A control method for paving stone-filled roadbed based on image processing

Abstract

The present invention proposes a paving control method for a stone-filled roadbed based on image processing, which collects the surface image of the stone-filled roadbed of the paved and compacted road section, corrects the grayscale histogram of the original image, expands the grayscale spacing of the image or makes the grayscale distribution uniform, thereby improving the contrast and the details of the image, thereby enhancing the image, performing black-and-white processing on the image with the optimal threshold, reducing the probability of misclassification of the background and the target in the image, and identifying the void pixel points and the total volume pixel points in the processed grayscale image to determine the void ratio of the surface of the stone-filled roadbed. The edge width of the material of the paver when paving the stone-filled roadbed is calculated by the measured void ratio, which can effectively control the paving quality of the stone-filled roadbed, thereby ensuring the compaction effect, and ensuring the overall quality and bearing capacity of the roadbed.

Description

Technical Field

[0001] The present invention relates to the field of information model technology, and in particular to the application of image processing technology in pavement engineering. The present invention proposes a stone-filled roadbed paving control method based on image processing. Background Art

[0002] The stone-filled roadbed requires easy excavation, easy compaction, high strength, and good water stability. At present, the commonly used roadbed paving methods for filling materials during roadbed construction are progressive paving, backward paving, and mixed paving. For the common stone-filled roadbed paving methods, there are problems: if there is too much filler or uneven paving, it is easy to cause excessive porosity and problems with the compaction of the roadbed, so that it cannot bear the load. The construction quality during the paving process can be controlled by controlling the width of the material edge of the paver. Therefore, there is an urgent need for a relatively accurate and efficient operation method to control the paving of the stone-filled roadbed. Summary of the invention

[0003] In order to solve the problem of how to control the paving of a stone-filled roadbed during the construction process, the present invention proposes a stone-filled roadbed paving control method based on image processing.

[0004] The stone-filled roadbed paving control method based on image processing comprises the following steps:

[0005] Step 1: Collect the surface image of the stone-filled roadbed of the paved and compacted road section;

[0006] Step 2, correcting the grayscale histogram of the collected stone-filled roadbed surface image to a uniform histogram;

[0007] Step 3, performing optimal threshold black-and-white processing on the image processed in step 2;

[0008] Step 4, calculating the void ratio of the stone-filled roadbed;

[0009] Step five, calculate the material edge width of the paver when paving the stone-filled roadbed.

[0010] Further technology of the present invention:

[0011] Preferably, the grayscale of the image after histogram correction in step 2 is calculated according to the following method:

[0012] ;

[0013] Where: —The grayscale of the image pixels after histogram correction; —The grayscale of the original image pixels; —Probability density function of the grayscale of the original image pixels; —The standard deviation of the grayscale values ​​of the four adjacent points around the original image pixel.

[0014] Preferably, the optimal threshold black and white processing in step 3 is performed according to the following method:

[0015] Compare the gray value of each pixel on the image with the optimal threshold. If the gray value of a pixel is less than the threshold, the gray value of the pixel is set to 0, that is, black; otherwise, it is set to 255, that is, white. The optimal threshold is calculated according to the following formula:

[0016] ;

[0017] Where: —Optimal threshold; — threshold value;

[0018] —Pixel grayscale is divided into The probability of —Pixel grayscale is divided into The probability of

[0019] — was assigned The average gray value of the pixels in ; — was assigned The average gray value of the pixels in ;

[0020] —The average gray value of the image; N—the total number of gray levels of the image; —The grayscale level of the image;

[0021] —Total number of pixels; —Grayscale level is The number of pixels.

[0022] Preferably, the surface porosity of the stone-filled roadbed in step 4 is determined by identifying the pore pixel points and the total volume pixel points in the grayscale image processed in step 3, and is specifically calculated according to the following formula:

[0023] ;

[0024] Where: —Surface void ratio of rock-filled roadbed; — gray level; —Grayscale level The corresponding value in the grayscale histogram;

[0025] —The maximum gray level of the image; —Gray levels in the image The corresponding pixel size; n—the pixel size of the entire image.

[0026] Preferably, the material edge width of the paver when paving the stone-filled roadbed in step 5 is determined by the following method:

[0027] ;

[0028] Where: — fabric edge width; — half paving width; — half width of scraper;

[0029] —Outer diameter of the first-stage spiral blade; —screw shaft diameter;

[0030] — Friction coefficient between permeable concrete and distributor blades; — helical pitch; —The vertical distance from the spiral blade surface of the distributor to the axis.

[0031] The beneficial effects of the present invention are:

[0032] The present invention proposes a control method for paving a stone-filled roadbed based on image processing. By collecting the surface image of the stone-filled roadbed of the paved and compacted road section, the grayscale histogram of the original image is corrected, the grayscale spacing of the image is expanded or the grayscale distribution is uniform, so as to improve the contrast and the details of the image, thereby enhancing the image. The image is processed black and white with the optimal threshold to reduce the probability of misclassification of the background and the target in the image. The void pixel points and the total volume pixel points in the processed grayscale image are identified to determine the void ratio of the surface of the stone-filled roadbed, which has the advantages of being automatic, efficient and highly accurate. The edge width of the material of the paver when paving the stone-filled roadbed is calculated by the measured void ratio, which can effectively control the paving quality of the stone-filled roadbed, thereby ensuring the compaction effect and the overall quality and bearing capacity of the roadbed. DETAILED DESCRIPTION

[0033] In order to make the technical means, creative features, purpose and efficacy of the present invention easy to understand, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain this description and are not intended to limit the present invention.

[0034] Embodiment: A method for controlling the paving of a stone-filled roadbed based on image processing comprises the following steps:

[0035] Step 1: Collect the surface image of the stone-filled roadbed of the paved and compacted road section.

[0036] Step 2: Correct the grayscale histogram of the collected stone-filled roadbed surface image to a uniform histogram.

[0037] The grayscale of the image after histogram correction in step 2 is calculated as follows:

[0038] ;

[0039] Where: —The grayscale of the image pixels after histogram correction; —The grayscale of the original image pixels; —Probability density function of the grayscale of the original image pixels; —The standard deviation of the grayscale values ​​of the four adjacent points around the original image pixel.

[0040] Step three, perform optimal threshold black and white processing on the image processed in step two.

[0041] The best threshold black and white processing is as follows:

[0042] Compare the grayscale value of each pixel on the image with the optimal threshold. If the grayscale value of a pixel is less than the optimal threshold, the grayscale value of the pixel is set to 0, that is, black, otherwise it is set to 255, that is, white. The optimal threshold is calculated according to the following formula:

[0043] ;

[0044] Where: —Optimal threshold; — threshold value;

[0045] —Pixel grayscale is divided into The probability of —Pixel grayscale is divided into The probability of

[0046] — was assigned The average gray value of the pixels in ; — was assigned The average gray value of the pixels in ;

[0047] —The average gray value of the image; N—the total number of gray levels of the image; —The grayscale level of the image;

[0048] —Total number of pixels; —Grayscale level is The number of pixels.

[0049] Step 4: Calculate the void ratio of the stone-filled roadbed.

[0050] The surface porosity of the stone-filled roadbed is determined by identifying the pore pixels and the total volume pixels in the grayscale image processed in step 3, and is calculated according to the following formula:

[0051] ;

[0052] Where: —Surface void ratio of rock-filled roadbed; — gray level; —Grayscale level The corresponding value in the grayscale histogram;

[0053] The grayscale histogram satisfies the distribution form of two normal distribution density function curves, as shown below:

[0054] , the horizontal axis is the gray value and the vertical axis is the frequency.

[0055] ( They are 16.7, 96.3 and 26.2 respectively. 8.1, 62.3, 15.4 respectively)

[0056] —The maximum grayscale level of the image is 182; —Gray levels in the image The corresponding pixel size is automatically read by the computer in image recognition; n—the pixel size of the entire image, which is automatically read by the computer in image recognition;

[0057] Calculate the surface void ratio of the stone-filled roadbed It is 23%.

[0058] Step 5, using the obtained void ratio value of the stone-filled roadbed to calculate the edge width of the material spreader when paving the stone-filled roadbed.

[0059] When paving a stone-filled roadbed, the width of the spreading edge of the paver is determined by the following method:

[0060] ;

[0061] Where: — fabric edge width;

[0062] — Half paving width, take 5m;

[0063] - Half width of scraper: 0.68m;

[0064] —The outer diameter of the first-stage spiral blade is 0.48m;

[0065] —Screw shaft diameter, take 0.1m;

[0066] —The friction coefficient between the permeable concrete and the distributor blade is taken as 0.3;

[0067] —Spiral pitch: 0.28m;

[0068] —The vertical distance from the spiral blade surface of the distributor to the axis is 180mm.

[0069] Calculations show that the edge width of the fabric needs to be controlled at 1.2m during paver construction.

[0070] According to the calculated value of 1.2m, the edge width of the paver is adjusted to carry out paving construction. The image of the stone-filled roadbed after paving is collected, and the void ratio of the stone-filled roadbed is recalculated according to the method in step 4 to obtain a value of 20%. It can be seen that the void ratio of the stone-filled roadbed has become smaller after the edge width of the paver is adjusted. The bearing capacity of the stone-filled roadbed is closely related to the void ratio value. Under the premise that the grading of the stone-filled roadbed and other factors are determined, the smaller the void ratio, the stronger its bearing capacity. Therefore, the adjustment of the edge width of the paver enhances the bearing capacity of the stone-filled roadbed and improves the paving construction quality of the stone-filled roadbed.

[0071] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A stone-filled roadbed paving control method based on image processing, characterized in that: The following steps are involved: Step 1: Collect the surface image of the stone-filled roadbed of the paved and compacted road section; Step 2, correcting the grayscale histogram of the collected stone-filled roadbed surface image to a uniform histogram; The grayscale of the image after histogram correction in step 2 is calculated as follows: Where: y—image pixel grayscale after histogram correction; x—the grayscale of the original image pixel; P(x)—probability density function of the grayscale of the original image pixel; σ—the standard deviation of the grayscale values ​​of the four adjacent points around the original image pixel; Step 3, performing optimal threshold black-and-white processing on the image processed in step 2; The optimal threshold black and white processing in step 3 is as follows: Compare the gray value of each pixel on the image with the optimal threshold. If the gray value of a pixel is less than the optimal threshold, the gray value of the pixel is set to 0, that is, black; otherwise, it is set to 255, that is, white. The optimal threshold is calculated according to the following formula: T=ArgMax[p0(k)(z0(k)-Z T ) 2 +p1(k)(z1(k)-Z T ) 2 ] p1(k)=1-p0(k) Where: T—optimal threshold; k—threshold; p0—the probability that the pixel grayscale is classified into [0, k]; p1—the probability that the pixel grayscale is classified into [k+1, N-1]; z0(k)—the average gray value of pixels classified into [0, k]; z1(k)—the average gray value of the pixels classified into [k+1, N-1]; z T —The average gray value of the image; N—the total number of gray levels of the image; i—grayscale level of the image; m—total number of pixels; m i —The number of pixels with gray level i; Step 4, calculating the void ratio of the stone-filled roadbed; The surface porosity of the stone-filled roadbed is determined by identifying the pore pixels and the total volume pixels in the grayscale image processed in step 3, and is calculated according to the following formula: Where: V—surface void ratio of stone-filled roadbed; r i — gray level; H(r i )—Gray level r i The corresponding value in the grayscale histogram; r max —The maximum gray level of the image; n(r i )—gray level r in the image i The corresponding pixel size; n — pixel size of the entire image; Step 5: Calculate the edge width of the material when paving the stone-filled roadbed. The specific method is as follows: Where: L—width of fabric edge; B—paving half width; b—half width of scraper; D1—outer diameter of the first-stage spiral blade; D0—screw shaft diameter; μ—friction coefficient between permeable concrete and distributor blades; J—helical pitch; r—The vertical distance from the spiral blade surface of the distributor to the axis.

Images