Image processing-based seal coat and crushed stone spreading quality identification method

Abstract

The application discloses a seal coat chip spreading quality identification method based on image processing and belongs to the field of road engineering chip seal, which comprises the following steps: obtaining high-quality seal coat chip spreading images; pre-processing the seal coat chip spreading images to obtain binary images, wherein the white area is the chip; calculating the proportion of chip pixels in the binary image, i.e., the chip spreading rate, based on the built-in pixel calculation function of OpenCV; detecting the largest inscribed rectangle of the black area based on the image processing tool to obtain the area S of the largest inscribed rectangle, which represents the largest area of the chip that is not spread; and establishing a comprehensive evaluation system for the quality of chip spreading to evaluate the spreading quality of the seal coat chip. The method provided by the application is convenient and efficient and does not damage the seal coat chip in the detected area.

Description

Technical Field

[0001] This invention belongs to the field of road engineering chip seal technology, and particularly relates to a method for identifying the quality of chip seal application based on image processing. Background Technology

[0002] Chip seal, as a waterproof bonding layer, is widely used in the construction and maintenance of asphalt pavements. It effectively bonds the asphalt pavement surface layer to the base layer, providing waterproofing and enhancing the overall strength of the pavement. The construction quality of the seal significantly affects the service level of the entire pavement in the later stages. The most crucial factor is the quality of the chip seal application, which includes the chip distribution rate. Currently, the quality of chip distribution can only be roughly judged visually, which is highly subjective; alternatively, the distribution rate can be estimated by weighing the chip distribution per unit area using sampling methods. This is not only time-consuming and labor-intensive but also leaves untreated areas, creating potential problems for the overall construction quality. To improve the efficiency and effectiveness of identifying the chip seal application quality, some researchers have optimized equipment and methods based on existing traditional approaches, but these still degrade the chip seal within the detection area. Summary of the Invention

[0003] This invention proposes an image processing-based method for identifying the quality of sealing gravel spraying, in order to solve the technical problems existing in the prior art.

[0004] To achieve the above objectives, the present invention provides a method for identifying the quality of capping gravel spraying based on image processing, comprising:

[0005] Acquire a high-quality image of the seal layer gravel spraying; preprocess the seal layer gravel spraying image to obtain a binarized image, wherein the white area of ​​the binarized image represents gravel;

[0006] Based on OpenCV's built-in pixel calculation function, the proportion of white areas in the binary image relative to the total number of pixels is calculated, i.e., the gravel spillage rate.

[0007] Based on the image detection algorithm, the largest inscribed rectangle of the black area in the binarized image is detected to obtain the area of ​​the largest area where the gravel was not scattered.

[0008] The quality of the sealing layer crushed stone is evaluated based on the crushed stone coverage rate and the maximum area of ​​uncovered crushed stone.

[0009] Preferably, the process of obtaining high-quality images of the seal layer gravel spray includes:

[0010] A detection auxiliary device is constructed, which is a folding box with pointed legs. The pointed legs fix the detection auxiliary device to the gravel sealing layer. A light-blocking curtain that can block external light sources is set on the outside of the pointed legs. A telescopic vertical folding rod is connected to the pointed legs. A horizontal rod with a camera hole is set at the other end of the vertical folding rod. The camera hole is used to connect a camera device. A spotlight that provides a light source is set at the vertical angle between the vertical folding rod and the horizontal rod.

[0011] Preferably, the process of acquiring high-quality images of the seal layer gravel spray includes:

[0012] After selecting the detection area, pull up the folding box of the detection auxiliary device, insert the pointed support legs into the sprayed gravel seal layer, lower the light-blocking curtain, connect the camera device through the camera hole, turn on the spotlight, and use the camera device to obtain a high-quality image of the gravel seal layer spraying.

[0013] Preferably, the preprocessing of the sealing gravel spray image includes:

[0014] The image of the sealing gravel spray is denoised and enhanced by mean shifting in Gaussian filtering and edge-preserving filtering to obtain an enhanced image. The enhanced image is then binarized to obtain a binarized image.

[0015] Preferably, the process for evaluating the quality of the sealing chip application includes:

[0016] A design threshold for the gravel spreading rate is set. Based on the design threshold, the gravel spreading rate at each measuring point is judged to be qualified. If the gravel spreading rate exceeds the design threshold, the spreading quality is unqualified.

[0017] If the gravel spreading rate is within the design threshold, then based on the gravel spreading rate, the horizontal spreading uniformity index and the vertical spreading uniformity index are calculated respectively.

[0018] The maximum area of ​​unspread crushed stone and the maximum value of the spreading uniformity index are set. Based on the maximum area of ​​unspread crushed stone and the maximum value of the spreading uniformity index, the unspread area of ​​crushed stone in the test area, the horizontal spreading uniformity index and the vertical spreading uniformity index are judged respectively to obtain the judgment results. Based on the judgment results, the spreading quality of the sealing crushed stone is evaluated.

[0019] Preferably, the process of calculating the transverse spray uniformity index includes:

[0020] Based on the detection point image of the transverse detection end face, the pixel ratio of the transverse white area corresponding to the detection point image is selected, and the average pixel ratio of the transverse white area is calculated to obtain the transverse average value. Based on the transverse average value and the gravel spreading rate, the transverse spreading uniformity index is calculated.

[0021] Preferably, the process of calculating the longitudinal spray uniformity index includes:

[0022] Based on the detection point image of the longitudinal detection end face, the pixel ratio of the longitudinal white area corresponding to the detection point image is selected, and the average value of the pixel ratio of the longitudinal white area is calculated to obtain the longitudinal average value. Based on the longitudinal average value and the gravel spreading rate, the longitudinal spreading uniformity index is calculated.

[0023] Preferably, the process also includes calculating the comprehensive scoring index:

[0024] If the crushed stone spreading rate is within the design threshold, the maximum area of ​​the unspread crushed stone in the test area is not greater than the maximum set value of the maximum area of ​​the unspread crushed stone, and the horizontal spreading uniformity index and the vertical spreading uniformity index are both not greater than the maximum value of the spreading uniformity index, a comprehensive evaluation index is constructed. Based on the comprehensive evaluation index, a comprehensive score is calculated. Based on the comprehensive score, the spreading quality of the sealing layer crushed stone is evaluated.

[0025] Compared with the prior art, the present invention has the following advantages and technical effects:

[0026] This invention provides a method for identifying the quality of gravel sealing layer application based on image processing. It acquires high-precision, high-quality images of the gravel sealing layer, employs digital image processing techniques to identify the quality of the gravel sealing layer application, and proposes a quality evaluation system for the application. The method provided by this invention is convenient, efficient, and does not damage the gravel sealing layer within the detected area. Attached Figure Description

[0027] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0028] Figure 1 This is a schematic diagram of the detection auxiliary device according to an embodiment of the present invention;

[0029] Figure 2 This is a flowchart of a method according to an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of the comprehensive evaluation system for the quality of gravel spraying according to an embodiment of the present invention. Detailed Implementation

[0031] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0032] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0033] Example 1

[0034] like Figure 1 As shown, this embodiment provides an auxiliary device for detecting the quality of sealing layer gravel spraying based on image processing, mainly for obtaining high-definition photos of the sealing layer that are not affected by external factors.

[0035] The testing auxiliary device has two pointed legs that secure the device to the seal coat without adhering to the seal coat asphalt. Connected to the pointed legs is a retractable vertical folding rod. When the vertical folding rod is extended, both the vertical folding rod and the pointed legs are perpendicular to the ground. A horizontal rod is located at the other end of the vertical folding rod, and spotlights are positioned at the perpendicular angle between the vertical folding rod and the horizontal rod, providing a stable light source. Simultaneously, a light-shielding curtain is installed on the outside of the pointed legs to block external light sources. A camera hole is located in the middle of the horizontal rod, reserved for connecting camera equipment. This testing auxiliary device is in the form of a folding box, which can be folded for easy portability and storage.

[0036] To determine the effectiveness of image processing-based identification of the gravel coverage rate, gravel with different coverage rates was laid in the test section based on the full paving quality. The above method was then used to identify the gravel coverage rate. The specific process is as follows:

[0037] (1) Based on the full paving weight of crushed stone: 13.12 kg / m 2 The mass of crushed stone sprayed at different spraying rates of 20%, 40%, 60%, and 80% was calculated. Based on this, crushed stone was sprayed in sections at different spraying rates in the test section. Three measuring points were selected for each road section;

[0038] (2) Pull up the folding box of the detection auxiliary device, insert the pointed support legs into the gravel seal layer after spraying, lower the light-blocking curtain, and fix the detection area; connect the camera device through the camera hole, turn on the spotlight, and use the camera device to obtain the image of the gravel seal layer spraying;

[0039] (3) Perform image denoising, enhancement and binarization on the acquired image to obtain a binarized image, in which the gravel is white and the rest is black;

[0040] Because the acquired images eliminate interference from external environmental factors such as lighting, the image processing process is greatly simplified, and excellent recognition results are achieved. Specifically:

[0041] The acquired image is processed using mean shifting from Gaussian filtering and edge-preserving filtering.

[0042] The processed image is then converted to grayscale and binarized.

[0043] (4) Using OpenCV's built-in pixel calculation functions, the percentage of white region pixels in the binary image of different detection road sections relative to the total number of pixels in the image was calculated, i.e., the gravel spread rate W. The image recognition results under different gravel spread rates were obtained, as shown in Table 1. The relationship between the two is: Among them, the correlation index R 2 It is 0.9916.

[0044] Table 1

[0045]

[0046] Example 2

[0047] like Figure 2 As shown in the figure, this embodiment provides a method for identifying the quality of sealing gravel spraying based on image processing. The specific steps are as follows:

[0048] (1) Select three station numbers (1, 2, 3) every 50-100m as transverse detection sections. Select three detection points (m, l, r) on the middle of the road, the left side of the road, and the right side of the road for each section. The roadside detection points are 1-3m away from the edge of the road.

[0049] (2) Pull up the folding box of the detection auxiliary device, insert the pointed support legs into the gravel seal layer after spraying, lower the light-blocking curtain, and fix the detection area; connect the camera device through the camera hole, turn on the spotlight, and use the camera device to obtain the image of the gravel seal layer spraying;

[0050] (3) Perform image denoising, enhancement and binarization on the acquired image to obtain a binarized image, in which the gravel is white and the rest is black;

[0051] Because the acquired images eliminate interference from external environmental factors such as lighting, the image processing process is greatly simplified, and excellent recognition results are achieved. Specifically:

[0052] The acquired image is processed using mean shifting from Gaussian filtering and edge-preserving filtering.

[0053] The processed image is then converted to grayscale and binarized.

[0054] (4) Using OpenCV's built-in pixel calculation functions, calculate the percentage of white pixels in the binarized images of the nine detection points (r1, r2, r3, m1, m2, m3, l1, l2, l3) to the total number of pixels in the image, i.e., the gravel spread rate W, and calculate its average value. Simultaneously, an image detection algorithm is used to detect the largest inscribed rectangle of the black area, obtain its area S, and calculate its average value.

[0055] (5) Calculate W r1 W r2 W r3 average W r Calculate W m1 W m2 W m3 average W m Calculate W l1 W l2 W l3 average W l The horizontal spray uniformity index P1 is calculated according to the following formula;

[0056]

[0057] (6) Calculate W r1 W m1 W l1 Average value W1, calculate W r2 W m2 W l2 Calculate W based on the average value W2. r3 W m3 W l3 The average value W3 is used to calculate the longitudinal spray uniformity index P2 according to the following formula.

[0058]

[0059] (7) Figure 3 As shown, firstly, the crushed stone spreading rate at each measuring point is compared with the design value. If it is not within ±5% of the design value, it is judged as unqualified. Then, the S value at each measuring point is compared with the maximum unspread area set to the maximum value S0, and P1, P2 are compared with the maximum value P0 of the uniformity index. If they are greater than the set maximum values, they are directly judged as unqualified. If S≤S0 and P1, P2≤P0, the comprehensive score index R of crushed stone spreading quality is calculated according to the following formula. R≥90, the crushed stone spreading quality is judged as excellent; 90>R≥70, it is good; 70>R≥60, it is qualified; R<60, it is unqualified.

[0060]

[0061] A test was conducted on a certain road section where the designed crushed stone spreading rate was 60%. The crushed stone spreading rate W and the maximum area S of unspread crushed stone were obtained at 9 measuring points. The results were then calculated using the above formula. P1 and P2 are shown in Table 2;

[0062] Table 2

[0063]

[0064] The gravel coverage rate at each measuring point was within 60% ± 5%, and further evaluation was conducted. S0 was set as 3% of the total image pixels, with a single image pixel value of 725904, i.e., S0 was set to 21777, and P0 was set to 15. All of the above S values ​​were less than S0, and P1 and P2 were less than P0. With a = 20 and b = c = 40, the comprehensive gravel coverage quality score R was calculated to be 75.25, indicating that the gravel coverage quality was good.

[0065] The above description is merely a preferred embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for identifying the quality of capping gravel spraying based on image processing, characterized in that, Includes the following steps: Obtain high-quality images of the seal layer crushed stone spraying; The image of the sealing gravel spray is preprocessed to obtain a binarized image, wherein the white area of ​​the binarized image is gravel; Based on OpenCV's built-in pixel calculation function, the proportion of white areas in the binary image relative to the total pixels is calculated, i.e., the gravel spillage rate. Based on the image detection algorithm, the largest inscribed rectangle of the black area in the binarized image is detected to obtain the area of ​​the largest area where the gravel was not scattered. The quality of the sealing layer crushed stone is evaluated based on the crushed stone spreading rate and the area of ​​the largest unspread crushed stone area. The process of evaluating the quality of the sealing layer chip application includes: A design threshold for the gravel spreading rate is set. Based on the design threshold, the gravel spreading rate at each measuring point is judged to be qualified. If the gravel spreading rate exceeds the design threshold, the spreading quality is unqualified. If the gravel spreading rate is within the design threshold, then based on the gravel spreading rate, the horizontal spreading uniformity index and the vertical spreading uniformity index are calculated respectively. The maximum area of ​​unspread crushed stone and the maximum value of the spreading uniformity index are set. Based on the maximum area of ​​unspread crushed stone and the maximum value of the spreading uniformity index, the maximum area of ​​unspread crushed stone, the transverse spreading uniformity index and the longitudinal spreading uniformity index of the test area are judged respectively to obtain the judgment results. Based on the judgment results, the spreading quality of the sealing crushed stone is evaluated. The process of calculating the transverse spray uniformity index includes: Based on the detection point image of the transverse detection end face, the pixel ratio of the transverse white area corresponding to the detection point image is selected, and the average pixel ratio of the transverse white area is calculated to obtain the transverse average value. Based on the transverse average value and the gravel spreading rate, the transverse spreading uniformity index is calculated. The process of calculating the longitudinal spray uniformity index includes: Based on the detection point image of the longitudinal detection end face, the pixel ratio of the longitudinal white area corresponding to the detection point image is selected, and the average value of the pixel ratio of the longitudinal white area is calculated to obtain the longitudinal average value. Based on the longitudinal average value and the gravel spreading rate, the longitudinal spreading uniformity index is calculated. The process of calculating the comprehensive score: If the crushed stone spreading rate is within the design threshold, the maximum area of ​​the unspread crushed stone in the test area is not greater than the maximum area of ​​the unspread crushed stone, and the horizontal spreading uniformity index and the vertical spreading uniformity index are not greater than the maximum spreading uniformity index, a comprehensive evaluation index is constructed. Based on the comprehensive evaluation index, a comprehensive score is calculated. Based on the comprehensive score, the spreading quality of the sealing layer crushed stone is evaluated.

2. The method for identifying the quality of capping gravel spraying based on image processing according to claim 1, characterized in that, Before obtaining high-quality images of seal gravel spray, the following steps are required: A detection auxiliary device is constructed, which is a folding box with pointed legs. The pointed legs fix the detection auxiliary device to the gravel sealing layer. A light-blocking curtain that can block external light sources is set on the outside of the pointed legs. A telescopic vertical folding rod is connected to the pointed legs. A horizontal rod with a camera hole is set at the other end of the vertical folding rod. The camera hole is used to connect a camera device. A spotlight that provides a light source is set at the vertical angle between the vertical folding rod and the horizontal rod.

3. The method for identifying the quality of capping gravel spraying based on image processing according to claim 2, characterized in that, The process of acquiring high-quality images of seal gravel spray includes: After selecting the detection area, pull up the folding box of the detection auxiliary device, insert the pointed support legs into the sprayed gravel seal layer, lower the light-blocking curtain, connect the camera device through the camera hole, turn on the spotlight, and use the camera device to obtain a high-quality image of the gravel seal layer spraying.

4. The method for identifying the quality of capping gravel spraying based on image processing according to claim 1, characterized in that, The preprocessing process for the image of the sealing gravel spray includes: The image of the sealing gravel spray is denoised and enhanced by mean shifting in Gaussian filtering and edge-preserving filtering to obtain an enhanced image. The enhanced image is then binarized to obtain a binarized image.

Images