CN111915577A - Method and system for detecting crack proportion in pavement image - Google Patents
Method and system for detecting crack proportion in pavement image Download PDFInfo
- Publication number
- CN111915577A CN111915577A CN202010681801.4A CN202010681801A CN111915577A CN 111915577 A CN111915577 A CN 111915577A CN 202010681801 A CN202010681801 A CN 202010681801A CN 111915577 A CN111915577 A CN 111915577A
- Authority
- CN
- China
- Prior art keywords
- road surface
- surface image
- image
- crack
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20101—Interactive definition of point of interest, landmark or seed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a method and a system for detecting the proportion of cracks in a pavement image, wherein the detection method comprises the following steps: acquiring a road surface image and preprocessing the road surface image; establishing a plane coordinate system, and placing the road surface image in the established plane coordinate system; randomly selecting a pixel point in the pavement image, taking the pixel point as a starting point, obtaining a test point at intervals of a first set distance to obtain the gray value of each test point, and judging whether the difference between the maximum value and the minimum value is greater than the set pixel difference value; if the gray value is larger than the preset gray value, taking the pixel point with the maximum gray value as an initial point of the crack area; self-growing is carried out from the initial point of the crack area to obtain pixel points of the crack area; establishing a square by taking each pixel point in the crack area as a center; and obtaining the proportion of the cracks on the pavement image according to the number of the squares in the crack area and the total number of the squares on the pavement image. The technical scheme provided by the invention can provide a basis for evaluating the influence degree of the cracks.
Description
Technical Field
The invention belongs to the technical field of pavement crack detection, and particularly relates to a method and a system for detecting the crack proportion in a pavement image.
Background
Along with the continuous construction of the highway, the continuous perfection of the infrastructure of the highway, the transportation efficiency and the transportation capacity of the highway are also continuously improved, the research on the road maintenance and the disease detection method is gradually emphasized, the condition of the road surface is complex and various, and no matter the road surface is asphalt or cement, after the vehicle is on for a period of time, the condition of cracks on the road surface is caused by the external environment, so that great hidden danger is brought to the normal use of the road surface.
Pavement cracks are a common phenomenon, and in order to ensure long-term normal use of a road, municipal workers are required to improve construction quality during road construction and perform regular maintenance and detection on the pavement. Most of traditional road surface detection work needs to be finished in a manual walking mode, in the process of road surface detection, one inspector can only finish detection of less than 10 kilometers every day, a large amount of time and energy are consumed, and the work efficiency is low. In addition, the traffic jam of the traffic road network such as urban expressways, main roads and expressways can also be caused, so that the normal traffic operation of people is influenced, and meanwhile, a huge safety problem exists, so that an effective detection and evaluation method is needed to detect and identify potential hazards, thereby avoiding potential hazards.
The conditions of the road surface are complex and various, general manpower detection is not only serious in consumption but also poor in timeliness and reliability, so that the technology for automatically detecting the road surface cracks by adopting a computer becomes one of research hotspots in the technical field.
The current detection methods of pavement cracks can be divided into a point feature method, a line feature method, a texture feature method, a transform domain feature method and the like according to different feature extraction methods. The point feature method commonly uses a detection method based on a target point minimum spanning tree and a detection method based on an image three-dimensional terrain model, the linear feature method commonly uses a detection method based on a direction feature and an attraction model, the texture feature method commonly uses a pavement crack detection algorithm based on a weighted fusion texture, the transform domain feature method commonly uses a pavement image crack detection method based on a Beamlet transform, and the local contrast adjustment detection method based on NSCT transform. In addition, the detection of cracks on the pavement image is realized by using a dynamic optimization method, such as an artificial bee colony detection method and the like.
The pavement crack detection method can detect whether cracks appear through the identification of the pavement images, but the sizes of the cracks cannot be obtained, and the method cannot provide basis for evaluating the influence degree of the cracks.
Disclosure of Invention
The invention aims to provide a method and a system for detecting the proportion of cracks in a pavement image, and aims to solve the problem that the method for detecting the proportion of the cracks in the pavement image in the prior art cannot provide a basis for evaluating the influence degree of the cracks because the proportion of the cracks in the pavement image cannot be calculated.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for detecting the proportion of cracks in a pavement image comprises the following steps:
the method comprises the following steps: acquiring a road surface image and preprocessing the road surface image; the preprocessing comprises the steps of carrying out graying processing and filtering processing on the road surface image;
step two: determining a crack region in the road surface image, and calculating the proportion of the crack region in the road surface image, wherein the calculation process comprises the following substeps:
2.1: establishing a plane coordinate system, wherein the plane coordinate system comprises an x axis and a y axis which are vertical to each other, and placing the road surface image in the established plane coordinate system;
2.2: randomly selecting a pixel point in the pavement image, taking the pixel point as a starting point, obtaining a test point at a first set distance on an x-axis coordinate and a y-axis coordinate of the starting point to obtain a gray value of each test point, and judging whether the difference between the maximum value and the minimum value is greater than a set pixel difference value;
if not, reselecting the starting point and executing the substep 2.2;
if the gray value is larger than the preset gray value, taking the pixel point with the maximum gray value as an initial point of the crack area;
2.3: self-growing along the directions of the x axis and the y axis from the initial point of the crack area to obtain a pixel point of the crack area; the pixel point of the crack area is a pixel point with the difference from the gray value of the starting point smaller than a first set value;
2.4: establishing a square by taking each pixel point of the obtained crack area as a center, wherein four edges of the square are parallel to an x axis and a y axis respectively, and obtaining gray values of four vertexes of the square, wherein the side length is a second set distance; judging whether at least two differences between the gray values of the four fixed points of each square and the crack starting point are larger than a set value; if the square is larger than the crack area, the square is judged to be in the crack area;
2.5: and obtaining the proportion of the cracks on the pavement image according to the number of the squares in the crack area and the total number of the squares on the pavement image.
Further, the method for performing graying processing on the road surface image comprises the following steps:
if I (I, j) is the gray scale value of the ith row and the jth column in the road surface image, and R (I, j), G (I, j) and B (I, j) are the values of R, G, B component corresponding points in the road surface image color image respectively, then
I(i,j)＝0.3R(i,j)+0.59G(i,j)+0.11B(i,j)。
Further, the method for filtering the road surface image comprises the following steps:
wherein F (i, j) and F (i, j) respectively represent pixels in the original image and the enhanced image, and the gray scale value range of the original input image is [ Fmin,fmax]The gray scale value range of the output image is [ F ]min,Fmax]。
Further, when the calculated crack ratio is smaller than the set ratio, the detected crack area is judged to be noise, and the second step is executed again.
Further, the self-growth process is as follows: and taking the starting point as a center, obtaining pixel points which are spaced at a second set distance in the positive direction and the negative direction of the x axis and the positive direction and the negative direction of the y axis, judging whether the difference between the gray value of the pixel points and the gray value of the starting point is greater than a second set value, if not, taking the pixel points as the pixel points of the crack area, and taking the pixel points as new centers to start the next growth until all the pixel points in the crack area are obtained.
A crack proportion detection system in a road surface image comprises a processor and a memory, wherein the memory stores a computer program for being executed on the processor; when the processor executes the computer program, the method for detecting the crack proportion in the road surface image is realized, and the method comprises the following steps:
the method comprises the following steps: acquiring a road surface image and preprocessing the road surface image; the preprocessing comprises the steps of carrying out graying processing and filtering processing on the road surface image;
step two: determining a crack region in the road surface image, and calculating the proportion of the crack region in the road surface image, wherein the calculation process comprises the following substeps:
2.1: establishing a plane coordinate system, wherein the plane coordinate system comprises an x axis and a y axis which are vertical to each other, and placing the road surface image in the established plane coordinate system;
2.2: randomly selecting a pixel point in the pavement image, taking the pixel point as a starting point, obtaining a test point at a first set distance on an x-axis coordinate and a y-axis coordinate of the starting point to obtain a gray value of each test point, and judging whether the difference between the maximum value and the minimum value is greater than a set pixel difference value;
if not, reselecting the starting point and executing the substep 2.2;
if the gray value is larger than the preset gray value, taking the pixel point with the maximum gray value as an initial point of the crack area;
2.3: self-growing along the directions of the x axis and the y axis from the initial point of the crack area to obtain a pixel point of the crack area; the pixel point of the crack area is a pixel point with the difference from the gray value of the starting point smaller than a first set value;
2.4: establishing a square by taking each pixel point of the obtained crack area as a center, wherein four edges of the square are parallel to an x axis and a y axis respectively, and obtaining gray values of four vertexes of the square, wherein the side length is a second set distance; judging whether at least two differences between the gray values of the four fixed points of each square and the crack starting point are larger than a set value; if the square is larger than the crack area, the square is judged to be in the crack area;
2.5: and obtaining the proportion of the cracks on the pavement image according to the number of the squares in the crack area and the total number of the squares on the pavement image.
Further, the method for performing graying processing on the road surface image comprises the following steps:
if I (I, j) is the gray scale value of the ith row and the jth column in the road surface image, and R (I, j), G (I, j) and B (I, j) are the values of R, G, B component corresponding points in the road surface image color image respectively, then
I(i,j)＝0.3R(i,j)+0.59G(i,j)+0.11B(i,j)。
The system for detecting the proportion of cracks in the road surface image according to claim 6, wherein the method for performing filtering processing on the road surface image comprises the following steps:
wherein F (i, j) and F (i, j) respectively represent pixels in the original image and the enhanced image, and the gray scale value range of the original input image is [ Fmin,fmax]The gray scale value range of the output image is [ F ]min,Fmax]。
Further, when the calculated crack ratio is smaller than the set ratio, the detected crack area is judged to be noise, and the second step is executed again.
Further, the self-growth process is as follows: and taking the starting point as a center, obtaining pixel points which are spaced at a second set distance in the positive direction and the negative direction of the x axis and the positive direction and the negative direction of the y axis, judging whether the difference between the gray value of the pixel points and the gray value of the starting point is greater than a second set value, if not, taking the pixel points as the pixel points of the crack area, and taking the pixel points as new centers to start the next growth until all the pixel points in the crack area are obtained.
According to the technical scheme provided by the invention, firstly, a pavement image is preprocessed, then, pixel points in a crack area are determined according to the difference of gray values of all the pixel points in the preprocessed pavement image, finally, a square is established by taking all the pixel points in the crack area as the center to obtain a square in the crack area, and the proportion of cracks in the pavement image is obtained according to the proportion between the square in the crack area and the square in the whole pavement image. The technical scheme provided by the invention can accurately detect the proportion of the cracks in the pavement image and provides a basis for evaluating the influence degree of the cracks.
Drawings
FIG. 1 is a flow chart of a pavement image crack ratio detection method according to an embodiment of the method of the present invention;
FIG. 2 is a flow chart of pre-processing an image according to an embodiment of the method of the present invention;
FIG. 3 is a flowchart of a method for calculating the proportion of cracks in a road surface image according to an embodiment of the method of the present invention;
FIG. 4 is a schematic diagram of a two-dimensional plane coordinate system in an embodiment of the method of the present invention.
Detailed Description
The method comprises the following steps:
the embodiment provides a method for detecting the proportion of cracks in a pavement image, which is used for detecting the proportion of the cracks in the pavement image and providing a basis for evaluating the influence degree of the cracks.
The flow of the method for detecting the crack ratio of the pavement image provided by the embodiment is shown in fig. 1, and the method comprises the following steps:
the method comprises the following steps: and acquiring a road surface image, preprocessing the road surface image, and eliminating a noise signal in the road surface image.
The flow of preprocessing the road surface image is shown in fig. 2, and includes the following steps:
1.1: the collected pavement images are subjected to graying processing, and a pixel difference value between an image background and the cracks is increased by adopting a linear gray scale conversion spatial domain enhancement method, so that the cracks are more prominent from the background.
Because human eyes have the highest sensitivity to green, the second red and the lowest sensitivity to blue, the color images R, G and B are weighted and averaged by different weights according to the following formula
I(i,j)＝0.3R(i,j)+0.59G(i,j)+0.11(i,j)
Wherein, I (I, j) is the gray scale value of the ith row and the jth column in the gray scale image, and R (I, j), G (I, j) and B (I, j) are the values of R, G, B component corresponding points in the color image respectively.
1.2: and increasing pixel difference values among cracks of the image background by adopting a linear gray scale conversion spatial domain enhancement method so as to enable the cracks to be more prominent from the background. Pixels in the original image and the enhanced image are represented by F (i, j) and F (i, j), respectively, assuming the gray of the original input imageThe value range of degree is [ f ]min,fmax]The gray scale value range of the output image is [ F ]min,Fmax]The transformation formula is as follows:
noise existing in the crack image mostly exists in isolated points, and noise reduction and filtering are performed on the crack image through the method, so that high-frequency noise points in the image can be removed, and crack edge information can be well protected.
Step two: and determining the position of the crack in the road surface image, and calculating the proportion of the crack in the road surface image.
The process of determining the position of the crack in the road surface image and calculating the proportion of the crack in the image is shown in fig. 3, and comprises the following steps:
2.1: a two-dimensional plane coordinate system is established, as shown in fig. 4, the plane coordinate system includes an x axis and a y axis perpendicular to each other, and the road surface image is placed into the established two-dimensional plane coordinate system.
2.2: randomly selecting a pixel point in the road surface image, taking the pixel point as a starting point, and setting the coordinates of the starting point as (x0, y 0);
obtaining a test point at intervals of a first set distance on an x-axis coordinate and a y-axis coordinate of the starting point to obtain a gray value of each test point, and judging whether the difference between the maximum value and the minimum value is greater than a set pixel difference value;
if the first set distance is d, the obtained test points are (x0+ d, y0), (x0+2d, y0), (x0+3d, y0) (x0+4d, y0) … …, (x0-d, y0), (x0-2d, y0), (x0-3d, y0) (x0-4d, y0) … …, (x0, y0+ d), (x0, y0+2d), (x0, y0+3d) (x0, y0+4d) … …, (x0, y0-d), (x0, y0-2d), (x0, y0-3d) (x0, y0-4d) … … -4d)
If not, reselecting the starting point and executing the steps;
and if so, taking the pixel point with the maximum gray value as an initial point of the crack region.
2.3: and self-growing from the initial point of the crack region to obtain pixel points belonging to the crack region.
The method for self-growing from the initial point of the crack zone comprises the following steps:
first, a first step of self-growth is performed centering on the initial point of the crack region.
And taking the initial point of the crack area as a middle point, obtaining the gray values of the pixel points at the second set distance in the positive direction and the negative direction of the x axis of the initial point coordinate of the crack area and the positive direction and the negative direction of the y axis of the initial point coordinate of the crack area, judging whether the difference value between the gray value of the pixel points and the gray value of the initial point of the crack is greater than a set value, and if so, taking the pixel points as the pixel points of the crack area.
And (3) setting the coordinates of the starting point of the crack region as (x1, y1) and the second set distance as b, judging whether the difference between the gray value of the pixel point of the positive direction of the x axis and the negative direction of the obtained coordinates of the starting point of the crack region and the gray value of the pixel point of the second set distance in the positive direction of the y axis and the negative direction of the y axis is (x1+ b, y1), (x1-b, y1), (x1, y1+ b), (x1, y1-b) is larger than a set difference value, if so, judging that the pixel point does not belong to the crack region, and if so, judging that the pixel point belongs to the crack region.
And then carrying out second-step self-growth by taking pixel points with coordinates of (x1+ b, y1), (x1-b, y1), (x1, y1+ b), (x1, y1-b) as centers, wherein the method for the second-step self-growth is the same as the method for carrying out the first-step self-growth by taking the initial point of the crack region as a center.
And after the second self-growth step is finished, carrying out third self-growth, and so on until all crack pixel points of the crack area in the pavement image are obtained.
2.4: establishing a square by taking each pixel point of the obtained crack area as a center, wherein four edges of the square are parallel to an x axis and a y axis respectively, and obtaining gray values of four vertexes of the square, wherein the side length is a second set distance; judging whether at least two differences between the gray values of the four fixed points of each square and the crack starting point are larger than a set value; if so, the square is judged to be in the crack area.
Obtaining the number of all squares in the crack area according to the steps, and setting the number as m;
calculating the total number of squares on the road surface image according to the size of the squares and the size of the road surface image, and setting the total number as M, wherein the proportion of cracks on the road surface image is p-M/M
Assuming that the length of the road surface image on the x axis is Lx and the length on the y axis is Ly, the road surface image is obtained
In another real-time mode, when the crack ratio is smaller than the set ratio value, the crack is determined to be a noise signal, and the step (2) is executed again.
The embodiment of the system is as follows:
the embodiment provides a system for detecting the proportion of cracks in a road surface image, which comprises a processor and a memory, wherein the memory is stored with a computer program for being executed on the processor, and when the processor executes the computer program, the method for detecting the proportion of cracks in the road surface image is realized.
The embodiments of the present invention disclosed above are intended merely to help clarify the technical solutions of the present invention, and it is not intended to describe all the details of the invention nor to limit the invention to the specific embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A method for detecting the proportion of cracks in a pavement image is characterized by comprising the following steps:
the method comprises the following steps: acquiring a road surface image and preprocessing the road surface image; the preprocessing comprises the steps of carrying out graying processing and filtering processing on the road surface image;
step two: determining a crack region in the road surface image, and calculating the proportion of the crack region in the road surface image, wherein the calculation process comprises the following substeps:
2.1: establishing a plane coordinate system, wherein the plane coordinate system comprises an x axis and a y axis which are vertical to each other, and placing the road surface image in the established plane coordinate system;
2.2: randomly selecting a pixel point in the pavement image, taking the pixel point as a starting point, obtaining a test point at a first set distance on an x-axis coordinate and a y-axis coordinate of the starting point to obtain a gray value of each test point, and judging whether the difference between the maximum value and the minimum value is greater than a set pixel difference value;
if not, reselecting the starting point and executing the substep 2.2;
if the gray value is larger than the preset gray value, taking the pixel point with the maximum gray value as an initial point of the crack area;
2.3: self-growing along the directions of the x axis and the y axis from the initial point of the crack area to obtain a pixel point of the crack area; the pixel point of the crack area is a pixel point with the difference from the gray value of the starting point smaller than a first set value;
2.4: establishing a square by taking each pixel point of the obtained crack area as a center, wherein four edges of the square are parallel to an x axis and a y axis respectively, and obtaining gray values of four vertexes of the square, wherein the side length is a second set distance; judging whether at least two differences between the gray values of the four fixed points of each square and the crack starting point are larger than a set value; if the square is larger than the crack area, the square is judged to be in the crack area;
2.5: and obtaining the proportion of the cracks on the pavement image according to the number of the squares in the crack area and the total number of the squares on the pavement image.
2. The method for detecting the proportion of cracks in the road surface image according to claim 1, wherein the method for performing the graying processing on the road surface image comprises the following steps:
if I (I, j) is the gray scale value of the ith row and the jth column in the road surface image, and R (I, j), G (I, j) and B (I, j) are the values of R, G, B component corresponding points in the road surface image color image respectively, then
I(i,j)＝0.3R(i,j)+0.59G(i,j)+0.11B(i,j)。
3. The method for detecting the proportion of the cracks in the road surface image according to claim 1, wherein the method for performing the filtering process on the road surface image comprises the following steps:
wherein F (i, j) and F (i, j) respectively represent pixels in the original image and the enhanced image, and the gray scale value range of the original input image is [ Fmin,fmax]The gray scale value range of the output image is [ F ]min,Fmax]。
4. The method according to claim 1, wherein when the ratio of the cracks is calculated to be smaller than a predetermined ratio, the detected crack region is determined to be noise, and the second step is executed again.
5. The method for detecting the proportion of cracks in a road surface image according to claim 1, wherein the self-growth process is as follows: and taking the starting point as a center, obtaining pixel points which are spaced at a second set distance in the positive direction and the negative direction of the x axis and the positive direction and the negative direction of the y axis, judging whether the difference between the gray value of the pixel points and the gray value of the starting point is greater than a second set value, if not, taking the pixel points as the pixel points of the crack area, and taking the pixel points as new centers to start the next growth until all the pixel points in the crack area are obtained.
6. A crack proportion detection system in a road surface image comprises a processor and a memory, wherein the memory stores a computer program for being executed on the processor; the method is characterized in that the processor realizes the method for detecting the crack proportion in the road surface image when executing the computer program, and the method comprises the following steps:
the method comprises the following steps: acquiring a road surface image and preprocessing the road surface image; the preprocessing comprises the steps of carrying out graying processing and filtering processing on the road surface image;
step two: determining a crack region in the road surface image, and calculating the proportion of the crack region in the road surface image, wherein the calculation process comprises the following substeps:
2.1: establishing a plane coordinate system, wherein the plane coordinate system comprises an x axis and a y axis which are vertical to each other, and placing the road surface image in the established plane coordinate system;
2.2: randomly selecting a pixel point in the pavement image, taking the pixel point as a starting point, obtaining a test point at a first set distance on an x-axis coordinate and a y-axis coordinate of the starting point to obtain a gray value of each test point, and judging whether the difference between the maximum value and the minimum value is greater than a set pixel difference value;
if not, reselecting the starting point and executing the substep 2.2;
if the gray value is larger than the preset gray value, taking the pixel point with the maximum gray value as an initial point of the crack area;
2.3: self-growing along the directions of the x axis and the y axis from the initial point of the crack area to obtain a pixel point of the crack area; the pixel point of the crack area is a pixel point with the difference from the gray value of the starting point smaller than a first set value;
2.4: establishing a square by taking each pixel point of the obtained crack area as a center, wherein four edges of the square are parallel to an x axis and a y axis respectively, and obtaining gray values of four vertexes of the square, wherein the side length is a second set distance; judging whether at least two differences between the gray values of the four fixed points of each square and the crack starting point are larger than a set value; if the square is larger than the crack area, the square is judged to be in the crack area;
2.5: and obtaining the proportion of the cracks on the pavement image according to the number of the squares in the crack area and the total number of the squares on the pavement image.
7. The system for detecting the proportion of cracks in the road surface image according to claim 6, wherein the method for performing graying processing on the road surface image comprises the following steps:
if I (I, j) is the gray scale value of the ith row and the jth column in the road surface image, and R (I, j), G (I, j) and B (I, j) are the values of R, G, B component corresponding points in the road surface image color image respectively, then
I(i,j)＝0.3R(i,j)+0.59G(i,j)+0.11B(i,j)。
8. The system for detecting the proportion of cracks in the road surface image according to claim 6, wherein the method for performing filtering processing on the road surface image comprises the following steps:
wherein F (i, j) and F (i, j) respectively represent pixels in the original image and the enhanced image, and the gray scale value range of the original input image is [ Fmin,fmax]The gray scale value range of the output image is [ F ]min,Fmax]。
9. The system according to claim 6, wherein when the ratio of cracks calculated is smaller than a predetermined ratio, the detected crack region is determined to be noisy, and the second step is executed again.
10. The system for detecting the proportion of cracks in a road surface image according to claim 6, wherein the self-growth process is as follows: and taking the starting point as a center, obtaining pixel points which are spaced at a second set distance in the positive direction and the negative direction of the x axis and the positive direction and the negative direction of the y axis, judging whether the difference between the gray value of the pixel points and the gray value of the starting point is greater than a second set value, if not, taking the pixel points as the pixel points of the crack area, and taking the pixel points as new centers to start the next growth until all the pixel points in the crack area are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010681801.4A CN111915577A (en) | 2020-07-15 | 2020-07-15 | Method and system for detecting crack proportion in pavement image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010681801.4A CN111915577A (en) | 2020-07-15 | 2020-07-15 | Method and system for detecting crack proportion in pavement image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111915577A true CN111915577A (en) | 2020-11-10 |
Family
ID=73281236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010681801.4A Withdrawn CN111915577A (en) | 2020-07-15 | 2020-07-15 | Method and system for detecting crack proportion in pavement image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111915577A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114638805A (en) * | 2022-03-21 | 2022-06-17 | 武汉纵横天地空间信息技术有限公司 | Track slab crack detection method and system and storage medium |
-
2020
- 2020-07-15 CN CN202010681801.4A patent/CN111915577A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114638805A (en) * | 2022-03-21 | 2022-06-17 | 武汉纵横天地空间信息技术有限公司 | Track slab crack detection method and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108961235B (en) | Defective insulator identification method based on YOLOv3 network and particle filter algorithm | |
| WO2020233152A1 (en) | Urban building space data-based built-up area boundary identification method and device | |
| CN109443307B (en) | System and method for measuring settlement and inclination angle of transmission tower based on optical measurement | |
| CN110084241B (en) | Automatic ammeter reading method based on image recognition | |
| CN107240079A (en) | A kind of road surface crack detection method based on image procossing | |
| CN105975972A (en) | Bridge crack detection and characteristic extraction method based on image | |
| CN107045629A (en) | A kind of Multi-lane Lines Detection method | |
| CN103729853B (en) | High score remote sensing image building under three-dimension GIS auxiliary damages detection method | |
| CN104134080A (en) | Method and system for automatically detecting roadbed collapse and side slope collapse of road | |
| CN102096072B (en) | Method for automatically measuring urban parts | |
| CN112964712A (en) | Method for rapidly detecting state of asphalt pavement | |
| CN103048329A (en) | Pavement crack detecting method based on active contour model | |
| CN115564771A (en) | Concrete crack identification method based on building foundation column | |
| CN110379004A (en) | The method that a kind of pair of oblique photograph achievement carries out terrain classification and singulation is extracted | |
| CN108734124A (en) | A kind of laser radar dynamic pedestrian detection method | |
| CN104809756A (en) | Asphalt void space structure reconstruction method based on X-ray CT image | |
| CN114241024B (en) | Artificial neural network building texture mapping method and system based on sliding edge detection | |
| CN102393902A (en) | Vehicle color detection method based on H_S two-dimensional histogram and regional color matching | |
| CN110223332B (en) | Bridge crack calibration method | |
| Li et al. | Advanced pavement distress recognition and 3D reconstruction by using GA-DenseNet and binocular stereo vision | |
| CN112580542A (en) | Steel bar counting method based on target detection | |
| CN111915577A (en) | Method and system for detecting crack proportion in pavement image | |
| CN107610094B (en) | Three-dimensional crack detection method based on ellipsoid three-dimensional representation | |
| CN109697418B (en) | Post-processing method for extracting image for remote sensing image road network for scene restoration | |
| CN115358507B (en) | Production construction project disturbance map spot soil erosion risk identification and assessment method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201110 |
|
| WW01 | Invention patent application withdrawn after publication |