Road engineering construction quality detection method and system based on machine vision

Abstract

The invention relates to the technical field of image processing, in particular to a road engineering construction quality detection method and system based on machine vision, and the method comprises the steps: receiving a road surface construction image; performing graying processing on the road surface construction image to obtain a road surface grayscale image; acquiring an optical flow vector corresponding to the road surface grayscale image; obtaining the asphalt particle density of the part where each pixel point in the road surface gray level image is located; obtaining a distortion factor of each optical flow vector according to the optical flow vectors and the road surface grayscale image; obtaining a quality factor of each pixel point in the road surface grayscale image according to the asphalt particle density of the part where each pixel point is located and the distortion factor of each optical flow vector; and obtaining an abnormal area in the road surface construction image according to the quality factor of each pixel point. The detection accuracy and the detection efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for detecting road engineering construction quality based on machine vision. Background Art

[0002] Road construction refers to various construction activities carried out in accordance with design drawings and technical specifications during the road construction process, including the construction of the road base and surface. In order to ensure the bearing capacity and durability of the road, asphalt is generally laid according to the design requirements. However, when laying asphalt, due to temperature changes, cracks will appear on the road surface, resulting in uneven road surface, affecting driving comfort and safety.

[0003] In the related technology, workers will use equipment such as level meters to conduct inspections after the road is paved.

[0004] However, manual testing will make the test results inaccurate and the test efficiency low. Summary of the invention

[0005] In order to solve the technical problems of inaccurate detection results and low detection efficiency caused by manual detection, the purpose of the present invention is to provide a road engineering construction quality detection method and system based on machine vision. The technical solutions adopted are as follows: In a first aspect of the present disclosure, a method for detecting road engineering construction quality based on machine vision is provided, the method comprising: receiving a road surface construction image; grayscale the road surface construction image to obtain a road surface grayscale image; Obtaining an optical flow vector corresponding to the road surface grayscale image; According to the grayscale changes of the pixels in the road surface grayscale image, the density of asphalt particles at the location of each pixel in the road surface grayscale image is obtained; The method for obtaining the density of asphalt particles is as follows: according to the grayscale value of each first neighborhood pixel point in the first preset neighborhood of each pixel point, obtain the maximum grayscale value point corresponding to each pixel point; obtain the first distance between each pixel point and the central pixel point; according to the maximum grayscale value point corresponding to each pixel point and the first distance, obtain the density of asphalt particles at the location of each pixel point; According to the optical flow vectors and the road surface grayscale image, obtaining a distortion factor of each of the optical flow vectors; Obtaining a quality factor of each pixel point in the road surface grayscale image according to the density of asphalt particles at the location of each pixel point and the distortion factor of each optical flow vector; The abnormal area in the road surface construction image is obtained according to the quality factor of each pixel point.

[0006] In an implementable manner, the obtaining of the abnormal area in the road surface construction image according to the quality factor of each pixel point includes: Obtaining abnormal pixel points whose quality factors are greater than a preset quality factor among the pixel points; Acquire target abnormal pixel points whose density of the abnormal pixel points is greater than a preset density; Determine the area composed of the target abnormal pixel points as the abnormal area.

[0007] In an implementable manner, the step of obtaining the density of asphalt particles at a location where each pixel point is located according to the maximum gray value point corresponding to each pixel point and the first distance includes: Acquire the maximum gray value point closest to each of the maximum gray value points corresponding to each of the pixel points as the target maximum gray value point; Obtaining the number of the maximum gray value points corresponding to each of the pixel points; The density of asphalt particles at the location of each pixel point is obtained according to the maximum gray value point corresponding to each pixel point, each target maximum gray value point, the number and the first distance.

[0008] In an implementable manner, the step of obtaining the density of asphalt particles at the location of each pixel point according to the maximum gray value point corresponding to each pixel point, each target maximum gray value point, the number and the first distance includes: Obtaining the first grayscale value of each of the maximum grayscale value points corresponding to each of the pixel points; Acquire the second gray value of the target maximum gray value point that is closest to each of the maximum gray value points corresponding to each of the pixel points; Obtaining the grayscale value mean between each of the maximum grayscale value points corresponding to each of the pixel points and the corresponding target maximum grayscale value point; Obtaining a second distance between each of the maximum gray value points corresponding to each of the pixel points and the corresponding target maximum gray value point; The density of asphalt particles at the location of each pixel point is obtained according to the first grayscale value, the second grayscale value, the grayscale value average, the second distance, the number and the first distance corresponding to each pixel point.

[0009] In an implementable manner, the step of obtaining the grayscale value mean between each maximum grayscale value point corresponding to each pixel point and the corresponding target maximum grayscale value point includes: Obtain all intermediate gray value points between each maximum gray value point corresponding to each pixel point and the corresponding target maximum gray value point; Obtaining the grayscale value of each of the intermediate grayscale value points corresponding to each of the pixel points; Obtain the number of all the intermediate gray value points corresponding to each of the pixel points; The gray value mean is obtained according to the sum of the gray values ​​of each of the intermediate gray value points corresponding to each of the pixel points and the number.

[0010] In an implementable manner, acquiring the distortion factor of each of the optical flow vectors according to the optical flow vectors and the road surface grayscale image includes: Get the horizontal component of each optical flow vector; Obtaining the vertical component of each of the optical flow vectors; Acquire a third distance between the origin of each of the optical flow vectors and the center line of the road surface grayscale image; Acquire a fourth distance between the origin of each of the optical flow vectors and the bottom edge of the road surface grayscale image; The distortion factor of each of the optical flow vectors is acquired according to the vertical component, the horizontal component, the third distance, and the fourth distance of each of the optical flow vectors.

[0011] In an implementable manner, obtaining the quality factor of each pixel in the road surface grayscale image according to the density of asphalt particles at the location of each pixel and the distortion factor of each optical flow vector includes: Acquire each second neighborhood pixel point in a second preset neighborhood corresponding to each of the pixel points; Obtaining a distortion factor of the target light loss amount closest to each of the pixel points; Obtaining a fifth distance between each of the pixel points and the corresponding nearest light loss amount; The quality factor of each pixel in the road surface grayscale image is obtained according to the asphalt particle density of each pixel, the asphalt particle density of the second neighborhood pixel, the distortion factor of the target light loss, and the fifth distance.

[0012] In an implementable manner, obtaining the quality factor of each pixel in the road surface grayscale image according to the asphalt particle density of each pixel, the asphalt particle density of the second neighborhood pixel, the distortion factor of the target light loss, and the fifth distance includes: Obtaining the asphalt particle density variance between the asphalt particle density of each of the pixel points and the asphalt particle density of each of the second neighborhood pixel points in the corresponding second preset neighborhood; The quality factor of each pixel point in the road surface grayscale image is obtained according to the asphalt particle density of each pixel point, the asphalt particle density variance, the distortion factor of the target light loss, and the fifth distance.

[0013] In a second aspect of the present disclosure, a road engineering construction quality detection system based on machine vision is provided, the system comprising: a camera and a construction quality detection device; The camera is used to capture road surface construction images and send the road surface construction images to the machine vision-based road engineering construction quality detection device; The construction quality detection device is used to receive a road surface construction image; grayscale the road surface construction image to obtain a road surface grayscale image; obtain an optical flow vector corresponding to the road surface grayscale image; and obtain the asphalt particle density at the location of each pixel in the road surface grayscale image according to the grayscale change of the pixel in the road surface grayscale image. The asphalt particle density is obtained by: obtaining the maximum grayscale value point corresponding to each pixel according to the grayscale value of each first neighborhood pixel in the first preset neighborhood of each pixel; obtaining the first distance between each pixel and the central pixel; obtaining the asphalt particle density at the location of each pixel according to the maximum grayscale value point corresponding to each pixel and the first distance; obtaining the distortion factor of each optical flow vector according to the optical flow vector and the road surface grayscale image; obtaining the quality factor of each pixel in the road surface grayscale image according to the asphalt particle density at the location of each pixel and the distortion factor of each optical flow vector; and obtaining the abnormal area in the road surface construction image according to the quality factor of each pixel.

[0014] The present invention has the following beneficial effects: The present disclosure provides a method and system for detecting the quality of road engineering construction based on machine vision, the method comprising: receiving a road surface construction image; graying the road surface construction image to obtain a road surface gray image; obtaining an optical flow vector corresponding to the road surface gray image; obtaining the density of asphalt particles at the location of each pixel point in the road surface gray image; obtaining the distortion factor of each optical flow vector according to the optical flow vector and the road surface gray image; obtaining the quality factor of each pixel point in the road surface gray image according to the density of asphalt particles at the location of each pixel point and the distortion factor of each optical flow vector; obtaining the abnormal area in the road surface construction image according to the quality factor of each pixel point. Among them, the present disclosure analyzes the density of asphalt particles at various locations in the road through the gray situation, analyzes the distortion factor of the optical flow vector, and then combines the density of asphalt particles and the distortion factor to perform quality detection, which can improve the detection accuracy and detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a method for detecting road engineering construction quality based on machine vision provided by one embodiment of the present invention; Figure 2 A schematic diagram of an optical flow vector provided by an embodiment of the present invention; Figure 3 An embodiment of the present invention provides Figure 1 Detailed flow chart of step S104; Figure 4 An embodiment of the present invention provides Figure 3 Detailed flow chart of step S1043; Figure 5 An embodiment of the present invention provides Figure 4 Detailed flow chart of step S10433; Figure 6 An embodiment of the present invention provides Figure 5 Detailed flow chart of step S104335; Figure 7 An embodiment of the present invention provides Figure 1 Detailed flow chart of step S105; Figure 8 An embodiment of the present invention provides Figure 1 Detailed flow chart of step S106; Fig. 9 An embodiment of the present invention provides Figure 8 Detailed flowchart of step S1064; Fig.10 An embodiment of the present invention provides Figure 1 Detailed flow chart of step S107; Fig.11 A schematic diagram of a road engineering construction quality inspection system based on machine vision provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the road engineering construction quality detection method and system based on machine vision proposed by the present invention, its specific implementation method, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the road engineering construction quality detection method and system based on machine vision provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a method for detecting road construction quality based on machine vision provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes the following steps S101-S107: S101: Receive a road surface construction image.

[0021] During road construction, asphalt mixture is prepared according to design requirements to ensure that the material quality meets the standards. Then a special paving machine is used to evenly lay the prepared asphalt mixture on the base layer, and a roller is used to compact the laid asphalt to ensure that it is dense enough to reach the designed thickness.

[0022] During the asphalt cooling process, it will be affected by the temperature, causing the asphalt to cool faster, resulting in cracks on the surface during rolling, making the paved road uneven.

[0023] In order to prevent this phenomenon from happening, it is necessary to conduct defect detection on the paved roads so that relevant remedial measures can be taken in time when the above situation is detected.

[0024] In the present disclosure, in order to detect defects on the road after rolling, a camera is installed on the rear side of the forward direction of the roller, the roller is started to move forward to roll the road, and the camera is used to take pictures of the rolled road to obtain several road surface construction images.

[0025] The above-mentioned camera may be an industrial high-resolution camera.

[0026] S102: grayscale the road surface construction image to obtain a road surface grayscale image.

[0027] Since the road defect detection needs to start from the road texture, the acquired road surface construction image is grayed to obtain a road surface gray image.

[0028] S103: Obtain an optical flow vector corresponding to the road surface grayscale image.

[0029] For the road surface grayscale image obtained by the above operation, the displacement of pixels located at the same part of the road surface grayscale image in adjacent frame images is the same due to the viewing angle problem. However, the cracks will cause the road to deform, resulting in changes in the displacement of the cracked part in the road surface grayscale image.

[0030] Therefore, for the acquired road surface grayscale image, the optical flow method is used to obtain the optical flow vector between adjacent frames, such as Figure 2 shown.

[0031] Among them, the optical flow method infers the direction and speed of movement by analyzing the changes in pixel intensity between consecutive frames. The optical flow method can obtain the optical flow vectors of adjacent frame images, where each pixel point corresponds to a motion vector, which is used to represent the direction and speed of movement of the object in the image.

[0032] For the optical flow vectors between adjacent road surface grayscale images obtained by the above operation, since the cracked part is caused by uneven cooling and rolling, the cracked part is uneven. In the optical flow detection, the cracked part will cause the optical flow vector of the cracked part to be different from the optical flow vector of the normal part around it due to the unevenness. Therefore, the defective area in the road can be determined based on the abnormal changes of the optical flow vectors of the adjacent road surface grayscale images.

[0033] However, since the road is not completely flat after being rolled by a roller, it is necessary to screen out defects based on the flatness of each part of the road.

[0034] For the acquired road surface, the cracks on the road surface are caused by the uneven cooling and shrinkage of different parts of the asphalt pavement due to the influence of temperature after paving, which leads to uneven density of asphalt particles on the road surface. When the road is subsequently rolled, cracks will appear due to uneven force. Therefore, it is necessary to obtain the grayscale conditions of each part of the road in the grayscale image of the road surface, so as to obtain the density of asphalt particles in each part of the grayscale image of the road surface.

[0035] S104: Obtain the density of asphalt particles at the location of each pixel point in the road surface grayscale image.

[0036] In one embodiment, Figure 3 As shown, the above step S104 includes the following sub-steps S1041-1043: Under normal circumstances, the density of asphalt particles on the surface of the asphalt pavement should be relatively uniform. However, due to uneven cooling shrinkage, the asphalt particles on the surface become uneven. Since there are small gaps between the asphalt particles, the denser the asphalt particles are, the more obvious the grayscale changes in the grayscale image of the road surface are, while the looser the parts are, the opposite is true. Therefore, it is necessary to analyze the asphalt particle density of each part according to the grayscale changes of the pixels in the grayscale image of the road surface, that is, the asphalt particle density of each pixel in the grayscale image of the road surface can be obtained according to the grayscale changes of the pixels in the grayscale image of the road surface.

[0037] S1041. Obtain a maximum gray value point corresponding to each pixel point according to the gray value of each first neighborhood pixel point in a first preset neighborhood of each pixel point.

[0038] Among them, the first neighborhood pixel point is a pixel point in the first preset neighborhood, and the first preset neighborhood can be a 5×5 neighborhood around the pixel point, that is, for any first neighborhood pixel point in the 5×5 neighborhood of the pixel point, if the grayscale value of a first neighborhood pixel point is the largest among the grayscale values ​​of its eight neighborhoods, then this first neighborhood pixel point is called the maximum grayscale value point corresponding to the pixel point.

[0039] S1042: Obtain a first distance between each pixel point and a central pixel point, where the central pixel point is a pixel point located at the center of the bottom of the road surface grayscale image.

[0040] Since the viewing angle difference causes objects far away from the camera to become smaller in the grayscale image of the road surface, it is also necessary to eliminate the difference caused by the viewing angle difference. In the present disclosure, the above difference is eliminated by the distance between the pixel point and the center pixel point.

[0041] S1043. Obtain the density of asphalt particles at the location of each pixel point according to the maximum gray value point corresponding to each pixel point and the first distance.

[0042] In one embodiment, Figure 4 As shown, the above step S1043 includes the following sub-steps S10431-10433: S10431. Obtain each target maximum gray value point that is closest to each maximum gray value point corresponding to each pixel point.

[0043] After obtaining the maximum gray value point corresponding to each pixel point, it is also possible to obtain the maximum gray value point closest to the maximum gray value point corresponding to the pixel point among the maximum gray value points corresponding to all the pixels points as the target maximum gray value point.

[0044] Taking pixel 1 as an example, after obtaining the maximum gray value points corresponding to all pixel points, the maximum gray value points that are closest to the maximum gray value points of pixel 1 are obtained among the maximum gray value points corresponding to all pixel points. These maximum value points that are closest to the maximum gray value points are called target maximum gray value points. At this time, it is necessary to find the target maximum gray value points corresponding to each maximum gray value point in pixel 1.

[0045] S10432. Obtain the number of maximum gray value points corresponding to each pixel point.

[0046] S10433. Obtain the density of asphalt particles at the location of each pixel point according to the maximum gray value point corresponding to each pixel point, each target maximum gray value point, the number and the first distance.

[0047] In one embodiment, Figure 5 As shown, the above step S10433 includes the following sub-steps S104331-104335: S104331. Obtain the first grayscale value of each maximum grayscale value point corresponding to each pixel point.

[0048] S104332. Obtain the second grayscale value of the target maximum grayscale value point that is closest to each maximum grayscale value point corresponding to each pixel point.

[0049] S104333. Obtain the mean grayscale value between each maximum grayscale value point corresponding to each pixel point and the corresponding target maximum grayscale value point.

[0050] In the present disclosure, it is necessary to analyze the density of asphalt particles in each part based on the grayscale change. Therefore, after obtaining the maximum grayscale value points corresponding to each pixel point, the first grayscale value of each maximum grayscale value point corresponding to each pixel point can also be obtained. After obtaining the target maximum grayscale value point closest to the maximum grayscale value point corresponding to each pixel point, it is also necessary to obtain the second grayscale value of each target maximum grayscale point. It is also necessary to obtain the grayscale value average between each maximum grayscale value point corresponding to each pixel point and the corresponding target maximum grayscale value point. Specifically, in one embodiment, Figure 6 As shown, the above step S104333 includes the following sub-steps A1-A4: A1. Obtain all intermediate gray value points between each maximum gray value point corresponding to each pixel point and the corresponding target maximum gray value point.

[0051] After obtaining the maximum gray value points corresponding to each pixel point and the target maximum gray value points corresponding to each maximum gray value point, the pixel points where the connecting lines between the maximum gray value points and their corresponding target maximum gray value points are located can be obtained, and these pixel points can be used as intermediate gray value points.

[0052] A2. Obtain the grayscale value of each intermediate grayscale point corresponding to each pixel point.

[0053] A3. Obtain the number of all intermediate gray value points corresponding to each pixel point.

[0054] A4. Obtain the gray value mean value according to the sum and number of gray values ​​of each intermediate gray value point corresponding to each pixel point.

[0055] S104334. Obtain the second distance between each maximum gray value point corresponding to each pixel point and the corresponding target maximum gray value point.

[0056] S104335. Obtain the density of asphalt particles at the location of each pixel point according to the first grayscale value, the second grayscale value, the grayscale value average, the second distance, the number and the first distance corresponding to each pixel point.

[0057] Specifically, step S104 can be implemented by the following formula: ; Among them, in the formula, Represents the first pixels, Represents the first The first preset neighborhood of the pixel point A maximum gray value point, Represents the first The number of maximum gray value points in the first preset neighborhood of pixels, Represents the grayscale image of the road surface The maximum gray value point of the pixel point is closest to the target maximum gray value point. Represents the first The density of asphalt particles at the location of each pixel, Represents the first The first distance between the pixel and the center pixel, Represents the first The pixel The first gray value of the maximum gray value point, Represents the grayscale image of the road surface The pixel The second gray value of the target maximum gray value point closest to the maximum gray value point. Represents the first The pixel The maximum gray value point and the distance The gray value average of the intermediate gray value points between the target maximum gray value points closest to the maximum gray value points, Represents the first The pixel The maximum gray value point and the The second distance between the maximum gray value point and the nearest target maximum gray value point, Represents a hyperbolic function.

[0058] In the above formula, The larger the value of is, the smaller the gray value between the maximum gray value points in the first preset neighborhood of the pixel point is, and thus the faster the gray value of the pixel point changes. The pixel The maximum gray value point and the The second distance between the maximum gray value point and the nearest target maximum gray value point The smaller the value, the faster the gray value of the first preset neighborhood of the pixel changes, which indicates that the density of asphalt particles at the location of the pixel is greater. Due to the perspective distortion of the camera, the farther away from the camera, the smaller the part will be in the image. Therefore, the above formula also uses the first distance between the pixel and the center pixel. Weighted.

[0059] S105 . Obtain a distortion factor of each optical flow vector according to the optical flow vector and the road surface grayscale image.

[0060] For the asphalt particle density at each pixel point in the current road surface grayscale image, the unevenness of the asphalt may cause cracks due to stress during the rolling process, and the unevenness of the asphalt may cause the road surface to be uneven due to uneven density in different parts when the asphalt is rolled, so that the uneven parts are more likely to crack in the subsequent process. Since the displacement of the same part in the image between two adjacent frames of a flat road is the same, it is necessary to judge the flatness of each part of the road based on the optical flow distribution in the image.

[0061] In order to obtain the smoothness of each part of the road and finally obtain the crack generation conditions of each part of the road, for the optical flow vectors in the adjacent frame images obtained by the above operation, the distance between its origin and the bottom edge of the image can be obtained according to each optical flow vector, and for each optical flow vector, its vertical component is obtained, and its horizontal component and the distance between its origin and the center line of the image are obtained, and then the distortion factor of each optical flow vector in the optical flow field is obtained based on these values. In one embodiment, Figure 7 As shown, the above step S105 includes the following sub-steps S1051-S1055: S1051. Obtain the horizontal component of each optical flow vector.

[0062] S1052: Obtain the vertical component of each optical flow vector.

[0063] S1053. Obtain a third distance between the origin of each optical flow vector and the center line of the road surface grayscale image.

[0064] S1054. Obtain a fourth distance between the origin of each optical flow vector and the bottom edge of the road surface grayscale image.

[0065] S1055. Obtain a distortion factor of each optical flow vector according to the vertical component, the horizontal component, the third distance, and the fourth distance of each optical flow vector.

[0066] Specifically, the distortion factor of each optical flow vector is obtained by the following formula: ; in, Indicates the first Optical flow vectors, Represents the first The distortion factor of the amount of light loss is Indicates the first The horizontal component of the light loss Indicates the first The vertical component of the optical flow vector, Indicates the first The third distance between the origin of the optical flow vector and the midline of the road surface grayscale image, Indicates the first The fourth distance between the origin of the optical flow vector and the bottom edge of the road surface grayscale image, Represents a hyperbolic function.

[0067] The absolute value of the difference between the ratio of the modulus of the horizontal component of any optical flow vector in the optical flow field to the third distance between its origin and the midline and 1 , the larger the value, the larger the difference between the upper and lower values ​​of the ratio, indicating that the modulus of the horizontal component of the optical flow loss and the third distance between its origin and the center line are more negatively correlated, but due to the camera viewing angle, the farther away from the center line the horizontal component of the vector should be, so its distortion factor is larger; and for any optical flow vector in the optical flow field, the absolute value of the difference between the modulus of the vertical component of the optical flow field and the fourth distance between its origin and the bottom edge of the image and 1 The smaller the value, the closer the upper and lower values ​​of the ratio are. Therefore, the modulus of the vertical component of the optical flow loss in the optical flow field is positively correlated with the fourth distance between its origin and the bottom edge of the image. However, due to the camera viewing angle, the farther away from the camera in the image, the smaller the vertical component of the optical flow vector in the image, so the larger the distortion factor.

[0068] S106. Obtain a quality factor of each pixel in the road surface grayscale image according to the density of asphalt particles at the location of each pixel and the distortion factor of each optical flow vector.

[0069] When asphalt is laid evenly in normal conditions, the particle density of asphalt is uniform and flat. Therefore, by analyzing the particle density of each pixel in the grayscale image of the road surface and the optical flow distortion factor, the construction quality of each part in the grayscale image of the road surface can be obtained. In one embodiment, Figure 8 As shown, the above step S106 includes the following sub-steps S1061-S1064: S1061. Obtain each second neighborhood pixel point in a second preset neighborhood corresponding to each pixel point.

[0070] For example, the second preset neighborhood may be an eight-neighborhood, and what is obtained in this step are each second neighborhood pixel point in the eight-neighborhood corresponding to each pixel point, wherein the second neighborhood pixel point is a pixel point in the eight-neighborhood.

[0071] S1062: Obtain a distortion factor of the target light loss closest to each pixel.

[0072] S1063. Obtain the fifth distance between each pixel point and the corresponding nearest light loss.

[0073] S1064. Obtain a quality factor of each pixel in the road surface grayscale image according to the asphalt particle density of each pixel, the asphalt particle density of the second neighborhood pixel, the distortion factor of the target light loss, and the fifth distance.

[0074] In one embodiment, Fig. 9 As shown, the above step S1064 includes the following sub-steps S10641-S10642: S10641. Obtain the asphalt particle density variance between the asphalt particle density of each pixel point and the asphalt particle density of each second neighborhood pixel point in the corresponding second preset neighborhood.

[0075] S10642. Obtain a quality factor of each pixel in the road surface grayscale image according to the asphalt particle density of each pixel, the asphalt particle density variance, the distortion factor of the target light loss, and the fifth distance.

[0076] For each pixel in the image, the density of asphalt particles is obtained from each pixel in its eight neighborhoods and the variance is taken, and the origin of the light loss closest to the pixel is obtained, so that the quality factor of each pixel in the road surface grayscale image can be obtained. Specifically, the quality factor of each pixel in the road surface grayscale image is obtained by the following formula: ; In the formula, Represents the first The quality factor of each pixel, Represents the first The density of asphalt particles at the pixel point is The variance of the asphalt particle density of the second neighborhood pixel points in the second preset neighborhood corresponding to the pixel points, Represents the grayscale image of the road surface The distortion factor of the light loss closest to the pixel point, Represents the first pixels and the The fifth distance between the nearest light loss of pixels, It is an exponential function with the natural constant e as its base.

[0077] For the road surface grayscale image The density of asphalt particles at the pixel point is The variance of the asphalt particle density of the second neighborhood pixel points in the second preset neighborhood corresponding to the pixel points The larger the value, the greater the difference between the asphalt particle density of the pixel and its surrounding pixels, indicating a lower quality.

[0078] S107. Acquire abnormal areas in the road surface construction image according to the quality factor of each pixel point.

[0079] In one embodiment, Fig.10 As shown, step S107 includes the following sub-steps S1071-S1073: S1071. Obtain abnormal pixel points whose quality factors are greater than a preset quality factor among the quality factors of the pixels.

[0080] S1072. Acquire target abnormal pixel points whose density of abnormal pixel points is greater than a preset density.

[0081] S1073. Determine that the area composed of target abnormal pixel points is an abnormal area.

[0082] The quality factor of each pixel in the road surface grayscale image obtained by the above operation is compared with the preset quality factor, wherein the pixel with a quality factor less than the preset quality factor is an abnormal pixel, which is marked in the road surface construction image. If the density of the abnormal pixel is higher than the preset density, these abnormal pixels are determined to be target abnormal pixels, and the area composed of these target abnormal pixels is the abnormal area. Engineers are required to detect the abnormal area, formulate a practical rectification plan, clarify the responsible person and rectification time, and carry out rectification according to the plan to ensure that the construction process meets the design requirements and relevant standards.

[0083] Take the preset quality factor as 0.6 and the preset density as 0.5 as an example: The quality factor of each pixel in the road surface grayscale image obtained by the above operation is compared with the preset quality factor For comparison, The pixel points are abnormal pixels and are marked in the road surface construction image. When the density of abnormal pixel points is higher than 0.5, it is an abnormal part. Engineers are required to detect the abnormal part, formulate a practical rectification plan, clarify the responsible person and rectification time, and rectify according to the plan to ensure that the construction process meets the design requirements and relevant standards.

[0084] In order to detect the construction quality of road projects, machine vision is used to collect images of roads after construction and perform quality inspection on their surfaces. However, since there is a large density of asphalt particles on the surface after road construction and the unevenness after road construction is relatively small, it is not obvious in the image, thus affecting the accuracy of road quality inspection.

[0085] In order to detect the construction quality of road projects, the present invention installs an industrial high-resolution camera behind a road roller to collect road surface construction images after construction and performs grayscale processing to obtain a road surface grayscale image, obtains the optical loss of the road surface grayscale image by an optical flow method, and obtains the asphalt particle density of pixel points at various parts of the road surface grayscale image according to the fluctuation of grayscale value changes between pixel points in the road surface grayscale image, and finally obtains the quality factor of each pixel point in combination with the obtained distortion factor of each optical flow vector, and then determines the abnormal area in the road surface construction image based on the quality factor, wherein the asphalt particle density is obtained by analyzing the grayscale situation in the image and combining the camera lens distortion, and the distortion of the optical flow vector is obtained according to the optical flow vector of adjacent frames, and finally quality detection is performed, so that inconspicuous abnormalities in the image can be detected, thereby improving the accuracy of the detection result and the detection efficiency.

[0086] like Fig.11As shown, the present disclosure also provides a road engineering construction quality detection system based on machine vision, the system comprising: a camera 11 and a construction quality detection device 12; The camera 11 is used to capture road surface construction images and send the road surface construction images to the machine vision-based road engineering construction quality detection device; The construction quality detection device 12 is used to receive a road surface construction image; grayscale the road surface construction image to obtain a road surface grayscale image; obtain an optical flow vector corresponding to the road surface grayscale image; and obtain the asphalt particle density at the location of each pixel in the road surface grayscale image according to the grayscale change of the pixel in the road surface grayscale image. The asphalt particle density is obtained by: obtaining the maximum grayscale value point corresponding to each pixel according to the grayscale value of each first neighborhood pixel in the first preset neighborhood of each pixel; obtaining the first distance between each pixel and the central pixel; obtaining the asphalt particle density at the location of each pixel according to the maximum grayscale value point corresponding to each pixel and the first distance; obtaining the distortion factor of each optical flow vector according to the optical flow vector and the road surface grayscale image; obtaining the quality factor of each pixel in the road surface grayscale image according to the asphalt particle density at the location of each pixel and the distortion factor of each optical flow vector; and obtaining the abnormal area in the road surface construction image according to the quality factor of each pixel.

[0087] In one achievable manner, in terms of obtaining the abnormal area in the road surface construction image according to the quality factor of each pixel point, the construction quality detection device 12 is specifically used to: Obtaining abnormal pixel points whose quality factors are greater than a preset quality factor among the pixel points; Acquire target abnormal pixel points whose density of the abnormal pixel points is greater than a preset density; Determine the area composed of the target abnormal pixel points as the abnormal area.

[0088] In one achievable manner, in the aspect of obtaining the density of asphalt particles at the location of each pixel point in the road surface grayscale image, the construction quality detection device 12 is specifically used to: According to the grayscale value of each first neighborhood pixel point in the first preset neighborhood of each pixel point, obtaining the maximum grayscale value point corresponding to each pixel point; Obtaining a first distance between each of the pixel points and a central pixel point, wherein the central pixel point is a pixel point located at the center of the bottom of the road surface grayscale image; The density of asphalt particles at the location of each pixel point is obtained according to the maximum gray value point corresponding to each pixel point and the first distance.

[0089] In one achievable manner, in the aspect of obtaining the density of asphalt particles at the location of each pixel point according to the maximum gray value point corresponding to each pixel point and the first distance, the construction quality detection device 12 is specifically used for: Acquire each target maximum gray value point that is closest to each maximum gray value point corresponding to each pixel point; Obtaining the number of the maximum gray value points corresponding to each of the pixel points; The density of asphalt particles at the location of each pixel point is obtained based on the maximum gray value point corresponding to each pixel point, each target maximum gray value point, the number and the first distance.

[0090] In one implementable manner, in the aspect of obtaining the density of asphalt particles at the location of each pixel point according to the maximum gray value point corresponding to each pixel point, each target maximum gray value point, the number and the first distance, the construction quality detection device 12 is specifically used for: Obtaining the first grayscale value of each of the maximum grayscale value points corresponding to each of the pixel points; Acquire the second gray value of the target maximum gray value point that is closest to each of the maximum gray value points corresponding to each of the pixel points; Obtaining the grayscale value mean between each of the maximum grayscale value points corresponding to each of the pixel points and the corresponding target maximum grayscale value point; Obtaining a second distance between each of the maximum gray value points corresponding to each of the pixel points and the corresponding target maximum gray value point; The density of asphalt particles at the location of each pixel point is obtained according to the first grayscale value, the second grayscale value, the grayscale value average, the second distance, the number and the first distance corresponding to each pixel point.

[0091] In one possible implementation, in the aspect of obtaining the gray value average between each maximum gray value point corresponding to each pixel point and the corresponding target maximum gray value point, the construction quality detection device 12 is specifically used for: Obtain all intermediate gray value points between each maximum gray value point corresponding to each pixel point and the corresponding target maximum gray value point; Obtaining the grayscale value of each of the intermediate grayscale value points corresponding to each of the pixel points; Obtain the number of all the intermediate gray value points corresponding to each of the pixel points; The gray value mean is obtained according to the sum of the gray values ​​of each of the intermediate gray value points corresponding to each of the pixel points and the number.

[0092] In an implementable manner, in the aspect of obtaining the distortion factor of each optical flow vector according to the optical flow vector and the road surface grayscale image, the construction quality detection device 12 is specifically used for: Get the horizontal component of each optical flow vector; Obtaining the vertical component of each of the optical flow vectors; Acquire a third distance between the origin of each of the optical flow vectors and the center line of the road surface grayscale image; Acquire a fourth distance between the origin of each of the optical flow vectors and the bottom edge of the road surface grayscale image; The distortion factor of each of the optical flow vectors is acquired according to the vertical component, the horizontal component, the third distance, and the fourth distance of each of the optical flow vectors.

[0093] In one achievable manner, in the aspect of obtaining the quality factor of each pixel point in the road surface grayscale image according to the asphalt particle density at the location of each pixel point and the distortion factor of each optical flow vector, the construction quality detection device 12 is specifically used for: Acquire each second neighborhood pixel point in a second preset neighborhood corresponding to each of the pixel points; Obtaining a distortion factor of the target light loss amount closest to each of the pixel points; Obtaining a fifth distance between each of the pixel points and the corresponding nearest light loss amount; The quality factor of each pixel in the road surface grayscale image is obtained according to the asphalt particle density of each pixel, the asphalt particle density of the second neighborhood pixel, the distortion factor of the target light loss, and the fifth distance.

[0094] In an implementable manner, in the aspect of obtaining the quality factor of each pixel in the road surface grayscale image according to the asphalt particle density of each pixel, the asphalt particle density of the second neighborhood pixel, the distortion factor of the target light loss, and the fifth distance, the construction quality detection device 12 is specifically used for: Obtaining the asphalt particle density variance between the asphalt particle density of each of the pixel points and the asphalt particle density of each of the second neighborhood pixel points in the corresponding second preset neighborhood; The quality factor of each pixel point in the road surface grayscale image is obtained according to the asphalt particle density of each pixel point, the asphalt particle density variance, the distortion factor of the target light loss, and the fifth distance.

[0095] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A road engineering construction quality detection method based on machine vision, characterized in that: The method comprises: receiving a road surface construction image; grayscale the road surface construction image to obtain a road surface grayscale image; Obtaining an optical flow vector corresponding to the road surface grayscale image; According to the grayscale changes of the pixels in the road surface grayscale image, the density of asphalt particles at the location of each pixel in the road surface grayscale image is obtained; The method for obtaining the density of asphalt particles is as follows: according to the grayscale value of each first neighborhood pixel point in the first preset neighborhood of each pixel point, obtain the maximum grayscale value point corresponding to each pixel point; obtain the first distance between each pixel point and the central pixel point; according to the maximum grayscale value point corresponding to each pixel point and the first distance, obtain the density of asphalt particles at the location of each pixel point; According to the optical flow vectors and the road surface grayscale image, obtaining a distortion factor of each of the optical flow vectors; Obtaining a quality factor of each pixel point in the road surface grayscale image according to the density of asphalt particles at the location of each pixel point and the distortion factor of each optical flow vector; The abnormal area in the road surface construction image is obtained according to the quality factor of each pixel point.

2. The road engineering construction quality detection method based on machine vision according to claim 1 is characterized in that: The obtaining of the abnormal area in the road surface construction image according to the quality factor of each pixel point includes: Obtaining abnormal pixel points whose quality factors are greater than a preset quality factor among the pixel points; Acquire target abnormal pixel points whose density of the abnormal pixel points is greater than a preset density; Determine the area composed of the target abnormal pixel points as the abnormal area.

3. The road engineering construction quality detection method based on machine vision according to claim 1 is characterized in that: The step of obtaining the density of asphalt particles at the location of each pixel point according to the maximum gray value point corresponding to each pixel point and the first distance includes: Acquire the maximum gray value point closest to each of the maximum gray value points corresponding to each of the pixel points as the target maximum gray value point; Obtaining the number of the maximum gray value points corresponding to each of the pixel points; The density of asphalt particles at the location of each pixel point is obtained according to the maximum gray value point corresponding to each pixel point, each target maximum gray value point, the number and the first distance.

4. The road engineering construction quality detection method based on machine vision according to claim 3 is characterized in that: The step of obtaining the density of asphalt particles at the location of each pixel point according to the maximum gray value point corresponding to each pixel point, each target maximum gray value point, the number and the first distance includes: Obtaining the first grayscale value of each of the maximum grayscale value points corresponding to each of the pixel points; Acquire the second gray value of the target maximum gray value point that is closest to each of the maximum gray value points corresponding to each of the pixel points; Obtaining the grayscale value mean between each of the maximum grayscale value points corresponding to each of the pixel points and the corresponding target maximum grayscale value point; Obtaining a second distance between each of the maximum gray value points corresponding to each of the pixel points and the corresponding target maximum gray value point; The density of asphalt particles at the location of each pixel point is obtained according to the first grayscale value, the second grayscale value, the grayscale value average, the second distance, the number and the first distance corresponding to each pixel point.

5. The method for detecting road engineering construction quality based on machine vision according to claim 4 is characterized in that: The step of obtaining the grayscale value mean between each of the maximum grayscale value points corresponding to each of the pixel points and the corresponding target maximum grayscale value point comprises: Obtain all intermediate gray value points between each maximum gray value point corresponding to each pixel point and the corresponding target maximum gray value point; Obtaining the grayscale value of each of the intermediate grayscale value points corresponding to each of the pixel points; Obtain the number of all the intermediate gray value points corresponding to each of the pixel points; The gray value mean is obtained according to the sum of the gray values ​​of each of the intermediate gray value points corresponding to each of the pixel points and the number.

6. The road engineering construction quality detection method based on machine vision according to claim 1 is characterized in that: The step of obtaining the distortion factor of each optical flow vector according to the optical flow vector and the road surface grayscale image comprises: Get the horizontal component of each optical flow vector; Obtaining the vertical component of each of the optical flow vectors; Acquire a third distance between the origin of each of the optical flow vectors and the center line of the road surface grayscale image; Acquire a fourth distance between the origin of each of the optical flow vectors and the bottom edge of the road surface grayscale image; The distortion factor of each of the optical flow vectors is acquired according to the vertical component, the horizontal component, the third distance, and the fourth distance of each of the optical flow vectors.

7. The road engineering construction quality detection method based on machine vision according to claim 1 is characterized in that: The step of obtaining the quality factor of each pixel in the road surface grayscale image according to the density of asphalt particles at the location of each pixel and the distortion factor of each optical flow vector comprises: Acquire each second neighborhood pixel point in a second preset neighborhood corresponding to each of the pixel points; Obtaining a distortion factor of the target light loss amount closest to each of the pixel points; Obtaining a fifth distance between each of the pixel points and the corresponding nearest light loss amount; The quality factor of each pixel in the road surface grayscale image is obtained according to the asphalt particle density of each pixel, the asphalt particle density of the second neighborhood pixel, the distortion factor of the target light loss, and the fifth distance.

8. The method for detecting road engineering construction quality based on machine vision according to claim 7 is characterized in that: The step of obtaining the quality factor of each pixel in the road surface grayscale image according to the asphalt particle density of each pixel, the asphalt particle density of the second neighborhood pixel, the distortion factor of the target light loss, and the fifth distance includes: Obtaining the asphalt particle density variance between the asphalt particle density of each of the pixel points and the asphalt particle density of each of the second neighborhood pixel points in the corresponding second preset neighborhood; The quality factor of each pixel point in the road surface grayscale image is obtained according to the asphalt particle density of each pixel point, the asphalt particle density variance, the distortion factor of the target light loss, and the fifth distance.

9. A road engineering construction quality inspection system based on machine vision, characterized in that: The system includes: a camera and a construction quality detection device; The camera is used to capture road surface construction images and send the road surface construction images to the machine vision-based road engineering construction quality detection device; The construction quality detection device is used to receive a road surface construction image; grayscale the road surface construction image to obtain a road surface grayscale image; obtain an optical flow vector corresponding to the road surface grayscale image; and obtain the asphalt particle density at the location of each pixel in the road surface grayscale image according to the grayscale change of the pixel in the road surface grayscale image. The asphalt particle density is obtained by: obtaining the maximum grayscale value point corresponding to each pixel according to the grayscale value of each first neighborhood pixel in the first preset neighborhood of each pixel; obtaining the first distance between each pixel and the central pixel; obtaining the asphalt particle density at the location of each pixel according to the maximum grayscale value point corresponding to each pixel and the first distance; obtaining the distortion factor of each optical flow vector according to the optical flow vector and the road surface grayscale image; obtaining the quality factor of each pixel in the road surface grayscale image according to the asphalt particle density at the location of each pixel and the distortion factor of each optical flow vector; and obtaining the abnormal area in the road surface construction image according to the quality factor of each pixel.

Images