Crack detection method and system suitable for desert area road

Abstract

The invention provides a crack detection method and system suitable for a desert area road, and relates to the technical field of road crack detection, and the method comprises the following steps: obtaining an original road image; preprocessing the original road image to obtain a to-be-recognized road image; for each to-be-recognized road image, calculating the texture direction of each pixel point, then determining whether to participate in voting according to the confidence level of the pixel point, and finally estimating the crack edge by adopting rapid local voting; the crack width is calculated, and cracks with the width larger than or equal to a preset threshold value are marked. Through the crack detection method suitable for the desert area road, the road crack covered by the sand and dust part can be accurately and reliably identified, and a more accurate and reliable basis is provided for road maintenance.

Description

Technical Field

[0001] The present application relates to the technical field of road crack detection, and in particular to a crack detection method and system suitable for roads in desert areas. Background Art

[0002] Roads in desert areas are of great significance for promoting local economic development, cultural exchanges and desert science research. Roads in desert areas are a difficult project that not only reflects human ability to understand nature, transform nature and overcome harsh environments, but also demonstrates the innovation and application of engineering technology under extreme conditions. Since roads in desert areas are often in extremely harsh environments, their monitoring and maintenance are of paramount importance.

[0003] For roads in desert areas, the cracks that appear are easily partially covered by sand and dust, making it difficult to accurately and reliably identify the cracks using existing image recognition algorithms, which is very unfavorable for road maintenance in desert areas. Summary of the invention

[0004] In order to solve the technical problems in the related art, the present application provides a crack detection method and system applicable to roads in desert areas. Through the crack detection method applicable to roads in desert areas of the present application, road cracks partially covered by sand and dust can be more accurately and reliably identified, providing a more accurate and reliable basis for road maintenance.

[0005] In order to achieve the above objectives, the technical solutions adopted in this application include:

[0006] According to a first aspect of the present application, a crack detection method applicable to roads in desert areas is provided, which is applicable to crack detection of road cracks filled with sand and dust, and comprises the following steps:

[0007] Step S1: obtaining an original road image;

[0008] Step S2: preprocessing the original road image to obtain a road image to be identified;

[0009] Step S3: for each road image to be identified, the texture direction of each pixel is calculated, and then the confidence level of the pixel is determined whether to participate in the voting, and finally the crack edge is estimated by fast local voting;

[0010] Step S4: Calculate the crack width and mark the cracks whose width is greater than or equal to a preset threshold.

[0011] Optionally, in step S1, the original road image is captured by a road inspection vehicle.

[0012] Optionally, the step S2 specifically includes:

[0013] Step S2-1: first grayscale the original road image;

[0014] Step S2-2: performing image filtering on the image obtained in step S2-1;

[0015] Step S2-3: Perform image enhancement on the image obtained in step S2-2.

[0016] Step S2-4: binarize the image obtained in step S2-3 to obtain a road image to be identified.

[0017] Optionally, the step S3 specifically includes:

[0018] Step S3-1: For each road image to be identified, a Gabor filter is used to calculate the texture direction of each pixel. The function expression of the Gabor filter is:

[0019]

[0020] In the formula, x ′ =xcosθ+ysinθ,y ′ = -xsinθ + ycosθ, λ is the wavelength, θ is the direction, ψ is the phase offset, σ is the standard deviation of the Gaussian function, τ is the spatial aspect ratio, α is the modulation coefficient, which is used to adjust the influence of the Gaussian function on the filter response, and β is a phase modulation coefficient, which is used to adjust the phase according to the distance of the pixel position;

[0021] Step S3-2: Perform a threshold judgment on the confidence level for each pixel in the road image to be identified, and use the pixel with a confidence level greater than the credible threshold ζ as a voting point;

[0022] Step S3-3-1: Create an edge map of the same size as the original image, initialized to 0, to record the edge possibility of each pixel;

[0023] Step S3-3-2: For each credible pixel point, use its texture direction as the gradient direction of the point;

[0024] Step S3-3-3: along the gradient direction, perform non-maximum suppression on each pixel to refine the edge;

[0025] Step S3-3-4: For each pixel, vote within its neighborhood according to its gradient direction;

[0026] Step S3-3-5: In the edge map, accumulate votes along the gradient direction;

[0027] Step S3-3-6: Apply a threshold to the edge map to determine which pixels are classified as edges. Optionally, in step S3-2, the credible threshold ζ is determined as follows:

[0028] ζ=0.712·(Z max -Z min )

[0029] In the formula, Z max is the maximum confidence level among all pixels in the road image to be identified, Z min is the minimum confidence level among all pixels in the road image to be identified.

[0030] Optionally, in step S3-3-4, the calculation function of the voting algorithm is:

[0031]

[0032] Among them, neighborhood(x,y) represents the set of pixels in the neighborhood centered at (x,y), θ(x,y) is the texture direction of the pixel, Z(x,y) is the confidence level of the pixel, V is the voting function, (i,j) is the loop variable used to traverse the field of the pixel (x,y), and the specific expression of V is:

[0033]

[0034] Where ρ1 and ρ2 are weight factors, and ρ1>ρ2.

[0035] Optionally, the step S4 specifically includes:

[0036] Step S4-1: Use edge fitting to fit the crack edge obtained in step S3;

[0037] Step S4-2: Find two points on the fitting line corresponding to the widest part of the crack, and calculate the distance between the two points, which is taken as the width of the crack;

[0038] Step S4-3: Mark the cracks whose width is greater than or equal to a preset threshold.

[0039] In a second aspect of the present application, a crack detection system applicable to roads in desert areas is also provided, which is applicable to the crack detection method applicable to roads in desert areas described in any technical solution in the first aspect of the present application, and the system comprises:

[0040] Data acquisition module: used to obtain original road images;

[0041] Data preprocessing module: used to preprocess the original road image to obtain the road image to be identified;

[0042] Crack edge recognition module: for each road image to be identified, calculates the texture direction of each pixel, then decides whether to participate in the vote based on the confidence level of the pixel, and finally uses fast local voting to estimate the crack edge;

[0043] Crack width calculation and marking module: used to calculate crack width and mark cracks whose width is greater than or equal to the preset threshold.

[0044] According to the third aspect of the present application, a computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the crack detection method applicable to roads in desert areas described in any one of the technical solutions in the first aspect of the present application can be implemented.

[0045] According to the fourth aspect of the present application, a computer-readable storage medium is also provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, it can implement the steps of the crack detection method applicable to roads in desert areas described in any technical solution in the first aspect of the present application.

[0046] Beneficial effects:

[0047] 1. Through the above technical scheme, the present application provides a new solution, that is, firstly, the texture direction of each pixel is calculated, then whether to participate in the voting is decided according to the confidence level of the pixel, and finally the position of the crack edge is estimated by the fast local voting algorithm. In this way, the influence of partial occlusion of sand and dust can be effectively eliminated, and the road crack situation can be identified more accurately and reliably. The development of the cracks can be marked by calculating the crack width, so as to provide a more accurate and reliable reference for road maintenance.

[0048] 2. Other beneficial effects or advantages of the present application will be described in detail in the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative labor.

[0050] in:

[0051] Figure 1 It is a schematic flow chart of the steps of a crack detection method applicable to roads in desert areas provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0053] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0054] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes other steps or units that are not listed, or optionally includes other steps or units that are inherent to these processes, methods, products or devices. Among them, it should also be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design solutions. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0055] To facilitate understanding by relevant technical personnel, the problems existing in the existing related technologies are first described in more detail below.

[0056] For application scenarios where cracks in desert roads are partially obscured by sand and dust, part of the edges of the road cracks are obscured, and existing road crack detection algorithms cannot accurately and reliably identify the actual edges of the road cracks, and cannot accurately calculate the crack width, that is, cannot accurately obtain the actual width of the road cracks.

[0057] For desert roads, cracks are more frequent due to the harsh environment, dry climate, small rainfall, large evaporation, strong winds and sand, and large daily temperature differences. After the road cracks develop to a certain extent (generally the crack width is used as the control indicator), corresponding maintenance measures need to be taken to prevent the cracks from affecting driving safety.

[0058] However, existing road crack detection algorithms cannot accurately and reliably identify the width of road cracks, and therefore cannot provide accurate and reliable reference for road maintenance.

[0059] In view of this, the present application provides a new solution, namely, the crack detection method applicable to roads in desert areas of the present application. Through the crack detection method applicable to roads in desert areas of the present application, road cracks partially covered by sand and dust can be identified more accurately and reliably, providing a more accurate and reliable basis for road maintenance.

[0060] The technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0061] Example 1

[0062] like Figure 1 As shown, according to the first aspect of the present application, a crack detection method applicable to roads in desert areas is provided, which is applicable to crack detection of road cracks filled with sand and dust, and comprises the following steps:

[0063] Step S1: obtaining an original road image;

[0064] Step S2: preprocessing the original road image to obtain a road image to be identified;

[0065] Step S3: for each road image to be identified, the texture direction of each pixel is calculated, and then the confidence level of the pixel is determined whether to participate in the voting, and finally the crack edge is estimated by fast local voting;

[0066] Step S4: Calculate the crack width and mark the cracks whose width is greater than or equal to a preset threshold.

[0067] Through the above technical scheme, the present application provides a new solution, that is, first calculate the texture direction of each pixel point, then decide whether to participate in the voting based on the confidence level of the pixel point, and finally use the fast local voting algorithm to estimate the position of the crack edge. In this way, the influence of partial occlusion by sand and dust can be effectively eliminated, and the road crack situation can be identified more accurately and reliably. The development of the cracks can be marked by calculating the crack width, so as to provide a more accurate and reliable reference for road maintenance.

[0068] In one implementation of the present application, in step S1 of the present application, the original road image can be captured by a road inspection vehicle. The road inspection vehicle can obtain image data of the road more quickly and accurately, which is conducive to improving the accuracy and efficiency of the inspection.

[0069] In one implementation of the present application, step S2 of the present application may specifically include:

[0070] Step S2-1: first grayscale the original road image; the grayscale processing can not only effectively reduce the amount of data and improve the processing speed, but also effectively eliminate color interference.

[0071] Step S2-2: Perform image filtering on the image obtained in step S2-1; through image filtering, the noise in the image can be effectively removed, which is beneficial to improving the efficiency and accuracy of recognition.

[0072] Step S2-3: Perform image enhancement on the image obtained in step S2-2. Image enhancement processing can help improve image contrast, making it easier to identify cracks in the image.

[0073] Step S2-4: binarize the image obtained in step S2-3 to obtain a road image to be identified.

[0074] In this implementation, the original road image is subjected to grayscale conversion, image filtering, image enhancement and binarization operations in sequence, thereby effectively improving the image quality and enhancing the efficiency and accuracy of crack recognition.

[0075] In one implementation of the present application, step S3 of the present application may specifically include:

[0076] Step S3-1: For each road image to be identified, a Gabor filter is used to calculate the texture direction of each pixel. The function expression of the Gabor filter is:

[0077]

[0078] In the formula, x ′ =xcosθ+ysinθ,y ′ = -xsinθ + ycosθ, λ is the wavelength, θ is the direction, ψ is the phase offset, σ is the standard deviation of the Gaussian function, τ is the spatial aspect ratio, α is the modulation coefficient, which is used to adjust the influence of the Gaussian function on the filter response, and β is a phase modulation coefficient, which is used to adjust the phase according to the distance of the pixel position;

[0079] Step S3-2: Perform a threshold judgment on the confidence level for each pixel in the road image to be identified, and use the pixel with a confidence level greater than the credible threshold ζ as a voting point;

[0080] Step S3-3-1: Create an edge map of the same size as the original image, initialized to 0, to record the edge possibility of each pixel;

[0081] Step S3-3-2: For each credible pixel point, use its texture direction as the gradient direction of the point;

[0082] Step S3-3-3: along the gradient direction, perform non-maximum suppression on each pixel to refine the edge;

[0083] Step S3-3-4: For each pixel, vote within its neighborhood according to its gradient direction; usually, both sides of the gradient direction will get votes, but the side the gradient direction points to will get more votes.

[0084] Step S3-3-5: In the edge map, accumulate votes along the gradient direction;

[0085] Step S3-3-6: Apply a threshold to the edge map to determine which pixels are classified as edges.

[0086] In this embodiment, for the Gabor filter, the present application has made improvements relative to the prior art, wherein the set α is a modulation coefficient used to adjust the influence of the Gaussian function on the filter response, and at the same time, the set β is a phase modulation coefficient used to adjust the phase according to the distance of the pixel position, thereby introducing additional frequency modulation. In this way, more flexibility can be provided for the Gabor filter, allowing the filter response to be adjusted according to the actual usage requirements of the scene. For example, the intensity of the central peak can be enhanced or weakened by setting α, and additional texture features can be introduced by setting β, which is more conducive to crack recognition scenarios suitable for desert roads.

[0087] In one implementation of the present application, in step S3-2 of the present application, the credible threshold ζ can be determined as follows:

[0088] ζ=0.712·(Z max -Z min )

[0089] In the formula, Z max is the maximum confidence level among all pixels in the road image to be identified, Z min is the minimum confidence level among all pixels in the road image to be identified.

[0090] In one implementation of the present application, in step S3-3-4 of the present application, the calculation function of the voting algorithm may be:

[0091]

[0092] Among them, neighborhood(x,y) represents the set of pixels in the neighborhood centered at (x,y), θ(x,y) is the texture direction of the pixel, Z(x,y) is the confidence level of the pixel, V is the voting function, (i,j) is the loop variable used to traverse the field of the pixel (x,y), and the specific expression of V is:

[0093]

[0094] In the formula, ρ1 and ρ2 are weight factors, and ρ1>ρ2. This effectively ensures that the side pointed by the gradient direction gets more votes than the other side.

[0095] In one implementation of the present application, step S4 of the present application may specifically include:

[0096] Step S4-1: Use edge fitting to fit the crack edge obtained in step S3;

[0097] Step S4-2: Find two points on the fitting line corresponding to the widest part of the crack, and calculate the distance between the two points, which is taken as the width of the crack;

[0098] Step S4-3: Mark the cracks whose width is greater than or equal to a preset threshold.

[0099] In a second aspect of the present application, a crack detection system applicable to roads in desert areas is also provided, which is applicable to a crack detection method applicable to roads in desert areas according to any technical solution in the first aspect of the present application, and the system comprises:

[0100] Data acquisition module: used to obtain original road images;

[0101] Data preprocessing module: used to preprocess the original road image to obtain the road image to be identified;

[0102] Crack edge recognition module: for each road image to be identified, calculates the texture direction of each pixel, then decides whether to participate in the vote based on the confidence level of the pixel, and finally uses fast local voting to estimate the crack edge;

[0103] Crack width calculation and marking module: used to calculate crack width and mark cracks whose width is greater than or equal to the preset threshold.

[0104] Through the crack detection system for roads in desert areas of the present application, road cracks partially covered by sand and dust can be identified more accurately and reliably, providing a more accurate and reliable basis for road maintenance.

[0105] According to the third aspect of the present application, a computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the crack detection method applicable to roads in desert areas in any technical solution in the first aspect of the present application can be implemented.

[0106] It is understood that in this embodiment, the memory may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid state drive; in addition, the memory may also include a combination of the above-mentioned types of memory. This application does not specifically limit this.

[0107] Similarly, the processor may be a processor that implements or executes various exemplary logic steps described in conjunction with the disclosure of the present application. The processor may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It may implement or execute various exemplary logic steps described in conjunction with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0108] According to the fourth aspect of the present application, a computer-readable storage medium is also provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, it can implement the steps of the crack detection method applicable to roads in desert areas in any technical solution in the first aspect of the present application.

[0109] In this embodiment, the computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer readable storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in an application-specific integrated circuit (ASIC). In the embodiments of the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0110] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A crack detection method suitable for roads in desert areas, characterized in that: Applicable to crack detection of road cracks filled with sand and dust, including the following steps: Step S1: obtaining an original road image; Step S2: preprocessing the original road image to obtain a road image to be identified; Step S3: for each road image to be identified, the texture direction of each pixel is calculated, and then the confidence level of the pixel is determined whether to participate in the voting, and finally the crack edge is estimated by fast local voting; Step S4: Calculate the crack width and mark the cracks whose width is greater than or equal to a preset threshold.

2. The crack detection method for desert roads according to claim 1, characterized in that: In step S1, the original road image is captured by a road inspection vehicle.

3. The crack detection method applicable to desert roads according to claim 1, characterized in that: The step S2 specifically includes: Step S2-1: first grayscale the original road image; Step S2-2: performing image filtering on the image obtained in step S2-1; Step S2-3: Perform image enhancement on the image obtained in step S2-2. Step S2-4: binarize the image obtained in step S2-3 to obtain a road image to be identified.

4. The crack detection method for desert roads according to claim 1, characterized in that: The step S3 specifically includes: Step S3-1: For each road image to be identified, a Gabor filter is used to calculate the texture direction of each pixel. The function expression of the Gabor filter is: In the formula, x ′ =xcosθ+ysinθ,y ′ = -xsinθ + ycosθ, λ is the wavelength, θ is the direction, ψ is the phase offset, σ is the standard deviation of the Gaussian function, τ is the spatial aspect ratio, α is the modulation coefficient, which is used to adjust the influence of the Gaussian function on the filter response, and β is a phase modulation coefficient, which is used to adjust the phase according to the distance of the pixel position; Step S3-2: Perform a threshold judgment on the confidence level for each pixel in the road image to be identified, and use the pixel with a confidence level greater than the credible threshold ζ as a voting point; Step S3-3-1: Create an edge map of the same size as the original image, initialized to 0, to record the edge possibility of each pixel; Step S3-3-2: For each credible pixel point, use its texture direction as the gradient direction of the point; Step S3-3-3: along the gradient direction, perform non-maximum suppression on each pixel to refine the edge; Step S3-3-4: For each pixel, vote within its neighborhood according to its gradient direction; Step S3-3-5: In the edge map, accumulate votes along the gradient direction; Step S3-3-6: Apply a threshold to the edge map to determine which pixels are classified as edges.

5. The crack detection method for desert roads according to claim 4, characterized in that: In step S3-2, the credible threshold ζ is determined as follows: ζ=0.712 (Z max -WITH min ) In the formula, Z max is the maximum confidence level among all pixels in the road image to be identified, Z min is the minimum confidence level among all pixels in the road image to be identified.

6. The crack detection method for desert roads according to claim 4, characterized in that: In step S3-3-4, the calculation function of the voting algorithm is: Among them, neighborhood(x,y) represents the set of pixels in the neighborhood centered at (x,y), θ(x,y) is the texture direction of the pixel, Z(x,y) is the confidence level of the pixel, V is the voting function, (i,j) is the loop variable used to traverse the field of the pixel (x,y), and the specific expression of V is: Where ρ1 and ρ2 are weight factors, and ρ1>ρ2.

7. The crack detection method for desert roads according to claim 1, characterized in that: The step S4 specifically includes: Step S4-1: Use edge fitting to fit the crack edge obtained in step S3; Step S4-2: Find two points on the fitting line corresponding to the widest part of the crack, and calculate the distance between the two points, which is taken as the width of the crack; Step S4-3: Mark the cracks whose width is greater than or equal to a preset threshold.

8. A crack detection system suitable for roads in desert areas, characterized in that: A crack detection method for desert roads according to any one of claims 1 to 7, the system comprising: Data acquisition module: used to obtain original road images; Data preprocessing module: used to preprocess the original road image to obtain the road image to be identified; Crack edge recognition module: for each road image to be identified, calculates the texture direction of each pixel, then decides whether to participate in the vote based on the confidence level of the pixel, and finally uses fast local voting to estimate the crack edge; Crack width calculation and marking module: used to calculate crack width and mark cracks whose width is greater than or equal to the preset threshold.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the crack detection method applicable to roads in desert areas described in any one of claims 1 to 7 can be implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the crack detection method applicable to roads in desert areas described in any one of claims 1 to 7 can be implemented.

Images