute surface irregularities.

[0009] Image and height data are processed. Image processing software is used to denoise, segment, and extract features from the collected road surface image data to identify defects such as cracks and potholes in the road surface. The height data collected by the laser scanner is used to calculate the road surface smoothness and to evaluate the area and degree of unevenness on the road surface through algorithms.

[0010] Friction coefficient measurement uses an on-board sensor system to measure the friction coefficient of the road surface in real time during vehicle operation. By having the sensor contact the road surface, the system detects changes in friction force in real time and calculates the friction coefficient to determine whether the road surface friction performance meets the standard requirements.

[0011] In the compressive strength analysis, intelligent vehicle-mounted pressure sensors and stress sensors are used during the testing process. By applying a certain pressure to the road surface and recording the response, the compressive strength of the road surface is analyzed. The data is transmitted to the data processing system in real time, and a calculation model is used to evaluate the compressive capacity of the road surface, predict its service life and whether there is structural damage.

[0012] Comprehensive evaluation and feedback involves a comprehensive analysis of the collected data, using machine learning algorithms or data mining techniques to assess the overall quality of the road surface, generating an evaluation report, and providing real-time feedback on the test results. The report includes the pass / fail status of the road surface's smoothness, coefficient of friction, and compressive strength, and provides detailed defect areas and improvement suggestions.

[0013] Preferably, the acquisition of road surface image data includes the following steps:

[0014] S1. High-definition camera: The high-definition camera installed on the inspection vehicle takes pictures from multiple angles. The camera resolution is no less than 8K to ensure that it can capture the fine cracks, potholes and ruts on the road surface. By adjusting the camera's focal length and viewing angle, road image information at different scales can be obtained.

[0015] S2. Laser Scanner: The laser scanner acquires height information of various points on the road surface during vehicle movement by emitting and receiving laser beams. It calculates the distance to each point by emitting laser beams and receiving the reflected signals of the laser beams, and generates a high-precision three-dimensional model of the road surface.

[0016] S3. Data synchronization: The high-definition camera and laser scanner need to achieve synchronized data acquisition. A GPS module and inertial measurement unit are used to time-stamp the acquired data to ensure that the data from different sensors can be accurately matched, providing a basis for subsequent processing.

[0017] S4. Data storage: All acquired image data and laser scanning data are transmitted to the vehicle computing platform in real time and stored. When the data volume is large, the capacity of the storage device and the data compression and encryption technology need to be considered.

[0018] Preferably, the processing of image data and height data includes the following steps:

[0019] S1. Image Denoising: Since the environment may affect image quality, image denoising algorithms are needed to remove noise from the image to ensure image clarity. The calculation formula is as follows:

[0020]

[0021] Where x is the distance from the center point; σ is the standard deviation, which controls the width of the Gaussian curve. The larger σ is, the wider the Gaussian curve and the stronger the smoothing effect.

[0022] S2. Image segmentation and feature extraction: Computer vision techniques are used to segment the image and identify defects such as cracks, potholes, ruts, and spalling. For crack detection, an edge detection algorithm is used to detect the edges of the cracks. The calculation formula is as follows:

[0023]

[0024] For potholes and ruts, a region growing algorithm is used to identify regions with uneven depth;

[0025] S3. Road surface smoothness calculation: The road surface model is constructed using the height data obtained by the laser scanner. The data of each laser point is converted into three-dimensional coordinates using a three-dimensional reconstruction algorithm to generate a road surface height map. By calculating the local elevation differences of the road surface, the smoothness standard is evaluated.

[0026] S4. Defect identification and classification: Combining machine learning algorithms, the detected defects are classified, and a deep learning model is trained using labeled data to improve the accuracy and automation of defect detection.

[0027] Preferably, the friction coefficient measurement includes the following steps:

[0028] S1. Friction system sensor: Vehicle friction coefficient measuring equipment usually consists of a sensor and a transmission device. Common equipment includes dry and wet skid testers, friction force sensors and accelerometers. The sensor is installed on the wheel or under the vehicle body to measure the friction force between the tire and the road surface and to calculate the friction coefficient using mechanical formulas.

[0029] S2. Measurement process: During vehicle operation, the sensor records the friction force between the wheel and the road surface in real time. Under different road surface conditions such as wet, dry and smooth, different friction force values ​​are obtained by measurement. By calculating the friction coefficient, the friction performance of the road surface is evaluated.

[0030] S3. Data Analysis and Feedback: Friction data collected by sensors is transmitted to the central data processing system via the onboard computer. The system analyzes and calculates the friction coefficient in real time and compares it with the standard value.

[0031] Preferably, the compressive strength analysis includes the following steps:

[0032] S1. Pressure sensor: The vehicle pressure sensor assesses the road surface's compressibility by measuring the pressure changes generated when the tire contacts the road surface. High-precision pressure sensors can monitor the pressure distribution in different road areas in real time, especially on bridges, tunnels, and old road sections.

[0033] S2. Stress sensor: In addition to pressure, the vehicle-mounted stress sensor can monitor the stress changes on the road surface under vehicle load. Through the stress sensor, the distribution of road surface force can be obtained, and it can be identified whether there is stress concentration due to structural problems.

[0034] S3. Data processing and evaluation: The data collected by the sensors is processed by the onboard computer system to analyze the compressive strength of the road surface.

[0035] Preferably, the comprehensive evaluation and feedback includes the following steps:

[0036] S1. Data fusion and analysis: The system integrates and analyzes image data, laser scanning data, friction system data, and pressure sensor data through data fusion technology.

[0037] S2. Machine learning and intelligent analysis: The system can use machine learning algorithms for pattern recognition and anomaly detection to automatically identify potential problems on the road surface;

[0038] S3. Report generation and feedback mechanism: Based on the test results, the system automatically generates reports, which include detailed information on indicators such as pavement smoothness, friction coefficient, compressive strength, and defect distribution.

[0039] S4. Feedback and Maintenance Suggestions: The system will provide specific maintenance suggestions based on the comprehensive evaluation results. Relevant departments can prioritize maintenance based on the information fed back by the system to reduce traffic safety hazards.

[0040] (III) Beneficial Effects

[0041] This invention provides a method for inspecting the quality of road surfaces in traffic engineering. It has the following beneficial effects:

[0042] 1. In this invention, the collaborative work of intelligent sensors and data processing systems greatly improves the automation level of road quality detection, reduces the need for manual intervention, and improves work efficiency.

[0043] 2. In this invention, laser scanning, high-definition image acquisition, and sensor technology are used to accurately detect minute defects in the road surface, ensuring the accuracy of the detection results.

[0044] 3. In this invention, the detection data can be fed back to the management system in real time, which facilitates timely road surface oxidation and repair, and avoids traffic safety hazards caused by road surface quality problems. This method can not only evaluate the smoothness and friction coefficient of the road surface, but also analyze the compressive strength of the road surface and provide a comprehensive quality assessment report. Detailed Implementation

[0045] The technical solutions 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 some embodiments of the present invention, and not all 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.

[0046] Example 1:

[0047] This invention provides a method for detecting the quality of road surfaces in traffic engineering, comprising:

[0048] Road surface image data is collected using a high-definition camera and laser scanner mounted on a dedicated inspection vehicle. This data includes road surface images and surface height data, which are then used to construct a three-dimensional model of the road surface smoothness. The laser scanner should have an accuracy of no less than millimeters to ensure the accuracy of detecting minute surface irregularities.

[0049] Image and height data are processed. Image processing software is used to denoise, segment, and extract features from the collected road surface image data to identify defects such as cracks and potholes in the road surface. The height data collected by the laser scanner is used to calculate the road surface smoothness and to evaluate the area and degree of unevenness on the road surface through algorithms.

[0050] Friction coefficient measurement uses an on-board sensor system to measure the friction coefficient of the road surface in real time during vehicle operation. By having the sensor contact the road surface, the system detects changes in friction force in real time and calculates the friction coefficient to determine whether the road surface friction performance meets the standard requirements.

[0051] In the compressive strength analysis, intelligent vehicle-mounted pressure sensors and stress sensors are used during the testing process. By applying a certain pressure to the road surface and recording the response, the compressive strength of the road surface is analyzed. The data is transmitted to the data processing system in real time, and a calculation model is used to evaluate the compressive capacity of the road surface, predict its service life and whether there is structural damage.

[0052] Comprehensive evaluation and feedback involves a comprehensive analysis of the collected data, using machine learning algorithms or data mining techniques to assess the overall quality of the road surface, generating an evaluation report, and providing real-time feedback on the test results. The report includes the pass / fail status of the road surface's smoothness, coefficient of friction, and compressive strength, and provides detailed defect areas and improvement suggestions.

[0053] The process of collecting road surface image data includes the following steps:

[0054] S1. High-definition camera: The high-definition camera installed on the inspection vehicle takes pictures from multiple angles. The camera resolution is no less than 8K to ensure that it can capture the fine cracks, potholes and ruts on the road surface. By adjusting the camera's focal length and viewing angle, road image information at different scales can be obtained.

[0055] S2. Laser Scanner: The laser scanner acquires height information of various points on the road surface during vehicle movement by emitting and receiving laser beams. It calculates the distance to each point by emitting laser beams and receiving the reflected signals of the laser beams, and generates a high-precision three-dimensional model of the road surface.

[0056] S3. Data synchronization: The high-definition camera and laser scanner need to achieve synchronized data acquisition. A GPS module and inertial measurement unit are used to time-stamp the acquired data to ensure that the data from different sensors can be accurately matched, providing a basis for subsequent processing.

[0057] S4. Data storage: All acquired image data and laser scanning data are transmitted to the vehicle computing platform in real time and stored. When the data volume is large, the capacity of the storage device and the data compression and encryption technology need to be considered.

[0058] Processing image and height data includes the following steps:

[0059] S1. Image Denoising: Since the environment may affect image quality, image denoising algorithms are needed to remove noise from the image to ensure image clarity. The calculation formula is as follows:

[0060]

[0061] Where x is the distance from the center point; σ is the standard deviation, which controls the width of the Gaussian curve. The larger σ is, the wider the Gaussian curve and the stronger the smoothing effect.

[0062] S2. Image segmentation and feature extraction: Computer vision techniques are used to segment the image and identify defects such as cracks, potholes, ruts, and spalling. For crack detection, an edge detection algorithm is used to detect the edges of the cracks. The calculation formula is as follows:

[0063]

[0064] For potholes and ruts, a region growing algorithm is used to identify regions with uneven depth;

[0065] S3. Road surface smoothness calculation: The road surface model is constructed using the height data obtained by the laser scanner. The data of each laser point is converted into three-dimensional coordinates using a three-dimensional reconstruction algorithm to generate a road surface height map. By calculating the local elevation differences of the road surface, the smoothness standard is evaluated.

[0066] S4. Defect identification and classification: Combining machine learning algorithms, the detected defects are classified, and a deep learning model is trained using labeled data to improve the accuracy and automation of defect detection.

[0067] The measurement of the coefficient of friction includes the following steps:

[0068] S1. Friction system sensor: Vehicle friction coefficient measuring equipment usually consists of a sensor and a transmission device. Common equipment includes dry and wet skid testers, friction force sensors and accelerometers. The sensor is installed on the wheel or under the vehicle body to measure the friction force between the tire and the road surface and to calculate the friction coefficient using mechanical formulas.

[0069] S2. Measurement process: During vehicle operation, the sensor records the friction force between the wheel and the road surface in real time. Under different road surface conditions such as wet, dry and smooth, different friction force values ​​are obtained by measurement. By calculating the friction coefficient, the friction performance of the road surface is evaluated.

[0070] S3. Data Analysis and Feedback: Friction data collected by sensors is transmitted to the central data processing system via the onboard computer. The system analyzes and calculates the friction coefficient in real time and compares it with the standard value.

[0071] Compressive strength analysis includes the following steps:

[0072] S1. Pressure sensor: The vehicle pressure sensor assesses the road surface's compressibility by measuring the pressure changes generated when the tire contacts the road surface. High-precision pressure sensors can monitor the pressure distribution in different road areas in real time, especially on bridges, tunnels, and old road sections.

[0073] S2. Stress sensor: In addition to pressure, the vehicle-mounted stress sensor can monitor the stress changes on the road surface under vehicle load. Through the stress sensor, the distribution of road surface force can be obtained, and it can be identified whether there is stress concentration due to structural problems.

[0074] S3. Data processing and evaluation: The data collected by the sensors is processed by the onboard computer system to analyze the compressive strength of the road surface.

[0075] The comprehensive assessment and feedback includes the following steps:

[0076] S1. Data fusion and analysis: The system integrates and analyzes image data, laser scanning data, friction system data, and pressure sensor data through data fusion technology.

[0077] S2. Machine learning and intelligent analysis: The system can use machine learning algorithms for pattern recognition and anomaly detection to automatically identify potential problems on the road surface;

[0078] S3. Report generation and feedback mechanism: Based on the test results, the system automatically generates reports, which include detailed information on indicators such as pavement smoothness, friction coefficient, compressive strength, and defect distribution.

[0079] S4. Feedback and Maintenance Suggestions: The system will provide specific maintenance suggestions based on the comprehensive evaluation results. Relevant departments can prioritize maintenance based on the information fed back by the system to reduce traffic safety hazards.

[0080] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for testing the quality of road surface in traffic engineering, characterized in that: include: Road surface image data is collected using a high-definition camera and laser scanner mounted on a dedicated inspection vehicle. This data includes road surface images and surface height data, which are then used to construct a three-dimensional model of the road surface smoothness. The laser scanner should have an accuracy of no less than millimeters to ensure the accuracy of detecting minute surface irregularities. Image and height data are processed. Image processing software is used to denoise, segment, and extract features from the collected road surface image data to identify defects such as cracks and potholes in the road surface. The height data collected by the laser scanner is used to calculate the road surface smoothness and to evaluate the area and degree of unevenness on the road surface through algorithms. Friction coefficient measurement uses an on-board sensor system to measure the friction coefficient of the road surface in real time during vehicle operation. By having the sensor contact the road surface, the system detects changes in friction force in real time and calculates the friction coefficient to determine whether the road surface friction performance meets the standard requirements. In the compressive strength analysis, intelligent vehicle-mounted pressure sensors and stress sensors are used during the testing process. By applying a certain pressure to the road surface and recording the response, the compressive strength of the road surface is analyzed. The data is transmitted to the data processing system in real time, and a calculation model is used to evaluate the compressive capacity of the road surface, predict its service life and whether there is structural damage. Comprehensive evaluation and feedback involves a comprehensive analysis of the collected data, using machine learning algorithms or data mining techniques to assess the overall quality of the road surface, generating an evaluation report, and providing real-time feedback on the test results. The report includes the pass / fail status of the road surface's smoothness, coefficient of friction, and compressive strength, and provides detailed defect areas and improvement suggestions.

2. The method for detecting the quality of road surface in traffic engineering according to claim 1, characterized in that: The process of acquiring road surface image data includes the following steps: S1. High-definition camera: The high-definition camera installed on the inspection vehicle takes pictures from multiple angles. The camera resolution is no less than 8K to ensure that it can capture the fine cracks, potholes and ruts on the road surface. By adjusting the camera's focal length and viewing angle, road image information at different scales can be obtained. S2. Laser Scanner: The laser scanner acquires height information of various points on the road surface during vehicle movement by emitting and receiving laser beams. It calculates the distance to each point by emitting laser beams and receiving the reflected signals of the laser beams, and generates a high-precision three-dimensional model of the road surface. S3. Data synchronization: The high-definition camera and laser scanner need to achieve synchronized data acquisition. A GPS module and inertial measurement unit are used to time-stamp the acquired data to ensure that the data from different sensors can be accurately matched, providing a basis for subsequent processing. S4. Data storage: All acquired image data and laser scanning data are transmitted to the vehicle computing platform in real time and stored. When the data volume is large, the capacity of the storage device and the data compression and encryption technology need to be considered.

3. The method for detecting the quality of road surface in traffic engineering according to claim 1, characterized in that: The processing of image data and height data includes the following steps: S1. Image Denoising: Since the environment may affect image quality, image denoising algorithms are needed to remove noise from the image to ensure image clarity. The calculation formula is as follows: Where x is the distance from the center point; σ is the standard deviation, which controls the width of the Gaussian curve. The larger σ is, the wider the Gaussian curve and the stronger the smoothing effect. S2. Image segmentation and feature extraction: Computer vision techniques are used to segment the image and identify defects such as cracks, potholes, ruts, and spalling. For crack detection, an edge detection algorithm is used to detect the crack edges. The calculation formula is as follows: For potholes and ruts, a region growing algorithm is used to identify regions with uneven depth; S3. Road surface smoothness calculation: The road surface model is constructed using the height data obtained by the laser scanner. The data of each laser point is converted into three-dimensional coordinates using a three-dimensional reconstruction algorithm to generate a road surface height map. By calculating the local elevation differences of the road surface, the smoothness standard is evaluated. S4. Defect identification and classification: Combining machine learning algorithms, the detected defects are classified, and a deep learning model is trained using labeled data to improve the accuracy and automation of defect detection.

4. The method for detecting the quality of road surface in traffic engineering according to claim 1, characterized in that: The friction coefficient measurement includes the following steps: S1. Friction system sensor: Vehicle friction coefficient measuring equipment usually consists of a sensor and a transmission device. Common equipment includes dry and wet skid testers, friction force sensors and accelerometers. The sensor is installed on the wheel or under the vehicle body to measure the friction force between the tire and the road surface and to calculate the friction coefficient using mechanical formulas. S2. Measurement process: During vehicle operation, the sensor records the friction force between the wheel and the road surface in real time. Under different road surface conditions such as wet, dry and smooth, different friction force values ​​are obtained by measurement. By calculating the friction coefficient, the friction performance of the road surface is evaluated. S3. Data Analysis and Feedback: Friction data collected by sensors is transmitted to the central data processing system via the onboard computer. The system analyzes and calculates the friction coefficient in real time and compares it with the standard value.

5. The method for detecting the quality of road surface in traffic engineering according to claim 1, characterized in that: The compressive strength analysis includes the following steps: S1. Pressure sensor: The vehicle pressure sensor assesses the road surface's compressibility by measuring the pressure changes generated when the tire contacts the road surface. High-precision pressure sensors can monitor the pressure distribution in different road areas in real time, especially on bridges, tunnels, and old road sections. S2. Stress sensor: In addition to pressure, the vehicle-mounted stress sensor can monitor the stress changes on the road surface under vehicle load. Through the stress sensor, the distribution of road surface force can be obtained, and it can be identified whether there is stress concentration due to structural problems. S3. Data processing and evaluation: The data collected by the sensors is processed by the onboard computer system to analyze the compressive strength of the road surface.

6. The method for detecting the quality of road surface in traffic engineering according to claim 1, characterized in that: The comprehensive assessment and feedback includes the following steps: S1. Data fusion and analysis: The system integrates and analyzes image data, laser scanning data, friction system data, and pressure sensor data through data fusion technology. S2. Machine learning and intelligent analysis: The system can use machine learning algorithms for pattern recognition and anomaly detection to automatically identify potential problems on the road surface; S3. Report generation and feedback mechanism: Based on the test results, the system automatically generates reports, which include detailed information on indicators such as pavement smoothness, friction coefficient, compressive strength, and defect distribution. S4. Feedback and Maintenance Suggestions: The system will provide specific maintenance suggestions based on the comprehensive evaluation results. Relevant departments can prioritize maintenance based on the information fed back by the system to reduce traffic safety hazards.

Images