A method, device, equipment and storage medium for monitoring the temperature of asphalt on a highway surface

Abstract

The present invention provides a method, device, equipment, and storage medium for monitoring the temperature of asphalt on a highway surface, belonging to the field of temperature monitoring. The method comprises: extracting the three-primary-color brightness values ​​and the shooting angle of a labeled sample temperature field image; constructing a correlation equation between the brightness value, shooting angle, and temperature based on the principle of a two-color temperature measurement method; substituting the labeled data into the correlation equation to determine the original parameters of the correlation equation; obtaining a temperature field image of the asphalt on the target road section and the actual shooting angle corresponding to the temperature field image; extracting the target three-primary-color brightness values ​​of the temperature field image, substituting the target three-primary-color brightness values ​​and the actual shooting angle into the adjusted correlation equation to obtain the temperature of the asphalt on the target road section. In this way, the influence of different monitoring angles on the temperature monitoring results at fixed monitoring points can be eliminated, thereby improving the accuracy of the temperature monitoring results and the monitoring effect of road asphalt temperature monitoring.

Description

Technical Field

[0001] The present invention belongs to the field of temperature monitoring, and in particular relates to a method, device, equipment and storage medium for monitoring the temperature of asphalt on a highway surface. Background Art

[0002] Temperature monitoring is crucial in asphalt pavement construction. The performance of asphalt is closely related to temperature. Appropriate temperature can ensure construction quality, guarantee the strength, durability and smoothness of the pavement, and improve the overall quality of highway construction.

[0003] At present, during asphalt pavement construction, there are several different stages for asphalt temperature monitoring, such as temperature monitoring during asphalt transportation, temperature monitoring during asphalt discharge, temperature monitoring during asphalt paving, temperature monitoring during asphalt compaction, etc. Non-contact temperature monitoring methods are usually used.

[0004] In the temperature monitoring after asphalt paving, the main focus is to observe whether the temperature of the asphalt meets the compaction standard before compaction. For example, compacting asphalt when the temperature is too high may cause asphalt aging and oil leakage, increasing the difficulty of construction. When the temperature is too low, the asphalt will be insufficiently compacted and have too large a void ratio, affecting the overall construction quality of the asphalt. Therefore, by monitoring the temperature of the paved asphalt, the compaction quality of the asphalt can be ensured as much as possible.

[0005] In the existing technology, general temperature monitoring is carried out through manual collection or collection by a device fixed at a certain point. Continuous temperature monitoring of a certain area of ​​asphalt is carried out through methods such as radiation temperature measurement. For the repair of a damaged point on the road surface, manual collection is generally used because the scope of the objects to be monitored is small and the time is short. However, for newly paved roads, for longer asphalt paving sections to be compacted, the monitoring range is large, so the existing technology usually uses a device at a fixed point for temperature collection.

[0006] However, in continuous temperature monitoring, the monitoring instrument needs to collect temperature from a large area of ​​road sections. For monitoring instruments at fixed points, collecting the temperature of a large range of road sections is prone to deviations in asphalt temperature monitoring at different points on the road surface due to the wide collection area. Therefore, in this case, it is only possible to ensure that the temperature of a smaller area within a fixed range is collected with high accuracy. For other road sections that are farther away from the fixed range, the temperature collection accuracy is low and the monitoring effect is poor. Summary of the Invention

[0007] In order to solve the problem of low accuracy of fixed-point detection instruments in monitoring asphalt temperature on a large road section, the present invention provides a method, device, equipment and storage medium for monitoring asphalt temperature on a highway surface.

[0008] In order to achieve the above object, the present invention provides the following technical solutions:

[0009] First, a method for monitoring the temperature of asphalt on a highway surface is provided, the method comprising:

[0010] Extract the three primary color brightness values ​​of the labeled sample temperature field image and the shooting angle of the sample temperature field image;

[0011] Based on the two-color temperature measurement method, the correlation equation between the brightness value of the three primary colors, the shooting angle and the temperature is constructed;

[0012] Substituting the labeled data of the sample temperature field image into the correlation equation to determine the original parameters of the correlation equation; the labeled data includes the brightness values ​​of the three primary colors, the shooting angle, and the corresponding labeled temperature;

[0013] Acquire the temperature field image of the asphalt on the target road section surface and the actual shooting angle corresponding to the temperature field image;

[0014] The target three primary color brightness values ​​of the temperature field image of the asphalt on the target road section surface are extracted, and the target three primary color brightness values ​​and the actual shooting angle are substituted into the correlation formula to obtain the temperature of the asphalt on the target road section surface.

[0015] Optionally, constructing a correlation equation between the brightness values ​​of the three primary colors, the shooting angle, and the temperature based on the two-color temperature measurement method includes:

[0016] Shoot the same target from multiple angles and determine the brightness values ​​of the three primary colors at different shooting angles;

[0017] Fit multiple shooting angles and their corresponding three primary color brightness values ​​to determine the angle influence coefficients corresponding to different primary color brightness values;

[0018] The two-color temperature measurement formula based on brightness value and angle influence coefficient is constructed, and the correction coefficient is added to obtain the relevant relationship.

[0019] Optionally, the angle influence coefficient is determined by:

[0020] α i =β0+β1*A;

[0021] Among them, α i is the angular influence coefficient of the i-th primary color, β0 and β1 are the relevant parameters obtained by fitting, and A is the shooting angle.

[0022] Optionally, the correlation equation is:

[0023]

[0024] Wherein, L1 and L2 are the brightness values ​​of any two primary colors in the three primary color brightness values, K1 and K2 are correction coefficients, λ1 and λ2 are the wavelengths corresponding to L1 and L2, T is the temperature, C2 is the second radiation constant, ε(λ,T) is a dimensionless parameter representing the spectral emissivity, and α1 and α2 are the angle influence coefficients corresponding to L1 and L2, respectively, determined by the shooting angle.

[0025] Optionally, before substituting the target three primary color brightness values ​​and the actual shooting angle into the correlation equation, the parameters of the correlation equation are further adjusted, including:

[0026] Substituting the original parameters into the correlation equation for verification, we can obtain the measured temperatures corresponding to multiple sets of dual primary colors of the sample temperature field image.

[0027] The difference between different measured temperatures corresponding to the multiple sets of dual primary colors is used as a loss value, and the original parameters of the correlation equation are adjusted with the goal of minimizing the loss value.

[0028] Optionally, taking the difference between different measured temperatures corresponding to the multiple sets of dual primary colors as a loss value and adjusting the original parameters of the correlation equation with the goal of minimizing the loss value includes:

[0029] Taking the marked temperature as a reference and minimizing the loss value as a goal, adjusting the correction coefficient;

[0030] The correction coefficient is obtained when the loss value is minimum and the difference between the measured temperature and the marked temperature is within a preset error range.

[0031] Optionally, substituting the target three primary color brightness values ​​and the actual shooting angle into a correlation equation to obtain the temperature of the asphalt on the target road section surface includes:

[0032] The brightness values ​​of any two primary colors in the target three primary colors of the temperature field image are extracted as a group. Multiple groups of target brightness values ​​and corresponding actual shooting angles are substituted into the calculation to obtain multiple groups of monitored temperatures.

[0033] The average of multiple groups of monitored temperatures is used as the surface asphalt temperature of the target road section.

[0034] A device for monitoring the temperature of asphalt on a road surface is also provided, the device comprising:

[0035] An extraction module is used to extract the three primary color brightness values ​​of the labeled sample temperature field image and the shooting angle of the sample temperature field image;

[0036] A construction module, used to construct a correlation equation between the brightness values ​​of the three primary colors, the shooting angle and the temperature based on a two-color temperature measurement method;

[0037] A determination module is used to substitute the annotated data of the sample temperature field image into the correlation equation to determine the original parameters of the correlation equation; the annotated data includes the brightness values ​​of the three primary colors, the shooting angle, and the corresponding annotated temperature;

[0038] An acquisition module is used to acquire a temperature field image of the asphalt on the surface of the target road section and a shooting angle corresponding to the temperature field image;

[0039] The measurement module is used to extract the target three primary color brightness values ​​of the temperature field image of the asphalt on the target road section surface, substitute the target three primary color brightness values ​​and the actual shooting angle into the correlation formula, and obtain the temperature of the asphalt on the target road section surface.

[0040] In addition, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for monitoring the temperature of asphalt on a highway surface is implemented.

[0041] Finally, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned method for monitoring the temperature of asphalt on a road surface is implemented.

[0042] The method for monitoring the temperature of asphalt on a highway surface provided by the present invention has the following beneficial effects:

[0043] First, relevant data of the sample temperature field image is obtained. Secondly, the principle of the two-color temperature measurement method is used to construct a correlation formula, which can associate the brightness value information and shooting angle in the image with the temperature. In this way, based on the actual situation of large-scale monitoring of the monitoring instrument, improvements are made on the basis of the two-color temperature measurement method. When the monitoring instrument at a fixed point performs large-scale temperature collection, the influence of the angle problem on the accuracy of temperature monitoring can be eliminated, so that the monitoring instrument can avoid the influence of the angle factor in large-scale temperature collection, which is beneficial to improve the accuracy of temperature monitoring of highway asphalt paving; and improve the monitoring effect of the monitoring instrument on road asphalt temperature monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] To more clearly illustrate the embodiments of the present invention and its design, the following briefly introduces the drawings required for this embodiment. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0045] Figure 1 The figure is a flow chart of a method for monitoring the temperature of asphalt on a highway surface according to an exemplary embodiment of the present invention.

[0046] Figure 2The figure is a schematic diagram of the correlation between brightness value and shooting angle according to an exemplary embodiment of the present invention.

[0047] Figure 3 A schematic diagram of a multi-channel network model provided according to an exemplary embodiment of the present invention.

[0048] Figure 4 This is a block diagram of a device for monitoring the temperature of asphalt on a highway surface according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the technical solution of the present invention and to be able to implement it, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solution of the present invention and are not intended to limit the scope of protection of the present invention.

[0050] The technical solutions provided by various embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0051] This study, through controlled experiments examining various conditions, including angle, lighting, and distance, found that, under otherwise identical conditions, varying angles had the greatest impact on the three-primary-color brightness values ​​obtained by the monitoring instrument, leading to the largest deviations in the temperature values ​​ultimately obtained using the two-color temperature measurement method. Therefore, to address the low accuracy of fixed-point detection instruments in the prior art for monitoring asphalt surface temperature over large road sections, this study incorporates an angle-influence factor into the two-color temperature measurement method to eliminate the temperature deviations caused by angle issues.

[0052] First, the present invention provides a method for monitoring the temperature of asphalt on a road surface. Figure 1 As shown, the following steps are included:

[0053] S101: Construct a correlation equation among brightness value, shooting angle and temperature.

[0054] In this step, the three primary color brightness values ​​and the shooting angle of the labeled sample temperature field image are first extracted; and the correlation equation between the three primary color brightness values, the shooting angle and the temperature is constructed based on the two-color temperature measurement method.

[0055] The labeled sample data includes pre-acquired temperature field images shot at multiple different angles of the same target point.

[0056] In this step, a series of temperature field images with temperature annotations need to be collected as training samples. These images should cover different temperature ranges, lighting conditions, and shooting angles to ensure the generalization ability of the model. For each image, use image processing software (such as OpenCV, MATLAB, etc.) to extract the brightness values ​​of its three primary colors (red, green, and blue), and record the angle information when shooting (such as horizontal angle, vertical angle). Then, a data set is constructed based on the recorded data, which contains 100 asphalt pavement temperature field images taken at different time points and under different weather conditions. Each image is accompanied by a corresponding temperature annotation (obtained by contact thermometer measurement). Use the OpenCV library to read these images and extract the brightness values ​​of the three primary colors of red, green, and blue for each image. At the same time, record the shooting angle of each image. For example, the horizontal angle of an image is 30 degrees and the vertical angle is 45 degrees.

[0057] In one embodiment, for the construction of the correlation equation, it is necessary to first clarify the influence coefficient of the shooting angle on the brightness value; specifically, the same target can be photographed from multiple angles to determine the brightness values ​​of the three primary colors at different shooting angles; the multiple shooting angles and their corresponding brightness values ​​of the three primary colors are fitted to determine the angle influence coefficients corresponding to the brightness values ​​of the different primary colors; a two-color temperature measurement formula based on the brightness value and the angle influence coefficient is constructed, and a correction coefficient is added to obtain the correlation equation.

[0058] For example, take photos of the same target from multiple different angles to ensure that each angle can fully display the three primary color characteristics of the target. For each shooting angle, record the brightness values ​​of the three primary colors (red, green, and blue). For the acquired data, first check the data integrity and remove outliers or invalid data. If the brightness values ​​at different angles or different temperatures vary greatly, you can consider standardizing the data to better facilitate subsequent analysis, such as Figure 2 As shown, the changes in the brightness values ​​of RGB (three primary colors) with angles are recorded. Each primary color is then fitted separately, and for each primary color (red, green, blue), a statistical method (such as linear regression, polynomial regression, etc.) is used to fit the relationship between the shooting angle and the brightness value of the primary color. The purpose of this step is to obtain the trend of each primary color brightness value changing with angle, and to obtain the influence factor of the angle on the brightness value. Based on the influence factor, a mathematical model related to the shooting angle (A) can be constructed. The present invention uses linear regression to fit the relationship between angle and brightness value, and then extracts the variation law of the angle influence coefficient. The formula for determining the angle influence coefficient is:

[0059] α i =β0+β1*A;

[0060] Among them, α iis the angular influence coefficient of the i-th primary color, β0 and β1 are the relevant parameters obtained by fitting, and A is the shooting angle.

[0061] Based on the principle of two-color temperature measurement method, adding the above angle influence coefficient and correction coefficient, the relevant relationship can be obtained as follows:

[0062]

[0063] Among them, L1 and L2 are the brightness values ​​of any two primary colors in the three primary colors, K1 and K2 are correction coefficients, λ1 and λ2 are the wavelengths corresponding to L1 and L2, T is the temperature, C2 represents the second radiation constant, ε(λ,T) is a dimensionless parameter representing the spectral emissivity, and α1 and α2 are the angle influence coefficients corresponding to L1 and L2, respectively, determined by the shooting angle. In this way, the angle influence coefficient is added to the two-color temperature measurement method based on the influence of the shooting angle on the brightness value, minimizing the influence of the shooting angle on the brightness value of the three primary colors, which is conducive to improving the accuracy of temperature monitoring.

[0064] S102: Substitute the labeled data of the sample temperature field image into the correlation equation to determine the original parameters of the correlation equation.

[0065] The annotation data includes the brightness values ​​of the three primary colors, the shooting angle, and the corresponding annotation temperature.

[0066] In one embodiment, the constructed correlation equation still needs to be substituted with specific data to determine its parameters. Specifically, the annotated data of the sample temperature field image can be substituted. By substituting multiple sets of annotated data and performing simultaneous elimination, the parameters of the correlation equation can be calculated. It should be noted that to avoid the influence of environmental factors on wavelength, the multiple sets of annotated data need to be screened, and multiple sets of annotated data with the same primary color combination are selected to minimize variables and avoid the influence of unknown factors.

[0067] In addition, theoretically, the parameters calculated for multiple combinations of different primary colors should be the same. However, due to the influence of various external factors, there are errors in the parameters finally calculated for multiple combinations of different primary colors, and thus there is a difference between the predicted temperature and the marked temperature. Therefore, it is necessary to introduce a correction coefficient to correct the error to improve the accuracy of the calculated parameters; the correction coefficient in the correlation equation will be processed later.

[0068] In another embodiment, it is necessary to substitute the brightness values ​​of different primary colors into the correlation to adjust the original parameters of the correlation equation to reduce the error.

[0069] In this step, the original parameters need to be substituted into the correlation equation, and then the correlation equation with the original parameters substituted into it is verified. After the original parameters are substituted into the correlation equation, multiple sets of different dual primary colors with the same labeled temperature of the sample temperature field and their corresponding shooting angles can be input into the correlation equation to obtain the measured temperatures corresponding to the multiple sets of dual primary colors at the same temperature of the sample temperature field image. The difference between the different measured temperatures corresponding to the multiple sets of dual primary colors is used as the loss value, and the original parameters of the correlation equation are adjusted with the goal of minimizing the loss value.

[0070] In addition, for the correction coefficient, in order to improve the accuracy of the final predicted temperature, the correction coefficient is adjusted with the marked temperature as the benchmark and the loss value as the goal; the correction coefficient is obtained when the loss value is minimized and the difference between the measured temperature and the marked temperature is within the preset error range.

[0071] For example, to verify the accuracy of the correlation, you can apply the correlation to new samples with the original parameters and compare the temperature predicted by the model with the actual labeled temperature. Furthermore, to explore the potential of two-color temperature measurement, you can try using any two color combinations—red and green, red and blue, or green and blue—to predict temperature and compare the prediction results for different combinations.

[0072] Specifically, the trained linear regression model can be used to predict the images in the validation set of the sample temperature field image, and the mean square error (MSE) between the predicted temperature and the actual temperature can be calculated. Then, the model can be retrained using the three color groups of red and green, red and blue, and green and blue as features, and their prediction performance can be compared.

[0073] In one embodiment, after inputting specific data of multiple combinations of different dual primary colors, multiple relationship equations between brightness values, shooting angles, and temperatures are obtained. Each relationship equation can be mapped to a unit structure of a neural network, and then the multiple relationship equations can be constructed into a multi-channel neural network, with the difference between the outputs of multiple channels as the loss function. The neural network is then trained through machine learning methods, and the parameters of the neural network are adjusted to complete the parameter adjustment of the relevant relationship equations.

[0074] When the brightness values ​​of the three channels of RGB (three primary colors) of a pixel are known, a relational expression can be constructed for each pixel. If the number of unknowns (i.e., original parameters) in the relational expression is known, the unknowns can be solved theoretically by constructing a relational expression with a corresponding number of pixels at different temperatures. A unit structure can input one pixel at a time, so a multi-channel network model can be constructed by using a parallel unit structure corresponding to the number of unknowns at the same time. Figure 3 As shown, a six-channel network model is constructed.

[0075] Taking the red-blue two-color temperature measurement method and the red-green two-color temperature measurement method as examples, since the temperature values ​​measured by the red-blue two-color temperature measurement method and the red-green two-color temperature measurement method are theoretically equal, the present invention constructs a sub-model for each of the red-blue two-color temperature measurement method and the red-green two-color temperature measurement method according to the mechanism formula. Theoretically, after inputting the brightness value, the two sub-models will output the temperature value, and the temperature values ​​are theoretically equal. However, both sub-models have unknown quantities that need to be trained during construction. Before training, the temperature values ​​output by the two sub-models are not equal, so these two different temperature values ​​will generate a loss value. Using this loss value as a constraint, a multi-channel neural network model is constructed to map the brightness value to the predicted temperature.

[0076] However, using the difference between the temperature values ​​predicted by the two sub-models as the loss value to train the multi-channel neural network model will result in the predicted parameters being proportional parameters of the true parameters. Therefore, it is necessary to adjust the trained parameters based on the original parameters to finally obtain the adjusted correlation equation.

[0077] For example, multiple original parameters can be determined through multiple groups of different dual-primary color brightness values, and the parameters obtained by training can be adjusted. When the sum of the variances of the parameters obtained by training and the multiple original parameters is minimized, the parameters obtained by training can be determined as the adjusted parameters.

[0078] S103: Determine the road surface asphalt temperature of the target road section using the correlation equation.

[0079] Obtain a temperature field image of the target road section's asphalt surface and the actual shooting angle corresponding to the temperature field image. Extract the target three primary color brightness values ​​of the target road section's asphalt surface temperature field image. Substitute the target three primary color brightness values ​​and the actual shooting angle into the correlation equation to obtain the target road section's asphalt surface temperature.

[0080] In this step, you can use a drone or a fixed-point camera to capture temperature field images of the target road section and record the angle of capture. These images will be used for subsequent temperature prediction. For example, you can use a drone to take aerial photos of a section of highway, or use an image acquisition device fixed at a specific point to capture the temperature field images of the asphalt surface on the highway. At the same time, record the drone's flight altitude, heading, and other information to facilitate subsequent calculation of the capture angle.

[0081] Image processing software is then used to extract the brightness values ​​of the three primary colors of the target image. These values, along with the shooting angle, are then substituted into the adjusted correlation equation to obtain the temperature distribution of the target road section. For example, the OpenCV library can be used to extract the red, green, and blue brightness values ​​of a temperature field image captured by a drone. These values, along with the calculated shooting angle, are then substituted into the adjusted correlation equation to obtain the temperature value of each pixel, thereby generating a temperature distribution map for the entire road section.

[0082] For example, the brightness values ​​of any two of the three target primary colors of the temperature field image are extracted as a group, and multiple groups of brightness values ​​and the corresponding actual shooting angles are substituted into the calculation to obtain multiple groups of monitoring temperatures; the average of the multiple groups of monitoring temperatures is used as the temperature of the asphalt surface of the target road section.

[0083] The temperature distribution map of the entire road section can also be drawn into a two-dimensional diagram of road section-temperature or temperature-time for the same road section, so that relevant personnel can have a more intuitive understanding of the asphalt temperature on the surface of the target road section.

[0084] Using the above method, first, relevant data of the sample temperature field image is obtained, and then the principle of the two-color temperature measurement method is used to construct a correlation formula, which can associate the brightness value information and shooting angle in the image with the temperature. In this way, based on the actual situation of large-scale monitoring of the monitoring instrument, an improvement is made on the basis of the two-color temperature measurement method. When the monitoring instrument at a fixed point performs large-scale temperature collection, the influence of the angle problem on the accuracy of temperature monitoring can be eliminated, so that the monitoring instrument can avoid the influence of the angle factor in large-scale temperature collection, which is beneficial to improving the accuracy of temperature monitoring of highway asphalt paving and improving the monitoring effect of the monitoring instrument on road asphalt temperature monitoring.

[0085] Secondly, the present invention also provides a road surface asphalt temperature monitoring device, such as Figure 4 Shown, including:

[0086] The extraction module 401 is used to extract the three primary color brightness values ​​of the labeled sample temperature field image and the shooting angle of the sample temperature field image.

[0087] The construction module 402 is used to construct a correlation equation among the brightness values ​​of the three primary colors, the shooting angle and the temperature based on the two-color temperature measurement method.

[0088] The determination module 403 is used to substitute the annotated data of the sample temperature field image into the correlation equation to determine the original parameters of the correlation equation; the annotated data includes the brightness values ​​of the three primary colors, the shooting angle and the corresponding annotated temperature.

[0089] The acquisition module 404 is used to acquire a temperature field image of the asphalt on the surface of the target road section and a shooting angle corresponding to the temperature field image.

[0090] The measurement module 405 is used to extract the target three primary color brightness values ​​of the temperature field image of the target road section surface asphalt, substitute the target three primary color brightness values ​​and the actual shooting angle into the correlation formula to obtain the temperature of the target road section surface asphalt.

[0091] By using the above device, first, relevant data of the sample temperature field image is obtained, and then the principle of the two-color temperature measurement method is used to construct a correlation formula, which can associate the brightness value information and shooting angle in the image with the temperature. In this way, based on the actual situation of large-scale monitoring of the monitoring instrument, improvements are made on the basis of the two-color temperature measurement method. When the monitoring instrument at a fixed point performs large-scale temperature collection, the influence of the angle problem on the accuracy of temperature monitoring can be eliminated, so that the monitoring instrument can avoid the influence of the angle factor in large-scale temperature collection, which is beneficial to improving the accuracy of temperature monitoring of highway asphalt paving; improving the monitoring effect of the monitoring instrument on road asphalt temperature monitoring.

[0092] The present invention also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 The present invention provides steps for a method for monitoring the temperature of asphalt on a highway surface.

[0093] The present invention also provides a computer device. At the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The present invention provides steps for a method for monitoring the temperature of asphalt on a highway surface.

[0094] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0098] It should be noted that the above specific embodiments can enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although this specification has described the present invention in detail, those skilled in the art should understand that the present invention can still be modified or replaced with equivalents; and all technical solutions and improvements that do not depart from the spirit and scope of the present invention are included in the scope of protection of the patent for the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A method for monitoring the temperature of asphalt on a highway surface, characterized in that: The method comprises: Extract the three primary color brightness values ​​of the labeled sample temperature field image and the shooting angle of the sample temperature field image; Based on the two-color temperature measurement method, the correlation equation between the brightness value of the three primary colors, the shooting angle and the temperature is constructed; Substituting the labeled data of the sample temperature field image into the correlation equation to determine the original parameters of the correlation equation; the labeled data includes the brightness values ​​of the three primary colors, the shooting angle, and the corresponding labeled temperature; Acquire the temperature field image of the asphalt on the target road section surface and the actual shooting angle corresponding to the temperature field image; Extracting target three-primary color brightness values ​​of the temperature field image of the asphalt on the target road section surface, substituting the target three-primary color brightness values ​​and the actual shooting angle into a correlation formula to obtain the temperature of the asphalt on the target road section surface; The related relationship is: ; in, and are the brightness values ​​of any two primary colors in the three primary colors, and are the correction coefficients, and Corresponding to and The wavelength, is the temperature, C2 represents the second radiation constant, is a dimensionless parameter representing the spectral emissivity, α 1 and α 2 are respectively determined by the shooting angle corresponding to and The angular influence coefficient of .

2. A method for monitoring the temperature of asphalt on a road surface according to claim 1, characterized in that: The correlation equation between the brightness values ​​of the three primary colors, the shooting angle and the temperature constructed based on the two-color temperature measurement method includes: Shoot the same target from multiple angles and determine the brightness values ​​of the three primary colors at different shooting angles; Fit multiple shooting angles and their corresponding three primary color brightness values ​​to determine the angle influence coefficients corresponding to different primary color brightness values; The two-color temperature measurement formula based on brightness value and angle influence coefficient is constructed, and the correction coefficient is added to obtain the relevant relationship.

3. A method for monitoring the temperature of asphalt on a road surface according to claim 2, characterized in that: The formula for determining the angle influence coefficient is: α i =β 0 +β 1* A ； in, α i is the angular influence coefficient of the i-th primary color, β 0 and β 1 are the relevant parameters obtained by fitting, A It's the shooting angle.

4. A method for monitoring the temperature of asphalt on a road surface according to claim 1, characterized in that: Before substituting the target three primary color brightness values ​​and the actual shooting angle into the correlation equation, the parameters of the correlation equation are adjusted, including: Substituting the original parameters into the correlation equation for verification, we can obtain the measured temperatures corresponding to multiple sets of dual primary colors of the sample temperature field image. The difference between different measured temperatures corresponding to the multiple sets of dual primary colors is used as a loss value, and the original parameters of the correlation equation are adjusted with the goal of minimizing the loss value.

5. A method for monitoring the temperature of asphalt on a road surface according to claim 4, characterized in that: The method of using the difference between different measured temperatures corresponding to the multiple sets of dual primary colors as the loss value and adjusting the original parameters of the correlation equation with the goal of minimizing the loss value includes: Taking the marked temperature as a reference and minimizing the loss value as a goal, adjusting the correction coefficient; The correction coefficient is obtained when the loss value is minimum and the difference between the measured temperature and the marked temperature is within a preset error range.

6. A method for monitoring the temperature of asphalt on a road surface according to claim 1, characterized in that: Substituting the target three primary color brightness values ​​and the actual shooting angle into the relevant equation, the temperature of the target road section surface asphalt is obtained: The brightness values ​​of any two primary colors in the target three primary colors of the temperature field image are extracted as a group. Multiple groups of brightness values ​​and corresponding actual shooting angles are substituted into the calculation to obtain multiple groups of monitored temperatures. The average of multiple groups of monitored temperatures is used as the surface asphalt temperature of the target road section.

7. A road surface asphalt temperature monitoring device, characterized in that: The device comprises: An extraction module is used to extract the three primary color brightness values ​​of the labeled sample temperature field image and the shooting angle of the sample temperature field image; A construction module is used to construct a correlation equation among the brightness values ​​of the three primary colors, the shooting angle, and the temperature based on the two-color temperature measurement method; wherein the correlation equation is: ; in, and are the brightness values ​​of any two primary colors in the three primary colors, and are the correction coefficients, and Corresponding to and The wavelength, is the temperature, C2 represents the second radiation constant, is a dimensionless parameter representing the spectral emissivity, α 1 and α 2 are respectively determined by the shooting angle corresponding to and Angle influence coefficient; A determination module is used to substitute the annotated data of the sample temperature field image into the correlation equation to determine the original parameters of the correlation equation; the annotated data includes the brightness values ​​of the three primary colors, the shooting angle, and the corresponding annotated temperature; An acquisition module is used to acquire a temperature field image of the asphalt on the target road surface and an actual shooting angle corresponding to the temperature field image; The measurement module is used to extract the target three primary color brightness values ​​of the temperature field image of the asphalt on the target road section surface, substitute the target three primary color brightness values ​​and the actual shooting angle into the correlation formula, and obtain the temperature of the asphalt on the target road section surface.

8. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

Images