A municipal road intelligent maintenance method
Through high-definition cameras, road images are collected and cracks and auxiliary line areas are segmented using image marking models, which solves the problem of missed detection and misjudgment in municipal road maintenance, and accurately evaluates and timely maintenance of road damage, improving vehicle driving safety .
Patent Information
- Application Number
- CN202411433961.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-10-15
AI Technical Summary
In the existing technology, municipal road maintenance methods have missed inspections or misjudgments, and road damage cannot be discovered and maintained in a timely manner, affecting the safety of vehicles.
High-definition cameras are used to collect road surface images, and threshold segmentation of crack areas and auxiliary line areas is performed through image marking models, the percentage of damage is determined, alarm prompts are generated and sent to the management backend, so as to achieve accurate assessment and timely maintenance of road damage.
It improves the accuracy and reliability of road damage inspection, ensures vehicle driving safety, and reduces the risk of missed inspection and misjudgment in manual inspections.
Smart Images

Figure CN118941972B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image processing, and in particular to an intelligent maintenance method for municipal roads. Background Art
[0002] With the continuous development of the economy and society and the accelerated progress of urban road construction, the mileage of road paving has gradually increased, and the resulting road damage problem has become increasingly serious. For example, when the road is used for a long time, the overweight of vehicles and natural factors will cause road damage such as wear, potholes, and cracks on the road surface, which seriously affects vehicle driving safety.
[0003] In order to ensure the driving safety of vehicles, the existing technology uses manual inspections and visual observations to check the degree of road damage. Affected by factors such as manual experience and visual fatigue, the road maintenance method of the existing technology may have missed inspections or misjudgments, and damaged roads cannot be maintained in time, thus affecting the driving safety of vehicles. Summary of the invention
[0004] In order to solve the technical problems of missed detection or misjudgment in the existing road maintenance methods, the purpose of the present invention is to provide an intelligent maintenance method for municipal roads, and the technical solutions adopted are as follows:
[0005] In a first aspect, an embodiment of the present invention provides a method for intelligent maintenance of municipal roads, the method comprising: acquiring a road surface image, and inputting the road surface image into an image marking model to obtain a marked image;
[0006] Performing threshold segmentation of crack regions on the marked image, dividing at least one crack region from at least one pixel point obtained after the segmentation, wherein a characteristic value of the crack region is greater than a first threshold value, and the characteristic value of the crack region is determined according to the number of pixels included in the crack region, the distance between each pixel point in the crack region and the center point of the crack region, and the number of pixels in the crack region in the horizontal and vertical directions;
[0007] Performing threshold segmentation of auxiliary line regions on the marked image, dividing at least one auxiliary line region from at least one pixel point obtained after segmentation, wherein the grayscale value of each pixel point in the auxiliary line region is greater than a preset value and the edge of the auxiliary line region is a straight line;
[0008] A damage percentage is determined based on the at least one crack region and the at least one auxiliary line region.
[0009] In a possible implementation manner of the first aspect, performing threshold segmentation of the crack region on the marked image, and dividing at least one crack region from at least one pixel point obtained after the segmentation, includes:
[0010] Performing threshold segmentation of the crack region on the marked image to obtain at least one pixel point, wherein the data of each pixel point includes a point position and a grayscale value;
[0011] At least one target area is divided from the at least one pixel, wherein each pixel in the target area satisfies a target area division condition, and the target area division condition refers to that the gray value of each pixel in the target area is a first preset value, and there are pixels with a gray value of the first preset value in a preset adjacent area of each pixel;
[0012] At least one preset crack region is selected from the at least one target region according to a preset crack region condition, wherein the preset crack region condition refers to that the number of pixels contained in the preset crack region is greater than a first preset number, the number of pixels in the horizontal direction of the crack region is less than a second preset number, the number of pixels in the vertical direction is less than a third preset number, and the distance between each pixel in the preset crack region and the center point of the preset crack region is greater than a preset distance, wherein the center point is the position center point of the preset crack region;
[0013] Determine the characteristic value of the preset crack area according to the number of pixels contained in the preset crack area, the distance between each pixel in the preset crack area and the center point of the preset crack area, the number of pixels in the horizontal direction in the crack area, and the number of pixels in the vertical direction in the crack area;
[0014] A preset crack region whose characteristic value is greater than a first threshold is determined as a crack region.
[0015] In a possible implementation manner of the first aspect, determining the characteristic value of the preset crack area according to the number of pixels included in the preset crack area, the distance between each pixel in the preset crack area and the center point of the preset crack area, the number of pixels in the horizontal direction of the crack area, and the number of pixels in the vertical direction of the crack area includes:
[0016]
[0017] in, represents the characteristic value of the vth preset crack area, Indicates In the preset crack area The coordinates of the pixels; Indicates The center point position of a preset crack area, Indicates The number of pixels in a preset crack area, Indicates The first The number of pixels in the horizontal direction. Indicates The first The number of pixels in the vertical direction of a pixel, norm() is the normalization function.
[0018] In a possible implementation manner of the first aspect, performing threshold segmentation of the auxiliary line area on the marked image, and dividing at least one auxiliary line area from at least one pixel point obtained after the segmentation, includes:
[0019] Performing threshold segmentation of the auxiliary line area on the marked image to obtain at least one pixel point, wherein the data of each pixel point includes a point position and a grayscale value;
[0020] Determine a pixel point whose grayscale is greater than a second preset value among the pixels as a target pixel point;
[0021] At least one auxiliary line region satisfying a preset condition is selected from the at least one target pixel point, wherein the preset condition is that the point positions of all target pixel points contained in the auxiliary line region are on a straight line.
[0022] In a possible implementation manner of the first aspect, determining the damage percentage according to the at least one crack region and the at least one auxiliary line region includes:
[0023] For each auxiliary line region, determining at least one overlapping crack region corresponding to the auxiliary line region;
[0024] Determine the damage percentage corresponding to each auxiliary line region according to each auxiliary line region and the corresponding at least one overlapping crack region;
[0025] The damage percentage corresponding to the road pavement image is determined according to the total number of the crack areas, the total number of the auxiliary line areas, the damage percentage corresponding to each of the auxiliary line areas, and the characteristic value of each overlapping crack area.
[0026] In a possible implementation manner of the first aspect, determining, for each auxiliary line region, at least one overlapping crack region corresponding to the auxiliary line region includes:
[0027] An overlapping crack area that meets the overlap condition is selected from the at least one crack area, wherein the overlap condition refers to the presence of overlapping pixel points in the overlapping crack area that have the same position as the auxiliary line area, and the number of the overlapping pixel points is greater than a fourth preset number.
[0028] In a possible implementation manner of the first aspect, determining, according to each auxiliary line region and the corresponding at least one overlapping crack region, a damage percentage corresponding to the auxiliary line region includes:
[0029] For each auxiliary line region, the number of all pixels contained in the auxiliary line region is used as a first parameter, the total number of pixels whose grayscale values of the pixels in the auxiliary line region are a second preset value is used as a second parameter, and the number of the overlapping crack regions is used as a third parameter;
[0030] The damage percentage corresponding to the auxiliary line area is determined according to the first parameter, the second parameter, the third parameter corresponding to the auxiliary line area and the characteristic value of each overlapping crack area corresponding to the auxiliary line area.
[0031] In a possible implementation manner of the first aspect, determining the damage percentage corresponding to the auxiliary line area according to the first parameter, the second parameter, the third parameter corresponding to the auxiliary line area, and the characteristic value of each overlapping crack area corresponding to the auxiliary line area includes:
[0032]
[0033] in, Indicates the damage percentage of the nth auxiliary line curve, For the The first parameter corresponding to the auxiliary line area, Indicates The second parameter corresponding to the auxiliary line area, No. The third parameter corresponding to the auxiliary line area, Indicates The auxiliary line area corresponds to the The eigenvalues of the overlapping crack regions are: and All are positive integers.
[0034] In a possible implementation manner of the first aspect, determining the damage percentage corresponding to the road pavement image according to the total number of the crack areas, the total number of the auxiliary line areas, the damage percentage corresponding to each of the auxiliary line areas, and the characteristic value of each overlapping crack area includes:
[0035]
[0036] in, is the percentage of damage, , Indicates The auxiliary line area corresponds to the The eigenvalues of the overlapping crack regions, Indicates the total number of crack areas Indicates the total number of auxiliary line areas. and All are positive integers.
[0037] In a possible implementation manner of the first aspect, after determining the damage percentage according to the at least one crack region and the at least one auxiliary line region, the method further includes:
[0038] If the damage percentage is greater than or equal to a preset damage threshold, generating a damage warning prompt according to the road surface image, wherein the warning prompt includes the road location and the damage percentage;
[0039] The warning prompt is sent to a management background, so that the management background generates road maintenance information according to the road location and damage percentage obtained in the warning prompt information.
[0040] The present invention has the following beneficial effects: the present invention inputs the road pavement image collected by the high-definition camera into the image marking model to obtain the marked image, and performs threshold segmentation of the crack area on the marked image to divide at least one crack area from at least one pixel point obtained after the segmentation, and at the same time performs threshold segmentation of the auxiliary line area on the marked image to divide at least one auxiliary line area from at least one pixel point obtained after the segmentation, thereby determining the damage percentage according to at least one crack area and at least one auxiliary line area. The present invention determines the damage percentage corresponding to the road pavement image based on the crack information and auxiliary line information implicit in the road pavement image, determines the degree of road damage by the damage percentage, and improves the accuracy and reliability of inspecting the degree of road damage. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] 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.
[0042] Figure 1 It is a flowchart of a municipal road intelligent maintenance method provided by an embodiment of the present invention;
[0043] Figure 2 A road surface image provided by an embodiment of the present invention;
[0044] Figure 3It is a schematic diagram of post-processing steps of the municipal road intelligent maintenance method provided by an embodiment of the present invention;
[0045] Figure 4 is a structural block diagram of a municipal road intelligent maintenance device provided by an embodiment of the present invention;
[0046] Figure 5 It is a schematic diagram of the structure of a server provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0047] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.
[0048] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include a particular feature, structure or characteristic described in conjunction with the embodiment. Thus, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.
[0049] There are lane lines and auxiliary lines such as turn signs drawn on municipal roads. Cracks on the lanes may damage the lane lines and turn signs, causing a certain degree of damage to the lane lines, etc. Since lane lines and turn signs are important for people driving vehicles, road maintenance is required in a timely manner when lane lines, etc. are damaged. Usually, the auxiliary lines are generally white, which has a great degree of color difference from the color of the road surface, and the color of the road surface is generally black. Therefore, by analyzing the distribution of crack areas on the road surface and combining the distribution status of the auxiliary lines on the road, the degree of damage to the road auxiliary lines caused by the cracks is determined, thereby evaluating the degree of damage to the road surface.
[0050] Figure 1 1 is a flow chart of the municipal road intelligent maintenance method provided by the embodiment of the present invention. As an example but not a limitation, the execution subject of this embodiment is a backend server in the road pavement maintenance system, and this embodiment is not particularly limited here.
[0051] S101: Acquire a road surface image, and input the road surface image into an image labeling model to obtain a labeled image.
[0052] It should be understood that in the embodiment of the present invention, high-definition cameras on both sides of the road are used to regularly collect road surface images. Specifically, the collected road surface images are as follows: Figure 2 As shown, Figure 2 The road surface image provided by the embodiment of the present invention. Further, a high-definition camera is set to transmit the collected road surface image to the background server of the road maintenance system. Exemplarily, for the same section of road surface, high-definition cameras are set on both sides of the road surface at different positions according to the length of the entire road to regularly capture road surface images. Exemplarily, in order to improve the clarity of the collected road surface image, high-definition cameras can be set at multiple angles to reduce the blind spots of road surface image collection.
[0053] It should be noted that the road surface image captured by the high-definition camera is a high-definition image of the road surface. In an embodiment of the present invention, by inputting the road surface image into a trained image labeling model, the image labeling model outputs a labeled image corresponding to the road surface image. Optionally, the pixel point in the lower left corner of the collected road surface image is used as the coordinate origin to construct an XY coordinate system. Exemplarily, the road surface labeling model is obtained by training a labeled image library, wherein the labeled image library contains several road surface sample images and a labeled image corresponding to each road surface sample image. Among them, the labeled image corresponding to each road surface sample image can be manually labeled, or the road surface sample image can be labeled using artificial intelligence technology, and the image labeling method is not limited here.
[0054] S102: Perform threshold segmentation of crack areas on the marked image, and divide at least one crack area from at least one pixel point obtained after the segmentation, wherein a characteristic value of the crack area is greater than a first threshold value, and the characteristic value of the crack area is determined based on the number of pixels contained in the crack area, the distance between each pixel point in the crack area and the center point of the crack area, and the number of pixels in the crack area in the horizontal and vertical directions.
[0055] Exemplarily, the marked road surface image is subjected to threshold segmentation to distinguish normal road surface pixels and non-road surface pixels in the image. For example, non-road surface pixels are crack pixels or manhole cover pixels. Exemplarily, since the color of cracks on the lane is significantly different from the color of other places on the lane under the illumination of sunlight or light, the threshold segmentation in the embodiment of the present invention adopts the Otsu threshold method, thereby segmenting more non-road surface pixels.
[0056] Exemplarily, the characteristic value of the crack area is greater than a first threshold value, and the characteristic value of the crack area is determined based on the number of pixels contained in the crack area, the distance between each pixel point in the crack area and the center point of the crack area, and the number of pixels in the horizontal and vertical directions in the crack area, and the area with a characteristic value greater than the first threshold value is determined as the crack area.
[0057] Specifically, the specific steps of implementing the division of the crackle area in S102 are as follows:
[0058] S1021: Perform threshold segmentation of the crack area on the marked image to obtain at least one pixel point.
[0059] It should be understood that the data of each pixel point includes the point position and the grayscale value.
[0060] S1022: Divide at least one target area from at least one pixel point.
[0061] Exemplarily, each pixel in the target area satisfies the target area division condition. Specifically, the target area division condition means that the grayscale value of each pixel in the target area is a first preset value, and there are pixels with grayscale values of the first preset value in the preset adjacent areas of each pixel.
[0062] Specifically, the first preset value is 0, and the preset adjacent area can be an adjacent area within a 5*5 range around the current pixel. The process of dividing the target area is: select the first pixel on the image after threshold segmentation. Analyze the pixel with gray value of 0, and analyze whether there is a pixel with gray value of the first preset value in the surrounding 5*5 range. If there is a pixel with gray value of the first preset value, compare all the pixels in this range with the first preset value. pixels are divided into the same target area. Then select The pixels are divided into pixels in the same area to determine whether there are pixels with a grayscale value of the first preset value within a 5*5 range around them, until there are no other pixels distributed within a 5*5 range around the pixels in this area.
[0063] S1023: Select at least one preset crack region from at least one target region according to a preset crack region condition.
[0064] Exemplarily, the preset crack area condition means that the number of pixel points contained in the preset crack area is greater than a first preset number, the number of pixel points in the horizontal direction in the crack area is less than a second preset number, the number of pixel points in the vertical direction is less than a third preset number, and the distance between each pixel point in the preset crack area and the center point of the preset crack area is greater than a preset distance, wherein the center point is the position center point of the preset crack area.
[0065] Exemplarily, image processing is performed on multiple road surface images included in an existing road surface sample image set. The image processing process includes marking the crack area and marking the number of all pixels included in the crack area, the number of pixels in the horizontal direction, and the number of pixels in the vertical direction. The average value of the number of all pixels included in each crack area in each image in the processed road surface sample image set is used as the first preset number, and the average value of the number of pixels in the horizontal direction is used as the second preset number, and the average value of the number of pixels in the vertical direction is used as the third preset number.
[0066] It should be understood that due to the existence of other uncontrollable factors on the road surface, there are not only crack pixels on the image after threshold segmentation, but also pixels in the manhole cover area and so on. According to the slender characteristics of the crack, the pixel area belonging to the crack area is identified. Since the shape distribution of the crack is slender, the distance between the pixel points and the center in the crack area will be different. The number of pixels in the crack area is also greater than the number of pixels in other influencing factors. Moreover, due to the shape distribution of the pixels in the crack area, the number of pixels distributed in the horizontal and vertical directions for each pixel is small. Therefore, the greater the variance between the regional pixels and the regional center, the more regional pixels, and the smaller the average number of pixels distributed in the horizontal and vertical directions, the greater the possibility that the area belongs to the lane crack area.
[0067] S1024: Determine a characteristic value of the preset crack area according to the number of pixels contained in the preset crack area, the distance between each pixel in the preset crack area and the center point of the preset crack area, the number of pixels in the horizontal direction in the crack area, and the number of pixels in the vertical direction in the crack area.
[0068] Specifically, the formula for determining the characteristic value of the preset crack area is shown in formula (1):
[0069] (1)
[0070] in, represents the characteristic value of the vth preset crack area, Indicates In the preset crack area The coordinates of the pixels; Indicates The center point position of a preset crack area, Indicates The number of pixels in a preset crack area, Indicates The first The number of pixels in the horizontal direction. Indicates The first The number of pixels in the vertical direction of a pixel, norm() is the normalization function, Indicates The distance between the pixel point in the preset crack area and the pixel point at the center position, It indicates the distribution of pixels. It should be noted that the normalization function can use conventional mathematical methods such as linear normalization function or function mapping.
[0071] S1025: Determine a preset crack region whose characteristic value is greater than a first threshold as a crack region.
[0072] Specifically, the first threshold is set to It should be understood that the characteristic value represents the probability value of the crack region, and therefore, when the characteristic value of the crack region is higher than the set first threshold, the accuracy of the crack region determined by the embodiment of the present invention is higher.
[0073] S103: Perform threshold segmentation of auxiliary line areas on the marked image, and divide at least one auxiliary line area from at least one pixel point obtained after segmentation, wherein the grayscale value of each pixel point in the auxiliary line area is greater than a preset value and the edge of the auxiliary line area is a straight line.
[0074] Specifically, the auxiliary line area of the marked image is threshold-segmented to obtain at least one pixel point, the data of each pixel point includes the point position and the grayscale value, and the pixel point whose grayscale is greater than the second preset value is determined as the target pixel point, and finally at least one auxiliary line area that meets the preset condition is selected from the at least one target pixel point, and the preset condition means that the point positions of all the target pixel points contained in the auxiliary line area are on a straight line.
[0075] It should be understood that, on the one hand, the image of the road surface marking can be re-threshold segmented by using the Otsu threshold method to identify the distribution of the auxiliary lines on the road. On the other hand, since the auxiliary lines on the road surface are brighter in color, the target pixel points with a grayscale value of 1 in the image after threshold segmentation can be set to correspond to the auxiliary lines on the road surface. Specifically, according to the performance of continuous pixel points, the pixel points with a grayscale value of 1 are divided into different blocks, that is, different blocks correspond to different auxiliary lines. Exemplarily, the second preset value is set to 1.
[0076] Furthermore, the edge lines of the auxiliary line area, i.e., the lane auxiliary lines, are generally presented as straight lines, which allows the coordinates of the pixel points located on the lane auxiliary lines to be fitted into a function, i.e., the point positions of all target pixel points contained in the auxiliary line area are on a straight line.
[0077] S104: Determine a damage percentage according to at least one crack region and at least one auxiliary line region.
[0078] It should be understood that the auxiliary line area is usually the lane lines and auxiliary lines such as turn signs on the road surface. When cracks on the road surface damage the auxiliary lines, that is, when cracks appear in the lane lines or turn signs, the auxiliary lines will be damaged to a certain extent. Therefore, the percentage of damage to the road surface can be evaluated by the degree to which the cracks damage the auxiliary lines.
[0079] Specifically, first, for each auxiliary line area, at least one overlapping crack area corresponding to the auxiliary line area is determined. Secondly, an overlapping crack area that meets the overlap condition is selected from at least one crack area, wherein the overlap condition refers to the presence of overlapping pixels in the overlapping crack area at the same position as the auxiliary line area, and the number of overlapping pixels is greater than a fourth preset number. Specifically, the fourth preset number is set to 5. According to each auxiliary line area and the corresponding at least one overlapping crack area, the percentage of damage corresponding to the auxiliary line area is determined. Further, for each auxiliary line area, the number of all pixels contained in the auxiliary line area is taken as the first parameter, the total number of pixels whose grayscale value of the pixels in the auxiliary line area is the second preset value is taken as the second parameter, and the number of overlapping crack areas is taken as the third parameter. Finally, according to the first parameter, the second parameter, the third parameter corresponding to the auxiliary line area and the characteristic value of each overlapping crack area corresponding to the auxiliary line area, the percentage of damage corresponding to the auxiliary line area is determined.
[0080] It should be understood that on the road surface, some auxiliary line areas may be damaged by the crack area, and some auxiliary line areas may not be damaged by the crack area. Therefore, by identifying the overlapped crack area with the same overlapped pixel points as the auxiliary line area, and the overlapped crack area with the number of overlapped pixel points greater than the preset number through the overlapped condition, the damage degree of the auxiliary line area can be accurately evaluated using the overlapped crack area. Specifically, after identifying the overlapped crack area corresponding to each auxiliary line area, the damage percentage corresponding to the auxiliary line area is determined according to each auxiliary line area and the corresponding at least one overlapped crack area.
[0081] Specifically, after determining the damage percentage corresponding to the auxiliary line area, for each auxiliary line area, the number of all pixels contained in the auxiliary line area is used as the first parameter, the total number of pixels in the auxiliary line area whose grayscale value is the second preset value is used as the second parameter, and the number of overlapping crack areas is used as the third parameter.
[0082] Optionally, the process of determining the damage percentage corresponding to the auxiliary line area according to the first parameter, the second parameter, the third parameter corresponding to the auxiliary line area and the characteristic value of each overlapping crack area corresponding to the auxiliary line area proposed in the embodiment of the present invention is as shown in formula (2):
[0083] (2)
[0084] in, Indicates the damage percentage of the nth auxiliary line curve, For the The first parameter corresponding to the auxiliary line area, Indicates The second parameter corresponding to the auxiliary line area, No. The third parameter corresponding to the auxiliary line area, Indicates The auxiliary line area corresponds to the The eigenvalues of the overlapping crack regions are: and All are positive integers.
[0085] It should be understood that when The larger the difference, the greater the degree of wear and tear of the auxiliary line due to the existence of the crack area, and the greater the degree of damage to the auxiliary line area. On the other hand, the more crack areas there are and the larger the characteristic value of each crack area, that is, the greater the degree of crack manifestation, the greater the degree of damage to the auxiliary line.
[0086] In an embodiment of the present invention, after determining the damage percentage corresponding to each auxiliary line area, the damage percentage corresponding to the road pavement image can be determined based on the total number of crack areas, the total number of auxiliary line areas, the damage percentage corresponding to each auxiliary line area, and the characteristic value of each overlapping crack area. It can be understood that the more crack areas there are on the road pavement, and the greater the degree of damage to the auxiliary line areas caused by the crack areas, the greater the degree of damage to the road pavement. Specifically, the process of determining the damage percentage corresponding to the road pavement image based on the total number of crack areas, the total number of auxiliary line areas, the damage percentage corresponding to each auxiliary line area, and the characteristic value of each overlapping crack area is as shown in formula (3):
[0087] (3)
[0088] in, The percentage of damage Indicates the damage percentage of the nth auxiliary line curve, Indicates The auxiliary line area corresponds to the The eigenvalues of the overlapping crack regions, represents the total number of crack areas, Indicates the total number of auxiliary line areas. and All are positive integers.
[0089] The municipal road intelligent maintenance method provided by the embodiment of the present invention processes the collected road pavement image by using the image marking model to obtain the marked image corresponding to the road pavement image, and processes the marked image to determine the crack area and auxiliary line area contained in the road pavement image, and analyzes the damage percentage of the road through the crack area and auxiliary line area. The municipal road intelligent maintenance method provided by the embodiment of the present invention estimates the degree of damage to the road based on the crack information and auxiliary line information implicit in the road pavement image, thereby improving the accuracy and reliability of inspecting the degree of damage to the road.
[0090] Figure 3 Schematic diagram of post-processing steps of the municipal road intelligent maintenance method provided by the embodiment of the present invention. Figure 3 As shown, in Figure 1 After determining the damage percentage according to at least one crack area and at least one auxiliary line area in the embodiment of the present invention, the embodiment of the present invention proposes a process for performing road maintenance according to the damage percentage, which is as follows:
[0091] S301: If the damage percentage is greater than or equal to a preset damage threshold, a damage warning prompt is generated according to the road surface image, wherein the warning prompt includes the road location and the damage percentage.
[0092] Specifically, the preset damage threshold is set to .exist Figure 1 After determining the damage percentage of the current road image, if the damage percentage is greater than a preset damage threshold When the high-definition camera is used to detect the road surface damage, it can be determined that the road surface currently photographed by the high-definition camera is severely damaged and the road needs to be maintained in a timely manner.
[0093] Furthermore, a damage alarm is generated when the damage percentage is greater than or equal to a preset damage threshold. Specifically, the damage alarm includes the road location and the damage percentage.
[0094] S302: Send the alarm prompt to the management background, so that the management background generates road maintenance information according to the road location and damage percentage obtained in the alarm prompt information.
[0095] In an embodiment of the present invention, an alarm is sent to a management background of the road surface, and in response to the alarm information sent by the management background, the damaged road is maintained according to the road location and damage percentage contained in the alarm information.
[0096] Furthermore, material consumption ratios corresponding to different damage percentages are set in the management background. Specifically, corresponding material consumption ratios are selected to perform intelligent maintenance on the road.
[0097] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0098] Corresponding to the municipal road intelligent maintenance method of the above embodiment, Figure 4 1 is a structural block diagram of a municipal road intelligent maintenance device provided in an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown.
[0099] Reference Figure 4 The municipal road intelligent maintenance device includes: a marking module 401, a first acquisition module 402, a second acquisition module 403, and a determination module 404.
[0100] The marking module 401 is used to obtain a road surface image and input the road surface image into an image marking model to obtain a marked image;
[0101] A first acquisition module 402 is used to perform threshold segmentation of crack regions on the marked image, and divide at least one crack region from at least one pixel point obtained after the segmentation;
[0102] The second acquisition module 403 is used to perform threshold segmentation of the auxiliary line area on the marked image, and divide at least one auxiliary line area from at least one pixel point obtained after the segmentation;
[0103] The determination module 404 is used to determine the damage percentage according to the at least one crack area and the at least one auxiliary line area.
[0104] It should be noted that the information interaction, execution process, etc. between the above-mentioned modules / units are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0105] in addition, Figure 4 The municipal road intelligent maintenance device shown can be a software unit, a hardware unit, or a combination of software and hardware units built into an existing control chip, or it can be integrated into the terminal device as an independent pendant, or it can exist as an independent terminal device.
[0106] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0107] Figure 5 is a schematic diagram of the structure of a server provided in an embodiment of the present invention. The server 50 provided in an embodiment of the present invention includes: at least one processor 51 ( Figure 5 Only one is shown), a memory 52 and a computer program 53 stored in the memory 52 and executable on the at least one processor 51, wherein the processor 51 implements the steps executed by the server in any of the above-mentioned embodiments of the municipal road intelligent maintenance method when executing the computer program 53.
[0108] The processor 51 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0109] In some embodiments, the memory 52 may be an internal storage unit of the server 50, such as a hard disk or memory of the server 50. In other embodiments, the memory 52 may also be an external storage device of the server 50, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the server 50. Further, the server 50 may also include both an internal storage unit of the server 50 and an external storage device. The memory 52 is used to store an operating system, an application program, a boot loader, data, and other programs, such as the program code of the computer program. The memory 52 may also be used to temporarily store data that has been output or is to be output.
[0110] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the server-executed steps in any of the above-mentioned municipal road intelligent maintenance method embodiments can be implemented.
[0111] An embodiment of the present invention provides a computer program product. When the computer program product runs on a terminal device, the terminal device implements the steps executed by the server in any of the above-mentioned municipal road intelligent maintenance method embodiments.
[0112] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.
[0113] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0114] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0115] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0116] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0117] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A method for intelligent maintenance of municipal roads, It is characterized in that The method comprises: Acquire a road surface image, and input the road surface image into an image labeling model to obtain a labeled image; Performing threshold segmentation of crack regions on the marked image, dividing at least one crack region from at least one pixel point obtained after the segmentation, wherein a characteristic value of the crack region is greater than a first threshold value, and the characteristic value of the crack region is determined according to the number of pixels included in the crack region, the distance between each pixel point in the crack region and the center point of the crack region, and the number of pixels in the crack region in the horizontal and vertical directions; Performing threshold segmentation of auxiliary line regions on the marked image, dividing at least one auxiliary line region from at least one pixel point obtained after segmentation, wherein the grayscale value of each pixel point in the auxiliary line region is greater than a preset value and the edge of the auxiliary line region is a straight line; determining a damage percentage based on the at least one crack region and the at least one auxiliary line region; The step of performing threshold segmentation of crack regions on the marked image and dividing at least one crack region from at least one pixel point obtained after the segmentation comprises: Performing threshold segmentation of the crack region on the marked image to obtain at least one pixel point, wherein the data of each pixel point includes a point position and a grayscale value; At least one target area is divided from the at least one pixel, wherein each pixel in the target area satisfies a target area division condition, and the target area division condition refers to that the gray value of each pixel in the target area is a first preset value, and there are pixels with a gray value of the first preset value in a preset adjacent area of each pixel; At least one preset crack region is selected from the at least one target region according to a preset crack region condition, wherein the preset crack region condition refers to that the number of pixels contained in the preset crack region is greater than a first preset number, the number of pixels in the horizontal direction of the crack region is less than a second preset number, the number of pixels in the vertical direction is less than a third preset number, and the distance between each pixel in the preset crack region and the center point of the preset crack region is greater than a preset distance, wherein the center point is the position center point of the preset crack region; Determine the characteristic value of the preset crack area according to the number of pixels contained in the preset crack area, the distance between each pixel in the preset crack area and the center point of the preset crack area, the number of pixels in the horizontal direction in the crack area, and the number of pixels in the vertical direction in the crack area; Determine a preset crack region whose characteristic value is greater than a first threshold as a crack region; The step of performing threshold segmentation of the auxiliary line region on the marked image and dividing at least one auxiliary line region from at least one pixel point obtained after the segmentation includes: Performing threshold segmentation of the auxiliary line area on the marked image to obtain at least one pixel point, wherein the data of each pixel point includes a point position and a grayscale value; Determine a pixel point whose grayscale is greater than a second preset value among the pixels as a target pixel point; At least one auxiliary line region satisfying a preset condition is selected from the at least one target pixel point, wherein the preset condition is that the point positions of all target pixel points contained in the auxiliary line region are on a straight line.
2. The municipal road intelligent maintenance method according to claim 1, It is characterized in that Determining the characteristic value of the preset crack area according to the number of pixels contained in the preset crack area, the distance between each pixel in the preset crack area and the center point of the preset crack area, the number of pixels in the horizontal direction of the crack area, and the number of pixels in the vertical direction of the crack area includes: in, represents the characteristic value of the vth preset crack area, Indicates In the preset crack area The coordinates of the pixels; Indicates The center point position of a preset crack area, Indicates The number of pixels in a preset crack area, Indicates The first The number of pixels in the horizontal direction. Indicates The first The number of pixels in the vertical direction of a pixel, norm() is the normalization function.
3. The municipal road intelligent maintenance method according to claim 1, It is characterized in that The determining of the damage percentage according to the at least one crack region and the at least one auxiliary line region comprises: For each auxiliary line region, determining at least one overlapping crack region corresponding to the auxiliary line region; Determine the damage percentage corresponding to each auxiliary line region according to each auxiliary line region and the corresponding at least one overlapping crack region; The damage percentage corresponding to the road pavement image is determined according to the total number of the crack areas, the total number of the auxiliary line areas, the damage percentage corresponding to each of the auxiliary line areas, and the characteristic value of each overlapping crack area.
4. The municipal road intelligent maintenance method according to claim 3, It is characterized in that The step of determining, for each auxiliary line region, at least one overlapping crack region corresponding to the auxiliary line region comprises: An overlapping crack area that meets the overlap condition is selected from the at least one crack area, wherein the overlap condition refers to the presence of overlapping pixel points in the overlapping crack area that have the same position as the auxiliary line area, and the number of the overlapping pixel points is greater than a fourth preset number.
5. The municipal road intelligent maintenance method according to claim 3, It is characterized in that The step of determining the damage percentage corresponding to each auxiliary line region according to each auxiliary line region and the corresponding at least one overlapping crack region includes: For each auxiliary line region, the number of all pixels contained in the auxiliary line region is used as a first parameter, the total number of pixels whose grayscale values of the pixels in the auxiliary line region are a second preset value is used as a second parameter, and the number of the overlapping crack regions is used as a third parameter; The damage percentage corresponding to the auxiliary line area is determined according to the first parameter, the second parameter, the third parameter corresponding to the auxiliary line area and the characteristic value of each overlapping crack area corresponding to the auxiliary line area.
6. The municipal road intelligent maintenance method according to claim 5, It is characterized in that The determining the damage percentage corresponding to the auxiliary line area according to the first parameter, the second parameter, the third parameter corresponding to the auxiliary line area and the characteristic value of each overlapping crack area corresponding to the auxiliary line area includes: in, Indicates the damage percentage of the nth auxiliary line curve, For the The first parameter corresponding to the auxiliary line area, Indicates The second parameter corresponding to the auxiliary line area, No. The third parameter corresponding to the auxiliary line area, Indicates The auxiliary line area corresponds to the The eigenvalues of the overlapping crack regions are: and All are positive integers.
7. The municipal road intelligent maintenance method according to claim 3, It is characterized in that The determining the damage percentage corresponding to the road pavement image according to the total number of the crack areas, the total number of the auxiliary line areas, the damage percentage corresponding to each of the auxiliary line areas, and the characteristic value of each overlapping crack area includes: in, The percentage of damage Indicates the damage percentage of the nth auxiliary line curve, Indicates The auxiliary line area corresponds to the The eigenvalues of the overlapping crack regions, represents the total number of crack areas, Indicates the total number of auxiliary line areas. and All are positive integers.
8. The municipal road intelligent maintenance method according to any one of claims 1 to 7, It is characterized in that After determining the damage percentage according to the at least one crack region and the at least one auxiliary line region, the method further includes: If the damage percentage is greater than or equal to a preset damage threshold, generating a damage warning prompt according to the road surface image, wherein the warning prompt includes the road location and the damage percentage; The warning prompt is sent to a management background, so that the management background generates road maintenance information according to the road location and damage percentage obtained in the warning prompt information.
