A method and system for identifying water damage on asphalt pavement

Abstract

The present invention discloses a method and system for identifying water damage on asphalt pavements. The method includes: determining whether each degree of correlation is greater than a first preset threshold; if a certain degree of correlation is not greater than the first preset threshold, removing a first asphalt pavement image from a set of asphalt pavement images, and updating the set of asphalt pavement images after removing the first asphalt pavement image according to a preset update strategy to obtain at least one updated target asphalt pavement image set; selecting a target asphalt pavement image from the set of target asphalt pavement images, obtaining a target core sample image at the location of a second target diseased area in the target asphalt pavement image, identifying the target core sample image, and using the identification result as the identification result for all target asphalt pavement images in the set of target asphalt pavement images. While reducing the need to collect core samples from asphalt pavements, the system can more accurately identify water damage on asphalt pavements.

Description

Technical Field

[0001] The present invention belongs to the technical field of asphalt pavement identification, and in particular relates to a method and system for identifying water damage on an asphalt pavement. Background Art

[0002] Water damage to asphalt pavements occurs when water enters the asphalt pavement structure, leading to a decrease in the adhesion between the asphalt and aggregate under the influence of vehicle loads and temperature fluctuations, resulting in loosening, flaking, potholes, and other road surface defects. Repairs for water damage differ from those for other non-water damage. For example, water damage repairs include spraying emulsified asphalt or modified emulsified asphalt on the pavement surface to form a waterproof layer and reduce water infiltration; laying a slurry seal to repair minor cracks and enhance the pavement's watertightness. Repairs for other non-water damage include: For cracks 2-5mm wide, hot asphalt grouting is used; for cracks wider than 5mm, modified asphalt grouting is used. Before grouting, debris and debris must be removed from the cracks to ensure they are dry. After grouting, coarse sand or 3-5mm stone chips are sprinkled on the surface to enhance the sealing effect.

[0003] To effectively identify water damage, existing technologies typically extract core samples from the affected area and then perform recognition on the captured core images. This method can accurately identify water-damaged areas on asphalt pavement. However, extracting core samples from each affected area individually often results in a high workload, which affects the efficiency of water damage identification. Summary of the Invention

[0004] The present invention provides a method and system for identifying water damage in asphalt pavement, which is used to solve the technical problem that extracting core samples from each damaged area one by one often results in a large workload, thereby affecting the efficiency of identifying water damage.

[0005] In a first aspect, the present invention provides a method for identifying water damage to an asphalt pavement, comprising:

[0006] Acquire asphalt pavement images of a continuous section of asphalt pavement, input each asphalt pavement image into a preset asphalt image recognition model, and output the asphalt image recognition model to obtain the defective area in each asphalt pavement image;

[0007] According to the location of each diseased area in the asphalt pavement image, the asphalt pavement images are divided using a preset area division rule to obtain at least one asphalt pavement image set;

[0008] Selecting a first asphalt pavement image and a second asphalt pavement image from a set of asphalt pavement images, and determining whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, wherein the first asphalt pavement image is the asphalt pavement image containing the largest number of defective areas, and the second asphalt pavement image is the asphalt pavement image containing the smallest number of defective areas;

[0009] If they are not the same asphalt pavement image, determining a degree of correlation between a first target defect area and other defect areas in the first asphalt pavement image, and judging whether each degree of correlation is greater than a first preset threshold, wherein the first target defect area is a defect area that is obtained by classifying the first asphalt pavement image into the set of asphalt pavement images, and the other defect areas are defect areas in the first asphalt pavement image excluding the target defect area;

[0010] If a certain correlation degree is not greater than a first preset threshold, removing the first asphalt road image from the certain asphalt road image set, and updating the certain asphalt road image set after removing the first asphalt road image according to a preset update strategy to obtain at least one updated target asphalt road image set;

[0011] A target asphalt pavement image is selected from a target asphalt pavement image set, and a target core sample image of a location of a second target defect area in the target asphalt pavement image is obtained. The target core sample image is identified, and the identification result is used as the identification result of all target asphalt pavement images in the target asphalt pavement image set.

[0012] In a second aspect, the present invention provides a system for identifying water damage to an asphalt pavement, characterized by comprising:

[0013] an acquisition module configured to acquire asphalt pavement images of a continuous section of asphalt pavement, input each asphalt pavement image into a preset asphalt image recognition model, and output the asphalt image recognition model to obtain a defective area in each asphalt pavement image;

[0014] a partitioning module configured to partition each asphalt pavement image according to a location of each diseased area in the asphalt pavement image using a preset area partitioning rule to obtain at least one asphalt pavement image set;

[0015] a first determination module configured to select a first asphalt pavement image and a second asphalt pavement image from a set of asphalt pavement images, and determine whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, wherein the first asphalt pavement image is the asphalt pavement image containing the largest number of defective areas, and the second asphalt pavement image is the asphalt pavement image containing the smallest number of defective areas;

[0016] a second judgment module configured to, if the images are not the same asphalt pavement image, determine a degree of correlation between a first target defect region and other defect regions in the first asphalt pavement image, and determine whether each degree of correlation is greater than a first preset threshold, wherein the first target defect region is a defect region that is classified into the set of asphalt pavement images by the first asphalt pavement image, and the other defect regions are defect regions in the first asphalt pavement image excluding the target defect region;

[0017] an updating module configured to remove the first asphalt pavement image from the set of asphalt pavement images if a certain correlation degree is not greater than a first preset threshold, and update the set of asphalt pavement images after removing the first asphalt pavement image according to a preset updating strategy to obtain at least one updated target asphalt pavement image set;

[0018] The recognition module is configured to select a target asphalt pavement image from a target asphalt pavement image set, obtain a target core sample image at a location of a second target diseased area in the target asphalt pavement image, recognize the target core sample image, and use the recognition result as the recognition result of all target asphalt pavement images in the target asphalt pavement image set.

[0019] In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method for identifying water damage to asphalt pavement of any embodiment of the present invention.

[0020] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the method for identifying water damage to an asphalt pavement according to any embodiment of the present invention.

[0021] The method and system for identifying water damage to asphalt pavement of the present application determine the degree of correlation between a first target diseased area and other diseased areas in a first asphalt pavement image, and judge whether each correlation degree is greater than a first preset threshold value. If a certain correlation degree is not greater than the first preset threshold value, the first asphalt pavement image is removed from a certain asphalt pavement image set, and the certain asphalt pavement image set after removing the first asphalt pavement image is updated according to a preset update strategy to obtain at least one updated target asphalt pavement image set, and a certain target asphalt pavement image is selected from the certain target asphalt pavement image set to obtain a target core sample image of the location of the second target diseased area in the certain target asphalt pavement image, identify the target core sample image, and use the identification result as the identification result of all target asphalt pavement images in the certain target asphalt pavement image set. In this way, while reducing the collection of core samples of the asphalt pavement, the water damage of the asphalt pavement can be more accurately identified. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 A flowchart of a method for identifying water damage to an asphalt pavement provided in one embodiment of the present invention;

[0024] Figure 2 This is a structural block diagram of a system for identifying water damage to asphalt pavement provided by one embodiment of the present invention;

[0025] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0027] See also Figure 1 , which shows a flow chart of a method for identifying water damage to asphalt pavement of the present application.

[0028] like Figure 1As shown, the method for identifying water damage to asphalt pavement specifically includes the following steps:

[0029] Step S101 : acquiring asphalt pavement images of a continuous section of asphalt pavement, inputting each asphalt pavement image into a preset asphalt image recognition model, and outputting the asphalt image recognition model to obtain the defective area in each asphalt pavement image.

[0030] In this step, the asphalt image recognition model can be trained using a YOLOv5 or YOLOv8 network. Specifically, collect asphalt pavement images containing cracks and rutting, ensuring that the collected image data covers different lighting conditions, angles, and disease types. Use annotation tools (such as LabelImg and CVAT) to annotate the cracks and rutting in the asphalt pavement images, generating bounding boxes and disease labels. Then, input the annotated asphalt pavement images and disease labels into a YOLOv5 or YOLOv8 network for iterative training to obtain the asphalt image recognition model.

[0031] After the asphalt image recognition model is trained, asphalt pavement images of a continuous section of asphalt pavement are acquired and fed into the pre-set asphalt image recognition model. The asphalt image recognition model then outputs the damaged areas within each asphalt pavement image. To better identify damaged areas caused by water damage, the present invention continues with steps S102 through S106.

[0032] Step S102 : dividing each asphalt pavement image according to the position of each defect area in the asphalt pavement image using a preset area division rule to obtain at least one asphalt pavement image set.

[0033] In this step, the asphalt pavement images are spliced together based on the chronological order of their acquisition, and the spliced images are placed in a pre-constructed two-dimensional coordinate system. Splicing the asphalt pavement images based on the chronological order of their acquisition specifically refers to sorting the asphalt pavement images based on the chronological order of their acquisition, and aligning one edge of two adjacent asphalt pavement images after the sorting process, thereby achieving splicing of the two adjacent asphalt pavement images. For example, for asphalt pavement image A and asphalt pavement image B, the right boundary line of asphalt pavement image A is aligned with the left boundary line of asphalt pavement image B, thereby completing the splicing of asphalt pavement image A and asphalt pavement image B. For another example, the lower left corner vertex of asphalt pavement image A is aligned with the origin of the two-dimensional coordinate system, thereby placing the spliced asphalt pavement images A and B in the pre-constructed two-dimensional coordinate system.

[0034] The coordinate information of the regional center points in each diseased area is obtained based on a two-dimensional coordinate system. Based on the coordinate information, each regional center point is divided using a regional division rule to obtain at least one set of regional center points. Specifically, the coordinate information of the regional center points in each diseased area can be obtained based on the two-dimensional coordinate system by obtaining the coordinate information of each pixel point in the diseased area in the two-dimensional coordinate system and taking the average of the coordinate information of each pixel point as the coordinate information of the regional center point. The regional center points of each diseased area can also be determined using a clustering algorithm (e.g., a K-Means clustering algorithm). The determination of regional center points is a conventional technique and is not further elaborated here.

[0035] The asphalt pavement images corresponding to each regional center point in a certain regional center point set are divided into the same asphalt pavement image set, that is, at least one asphalt pavement image set is obtained, wherein the certain regional center point set is any one regional center point set in the at least one regional center point set.

[0036] It should be noted that the specific area division rules are: setting different windows, and dividing all area center points into different windows according to the vertical coordinate values of each area center point; judging whether the difference between the first horizontal coordinate value of the first area center point and the second horizontal coordinate value of the second area center point in the same window is greater than a second preset threshold, wherein the first area center point and the second area center point are two adjacent area center points; if it is greater than the second preset threshold, the first area center point and the second area center point are not divided into the same area center point set; if it is not greater than the second preset threshold, the first area center point and the second area center point are divided into the same area center point set, that is, at least one area center set is obtained.

[0037] For example, suppose the windows are rectangular and contain window A, window B, and window C. The upper vertex of window A along the vertical axis corresponds to a vertical coordinate of 4, and the lower vertex of window A along the vertical axis corresponds to a vertical coordinate of 0. In this case, all region center points with vertical coordinates between 0 and 4 are assigned to window A. Similarly, region center points that meet the requirements can be assigned to windows B and C.

[0038] After the division, determine whether the difference in the horizontal coordinates of two adjacent region center points in window A is greater than a second preset threshold. If so, the two adjacent region center points are not divided into the same region center point set. If not, the two adjacent region center points are divided into the same region center point set. For example, window A contains region center point a, region center point b, region center point c, region center point d, and region center point e, in order.

[0039] Among them, if the difference in the horizontal coordinates of the regional center point a and the regional center point b is not greater than the second preset threshold, the difference in the horizontal coordinates of the regional center point b and the regional center point c is not greater than the second preset threshold, and the difference in the horizontal coordinates of the regional center point c and the regional center point d is not greater than the second preset threshold, then the regional center point a, the regional center point b and the regional center point c are divided into the same regional center point set.

[0040] Furthermore, setting different windows includes: obtaining coordinate information of the regional center points of each diseased area in all asphalt pavement images; clustering at least two regional center points in the same asphalt pavement image whose distance is not greater than a preset distance threshold according to the coordinate information to obtain at least one target regional center; selecting an asphalt pavement image with the largest number of target regional centers among all asphalt pavement images, and defining it as a target asphalt pavement image; setting a window according to each target regional center in the target asphalt pavement image, wherein the length of the window along the horizontal axis direction of the two-dimensional coordinate system is infinite, and the width of the window along the vertical axis direction of the two-dimensional coordinate system is twice the distance from the target regional center to the upper boundary or the lower boundary of the window.

[0041] In this embodiment, water damage often occurs in wheel tracks of the roadway, particularly in sections frequently traversed by heavy vehicles, or in areas with poor drainage, such as the inner side of super-elevated sections or waterlogged shoulders. This generally results in continuous water damage. Therefore, the asphalt pavement image is simultaneously divided based on the division of the region center points to obtain at least one set of asphalt pavement images. This allows asphalt pavement images with the same water damage type to be grouped together as much as possible, thereby improving the efficiency of water damage identification after executing steps S103-S106.

[0042] Step S103: Select a first asphalt pavement image and a second asphalt pavement image from a certain asphalt pavement image set, and determine whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, wherein the first asphalt pavement image is the asphalt pavement image containing the largest number of diseased areas, and the second asphalt pavement image is the asphalt pavement image containing the least number of diseased areas.

[0043] In this step, the defect areas of each asphalt pavement image in a set of asphalt pavement images are obtained. The asphalt pavement image with the largest number of defect areas is defined as the first asphalt pavement image, and the asphalt pavement image with the smallest number of defect areas is defined as the second asphalt pavement image. Therefore, a first asphalt pavement image and a second asphalt pavement image are selected from the set of asphalt pavement images, and a determination is made as to whether the first and second asphalt pavement images are the same asphalt pavement image.

[0044] In a specific embodiment, after determining whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, if they are the same asphalt pavement image, the first asphalt pavement image is not removed from a certain asphalt pavement image set, and a target core sample image of the location of the first target diseased area in the first asphalt pavement image is obtained; the target core sample image is input into a preset asphalt pavement water damage recognition model, and the asphalt pavement water damage recognition model outputs a water damage recognition result that is the same as the target core sample image; and the water damage recognition result is used as the recognition result of all target asphalt pavement images in a certain asphalt pavement image set.

[0045] Step S104: If they are not the same asphalt pavement image, determine the degree of association between the first target defect area and other defect areas in the first asphalt pavement image, and judge whether each degree of association is greater than a first preset threshold, wherein the first target defect area is the defect area that divides the first asphalt pavement image into the certain asphalt pavement image set, and the other defect areas are the defect areas in the first asphalt pavement image excluding the target defect area.

[0046] In this step, if they are not the same asphalt pavement image, determine whether there is partial overlap between the target diseased area and a certain diseased area; if there is partial overlap, directly define the value of the degree of association between the target diseased area and the certain diseased area as the first preset threshold; if there is no partial overlap, determine the target center point of the target diseased area and a certain center point of a certain diseased area, and define the distance between the target center point and the certain center point as the degree of association between the target diseased area and the certain diseased area.

[0047] For example, the first asphalt pavement image includes a defect area A, a defect area B, and a defect area C. The first asphalt pavement image is divided into a certain asphalt pavement image set according to the area center point of the defect area A. Therefore, the defect area A has a strong correlation with the first asphalt pavement image, and the defect area A is thus selected as the target defect area.

[0048] In a specific embodiment, after determining whether each correlation degree is greater than a first preset threshold, if each correlation degree is greater than the first preset threshold, the first asphalt pavement image is not removed from a certain asphalt pavement image set, and a target core sample image of the location of the first target diseased area in the first asphalt pavement image is obtained; the target core sample image is input into a preset asphalt pavement water damage recognition model, and the asphalt pavement water damage recognition model outputs a water damage recognition result that is the same as the target core sample image; and the water damage recognition result is used as the recognition result of all target asphalt pavement images in a certain asphalt pavement image set.

[0049] Step S105: If a certain correlation degree is not greater than a first preset threshold, the first asphalt pavement image is removed from the certain asphalt pavement image set, and the certain asphalt pavement image set after removing the first asphalt pavement image is updated according to a preset update strategy to obtain at least one updated target asphalt pavement image set.

[0050] In this step, if a certain correlation degree is not greater than a first preset threshold, the first asphalt pavement image is removed from the asphalt pavement image set, and a determination is made as to whether a distance between a third target defect area in a third asphalt pavement image and a fourth target defect area in a fourth asphalt pavement image in the asphalt pavement image set after the first asphalt pavement image is removed is greater than a second preset threshold. The third and fourth asphalt pavement images are adjacent asphalt pavement images, and the third target defect area is the defect area that causes the third asphalt pavement image to be classified into the asphalt pavement image set, and the fourth target defect area is the defect area that causes the third asphalt pavement image to be classified into the asphalt pavement image set. If the distance between the third and fourth target defect areas is greater than the second preset threshold, the third and fourth asphalt pavement images are respectively classified into different target asphalt pavement image sets to obtain at least one target asphalt pavement image set. If the distance between the third and fourth target defect areas is not greater than the second preset threshold, the third and fourth asphalt pavement images are respectively classified into the same target asphalt pavement image set to obtain at least one target asphalt pavement image set.

[0051] It should be noted that the third and fourth asphalt pavement images are only intended to define adjacent asphalt pavement images. When the second and fourth asphalt pavement images are adjacent, they are considered the same asphalt pavement image. The third and fourth target defect areas are the target defect areas in the third and fourth asphalt pavement images, respectively.

[0052] In this embodiment, if a certain correlation level is not greater than a first preset threshold, it indicates that the first target defect region in the first asphalt pavement image is likely part of a larger area caused by non-water damage. Therefore, the first asphalt pavement image is removed from the set of asphalt pavement images. This ensures that the defect regions in each asphalt pavement image in the set after the removal are all caused by water damage. Furthermore, the set of asphalt pavement images after the removal of the first asphalt pavement image is updated according to a preset update strategy to obtain at least one updated target asphalt pavement image set. This ensures that the defect types of each defect region in each asphalt pavement image in the same target asphalt pavement image set are as similar as possible, thereby effectively improving the accuracy of asphalt pavement image classification. Consequently, when executing step S106, the recognition result, when used as the recognition result for all target asphalt pavement images in the set of target asphalt pavement images, is as similar as possible to the actual recognition result of traversing and identifying all target asphalt pavement images in the set of target asphalt pavement images.

[0053] In one specific embodiment, a set of asphalt pavement images sequentially includes asphalt pavement image A, asphalt pavement image B, asphalt pavement image C, asphalt pavement image D, and asphalt pavement image E. After analysis, it is determined that asphalt pavement image D is the first asphalt pavement image, and the correlation between the first target defect area in asphalt pavement image D and the other defect areas is no greater than a first preset threshold. Asphalt pavement image D is then removed from the set of asphalt pavement images.

[0054] Afterwards, it is determined whether the distance between the target defect areas in the asphalt pavement image C and the asphalt pavement image E is greater than a second preset threshold. The distance is determined by the distance between the center points of the two target defect areas.

[0055] If the distance between the two target defect areas is greater than a second preset threshold, this indicates that the target defect area happened to exist in asphalt pavement image E, leading to the classification of asphalt pavement images A, B, C, D, and E into a single asphalt pavement image set. After asphalt pavement image D is removed, asphalt pavement image E, which was originally unrelated to asphalt pavement images A, B, and C, is also naturally separated. Therefore, asphalt pavement image C and asphalt pavement image E are each classified into different target asphalt pavement image sets.

[0056] Step S106: Select a target asphalt pavement image from a target asphalt pavement image set, obtain a target core sample image at the location of the second target defect area in the target asphalt pavement image, identify the target core sample image, and use the identification result as the identification result of all target asphalt pavement images in the target asphalt pavement image set.

[0057] In this step, the second target defect area is a defect area of a target asphalt pavement image divided into a target asphalt pavement image set;

[0058] Specifically, a target core sample image of a target diseased area in a target asphalt pavement image is obtained, wherein the target asphalt pavement image is any target asphalt pavement image in a target asphalt pavement image set; the target core sample image is input into a preset asphalt pavement water damage recognition model, and the asphalt pavement water damage recognition model outputs a water damage recognition result that is the same as the target core sample image; and the water damage recognition result is used as the recognition result of all target asphalt pavement images in the target asphalt pavement image set.

[0059] It should be noted that the asphalt pavement water damage recognition model can be trained using a convolutional neural network (CNN). For example, image processing techniques (such as gray-level co-occurrence matrix and fractal dimension) are used to extract texture features from the target core sample image. These texture features are then input into the trained asphalt pavement water damage recognition model for identification, resulting in water damage recognition results.

[0060] In summary, the method of the present application determines the degree of correlation between the first target disease area and other disease areas in the first asphalt pavement image, and judges whether each correlation degree is greater than a first preset threshold. If a certain correlation degree is not greater than the first preset threshold, the first asphalt pavement image is removed from a certain asphalt pavement image set, and the certain asphalt pavement image set after removing the first asphalt pavement image is updated according to a preset update strategy to obtain at least one updated target asphalt pavement image set, and selects a certain target asphalt pavement image from the certain target asphalt pavement image set, obtains a target core sample image of the location of the second target disease area in the certain target asphalt pavement image, identifies the target core sample image, and uses the identification result as the identification result of all target asphalt pavement images in the certain target asphalt pavement image set. In this way, while reducing the collection of core samples of the asphalt pavement, the water damage of the asphalt pavement can be more accurately identified.

[0061] See also Figure 2 , which shows a structural block diagram of an asphalt pavement water damage identification system of the present application.

[0062] like Figure 2As shown, the asphalt pavement water damage identification system 200 includes an acquisition module 210 , a division module 220 , a first judgment module 230 , a second judgment module 240 , an update module 250 and an identification module 260 .

[0063] Among them, the acquisition module 210 is configured to acquire asphalt pavement images of a continuous section of asphalt pavement, input each asphalt pavement image into a preset asphalt image recognition model, and the asphalt image recognition model outputs the diseased area in each asphalt pavement image; the division module 220 is configured to divide the each asphalt pavement image according to the position of each diseased area in the asphalt pavement image using a preset area division rule to obtain at least one asphalt pavement image set; the first judgment module 230 is configured to select a first asphalt pavement image and a second asphalt pavement image from a certain asphalt pavement image set, and judge whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, wherein the first asphalt pavement image is the asphalt pavement image containing the largest number of diseased areas, and the second asphalt pavement image is the asphalt pavement image containing the least number of diseased areas; the second judgment module 240 is configured to determine the difference between the first target diseased area in the first asphalt pavement image and the second target diseased area if they are not the same asphalt pavement image. The updating module 250 is configured to remove the first asphalt pavement image from the asphalt pavement image set if a certain correlation degree is not greater than the first preset threshold, and update the asphalt pavement image set after removing the first asphalt pavement image according to a preset updating strategy to obtain at least one updated target asphalt pavement image set; the identifying module 260 is configured to select a target asphalt pavement image from the target asphalt pavement image set, obtain a target core sample image at the location of the second target disease region in the target asphalt pavement image, identify the target core sample image, and use the identification result as the identification result of all target asphalt pavement images in the target asphalt pavement image set.

[0064] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects also apply to Figure 2 The modules in it will not be described in detail here.

[0065] In other embodiments, embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the method for identifying water damage to an asphalt pavement in any of the above method embodiments;

[0066] As an embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0067] Acquire asphalt pavement images of a continuous section of asphalt pavement, input each asphalt pavement image into a preset asphalt image recognition model, and output the asphalt image recognition model to obtain the defective area in each asphalt pavement image;

[0068] According to the location of each diseased area in the asphalt pavement image, the asphalt pavement images are divided using a preset area division rule to obtain at least one asphalt pavement image set;

[0069] Selecting a first asphalt pavement image and a second asphalt pavement image from a set of asphalt pavement images, and determining whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, wherein the first asphalt pavement image is the asphalt pavement image containing the largest number of defective areas, and the second asphalt pavement image is the asphalt pavement image containing the smallest number of defective areas;

[0070] If they are not the same asphalt pavement image, determining a degree of correlation between a first target defect area and other defect areas in the first asphalt pavement image, and judging whether each degree of correlation is greater than a first preset threshold, wherein the first target defect area is a defect area that is obtained by classifying the first asphalt pavement image into the set of asphalt pavement images, and the other defect areas are defect areas in the first asphalt pavement image excluding the target defect area;

[0071] If a certain correlation degree is not greater than a first preset threshold, removing the first asphalt road image from the certain asphalt road image set, and updating the certain asphalt road image set after removing the first asphalt road image according to a preset update strategy to obtain at least one updated target asphalt road image set;

[0072] A target asphalt pavement image is selected from a target asphalt pavement image set, and a target core sample image of a location of a second target defect area in the target asphalt pavement image is obtained. The target core sample image is identified, and the identification result is used as the identification result of all target asphalt pavement images in the target asphalt pavement image set.

[0073] The computer-readable storage medium may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function; the data storage area may store data generated based on the use of the asphalt pavement water damage identification system. Furthermore, the computer-readable storage medium may include high-speed random access memory and may also include storage, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include storage remote from the processor. Such remote storage may be connected to the asphalt pavement water damage identification system via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0074] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3 The example of a bus connection is used. Memory 320 is the aforementioned computer-readable storage medium. Processor 310 executes the various server functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in memory 320, thereby implementing the above-described method embodiment for identifying water damage to asphalt pavement. Input device 330 can receive input digital or character information and generate key signal input related to user settings and function control of the asphalt pavement water damage identification system. Output device 340 may include a display device such as a display screen.

[0075] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0076] As an embodiment, the electronic device is applied to a system for identifying water damage to asphalt pavement and is used on a client, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0077] Acquire asphalt pavement images of a continuous section of asphalt pavement, input each asphalt pavement image into a preset asphalt image recognition model, and output the asphalt image recognition model to obtain the defective area in each asphalt pavement image;

[0078] According to the location of each diseased area in the asphalt pavement image, the asphalt pavement images are divided using a preset area division rule to obtain at least one asphalt pavement image set;

[0079] Selecting a first asphalt pavement image and a second asphalt pavement image from a set of asphalt pavement images, and determining whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, wherein the first asphalt pavement image is the asphalt pavement image containing the largest number of defective areas, and the second asphalt pavement image is the asphalt pavement image containing the smallest number of defective areas;

[0080] If they are not the same asphalt pavement image, determining a degree of correlation between a first target defect area and other defect areas in the first asphalt pavement image, and judging whether each degree of correlation is greater than a first preset threshold, wherein the first target defect area is a defect area that is obtained by classifying the first asphalt pavement image into the set of asphalt pavement images, and the other defect areas are defect areas in the first asphalt pavement image excluding the target defect area;

[0081] If a certain correlation degree is not greater than a first preset threshold, removing the first asphalt road image from the certain asphalt road image set, and updating the certain asphalt road image set after removing the first asphalt road image according to a preset update strategy to obtain at least one updated target asphalt road image set;

[0082] A target asphalt pavement image is selected from a target asphalt pavement image set, and a target core sample image of a location of a second target defect area in the target asphalt pavement image is obtained. The target core sample image is identified, and the identification result is used as the identification result of all target asphalt pavement images in the target asphalt pavement image set.

[0083] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods of each embodiment or certain portions of the embodiments.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for identifying water damage to asphalt pavement, characterized in that: include: Acquire asphalt pavement images of a continuous section of asphalt pavement, input each asphalt pavement image into a preset asphalt image recognition model, and output the asphalt image recognition model to obtain the defective area in each asphalt pavement image; According to the location of each diseased area in the asphalt pavement image, the asphalt pavement images are divided using a preset area division rule to obtain at least one asphalt pavement image set; Selecting a first asphalt pavement image and a second asphalt pavement image from a set of asphalt pavement images, and determining whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, wherein the first asphalt pavement image is the asphalt pavement image containing the largest number of defective areas, and the second asphalt pavement image is the asphalt pavement image containing the smallest number of defective areas; If they are not the same asphalt pavement image, determining a degree of correlation between a first target defect area and other defect areas in the first asphalt pavement image, and judging whether each degree of correlation is greater than a first preset threshold, wherein the first target defect area is a defect area that is obtained by classifying the first asphalt pavement image into the set of asphalt pavement images, and the other defect areas are defect areas in the first asphalt pavement image excluding the target defect area; If a certain correlation degree is not greater than a first preset threshold, removing the first asphalt road image from the certain asphalt road image set, and updating the certain asphalt road image set after removing the first asphalt road image according to a preset update strategy to obtain at least one updated target asphalt road image set; A target asphalt pavement image is selected from a target asphalt pavement image set, and a target core sample image of a location of a second target defect area in the target asphalt pavement image is obtained. The target core sample image is identified, and the identification result is used as the identification result of all target asphalt pavement images in the target asphalt pavement image set.

2. The method for identifying water damage to an asphalt pavement according to claim 1, characterized in that: The asphalt pavement images are divided according to the positions of the diseased areas in the asphalt pavement images using a preset area division rule to obtain at least one asphalt pavement image set, including: The asphalt pavement images are stitched together based on the order of acquisition time, and the stitched asphalt pavement images are placed in a pre-constructed two-dimensional coordinate system; Obtaining coordinate information of regional center points in each diseased area according to the two-dimensional coordinate system, and dividing each regional center point according to the coordinate information using the regional division rule to obtain at least one set of regional center points; The asphalt pavement images corresponding to each regional center point in a certain regional center point set are divided into the same asphalt pavement image set, that is, the at least one asphalt pavement image set is obtained, wherein the certain regional center point set is any one regional center point set in the at least one regional center point set.

3. The method for identifying water damage to an asphalt pavement according to claim 2, characterized in that: The specific area division rules are as follows: Set different windows and divide all the center points of each area into different windows according to the vertical coordinate value of each area center point; Determine whether a difference between a first horizontal coordinate value of a first region center point and a second horizontal coordinate value of a second region center point in the same window is greater than a second preset threshold, wherein the first region center point and the second region center point are two adjacent region center points; If it is greater than a second preset threshold, the first area center point and the second area center point are not divided into the same area center point set; If it is not greater than a second preset threshold, the first region center point and the second region center point are divided into the same region center point set, that is, at least one region center set is obtained.

4. The method for identifying water damage to an asphalt pavement according to claim 3, characterized in that: The setting of different windows includes: Obtain the coordinate information of the center point of each diseased area in all asphalt pavement images; Clustering at least two region center points in the same asphalt pavement image whose distance is not greater than a preset distance threshold according to the coordinate information to obtain at least one target region center; An asphalt pavement image having the largest number of target area centers is selected from each asphalt pavement image and defined as a target asphalt pavement image; The window is set according to the center of each target area in the target asphalt pavement image, wherein the length of the window along the horizontal axis of the two-dimensional coordinate system is infinite, and the width of the window along the vertical axis of the two-dimensional coordinate system is twice the distance from the center of the target area to the upper boundary or the lower boundary of the window.

5. The method for identifying water damage to an asphalt pavement according to claim 1, characterized in that: After determining whether the first asphalt road surface image and the second asphalt road surface image are the same asphalt road surface image, the method further includes: If the asphalt pavement image is the same, the first asphalt pavement image is not removed from the set of asphalt pavement images, and a target core sample image of a location where a first target defect area is located in the first asphalt pavement image is obtained; Inputting the target core sample image into a preset asphalt pavement water damage recognition model, the asphalt pavement water damage recognition model outputting a water damage recognition result corresponding to the target core sample image; The water damage recognition result is used as the recognition result of all target asphalt pavement images in the certain asphalt pavement image set.

6. The method for identifying water damage to an asphalt pavement according to claim 1, characterized in that: Determining the degree of correlation between the target defect area and other defect areas in the first asphalt pavement image includes: Determine whether the target disease area partially overlaps with a certain disease area; If there is a partial overlap, the value of the correlation degree between the target disease area and the certain disease area is directly defined as the first preset threshold; If there is no partial overlap, determine the target center point of the target disease area and a certain center point of a certain disease area, and define the distance between the target center point and the certain center point as the degree of association between the target disease area and the certain disease area.

7. The method for identifying water damage to an asphalt pavement according to claim 1, characterized in that: After determining whether each correlation degree is greater than a first preset threshold, the method further includes: If all correlation levels are greater than a first preset threshold, the first asphalt pavement image is not removed from the set of asphalt pavement images, and a target core sample image of a location where a first target defect area is located in the first asphalt pavement image is obtained; Inputting the target core sample image into a preset asphalt pavement water damage recognition model, the asphalt pavement water damage recognition model outputting a water damage recognition result corresponding to the target core sample image; The water damage recognition result is used as the recognition result of all target asphalt pavement images in the certain asphalt pavement image set.

8. The method for identifying water damage to an asphalt pavement according to claim 1, characterized in that: The updating of a certain asphalt pavement image set after removing the first asphalt pavement image according to a preset updating strategy to obtain at least one updated target asphalt pavement image set includes: determining whether a distance between a third target defect area in a third asphalt pavement image and a fourth target defect area in a fourth asphalt pavement image in a set of asphalt pavement images after removing the first asphalt pavement image is greater than a second preset threshold, wherein the third asphalt pavement image and the fourth asphalt pavement image are two adjacent asphalt pavement images, and the third target defect area is the defect area that results from the third asphalt pavement image being classified into the set of asphalt pavement images, and the fourth target defect area is the defect area that results from the third asphalt pavement image being classified into the set of asphalt pavement images; If the distance between the third target defect area and the fourth target defect area is greater than a second preset threshold, dividing the third asphalt pavement image and the fourth asphalt pavement image into different target asphalt pavement image sets, respectively, to obtain at least one target asphalt pavement image set; If the distance between the third target defect area and the fourth target defect area is not greater than a second preset threshold, the third asphalt pavement image and the fourth asphalt pavement image are respectively divided into the same target asphalt pavement image set to obtain at least one target asphalt pavement image set.

9. The method for identifying water damage to an asphalt pavement according to claim 1, characterized in that: in, The second target defect area is a defect area obtained by dividing a target asphalt pavement image into the target asphalt pavement image set; The step of obtaining a target core sample image at a location of a target defect area in the target asphalt pavement image, identifying the target core sample image, and using the identification result as the identification result of all target asphalt pavement images in the target asphalt pavement image set includes: Acquire a target core sample image of a location of a target defect area in the target asphalt pavement image, wherein the target asphalt pavement image is any target asphalt pavement image in the target asphalt pavement image set; Inputting the target core sample image into a preset asphalt pavement water damage recognition model, the asphalt pavement water damage recognition model outputting a water damage recognition result corresponding to the target core sample image; The water damage recognition result is used as the recognition result of all target asphalt pavement images in the certain target asphalt pavement image set.

10. A system for identifying water damage to asphalt pavement, characterized in that: include: an acquisition module configured to acquire asphalt pavement images of a continuous section of asphalt pavement, input each asphalt pavement image into a preset asphalt image recognition model, and output the asphalt image recognition model to obtain a defective area in each asphalt pavement image; a partitioning module configured to partition each asphalt pavement image according to a location of each diseased area in the asphalt pavement image using a preset area partitioning rule to obtain at least one asphalt pavement image set; a first determination module configured to select a first asphalt pavement image and a second asphalt pavement image from a set of asphalt pavement images, and determine whether the first asphalt pavement image and the second asphalt pavement image are the same asphalt pavement image, wherein the first asphalt pavement image is the asphalt pavement image containing the largest number of defective areas, and the second asphalt pavement image is the asphalt pavement image containing the smallest number of defective areas; a second judgment module configured to, if the images are not the same asphalt pavement image, determine a degree of correlation between a first target defect region and other defect regions in the first asphalt pavement image, and determine whether each degree of correlation is greater than a first preset threshold, wherein the first target defect region is a defect region that is classified into the set of asphalt pavement images by the first asphalt pavement image, and the other defect regions are defect regions in the first asphalt pavement image excluding the target defect region; an updating module configured to remove the first asphalt pavement image from the set of asphalt pavement images if a certain correlation degree is not greater than a first preset threshold, and update the set of asphalt pavement images after removing the first asphalt pavement image according to a preset updating strategy to obtain at least one updated target asphalt pavement image set; The recognition module is configured to select a target asphalt pavement image from a target asphalt pavement image set, obtain a target core sample image at a location of a second target diseased area in the target asphalt pavement image, recognize the target core sample image, and use the recognition result as the recognition result of all target asphalt pavement images in the target asphalt pavement image set.

Images