A method, system and device for detecting asphalt temperature segregation

Abstract

The present application belongs to the technical field of asphalt paving segregation detection, and particularly relates to an asphalt temperature segregation detection method, system and device. The method comprises the following steps: S1, acquiring an asphalt infrared image; S2, performing superpixel processing on the asphalt infrared image by using a multi-scale morphological watershed algorithm to obtain a superpixel image; S3, performing clustering processing on the superpixel image by using a K-Means clustering algorithm to obtain a plurality of segmentation regions; S4, processing each segmentation region by using an FCM clustering algorithm to generate a fuzzy label, and merging the fuzzy label into the superpixel image as a segmentation result; and S5, extracting the temperatures of different points in the partition, and judging whether there is segregation in the corresponding partition according to the temperatures. The present application can improve positioning accuracy, thereby meeting the requirements of asphalt temperature detection during the paving process.

Description

Technical Field

[0001] This invention belongs to the field of asphalt paving segregation detection technology, specifically relating to an asphalt temperature segregation detection method, system and device. Background Technology

[0002] Temperature segregation is one of the important reasons for the decline in road construction quality. Due to its complex distribution and indistinguishability to the naked eye, the detection and location of temperature segregation are becoming increasingly important.

[0003] Traditional methods for detecting asphalt temperature segregation mainly include the following two types: One is the mercury thermometer method. This method has advantages such as simple structure and low cost, but its measurement time is as long as tens of seconds, the response speed is slow, and the temperature reading is subject to human error. It also poses certain dangers and can easily cause harm to the human body. Therefore, it is usually used as an instrument for on-site monitoring. The other is the thermocouple digital display thermometer method. The thermocouple digital display thermometer mainly consists of two parts: a measuring end and a reference end. When there is a temperature difference between the two ends, a current is generated in the circuit. Since the magnitude of the current is related to the temperature difference between the two ends, the temperature of the measuring end can be determined based on the temperature difference. However, this method suffers from rapid material consumption, and the temperature of the reference end cannot be kept constant, which affects the measurement accuracy.

[0004] With the development of infrared imaging technology, temperature measurement methods based on infrared thermal imagers have been increasingly used in various non-destructive testing fields. Infrared thermal imaging technology, with its numerous advantages such as non-contact temperature measurement, small instrument size, weak environmental influence, and fast response speed, has been gradually applied in highway construction, primarily for temperature detection of hot-mix asphalt to detect temperature segregation during asphalt paving. However, in actual engineering applications, the infrared image of asphalt is affected by the complex texture of the asphalt pavement, resulting in a highly dispersed temperature distribution. Therefore, commonly used asphalt temperature segregation detection methods can only detect temperature segregation phenomena existing in small areas. Furthermore, since existing detection methods are usually based on data fitting, they require extensive data post-processing and cannot achieve real-time detection during asphalt paving, thus failing to suppress asphalt temperature segregation at its source.

[0005] In summary, while infrared thermal imaging-based asphalt temperature segregation detection methods can address the limitations of traditional methods, such as "point measurement" and "high risk," the results are typically localized and discontinuous. They cannot provide real-time measurement of pavement temperature during asphalt paving or accurately pinpoint areas of temperature segregation. Therefore, researching methods to improve the precision and online capabilities of asphalt temperature segregation detection is crucial for extending road life and protecting driving safety. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a method, system and device for detecting asphalt temperature segregation, which can improve the positioning accuracy and thus meet the requirements for asphalt temperature detection during the paving process.

[0007] This invention is implemented as follows: This invention provides a method for detecting asphalt temperature segregation, comprising the following steps:

[0008] S1. Acquire infrared images of asphalt;

[0009] S2. The asphalt infrared image is processed by a multi-scale morphological watershed algorithm to obtain a superpixel image.

[0010] S3. The superpixel image is clustered using the K-Means clustering algorithm to obtain multiple segmented regions;

[0011] S4. The FCM clustering algorithm is used to process each segmented region, generate fuzzy labels, and merge the fuzzy labels into the superpixel image as the segmentation result;

[0012] S5. Extract the temperature of different points within the partition, and determine whether segregation exists in the corresponding partition based on the temperature.

[0013] Furthermore, step S2 includes the following sub-steps:

[0014] S201. Construct a multi-scale morphological gradient image based on the asphalt infrared image;

[0015] S202. Divide the multi-scale morphological gradient image into different regions and select the water injection point in each region;

[0016] S203. Assign a unique label to each water injection point in the region and perform simulated water injection to obtain the expanded region;

[0017] S204. When there are boundaries between the extended regions corresponding to different regions, a superpixel image is obtained.

[0018] Furthermore, the calculation formula for constructing the multi-scale morphological gradient image is as follows:

[0019] ;

[0020] In the above formula, R represents the result of multi-scale morphological gradient calculation. f Let g represent the asphalt infrared image, r represent the morphological convolution kernel size, and r∈(r1,r2);

[0021] The formula for calculating the water injection point is:

[0022] ;

[0023] In the above formula, M represents the water injection point, I represents the morphological gradient image, p represents the current pixel point, and q represents the points within the set neighborhood N(p).

[0024] The formula for calculating the extended region is:

[0025] ;

[0026] In the above formula, R k (h) indicates the extended region, pm k Indicates the distance from p to m k The path, m k This represents the minimum value in each region, indicating the water level.

[0027] The formula for calculating the boundary is:

[0028] ;

[0029] In the above formula, B represents the boundary, and L(p) represents that pixel p belongs to the local minimum m. k The starting area.

[0030] Furthermore, step S3 includes the following sub-steps:

[0031] S301. For each superpixel in the superpixel image, calculate its average gray value;

[0032] S302. For each superpixel, calculate the positional features of its set center;

[0033] S303. Randomly select several initial centers from the features of the superpixel as initial cluster centers;

[0034] S304. For each superpixel in the superpixel image, calculate the distance between its features and each cluster center, and assign the superpixel to the nearest cluster center based on the calculation results.

[0035] S305. Recalculate each cluster center by extracting the average feature value of all superpixels belonging to the cluster. If the center reaches the preset range or the preset number of iterations, proceed to S306; otherwise, proceed to S304.

[0036] S306. Aggregate the superpixel images of each cluster center into a region to obtain the segmented region.

[0037] Furthermore, the formula for calculating the average grayscale value is as follows:

[0038] ;

[0039] In the above formula, Cavg c represents the average value. i Let N represent the grayscale value of the i-th pixel, and N represent the number of superpixels in the entire image.

[0040] The formula for calculating the location feature is:

[0041] ;

[0042] In the above formula, (x centroid ,y centroid ) represents the location feature, (x i ,y i ) represents the position of the i-th pixel in the superpixel;

[0043] The formula for calculating the distance is:

[0044] ;

[0045] In the above formula, d(j,k) represents the distance between the j-th superpixel and the k-th center, and f j Let f represent the feature of the j-th superpixel. k Describe the feature of the k-th center, (x cj ,y cj (x) represents the center location feature of the j-th superpixel. ck ,y ck ) represents the central position feature of the k-th center point;

[0046] The formula for calculating the cluster centers is:

[0047] ;

[0048] In the above formula, μ k S represents the cluster center. k This represents the set of all superpixels assigned to k cluster centers.

[0049] Furthermore, step S4 includes the following sub-steps:

[0050] S401. Set clustering parameters, including the number of clusters and fuzzy coefficients;

[0051] S402. For each segmented region obtained by K-Means, select several points from that region as the initial cluster centers for FCM clustering.

[0052] S403. Calculate the membership degree of each point in each segmented region to each cluster center;

[0053] S404. Update the centroid by maximizing the membership degree so that the centroid position has the optimal representation for the data points in the current cluster. If the change in membership degree center is less than the preset threshold during iteration, proceed to S405; otherwise, repeat this step.

[0054] S405. Merge the cluster labels with the best membership degree and display them in the target image as the segmentation result.

[0055] Furthermore, the formula for calculating the membership degree is as follows:

[0056] ;

[0057] In the above formula, x i This represents the superpixel feature vector within each region, including color and spatial coordinates, i.e., the x-coordinate of the i-th pixel, v. j This represents the cluster center of the j-th cluster. v k Indicates the first k There are cluster centers for each class, where c represents the number of clusters and m represents the fuzzy coefficient.

[0058] The formula for calculating the cluster centers is:

[0059] ;

[0060] In the above formula, N represents the number of superpixels in this type.

[0061] Furthermore, step S5 includes the following sub-steps:

[0062] S501. Calculate the average temperature value of the center point of each superpixel in the segmented region, and use it as the representative temperature value of the segmented region;

[0063] S502. Calculate the temperature difference between different segmented regions based on the representative temperature value;

[0064] S503. Determine whether the temperature interpolation exceeds the temperature difference threshold for temperature segregation. If it does, determine that temperature segregation has occurred; otherwise, determine that temperature segregation has not occurred.

[0065] Based on the same inventive concept, the present invention also provides an asphalt temperature segregation detection system, comprising:

[0066] The acquisition module is used to acquire infrared images of asphalt.

[0067] The superpixel processing module is used to perform superpixel processing on the asphalt infrared image using a multi-scale morphological watershed algorithm to obtain a superpixel image.

[0068] The segmentation module is used to cluster the superpixel image using the K-Means clustering algorithm to obtain multiple segmented regions;

[0069] The merging module is used to process each segmented region using the FCM clustering algorithm, generate fuzzy labels, and merge the fuzzy labels into the superpixel image as the segmentation result;

[0070] The judgment module is used to extract the temperature of different points within the partition and determine whether segregation exists in the corresponding partition based on the temperature.

[0071] Based on the same inventive concept, the present invention also provides an asphalt temperature segregation detection device, including a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the steps of the above method.

[0072] The beneficial effects of this invention are:

[0073] 1) This invention improves the watershed superpixel algorithm by using multi-scale morphology, which reduces the number of temperature regions in asphalt infrared images while ensuring the correctness of the boundaries, thereby improving the usability of the images.

[0074] 2) This invention utilizes K-Means and FCM clustering methods to segment superpixels. The method starts from the pixel and optimizes segmentation accuracy and efficiency while eliminating the dependence of existing image segmentation methods on large datasets, thus improving the practical engineering application value of infrared image processing technology in temperature segregation detection.

[0075] 3) This invention helps to realize online detection of asphalt temperature segregation, thereby fundamentally reducing the probability of asphalt segregation events. Attached Figure Description

[0076] Figure 1 This is a flowchart of the method in this invention;

[0077] Figure 2 This is a demonstration image of infrared images of asphalt with temperature segregation detected using the method of the present invention.

[0078] Figure 3 This is a demonstration image of infrared images of asphalt without temperature segregation detected using the method of this invention.

[0079] Figure 4 This is a schematic diagram of the detection results in this invention. Detailed Implementation

[0080] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0081] Example 1: As Figure 1As shown in the figure, this embodiment discloses a method for detecting asphalt temperature segregation, including the following steps:

[0082] S1. Obtain an infrared image of asphalt.

[0083] S2. The asphalt infrared image is processed using a multi-scale morphological watershed algorithm to obtain a superpixel image. Specifically, this step includes the following sub-steps:

[0084] S201. Construct a multi-scale morphological gradient image based on the asphalt infrared image. This step includes the following sub-steps: First, set the morphological convolution kernel to a circle of size r, where r∈(r1,r2). According to cross-validation, r1=2 and r2=50 here. Then, calculate the morphological gradient image based on morphological operations and obtain the union of the morphological gradient images. The specific calculation formula is as follows: ;

[0085] In the above formula, R represents the result of multi-scale morphological gradient calculation. f represents morphological operations, and g represents the infrared image of asphalt.

[0086] S202. According to the watershed algorithm, the multi-scale morphological gradient image is divided into different regions, and the minimum value of each region is selected as the water injection point M. The minimum value of a region can be defined as the set of pixels in the morphological gradient image I that satisfy the following conditions:

[0087] ;

[0088] In the above formula, p represents the current pixel point, and q represents the points within the set neighborhood N(p).

[0089] S203. Assign a unique label to each water injection point in the region and define a label image L. Then, simulate water injection starting from the minimum value of the label, first setting the maximum water level h. max =256, gradually increasing from the lowest grayscale value. For each water level h, the expanded region R k The formula for calculating (h) is:

[0090] ;

[0091] In the above formula, pm k Indicates the distance from p to m k The path, m k This represents the minimum value for each region.

[0092] S204. When different regions share a common pixel p in their corresponding extended regions, denoted as boundary B, a superpixel image is obtained. The formula for calculating boundary B is:

[0093] ;

[0094] In the above formula, L(p) indicates that pixel p belongs to a local minimum m. k The starting area.

[0095] S3. The superpixel image is clustered using the K-Means clustering algorithm to obtain multiple segmented regions. This step includes the following sub-steps:

[0096] S301. For each superpixel in the superpixel image, calculate its average gray value. Since the superpixelated image is a grayscale image with only one average gray value, the average value C is... avg The calculation formula is:

[0097] ;

[0098] In the above formula, c i Let N represent the grayscale value of the i-th pixel, and N represent the number of superpixels in the entire image.

[0099] S302. For each superpixel, calculate the positional feature of its set center. The formula for calculating the positional feature is:

[0100] ;

[0101] In the above formula, (x centroid ,y centroid ) represents the location feature, (x i ,y i ) represents the position of the i-th pixel in the superpixel.

[0102] S303. Randomly select several initial centers from the features of the superpixels as initial cluster centers. In this example, since it is mainly used to determine whether the asphalt infrared image has temperature segregation, the final segmented region is 2. Therefore, randomly select k=2 initial centers, which are features of the superpixels.

[0103] S304. For each superpixel in the superpixel image, calculate the distance between its features and each cluster center, and assign the superpixel to the nearest cluster center based on the calculation results. The formula for calculating the distance is:

[0104] ;

[0105] In the above formula, d(j,k) represents the distance between the j-th superpixel and the k-th center, and f j Let f represent the feature of the j-th superpixel. k Describe the feature of the k-th center, (x cj ,y cj(x) represents the center location feature of the j-th superpixel. ck ,y ck ) represents the central position feature of the k-th center point.

[0106] S305. Recalculate each cluster center by extracting the average feature value of all superpixels belonging to that cluster. If the center reaches a preset range or a preset number of iterations, proceed to S306; otherwise, proceed to S304. The formula for calculating the cluster center is:

[0107] ;

[0108] In the above formula, μ k S represents the cluster center. k This represents the set of all superpixels assigned to the k cluster centers. In this example, the number of iterations is 200.

[0109] S306. Aggregate the superpixel images of each cluster center into one region to obtain two segmentation regions.

[0110] S4. The FCM clustering algorithm is used to process each segmented region, generating blurred labels, and these blurred labels are merged into the superpixel image as the segmentation result. This step includes the following sub-steps:

[0111] S401. Set clustering parameters: set the number of clusters c=2 and the fuzzy coefficient m=2.

[0112] S402. Select two points in each segmented region as cluster centers.

[0113] S403. Calculate the membership degree from each point within each segmented region to each cluster center. The formula for calculating the membership degree is:

[0114] ;

[0115] In the above formula, x i This represents the superpixel feature vector within each region, including color and spatial coordinates, i.e., the x-coordinate of the i-th pixel, v. j Let v represent the cluster center of the j-th cluster. k Let represent the cluster center of the kth cluster, c represent the number of clusters, and m represent the fuzzy coefficient.

[0116] S404. Update the centroid by maximizing the membership degree, so that the centroid position has the optimal representation for the data points in the current cluster. If the change in membership degree is less than a preset threshold during iteration, proceed to S405; otherwise, repeat this step. The formula for calculating the cluster center is:

[0117] In the above formula, N represents the number of superpixels in this class. In this example, the preset threshold is 0.005.

[0118] S405. Merge the cluster labels with the best membership degree and display them in the target image as the segmentation result.

[0119] S5. Extract the temperature of different points within the partition, and determine whether segregation exists in the corresponding partition based on the temperature. This step includes the following sub-steps:

[0120] S501. Calculate the average temperature value of the center point of each superpixel in the segmented region, and use it as the representative temperature value of the segmented region.

[0121] S502. Calculate the temperature difference between different segmented regions based on the representative temperature value.

[0122] S503. Determine whether the temperature interpolation exceeds the temperature difference threshold for temperature segregation. If it does, temperature segregation is determined to have occurred; otherwise, it is determined that temperature segregation has not occurred. Based on the physical parameters of the asphalt mixture, the temperature difference threshold for determining the presence of temperature segregation is determined to be 10℃. The asphalt mixture parameters are shown in Table 1:

[0123] Table 1: Temperature Requirements for Asphalt and Aggregates

[0124] project Temperature requirement (°C) Asphalt heating temperature 170 Aggregate heating temperature 180 discharge temperature range 170-180 The mixture is transported to the site at the specified temperature range. 165-175 Temperature requirements during paving process >60

[0125] Figure 2 and Figure 3 Demonstration images of infrared images with and without temperature segregation are shown. To verify the effectiveness of the method of this invention, 200 infrared images of asphalt were selected for temperature segregation detection, including 100 images with temperature segregation and 100 images without temperature segregation. Figure 4 As shown, temperature-segregated and non-temperature-segregated samples are labeled with the numbers -1 and 1, respectively. Of the 200 test images, 195 samples were correctly classified, resulting in an accuracy of 97.5% for this experiment.

[0126] Example 2: Based on the same inventive concept, the present invention also provides an asphalt temperature segregation detection system, comprising:

[0127] The acquisition module is used to acquire infrared images of asphalt.

[0128] The superpixel processing module is used to perform superpixel processing on the asphalt infrared image using a multi-scale morphological watershed algorithm to obtain a superpixel image.

[0129] The segmentation module is used to cluster the superpixel image using the K-Means clustering algorithm to obtain multiple segmented regions;

[0130] The merging module is used to process each segmented region using the FCM clustering algorithm, generate fuzzy labels, and merge the fuzzy labels into the superpixel image as the segmentation result;

[0131] The judgment module is used to extract the temperature of different points within the partition and determine whether segregation exists in the corresponding partition based on the temperature.

[0132] Example 3: Based on the same inventive concept, the present invention also provides an asphalt temperature segregation detection device, including a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the steps of the above method.

[0133] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for detecting asphalt temperature segregation, characterized in that, Includes the following steps: S1. Acquire infrared images of asphalt; S2. The asphalt infrared image is processed using a multi-scale morphological watershed algorithm to obtain a superpixel image; S2 includes the following sub-steps: S201. Construct a multi-scale morphological gradient image based on the asphalt infrared image; S202. Divide the multi-scale morphological gradient image into different regions and select the water injection point in each region; S203. Assign a unique label to each water injection point in the region and perform simulated water injection to obtain the expanded region; S204. When there are boundaries between the extended regions corresponding to different regions, a superpixel image is obtained; S3. The superpixel image is clustered using the K-Means clustering algorithm to obtain multiple segmented regions; S3 includes the following sub-steps: S301. For each superpixel in the superpixel image, calculate its average gray value; S302. For each superpixel, calculate the positional features of its set center; S303. Randomly select several initial centers from the features of the superpixel as initial cluster centers; S304. For each superpixel in the superpixel image, calculate the distance between its features and each cluster center, and assign the superpixel to the nearest cluster center based on the calculation results. S305. Recalculate each cluster center by extracting the average feature value of all superpixels belonging to the cluster. If the center reaches the preset range or the preset number of iterations, proceed to S306; otherwise, proceed to S304. S306. Aggregate the superpixel images of each cluster center into a region to obtain the segmented region; S4. The FCM clustering algorithm is used to process each segmented region, generate fuzzy labels, and merge the fuzzy labels into the superpixel image as the segmentation result; S5. Extract the temperature of different points within the partition, and determine whether segregation exists in the corresponding partition based on the temperature.

2. The method for detecting asphalt temperature segregation according to claim 1, characterized in that, The calculation formula for constructing a multi-scale morphological gradient image is as follows: ； In the above formula, R represents the result of multi-scale morphological gradient calculation. f Let g represent the asphalt infrared image, r represent the morphological convolution kernel size, and r∈(r1,r2); The formula for calculating the water injection point is: ； In the above formula, M represents the water injection point, I represents the morphological gradient image, p represents the current pixel point, and q represents the points within the set neighborhood N(p). The formula for calculating the extended region is: ； In the above formula, R k (h) indicates the extended region, pm k Indicates the distance from p to m k The path, m k This represents the minimum value in each region, indicating the water level. The formula for calculating the boundary is: ； In the above formula, B represents the boundary, and L(p) represents that pixel p belongs to the local minimum m. k The starting area.

3. The method for detecting asphalt temperature segregation according to claim 1, characterized in that, The formula for calculating the average grayscale value is: ； In the above formula, C avg c represents the average value. i Let N represent the grayscale value of the i-th pixel, and N represent the number of superpixels in the entire image. The formula for calculating the location feature is: ； In the above formula, (x centroid ,y centroid ) represents the location feature, (x i ,y i ) represents the position of the i-th pixel in the superpixel; The formula for calculating the distance is: ； In the above formula, d(j,k) represents the distance between the j-th superpixel and the k-th center, and f j Let f represent the feature of the j-th superpixel. k Describe the feature of the k-th center, (x cj ,y cj (x) represents the center location feature of the j-th superpixel. ck ,y ck ) represents the central position feature of the k-th center point; The formula for calculating the cluster centers is: ； In the above formula, μ k S represents the cluster center. k This represents the set of all superpixels assigned to k cluster centers.

4. The method for detecting asphalt temperature segregation according to claim 1, characterized in that, S4 includes the following sub-steps: S401. Set clustering parameters, including the number of clusters and fuzzy coefficients; S402. For each segmented region obtained by K-Means, select several points from that region as the initial cluster centers for FCM clustering. S403. Calculate the membership degree of each point in each segmented region to each cluster center; S404. Update the centroid by maximizing the membership degree so that the centroid position has the optimal representation for the data points in the current cluster. If the change in membership degree center is less than the preset threshold during iteration, proceed to S405; otherwise, repeat this step. S405. Merge the cluster labels with the best membership degree and display them in the target image as the segmentation result.

5. The method for detecting asphalt temperature segregation according to claim 4, characterized in that, The formula for calculating the membership degree is: ； In the above formula, x i This represents the superpixel feature vector within each region, including color and spatial coordinates, i.e., the x-coordinate of the i-th pixel, v. j This represents the cluster center of the j-th cluster. v k Indicates the first k There are cluster centers for each class, where c represents the number of clusters and m represents the fuzzy coefficient. The formula for calculating the cluster centers is: ； In the above formula, N represents the number of superpixels in this type.

6. The method for detecting asphalt temperature segregation according to claim 1, characterized in that, S5 includes the following sub-steps: S501. Calculate the average temperature value of the center point of each superpixel in the segmented region, and use it as the representative temperature value of the segmented region; S502. Calculate the temperature difference between different segmented regions based on the representative temperature value; S503. Determine whether the temperature interpolation exceeds the temperature difference threshold for temperature segregation. If it does, determine that temperature segregation has occurred; otherwise, determine that temperature segregation has not occurred.

7. A system for detecting asphalt temperature segregation, characterized in that, include: The acquisition module is used to acquire infrared images of asphalt. The superpixel processing module is used to perform superpixel processing on the asphalt infrared image using a multi-scale morphological watershed algorithm to obtain a superpixel image; this module performs the following sub-steps: Construct a multi-scale morphological gradient image based on the asphalt infrared image; The multi-scale morphological gradient image is divided into different regions, and water injection points are selected in each region; A unique label is assigned to each water injection point in the region, and a simulated water injection operation is performed to obtain the expanded region; When there are boundaries between the extended regions corresponding to different regions, a superpixel image is obtained; The segmentation module is used to cluster the superpixel image using the K-Means clustering algorithm to obtain multiple segmented regions; this module performs the following steps: For each superpixel in the superpixel image, calculate its average gray value; For each superpixel, calculate the positional features of its set center; Several initial centers are randomly selected from the features of the superpixels as initial cluster centers; For each superpixel in the superpixel image, calculate the distance between its features and each cluster center, and assign the superpixel to the nearest cluster center based on the calculation results; Recalculate each cluster center by extracting the average feature value of all superpixels belonging to the cluster. If the center reaches a preset range or a preset number of iterations, proceed to the next step; otherwise, proceed to the previous step. The superpixel images of each cluster center are aggregated into a region to obtain the segmented region; The merging module is used to process each segmented region using the FCM clustering algorithm, generate fuzzy labels, and merge the fuzzy labels into the superpixel image as the segmentation result; The judgment module is used to extract the temperature of different points within the partition and determine whether segregation exists in the corresponding partition based on the temperature.

8. A device for detecting asphalt temperature segregation, characterized in that, It includes a processor and a memory, the memory being used to store a computer program, and the processor being used to execute the computer program to implement the steps of the method of claim 1.

Images