Road surface friction coefficient detection method, system, equipment and medium

Abstract

The invention discloses a road surface friction coefficient detection method, system and device and a medium. The method comprises the following steps: acquiring at least two spectral images of a to-be-detected road surface; the spectral images are acquired by aiming at a reflection light source corresponding to the incident light source based on the to-be-detected road surface, and the light source characteristics of the incident light source corresponding to any two spectral images are different; spectral features of the to-be-detected road surface are extracted from the at least two spectral images respectively; calculating the roughness of the to-be-detected pavement according to the spectral characteristics; the pavement friction coefficient of the to-be-detected pavement is calculated according to the roughness, the pavement roughness and the friction coefficient can be rapidly and accurately detected, the reliability of a detection result is improved, and the detection efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of road detection, and in particular, to a method, system, device and medium for detecting the road surface friction coefficient. Background Art

[0002] With the growth of traffic flow and the increase of vehicle speed, it becomes particularly important to ensure that the road surface has sufficient friction. Among them, the road surface roughness and friction coefficient are important indicators for evaluating road quality and safety. A low friction coefficient may lead to problems such as vehicle skidding and increased braking distance, thus causing traffic accidents. Therefore, regular detection of the road surface friction coefficient is crucial for maintaining traffic safety.

[0003] Traditional detection methods include on-site tests using devices such as pendulum friction coefficient testers, which rely on physical contact to measure the friction coefficient by simulating the friction between the tire and the road surface. Moreover, the existing technologies for detecting road surface friction coefficient information based on laser or image processing are easily affected by the shooting environment. Therefore, the existing technologies have technical problems of low detection efficiency and inaccurate detection results. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of protection of the claims.

[0005] The main purpose of the embodiments of the present disclosure is to propose a method, system, device and storage medium for detecting the road surface friction coefficient, which can improve the reliability of the detection results and enhance the detection efficiency.

[0006] The first aspect of the embodiments of the present application provides a method for detecting the road surface friction coefficient for a central controller, and the method includes:

[0007] Obtaining at least two spectral images of the road surface to be detected; the spectral images are collected based on the reflected light source corresponding to the incident light source for the road surface to be detected, and the light source characteristics of the incident light sources corresponding to any two spectral images are different;

[0008] Respectively extracting the spectral characteristics of the road surface to be detected from the at least two spectral images;

[0009] Calculating the roughness of the road surface to be detected according to the spectral characteristics;

[0010] Calculating the road surface friction coefficient of the road surface to be detected according to the roughness.

[0011] An embodiment of the present application provides a method for detecting the road surface friction coefficient. The method includes obtaining at least two spectral images of the road surface to be detected; the spectral images are collected based on the reflected light source corresponding to the incident light source for the road surface to be detected, and the light source characteristics of the incident light sources corresponding to any two spectral images are different; respectively extracting the spectral characteristics of the road surface to be detected from the at least two spectral images; calculating the roughness of the road surface to be detected according to the spectral characteristics; and calculating the road surface friction coefficient of the road surface to be detected according to the roughness, which can realize the rapid and accurate detection of the road surface roughness and friction coefficient, improve the reliability of the detection result, and improve the detection efficiency.

[0012] In some embodiments of the present application, the step of respectively extracting the spectral characteristics of the road surface to be detected from the at least two spectral images includes:

[0013] Obtaining the reflectivity of the light source corresponding to the spectral image;

[0014] Setting the spectral weight coefficient corresponding to the spectral image;

[0015] Calculating the spectral characteristics of the road surface to be detected according to the reflectivity and the spectral weight coefficient.

[0016] In some embodiments of the present application, the spectral characteristics include the energy, contrast, homogeneity, and entropy of the road surface to be detected. The calculation formulas for the energy, contrast, homogeneity, and entropy of the road surface to be detected include:

[0017]

[0018] where p(i,j) is the probability of the occurrence of pixel pairs with pixel values i and j, Energy is the energy value, and n is the number of gray levels;

[0019]

[0020] where Contrast is the contrast value;

[0021]

[0022] where Homogeneity is the homogeneity value, and n is the number of gray levels;

[0023]

[0024] where Entropy is the entropy.

[0025] In some embodiments of the present application, the spectral characteristics include color characteristics. The calculation formula for the roughness includes:

[0026] R c= α·Contrast + β·Energy + γ·Homogeneity + δ·Entropy + ∈·ColorFeature;

[0027] Wherein, R c is the roughness, α, β, γ, δ and ∈ are weight coefficients, and ColorFeature is the color feature;

[0028] The conversion formula of the road surface friction coefficient includes:

[0029] μ = k·R c + C;

[0030] Wherein, μ is the road surface friction coefficient, and k and C are preset constants.

[0031] In some embodiments of the present application, before obtaining at least two spectral images of the road surface to be detected, it includes:

[0032] Collect the initial spectral image of the road surface to be detected;

[0033] Perform preprocessing operations on the initial spectral image to obtain the spectral image, wherein the preprocessing operations include at least one of grayscale conversion, denoising, contrast enhancement, and edge detection.

[0034] In some embodiments of the present application, after calculating the road surface friction coefficient of the road surface to be detected according to the roughness, it further includes:

[0035] Obtain the environmental parameters of the road surface to be detected, and adjust the road surface friction coefficient according to the environmental parameters;

[0036] The calculation formula for adjusting the road surface friction coefficient includes:

[0037] μ a = μ×(1 + β T ΔT + β H ΔH);

[0038] Wherein, μ a is the correction coefficient, μ is the road surface friction coefficient, β T is the temperature correction coefficient, ΔT is the temperature change, β H is the humidity correction coefficient, and ΔH is the humidity change.

[0039] In some embodiments of the present application, after adjusting the road surface friction coefficient, it further includes:

[0040] Compare the road surface friction coefficient with a preset standard to determine the anti-slip performance grade of the road surface to be detected.

[0041] To achieve the above object, a second aspect of the embodiments of the present invention provides a road surface friction coefficient detection system, which includes:

[0042] An acquisition module, configured to acquire at least two spectral images of the road surface to be detected; the spectral images are acquired based on the reflected light source corresponding to the incident light source of the road surface to be detected, and the light source characteristics of the incident light sources corresponding to any two spectral images are different;

[0043] An extraction module, configured to extract the spectral characteristics of the road surface to be detected from the at least two spectral images respectively;

[0044] A calculation module, configured to calculate the roughness of the road surface to be detected according to the spectral characteristics;

[0045] A processing module, configured to calculate the road surface friction coefficient of the road surface to be detected according to the roughness.

[0046] To achieve the above object, a third aspect of the embodiments of the present invention provides an electronic device, including: at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the above-mentioned road surface friction coefficient detection method.

[0047] To achieve the above object, a fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, which stores computer-executable instructions for causing a computer to execute the above-mentioned road surface friction coefficient detection method.

[0048] It can be understood that the beneficial effects of the above second aspect to the fourth aspect compared with the related art are the same as those of the above first aspect compared with the related art. For the relevant descriptions, reference can be made to the relevant descriptions in the above first aspect, and details are not described herein again. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present application will become apparent and easy to understand from the description of the embodiments in conjunction with the following drawings, where:

[0050] Figure 1 is a schematic flowchart of a road surface friction coefficient detection method provided by an embodiment of the present application;

[0051] Figure 2 is a schematic structural diagram of a road surface friction coefficient detection training system provided by an embodiment of the present application;

[0052] Figure 3It is a schematic diagram of the hardware structure of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0053] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and should not be construed as a limitation of the present application.

[0054] In the description of the present application, if the first, second, etc. are described, it is only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0055] In the description of the present application, it should be understood that for the orientation description, such as up, down, etc., the orientation or position relationship indicated is based on the orientation or position relationship shown in the accompanying drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present application.

[0056] In the description of the present application, it should be noted that unless otherwise clearly defined, words such as setting, installation, connection, etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above words in the present application in combination with the specific content of the technical solution.

[0057] The road traffic flow continues to grow, and the vehicle driving speed has increased significantly, which puts higher requirements on the anti-skid performance of the road surface. The surface texture characteristics and friction coefficient of the road surface are key technical indicators for evaluating road safety performance, which are directly related to driving safety and comfort. Research shows that when the road surface friction coefficient is lower than 0.4, the braking distance of the vehicle will increase significantly, and it is more likely to occur dangerous situations such as sideslip and tail flick under wet conditions, seriously threatening road traffic safety.

[0058] At present, the detection of the road surface friction coefficient mainly adopts two methods: contact type and non-contact type. The contact type detection is represented by the British Pendulum Tester, and the friction coefficient is measured by the rubber slider at the end of the pendulum hammer contacting and sliding on the road surface. Although the measurement principle of this method is intuitive, it has limitations such as low detection efficiency, large influence of the test results by the operator, and difficulty in realizing continuous detection. The non-contact type detection mainly adopts a laser profiler or digital image processing technology, and the friction coefficient is indirectly calculated by analyzing the road surface texture characteristics. However, these methods are easily interfered by factors such as light conditions, environmental humidity, and road surface pollutants, resulting in unstable measurement accuracy.

[0059] In addition, existing detection technologies not only have large-sized detection equipment, making it difficult to achieve rapid deployment and mobile detection, which in turn leads to traffic interruption during the detection process and affects the normal passage of roads. Moreover, the detection data acquisition frequency is low, making it difficult to comprehensively reflect the spatial distribution characteristics of the road surface friction coefficient. In addition, existing technologies lack effective real-time data processing and analysis methods and cannot timely warn of potential road surface safety hazards.

[0060] Based on this, the embodiments of the present application provide a road surface friction coefficient detection method, system, electronic device and medium, aiming to improve the reliability of detection results and enhance the detection efficiency.

[0061] The road surface friction coefficient detection method, system, electronic device and medium provided by the embodiments of the present application will be specifically described through the following embodiments. First, the road surface friction coefficient detection method in the embodiments of the present application will be described.

[0062] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, sense the environment, acquire knowledge and use knowledge to obtain the best results in theory, method, technology and application system.

[0063] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0064] The road surface friction coefficient detection method provided by the embodiments of the present application relates to the field of road detection technology. The road surface friction coefficient detection method provided by the embodiments of the present application can be applied to a terminal, or to a server side, or can also be software running on a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or distributed system composed of multiple physical servers, or can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the road surface friction coefficient detection method, etc., but is not limited to the above forms.

[0065] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0066] It should be noted that in each specific embodiment of this application, when it comes to performing relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of this application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or redirecting to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of this application will be obtained.

[0067] For this reason, referring to Figure 1 , an embodiment of this application provides a method for detecting the road surface friction coefficient. This method is applied to a central controller. The controller can be a server, an electronic device, or a mobile terminal, etc., which is not specifically limited here. The method includes the following steps S110 to step S140.

[0068] Step S110: Obtain at least two spectral images of the road surface to be detected; the spectral images are collected based on the reflected light source corresponding to the incident light source for the road surface to be detected, and the light source characteristics of the incident light sources corresponding to any two spectral images are different.

[0069] In this step, it is preferably to obtain the anisotropic reflection characteristics of the road surface to be detected through a polarization imaging module. Among them, the polarization imaging module uses an adjustable light source with a wavelength of 450 - 850 nm and a rotating polarizer assembly. Further, different wavelengths of light sources are emitted through the polarization imaging module, and the reflection characteristics of the road surface to be detected at different polarization angles are obtained through the rotating polarizer assembly, so as to obtain at least two spectral images with different light source characteristics, thereby avoiding physical damage to the road surface by traditional contact instruments.

[0070] Specifically, at least two spectral images are collected by using an adjustable light source and an image sensor, and each image corresponds to the spectral characteristics (such as wavelength, polarization state) of different incident light sources.

[0071] Before obtaining at least two spectral images of the road surface to be detected in step S110, it includes:

[0072] Collect the initial spectral image of the road surface to be detected;

[0073] Perform preprocessing operations on the so-called initial spectral image to obtain a spectral image. Among them, the preprocessing operations include at least one of grayscale conversion, denoising, contrast enhancement, and edge detection.

[0074] In this step, after collecting the initial spectral image of the road surface to be detected, a spectral image is obtained by performing preprocessing operations on the so-called initial spectral image. Image noise and uneven illumination are eliminated through preprocessing, and the stability and reliability of feature extraction are improved.

[0075] Specifically, the initial spectral image is not limited to the photos directly taken by the image processing device (such as a visual intelligent monitor, a smart terminal device) equipped with a road surface friction coefficient detection system, but also includes the pictures taken by other external devices (such as a network camera, a portable camera, etc.) and then imported or synchronized to the image processing device. In addition, the initial spectral image may also come from a cloud storage platform and directly reach the image processing device for processing through network transmission.

[0076] Further, the initial spectral image is grayscale processed, specifically by using a brightness weighting formula to retain key brightness information.

[0077] Further, the initial spectral image is denoised, specifically by adaptively selecting a filtering window for median filtering to reduce image noise.

[0078] Further, the initial spectral image is contrast enhanced, specifically by histogram equalization to expand the dynamic range and highlight texture details.

[0079] Thus, by performing preprocessing operations on the initial spectral image, the image quality is significantly improved, ensuring the accuracy and consistency of subsequent feature extraction. Among them, the preprocessing operations include at least one of graying, denoising, enhancing contrast, and edge detection.

[0080] Step S120: Extract the spectral features of the road surface to be detected from at least two spectral images respectively.

[0081] In this step, by analyzing the differences in the reflection characteristics of the road surface under different light source conditions from at least two spectral images, the optical features related to the friction coefficient are extracted, effectively reducing the influence of a single lighting condition (such as shadow, reflection) on the detection result and improving the detection accuracy.

[0082] In some embodiments, extracting the spectral features of the road surface to be detected from at least two spectral images respectively in step S120 includes the following steps S210 to S230:

[0083] Step S210: Obtain the reflectivity of the light source corresponding to the spectral image;

[0084] Step S220: Set the spectral weight coefficient corresponding to the spectral image;

[0085] Step S230: Calculate the spectral features of the road surface to be detected according to the reflectivity and the spectral weight coefficient.

[0086] In this embodiment, based on the light source wavelength and the response characteristics of the image sensor, the reflectivity of each band is calculated, and then according to the sensitivity of different bands to the friction coefficient, the spectral weight coefficient is dynamically adjusted to optimize the feature fusion strategy. By quantifying the reflectivity and the spectral weight coefficient, the feature extraction process is optimized and the data representation ability is enhanced.

[0087] Step S130: Calculate the roughness of the road surface to be detected according to the spectral features.

[0088] In this step, the spectral features include the energy, contrast, uniformity, entropy, and color features of the road surface to be detected. Among them, the energy, contrast, uniformity, and entropy are all texture features of the road surface to be detected. By extracting the texture features (such as energy, contrast, uniformity, entropy) and color features, the roughness information of the road surface is comprehensively reflected, improving the reliability of the detection.

[0089] In some embodiments, calculating the roughness of the road surface to be detected according to the spectral features in step S130 includes the following step S310:

[0090] Step S310: The calculation formulas for the energy, contrast, uniformity, and entropy of the road surface to be detected include:

[0091]

[0092] Among them, p(i, j) is the probability of the occurrence of pixel pairs with pixel values i and j, Energy is the energy value, and n is the number of gray levels;

[0093]

[0094] Among them, Contrast is the contrast value;

[0095]

[0096] Among them, Homogeneity is the uniformity value, and n is the number of gray levels;

[0097]

[0098] Among them, Entropy is the entropy.

[0099] In this embodiment, it is preferably to use gray-level co-occurrence matrix analysis to comprehensively quantify the microscopic morphology and macroscopic roughness of the road surface by introducing four types of texture features: energy, contrast, uniformity, and entropy.

[0100] Specifically, construct the probability distribution matrix of pixel pairs and calculate the following features:

[0101] The energy used to reflect texture uniformity, and the formula is:

[0102]

[0103] Among them, p(i, j) is the element value in the normalized gray-level co-occurrence matrix, representing the probability of the occurrence of pixel pairs with pixel values i and j, Energy is the energy value, and n is the number of gray levels.

[0104] The contrast used to characterize the difference in texture depth, and the formula is:

[0105]

[0106] Among them, Contrast is the contrast value;

[0107] The uniformity used to measure local consistency, and the formula is:

[0108]

[0109] Among them, Homogeneity is the uniformity value, and n is the number of gray levels.

[0110] The entropy used to describe texture complexity, and the formula is:

[0111]

[0112] Among them, Entropy is entropy.

[0113] In this embodiment, the macroscopic to microscopic roughness information of the road surface is comprehensively covered by four types of features, improving the comprehensiveness and accuracy of the friction coefficient prediction.

[0114] Step S140: Calculate the road surface friction coefficient of the road surface to be detected according to the roughness.

[0115] In this step, the roughness is mapped to the friction coefficient. Specifically, the optical features are converted into road surface roughness indexes and mapped to the friction coefficient through an empirical formula.

[0116] In some embodiments, calculating the roughness of the road surface to be detected according to the spectral features in step S140 includes the following step S320:

[0117] Step S320: The spectral features include color features, and the calculation formula of the roughness includes:

[0118] R c =α·Contrast + β·Energy + γ·Homogeneity + δ·Entropy + ∈·ColorFeature;

[0119] Among them, R c is the roughness, α, β, γ, δ and ∈ are weight coefficients, and ColorFeature is the color feature;

[0120] The conversion formula of the road surface friction coefficient includes:

[0121] μ = k·R c +C;

[0122] Among them, μ is the road surface friction coefficient, and k and C are preset constants.

[0123] In this embodiment, the spectral image is analyzed by color histogram to introduce color features as a supplement to solve the limitations of a single texture feature in complex scenarios (such as oil stains and water accumulation).

[0124] Specifically, the RGB image is divided into multiple color intervals, and the normalized pixel distribution is statistically analyzed.

[0125] Furthermore, the color feature and the texture feature are weighted and fused. Among them, the calculation formula of the roughness includes:

[0126] R c =α·Contrast + β·Energy + γ·Homogentity + δ·Entropy + ∈·ColorFeature;

[0127] Specifically, Rc where Roughness is the roughness, α, β, γ, δ, and ∈ are weight coefficients, and the weight coefficients are preferably calibrated by multiple regression, and ColorFeature is the color feature.

[0128] Furthermore, the roughness is mapped to the friction coefficient to enhance the detection robustness in complex scenarios by introducing the color feature and reduce the errors caused by road surface pollution or humidity changes.

[0129] After calculating the road surface friction coefficient of the road to be detected according to the roughness in step S140, the following steps are further included:

[0130] Obtain the environmental parameters of the road to be detected and adjust the road surface friction coefficient according to the environmental parameters;

[0131] The calculation formula for adjusting the road surface friction coefficient includes:

[0132] μ a = μ × (1 + β T ΔT + β H ΔH);

[0133] where, μ a is the correction coefficient, μ is the road surface friction coefficient, β T is the temperature correction coefficient, ΔT is the temperature change, β H is the humidity correction coefficient, and ΔH is the humidity change.

[0134] In this step, the friction coefficient is corrected by environmental parameters to solve the interference of temperature and humidity changes on the detection results. Specifically, by collecting environmental parameters, the temperature change ΔT and humidity change ΔH are obtained in real time, and then the correction coefficient for correcting the friction coefficient is determined according to the preset temperature correction coefficient, preset humidity correction coefficient, temperature change, and humidity change.

[0135] Furthermore, the road surface friction coefficient is adjusted according to the environmental parameters by adjusting the calculation formula of the road surface friction coefficient. Among them, the experimental coefficient can be calibrated through multiple experiments to reflect the influence law of environmental factors on the friction coefficient, and then effectively reduce the influence of temperature and humidity fluctuations on the detection results and improve the detection stability in complex environments.

[0136] After adjusting the road surface friction coefficient in this step, the following steps are further included:

[0137] Compare the road surface friction coefficient with the preset standard to determine the anti-slip performance grade of the road to be detected.

[0138] In this step, the anti-skid performance level of the road surface is evaluated by grading according to preset standards to achieve rapid and safe judgment, which specifically includes presetting multiple anti-skid levels (such as excellent, good, medium, and poor), each level corresponding to a specific friction coefficient range. The calculated friction coefficient can be further compared with the preset standard in real time through the embedded processing unit, and the grade result can be output to achieve automated evaluation, which greatly shortens the judgment time, meets real-time detection needs, provides immediate basis for road maintenance, and then instantly determines the anti-skid performance level of the road surface to be tested.

[0139] In one embodiment, a multispectral polarization image of the road surface is obtained through polarized light imaging and a multispectral dynamic acquisition module, and feature extraction and friction coefficient calculation are performed in combination with an embedded processing unit, which significantly improves detection accuracy and efficiency.

[0140] Specifically, the polarized light imaging module includes a 450-850nm adjustable light source and a rotating polarizer assembly to obtain the anisotropic reflectance characteristics of the road surface; the multispectral dynamic acquisition module integrates a 6-channel narrow-band filter array (center wavelength: 470nm, 530nm, 590nm, 650nm, 720nm, 850nm); the embedded processing unit is configured with the NVIDIA Jetson AGX Orin chipset to implement the feature extraction algorithm.

[0141] Among them, the feature extraction formula is:

[0142]

[0143] Among them, λ I is the spectral weight coefficient, R i is the reflectivity of the spectral image at the corresponding wavelength.

[0144] Furthermore, the polarized light imaging module includes a temperature and humidity compensation subsystem for establishing an environmental correction model:

[0145] μ a =μ×(1+β T ΔT+β H ΔH);

[0146] Among them, μ a is the correction coefficient, μ is the road friction coefficient, β T is the temperature correction coefficient, ΔR is the temperature change, β H is the humidity correction coefficient, and ΔH is the humidity change.

[0147] Furthermore, the multi-spectral dynamic acquisition module adopts the IMX585 image sensor (1 / 1.2 inch, 48 million pixels) and a tunable filter wheel (rotation speed 30rpm) to achieve 6-band spectral image acquisition (frame rate 60fps).

[0148] Furthermore, the embedded processing unit completes feature extraction (with a latency of <5 ms) through the FPGA pre-processor and finally calculates the friction coefficient.

[0149] In this embodiment, the anisotropic reflection characteristics of the road surface are obtained through the polarized light imaging module, the multi-band spectral image acquisition is realized by using the multi-spectral dynamic acquisition module, and the feature extraction and friction coefficient calculation are carried out in combination with the embedded processing unit, realizing the high-precision detection of the road surface friction coefficient. It has the advantages of high detection efficiency and low equipment cost. An environmental compensation model is also introduced, and the detection result is corrected by the temperature and humidity compensation subsystem, improving the reliability of the detection result. In addition, through the multi-factor verification matrix test, the prediction error of the friction coefficient is reduced, resulting in a significant improvement in the detection efficiency and a remarkable reduction in the cost of the detection equipment.

[0150] In an embodiment, by using an IMX585 image sensor (1 / 1.2 inch, 48 million pixels), in cooperation with a tunable filter wheel (rotation speed 30 rpm), the 6-band spectral image acquisition (frame rate 60 fps) is realized, that is, the image data of the cement pavement is collected by using a high-resolution camera to ensure the clarity and detail information of the image.

[0151] Specifically, the resolution of the camera should be not less than 12 million pixels to ensure that the collected image has sufficient detail information. The frame rate of the camera is 25 frames per second, adapting to the exposure control of dynamic light to ensure clear imaging under different lighting conditions.

[0152] Furthermore, the collected image data is preprocessed, including grayscale conversion, denoising, and contrast enhancement, to improve the quality of the image and the accuracy of subsequent processing. Among them, the preprocessing also includes edge detection and texture analysis of the image to enhance the feature information of the image.

[0153] Specifically, the image preprocessing steps are as follows:

[0154] (1) Grayscale conversion: Convert the RGB image to a grayscale image, and the specific formula is as follows:

[0155] Y = 0.299R + 0.587G + 0.114B;

[0156] (2) Denoising: Use the median filtering method to remove the noise in the image, and adaptively select the filtering window based on the image noise level.

[0157] (3) Contrast enhancement: Use the histogram equalization method to enhance the contrast of the image, making the details in the image clearer.

[0158] (4) Edge detection: Use the Canny edge detection algorithm to detect the edges in the image and dynamically adjust the edge detection threshold.

[0159] Furthermore, feature extraction is performed on the collected images, and characteristic parameters of the road surface in the images are extracted from the preprocessed images, including texture features and color features. Among them, the texture features can be calculated by the gray-level co-occurrence matrix method, and the color features can be obtained through color histogram analysis.

[0160] Specifically, the gray-level co-occurrence matrix method is used to calculate the texture features of the images, including energy, contrast, homogeneity, and entropy. The texture features of the images can reflect the roughness and texture changes of the road surface, providing important input data for subsequent roughness calculation.

[0161] Among them, energy represents the sum of the squares of the element values in the gray-level co-occurrence matrix of the image, reflecting the uniformity of the image. The higher the energy value, the more uniform the image and the lower the roughness of the road surface.

[0162]

[0163] Among them, p(i,j) is the element value in the normalized gray-level co-occurrence matrix, representing the probability of the occurrence of pixel pairs with pixel values i and j, ENergy is the energy value, and n is the number of gray levels. The energy value reflects the degree of uniformity of the gray-level distribution of the image. The larger the energy value, the more uniform the gray-level distribution of the image.

[0164] Contrast reflects the magnitude of the local gray-level difference in the image, that is, the clarity of the image and the depth of the texture. The higher the contrast value, the more obvious the texture in the image and the higher the roughness of the road surface.

[0165]

[0166] Among them, Contrast is the contrast value.

[0167] Homogeneity represents the distribution of the element values in the gray-level co-occurrence matrix of the image, reflecting the texture uniformity of the image. The higher the homogeneity value, the more uniform the image texture and the lower the roughness of the road surface.

[0168]

[0169] Among them, Homogeneity is the homogeneity value, and n is the number of gray levels.

[0170] Entropy reflects the complexity of the gray-level distribution of the image, that is, the randomness of the image. The higher the entropy value, the more complex the gray-level distribution of the image and the higher the roughness of the road surface.

[0171]

[0172] Among them, Entropy is the entropy.

[0173] Further, color features are extracted, preferably by calculating the color features of the image through the color histogram method. The color space is divided into 16 intervals, the number of pixels in each interval is counted, and normalization processing is performed. The color features can reflect the color distribution of the road surface and provide additional reference information for roughness calculation.

[0174] Further, the roughness index R of the road surface is calculated according to the extracted feature parameters c , using the following formula:

[0175] R c = α·Contrast + β·Energy + γ·Homogeneity + δ·Entropy + ∈·ColorFeature;

[0176] where, R c is the roughness, α, β, γ, δ and ∈ are weight coefficients used to adjust the contribution of different feature parameters to the roughness index. The weight coefficients of each feature are determined by fitting experimental data through multiple linear regression. ColorFeature is the color feature.

[0177] Each feature parameter in the roughness calculation formula is directly related to the texture feature and color feature in the feature extraction step. By performing weighted summation of these feature parameters, the texture and color information of the road surface can be comprehensively considered to obtain an index that can comprehensively reflect the roughness of the road surface.

[0178] Further, feature extraction is completed by the FPGA preprocessor (with a delay < 5 ms), and finally the friction coefficient is calculated in the embedded unit. According to the calculated roughness index R c , the road surface friction coefficient μ is obtained by conversion using the empirical formula. The conversion formula for the road surface friction coefficient is as follows:

[0179] μ = k·R c + C;

[0180] where, μ is the road surface friction coefficient, k and C are preset constants that can be obtained through experimental calibration.

[0181] Specifically, in some embodiments, the calibration method of the empirical constant is as follows:

[0182] (a) Experimental design: Select a group of standard road surface samples with different roughnesses. The roughness R of each sample c is calculated through the conversion formula of the road surface friction coefficient and measured using a traditional contact roughness meter as a reference value.

[0183] (b) Coefficient of friction measurement: Use a coefficient of friction test vehicle to conduct tests on a standard road surface to obtain the coefficient of friction μ for each sample.

[0184] (c) Data fitting: Perform linear fitting on the roughness R c and the coefficient of friction μ data obtained from the experiment to obtain the empirical formula μ = k·R c + C.

[0185] (6) Anti-skid performance evaluation: Compare the calculated road surface coefficient of friction μ with the preset standard to determine the anti-skid performance level of the road surface.

[0186] Among them, the preset standard can include multiple anti-skid performance levels, and each level corresponds to a coefficient of friction range. For example:

[0187] Excellent: μ > 0.7, Good: 0.6 < μ ≤ 0.7, Medium: 0.5 < μ ≤ 0.6, Poor: μ ≤ 0.5.

[0188] In some embodiments, after extracting the characteristic parameters of the road surface from the preprocessed image, a dynamic texture analysis module is added in the part of extracting image features. By analyzing the dynamic changes in the image sequence, richer texture information is extracted to enhance the robustness and accuracy of the features.

[0189] Specifically, video temporal analysis (frame rate 60fps) is used to calculate motion-invariant features. Among them, the formula for calculating dynamic texture features is as follows:

[0190]

[0191] Among them, MTF is the dynamic texture feature, I(t) is the pixel intensity in the image sequence, μ is the average value, and σ is the standard deviation.

[0192] In one embodiment, a transfer learning module is added in the step of extracting the characteristic parameters of the road surface from the preprocessed image.

[0193] Specifically, the transfer learning module plays a role in the feature extraction link, and a pre-trained convolutional neural network (such as VGG16 or ResNet) is used to extract the high-level features of the image. These pre-trained convolutional neural network models are trained on a large-scale dataset (such as ImageNet) and can extract feature representations with a deep understanding of the image content, thereby capturing the general features in the image, such as edges, shapes, and colors.

[0194] Furthermore, the extracted features are used for the feature representation of the road surface image and are fine-tuned on the target task. By freezing the first few layers of the pre-trained model and only training the last few layers or adding new fully connected layers, the model is adapted to the specific features of the road surface image.

[0195] In one embodiment, the road surface friction coefficient is detected by a collection unit, a processing unit, an evaluation unit, and a storage unit.

[0196] Specifically, the collection unit collects image data of the cement pavement. The collection unit includes a high-resolution camera and an auxiliary lighting device to ensure the clarity and uniformity of the image.

[0197] Furthermore, a high-dynamic range (HDR) image acquisition device with high resolution and low noise characteristics is used to effectively capture the detailed features of the road surface.

[0198] In some embodiments, the auxiliary lighting device uses white LED lights with a power of 30W, which can provide stable lighting under different lighting conditions to ensure the image quality.

[0199] Furthermore, the processing unit preprocesses and extracts features from the collected image data. The processing unit includes an image enhancement module and a feature extraction module.

[0200] Specifically, the image enhancement module uses an image enhancement algorithm based on wavelet transform, which can effectively remove noise in the image and enhance the detailed information. The feature extraction module is based on a convolutional neural network (CNN) model of deep learning. By training a large amount of road surface image data, features that can effectively characterize the surface roughness and friction coefficient of the road surface are extracted.

[0201] In some embodiments, the specific convolutional neural network model structure of the feature extraction module: includes an input layer with an input image size of 256×256 pixels, a convolutional layer 1 with a convolutional kernel size of 3×3, 32 channels, and a ReLU activation function, a pooling layer 1 with max pooling and a pooling window size of 2×2, a convolutional layer 2 with a convolutional kernel size of 3×3, 64 channels, and a ReLU activation function, a pooling layer 2 with max pooling and a pooling window size of 2×2, a fully connected layer 1 with 128 neurons and a ReLU activation function, and a fully connected layer 2 with 2 neurons corresponding to the outputs of roughness and friction coefficient respectively.

[0202] Furthermore, the evaluation unit calculates the roughness index according to the extracted feature parameters, converts it to obtain the road surface friction coefficient, compares it with the preset standard, and determines the anti-skid performance level of the road surface.

[0203] Specifically, the evaluation unit includes a roughness calculation module and a friction coefficient conversion module. The roughness calculation module, based on the gray-level co-occurrence matrix method and the wavelet analysis method, extracts multi-scale analysis and multi-directional texture features to comprehensively consider the roughness characteristics of the road surface. The friction coefficient conversion module uses a support vector machine (SVM) regression model. By training and optimizing a large amount of experimental data, a non-linear mapping relationship between the roughness index and the friction coefficient is established.

[0204] Furthermore, the storage unit stores the collected image data, calculation results, and evaluation results for subsequent analysis and evaluation. The storage unit adopts a distributed storage architecture, which can efficiently store and manage a large amount of data. The data storage format is HDF5, which supports multiple data types and compression algorithms, can save storage space, and improve data access speed.

[0205] In some embodiments, to verify the effectiveness of the present application, compared with the traditional method: a Mitutoyo SJ-210 portable roughness meter was used to detect the same section of cement pavement under completely dry conditions, and the obtained roughness value was 1.2 mm and the friction coefficient was 0.55. By using the present application to detect the same section of cement pavement, the obtained roughness value was 1.2 mm and the friction coefficient was 0.60.

[0206] It can be seen by comparison that the present application has the advantages of non-contact, fast, and automated, and is significantly better than the traditional method.

[0207] In some embodiments, to verify the usability of the present application, compared with the traditional method for detecting on a completely dry asphalt pavement, the traditional method used a Mitutoyo SJ-210 portable roughness meter to detect the asphalt pavement, and the obtained roughness value was 1.5 mm and the friction coefficient was 0.65. The present application detected the asphalt pavement, and the obtained roughness value was 1.5 mm and the friction coefficient was 0.70.

[0208] It can be seen by comparison that the detection results of the method of the present invention on different road surface materials are also very close to those of the traditional method, further verifying the applicability and reliability of the method of the present invention.

[0209] In some embodiments, to further verify the applicability of the present application, compared with the traditional method for detecting on a rainy asphalt pavement with a rainfall of (50±5) mm / h, the traditional method used a Mitutoyo SJ-210 portable roughness meter to detect the asphalt pavement under rainy conditions (rainfall of 10-25 mm / h), and the obtained roughness value was 1.5 mm and the friction coefficient was 0.40. The present application detected the asphalt pavement, and the obtained roughness value was 1.5 mm and the friction coefficient was 0.45.

[0210] It can be seen by comparison that the detection results of this application under different road surface materials and different environmental conditions are also very close to those of traditional methods, further verifying the applicability and reliability of the method of the present invention.

[0211] Such as Figure 2 As shown, some embodiments of this application provide a road surface friction coefficient detection system, which includes an acquisition module 210, an extraction module 220, a calculation module 230, and a processing module 240. Specifically:

[0212] The acquisition module 210 is used to acquire at least two spectral images of the road surface to be detected; the spectral images are acquired based on the reflected light source corresponding to the incident light source of the road surface to be detected, and the light source characteristics of the incident light sources corresponding to any two spectral images are different;

[0213] The extraction module 220 is used to extract the spectral characteristics of the road surface to be detected from at least two spectral images respectively;

[0214] The calculation module 230 is used to calculate the roughness of the road surface to be detected according to the spectral characteristics;

[0215] The processing module 240 is used to calculate the road surface friction coefficient of the road surface to be detected according to the roughness.

[0216] In some embodiments, the extraction module 220 may include: obtaining the reflectivity of the light source corresponding to the spectral image.

[0217] In some embodiments, the extraction module 220 may include: setting the spectral weight coefficient corresponding to the spectral image.

[0218] In some embodiments, the extraction module 220 may include: calculating the spectral characteristics of the road surface to be detected according to the reflectivity and the spectral weight coefficient.

[0219] In some embodiments, the extraction module 220 may include:

[0220]

[0221] where p(i,j) is the probability of the occurrence of pixel pairs with pixel values i and j, Energy is the energy value, and n is the number of gray levels;

[0222]

[0223] where Contrast is the contrast value;

[0224]

[0225] where Homogeneity is the uniformity value, and n is the number of gray levels;

[0226]

[0227] Among them, Entropy is entropy.

[0228] In some embodiments, the calculation module 230 may include:

[0229] R c = α·Contrast + β·Energy + γ·Homogeneity + δ·Entropy + ∈·ColorFeature;

[0230] Among them, R c is roughness, α, β, γ, δ, and ∈ are weight coefficients, and ColorFeature is color feature;

[0231] The conversion formula for the road surface friction coefficient includes:

[0232] μ = k·R c + C;

[0233] Among them, μ is the road surface friction coefficient, and k and C are preset constants.

[0234] In some embodiments, the acquisition module 210 may include: collecting an initial spectral image of the road surface to be detected.

[0235] In some embodiments, the acquisition module 210 may include: performing preprocessing operations on the initial spectral image to obtain a spectral image, where the preprocessing operations include at least one of graying, denoising, contrast enhancement, and edge detection.

[0236] In some embodiments, the processing module 240 may include: obtaining environmental parameters of the road surface to be detected and adjusting the road surface friction coefficient according to the environmental parameters.

[0237] In some embodiments, the processing module 240 may include:

[0238] μ a = μ×(1 + β T ΔT + β H ΔH);

[0239] Among them, μ a is the correction coefficient, μ is the road surface friction coefficient, β T is the temperature correction coefficient, ΔT is the temperature change, β H is the humidity correction coefficient, and ΔH is the humidity change.

[0240] In some embodiments, the processing module 240 may include: comparing the road surface friction coefficient with a preset standard to determine the anti-skid performance level of the road surface to be detected.

[0241] It should be noted that the road surface friction coefficient detection system provided in this embodiment and the above-mentioned road surface friction coefficient detection method are based on the same inventive concept. Therefore, the relevant content of the above-mentioned road surface friction coefficient detection method also applies to the content of the road surface friction coefficient detection system. Therefore, it will not be elaborated here.

[0242] To solve the technical problems of low detection efficiency and inaccurate detection results in the prior art, the system obtains at least two spectral images of the road surface to be detected; the spectral images are collected based on the reflected light source corresponding to the incident light source for the road surface to be detected, and the light source characteristics of the incident light sources corresponding to any two spectral images are different; extracting the spectral characteristics of the road surface to be detected from at least two spectral images; calculating the roughness of the road surface to be detected according to the spectral characteristics; calculating the road surface friction coefficient of the road surface to be detected according to the roughness. In this way, the rapid and accurate detection of the road surface roughness and friction coefficient can be realized, and the reliability of the detection result can be improved and the detection efficiency can be enhanced.

[0243] An embodiment of the present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the above-mentioned road surface friction coefficient detection method is implemented.

[0244] Such as Figure 3 , Figure 3 is a schematic hardware structure diagram of the electronic device provided in an embodiment of the present application. The electronic device includes:

[0245] At least one battery;

[0246] At least one memory;

[0247] At least one processor;

[0248] At least one program;

[0249] The program is stored in the memory, and the processor executes at least one program to implement the above-mentioned road surface friction coefficient detection method of the present disclosure.

[0250] The electronic device may be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (Personal Digital Assistant, PDA), an in-vehicle computer, etc.

[0251] The electronic device of the embodiment of the present application will be introduced in detail below.

[0252] The processor 1600 can be implemented in the form of a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present disclosure;

[0253] The memory 1700 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 1700 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1700 and are called by the processor 1600 to execute a method for detecting the road surface friction coefficient provided in the embodiments of the present disclosure.

[0254] The input / output interface 1800 is used to implement information input and output;

[0255] The communication interface 1900 is used to implement communication interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or through wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0256] The bus 2000 transmits information between various components of the device (such as the processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900);

[0257] Among them, the processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900 achieve communication connections with each other inside the device through the bus 2000.

[0258] The embodiments of the present disclosure also provide a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned method for detecting the road surface friction coefficient.

[0259] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include memories that are remotely located relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0260] The embodiments described in the embodiments of the present disclosure are for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are equally applicable to similar technical problems.

[0261] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present disclosure, and may include more or fewer steps than those shown, or combine certain steps, or different steps.

[0262] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0263] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof.

[0264] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of this application and the above figures are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0265] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (item) of the following" or its similar expressions refer to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0266] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0267] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0268] In addition, the functional units in each embodiment of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0269] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for causing an electronic device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The foregoing storage medium includes: various media that can store programs, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0270] The above has specifically described the preferred implementation of the embodiments of the present application. However, the embodiments of the present application are not limited to the above implementation manners. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the embodiments of the present application. These equivalent deformations or substitutions are all included within the scope defined by the claims of the embodiments of the present application.

[0271] The above has described the embodiments of the present application in detail with reference to the accompanying drawings. However, the present application is not limited to the above embodiments. Within the scope of knowledge possessed by those of ordinary skill in the art, various changes can also be made without departing from the purpose of the present application.

Claims

1. A method for detecting the pavement friction coefficient, characterized in that, The method includes: Obtaining at least two spectral images of the road surface to be detected; the spectral images are collected based on the reflected light source corresponding to the incident light source for the road surface to be detected, and the light source characteristics of the incident light sources corresponding to any two spectral images are different; Respectively extracting the spectral characteristics of the road surface to be detected from the at least two spectral images; Calculating the roughness of the road surface to be detected according to the spectral characteristics; Calculating the road surface friction coefficient of the road surface to be detected according to the roughness.

2. The road surface friction coefficient detection method according to claim 1, characterized in that The respectively extracting the spectral characteristics of the road surface to be detected from the at least two spectral images includes: Obtaining the reflectivity of the light source corresponding to the spectral image; Setting the spectral weight coefficient corresponding to the spectral image; Calculating the spectral characteristics of the road surface to be detected according to the reflectivity and the spectral weight coefficient.

3. The road surface friction coefficient detection method according to claim 2, wherein The spectral characteristics include the energy, contrast, uniformity, and entropy of the road surface to be detected. The calculation formulas for the energy, contrast, uniformity, and entropy of the road surface to be detected include: Where p(i,j) is the probability of the pixel pair with pixel values i and j appearing, Energy is the energy value, and n is the number of gray levels; Where Contrast is the contrast value; Where Homogeneity is the uniformity value, and n is the number of gray levels; Where Entropy is the entropy.

4. The road surface friction coefficient detection method according to claim 3, wherein, The spectral characteristics include color characteristics. The calculation formula for the roughness includes: R c = α·Contrast + β·Energy + γ·Homogeneity + δ·Entropy + ∈·ColorFeature; wherein, R c is the roughness, α, β, γ, δ, and ∈ are weighting coefficients, and ColorFeature is the color feature; The conversion formula for the road surface friction coefficient includes: μ = k·R c + C; Where μ is the road surface friction coefficient, and k and C are preset constants.

5. The road surface friction coefficient detection method according to claim 1, characterized in that Before obtaining at least two spectral images of the road surface to be detected, it includes: Collecting the initial spectral image of the road surface to be detected; Performing a preprocessing operation on the initial spectral image to obtain the spectral image, where the preprocessing operation includes at least one of graying, denoising, contrast enhancement, and edge detection.

6. The road surface friction coefficient detection method according to claim 1, wherein After calculating the road surface friction coefficient of the road surface to be detected according to the roughness, it further includes: Obtaining the environmental parameters of the road surface to be detected and adjusting the road surface friction coefficient according to the environmental parameters; The calculation formula for adjusting the road surface friction coefficient includes: μ a = μ × (1 + β T ΔT + β H ΔH); Among them, μ a is the correction coefficient, μ is the road surface friction coefficient, β T is the temperature correction coefficient, ΔT is the temperature change, β H is the humidity correction coefficient, ΔH is the humidity change.

7. The pavement friction coefficient detection method according to claim 6, characterized in that, After adjusting the road surface friction coefficient, it further includes: Comparing the road surface friction coefficient with a preset standard to determine the anti-slip performance level of the road surface to be detected.

8. A road surface friction coefficient detection system, characterized in that, The system includes: An acquisition module for obtaining at least two spectral images of the road surface to be detected; the spectral images are collected based on the reflected light source corresponding to the incident light source for the road surface to be detected, and the light source characteristics of the incident light sources corresponding to any two spectral images are different; An extraction module for respectively extracting the spectral characteristics of the road surface to be detected from the at least two spectral images; A calculation module for calculating the roughness of the road surface to be detected according to the spectral characteristics; A processing module for calculating the road surface friction coefficient of the road surface to be detected according to the roughness.

9. An electronic device, characterized in that: Comprising at least one control processor and a memory communicatively connected to the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute a road surface friction coefficient detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions for causing a computer to execute a road surface friction coefficient detection method according to any one of claims 1 to 7.

Images