CN118097384A - Prefabricated bridge hinge joint damage detection method based on image processing - Google Patents
Prefabricated bridge hinge joint damage detection method based on image processing Download PDFInfo
- Publication number
- CN118097384A CN118097384A CN202410529570.3A CN202410529570A CN118097384A CN 118097384 A CN118097384 A CN 118097384A CN 202410529570 A CN202410529570 A CN 202410529570A CN 118097384 A CN118097384 A CN 118097384A
- Authority
- CN
- China
- Prior art keywords
- hinge joint
- pixel
- target
- block
- degree
- 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.)
- Granted
Links
- 210000001503 joint Anatomy 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 title claims abstract description 20
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 64
- 238000005336 cracking Methods 0.000 claims abstract description 49
- 230000003628 erosive effect Effects 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 230000007547 defect Effects 0.000 claims description 23
- 238000010606 normalization Methods 0.000 claims description 9
- 230000007797 corrosion Effects 0.000 claims description 7
- 238000005260 corrosion Methods 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000035515 penetration Effects 0.000 claims 2
- 230000001419 dependent effect Effects 0.000 claims 1
- 238000001914 filtration Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the field of detection of hinge joints of bridges, in particular to a prefabricated bridge hinge joint damage detection method based on image processing. The method comprises the following steps: acquiring a gray level image of the hinge joint surface and acquiring an analysis area; calculating the subordinate probability of a target pixel point, and constructing a super pixel block; calculating the degree of deviation between the center point of the target super-pixel block and the center point of the super-pixel block adjacent to the target super-pixel block downwards in the vertical direction; calculating the region probability of a target super-pixel block, and dividing the target super-pixel block into a cracking block belonging to a hinge joint cracking region and a water seepage block belonging to a hinge joint water seepage region; and (5) weighting and calculating the hinge joint breakage degree by the hinge joint cracking degree, the hinge joint water seepage degree and the erosion alkalization degree, and finishing the detection of the prefabricated bridge hinge joint breakage. By the technical scheme, the efficiency and the accuracy of detecting the hinge joint damage of the precast bridge can be improved.
Description
Technical Field
The invention relates to the field of bridge hinge joint detection. More particularly, the invention relates to a prefabricated bridge hinge joint breakage detection method based on image processing.
Background
The load capacity of some prefabricated bridge designs at present is smaller than the actual required load capacity, and with the increasing of the vehicle flow, the load pressure of the prefabricated bridges is also increasing. If the load pressure is greater than the designed load capacity, the hinge joint of the precast bridge is damaged, particularly the hinge joint is cracked, permeated water and alkalized due to water erosion, and further the bridge deck pavement damage is caused to form a pavement pit, so that the driving safety is endangered. Therefore, the damage of the hinge joint of the precast bridge needs to be detected, so that the damaged hinge joint can be repaired in time.
The existing method for detecting the hinge joint damage of the precast bridge is mainly ultrasonic detection, needs professional technicians to operate, has high cost, and is not suitable for detecting the hinge joint damage of the precast bridge in a large range. Therefore, how to find a method for detecting the hinge joint damage of the prefabricated bridge based on image processing is a problem to be solved by those skilled in the art.
Disclosure of Invention
In order to solve one or more of the above technical problems, the present invention provides a method for detecting a hinge joint breakage of a precast bridge based on image processing. To this end, the present invention provides solutions in various aspects as follows.
A prefabricated bridge hinge joint damage detection method based on image processing comprises the following steps: obtaining a pretreated hinge joint surface gray level map, obtaining a defect area, wherein the obtaining of the defect area comprises the following steps: calculating a gradient value of each pixel point in the gray level map of the hinge joint surface, obtaining edge pixel points in the gray level map of the hinge joint surface according to a preset edge detection algorithm, and performing Bezier curve fitting on all the edge pixel points to obtain a defect region; calculating gray value difference values of two adjacent pixel points in the horizontal direction in the defect area by taking the edge pixel points of the defect area as starting points, stopping calculation when the gray value difference values are larger than a preset difference value threshold value, and taking the pixel points at the stopping positions as cut-off pixel points; taking the area between the edge pixel point and the cut pixel point of the defect area as an erosion alkalization area, and taking the area of the defect area except the erosion alkalization area as an analysis area; taking pixel points selected based on a preset interval in an analysis area as seed points, calculating the subordinate probability of a target pixel point in a search range of the target seed point, wherein the target seed point is any one seed point in the analysis area, the target pixel point is any one pixel point in the search range of the target seed point, traversing all the pixel points, and constructing a super pixel block, wherein the super pixel block comprises one seed point and at least one pixel point; calculating the deviation degree between the center point of a target super-pixel block and the center point of a super-pixel block adjacent to the target super-pixel block downwards in the vertical direction, wherein the target super-pixel block is any super-pixel block, traversing all super-pixel blocks downwards in the vertical direction with the target super-pixel block as a starting point to obtain the deviation degree between the center points of two adjacent super-pixel blocks, averaging all the deviation degrees to calculate the region probability of the target super-pixel block, and dividing the target super-pixel block into a cracking block belonging to a hinge joint cracking region and a water seepage block belonging to a hinge joint water seepage region by comparing the region probability with a preset probability threshold; calculating the hinge joint cracking degree of a hinge joint cracking region, calculating the hinge joint water seepage degree of a hinge joint water seepage region, and calculating the erosion alkalization degree of an erosion alkalization region; and weighting and calculating the hinge joint cracking degree, the hinge joint water seepage degree and the corrosion alkalization degree, and generating and sending a repair detection signal when the hinge joint cracking degree is larger than a preset damage threshold value.
In one embodiment, the obtaining the search range includes the steps of: acquiring the area of an analysis area and the number of seed points in the analysis area, and calculating the side length of a search range:
wherein, the method comprises the steps of, wherein, Indicating the side length of the search range,Indicating the area of the analysis region,Indicating the number of seed points in the analysis area.
And acquiring a search range of the target seed point by taking the target seed point as a center, wherein the size of the search range is the square of the side length multiple.
In one embodiment, the obtaining the slave probabilities comprises the steps of: calculating the subordinate probability of the target pixel point in the search range of the target seed point, wherein the subordinate probability satisfies the relation:
wherein, the method comprises the steps of, wherein, Represent the firstThe pixel point is at the firstThe subordinate probabilities in the search range of the individual seed points,Represent the firstThe average value of the gray values of all the pixel points in the searching range of the seed points,Represent the firstThe gray value of each pixel point,Represent the firstPixel dot and the firstThe euclidean distance of the individual seed points,The gray scale difference weight is represented as,Represents distance weights, satisfies，Indicating the side length of the search range,A sequence number representing a seed point,A sequence number representing a pixel point in the search range of the seed point,Represents an exponential function, in the subordinate probability relation, the thThe seed points are target seed points, the firstThe individual pixels are target pixels.
If the target pixel point exists in the search ranges of the seed points, calculating the subordinate probabilities of the target pixel point in each search range respectively, and selecting the largest subordinate probability as the subordinate probability of the target pixel point.
In one embodiment, calculating the degree of deviation comprises the steps of: establishing a coordinate system by taking the left upper corner of the gray level graph of the hinge joint surface as an origin, taking the right horizontal direction as a transverse axis and taking the downward vertical direction as a longitudinal axis; taking the intersection point of a first distance line segment and a second distance line segment of the target super-pixel block as a central point of the target super-pixel block, and obtaining the central point coordinate of the target super-pixel block, wherein the first distance line segment is a connecting line of the maximum Euclidean distance between all contour pixel points of the target super-pixel block in the horizontal direction, and the second distance line segment is a connecting line of the maximum Euclidean distance between all contour pixel points of the target super-pixel block in the vertical direction; traversing all the super pixel blocks to obtain the center point coordinates corresponding to each super pixel block; taking the difference value between the abscissa of the center point of the target superpixel block and the abscissa of the center point of the superpixel block adjacent to the target superpixel block downwards along the vertical direction as a first difference value, taking the difference value between the ordinate of the center point of the target superpixel block and the ordinate of the center point of the superpixel block adjacent to the target superpixel block downwards along the vertical direction as a second difference value, and normalizing the ratio of the first difference value to the second difference value to obtain the deviation degree.
In one embodiment, the dividing the target super pixel block into a cracking block belonging to a hinge cracking area and a water seepage block belonging to a hinge water seepage area comprises the steps of: calculating the region probability of the target super-pixel block, wherein the region probability meets the relation:
wherein, the method comprises the steps of, wherein, Represent the firstThe region probabilities of the individual super-pixel blocks,Represent the firstThe average value of the gray values of all pixel points in the super pixel blocks,Represent the firstThe variance of gray values of all pixel points in each super pixel block,Expressed by the firstEach super pixel block is taken as the average of all deviation degrees of the starting point in the vertical direction downwards,Represents an exponential function, in the regional probability relation, the thThe super pixel blocks are target super pixel blocks.
By comparing the region probability with a preset probability threshold, when the region probability is larger than the preset probability threshold, the target super-pixel block belongs to a cracking block of a hinge joint cracking region, and when the region probability is smaller than or equal to the preset probability threshold, the target super-pixel block belongs to a water seepage block of a hinge joint water seepage region.
In one embodiment, the hinge joint cracking degree satisfies the relation:
wherein, the method comprises the steps of, wherein, Indicating the degree of cracking of the hinge joint,Indicating the total number of pieces of the crack,Represent the firstThe area of the individual pieces of the crack,Indicating the area of the hinge joint cracking zone,Represent the firstThe average value of the gray values of all the pixels in each split block,The serial number of the crack block is indicated,Representing the normalization function.
In one embodiment, the hinge joint water permeability satisfies the relationship:
wherein, the method comprises the steps of, wherein, The water seepage degree of the hinge joint is indicated,Indicating the total number of water seepage blocks,Represent the firstThe area of each water seepage block is equal to the area of each water seepage block,Represents the area of the hinge joint water seepage area,Represent the firstThe average value of the gray values of all pixel points in each water seepage block,The serial number of the seepage block is indicated,Representing the normalization function.
In one embodiment, the obtaining the erosion alkalization degree comprises the steps of: taking the edge pixel point and the truncated pixel point as erosion alkalization points of the erosion alkalization area; taking Euclidean distance between two adjacent corrosion alkalization points as a third distance; traversing all the erosion alkalization points, and normalizing the average value of all the third distances to obtain the erosion alkalization degree.
In one embodiment, the hinge joint breakage degree satisfies the relation:
wherein, the method comprises the steps of, wherein, The damage degree of the hinge joint is indicated,Represents the weight of the degree of cracking of the hinge joint,Indicating the degree of cracking of the hinge joint,The weight of the water seepage degree of the hinge joint is expressed,The water seepage degree of the hinge joint is indicated,Indicating the weight of the degree of erosion alkalization,Indicating the degree of aggressive basification,Representing the normalization function.
The invention has the following technical effects:
According to the invention, the gray level map of the hinge joint surface is divided into an erosion alkalization area and an analysis area, the analysis area is thinned into a super pixel block, the super pixel block is divided into a cracking block and a water seepage block, so that the hinge joint cracking area and the hinge joint water seepage area are determined, the hinge joint cracking degree of the hinge joint cracking area, the hinge joint water seepage degree of the hinge joint water seepage area and the erosion alkalization degree of the erosion alkalization area are respectively calculated, the overall hinge joint damage degree is finally weighted, a preset damage threshold value is set, and the detection of the prefabricated bridge hinge joint damage is completed, so that the detection result is more accurate, the detection efficiency is improved, and the detection cost is reduced.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
Fig. 1 is a flowchart of a method for detecting a hinge joint breakage of a precast bridge based on image processing according to an embodiment of the present invention.
Fig. 2 is a gray scale diagram of a hinge joint surface of a prefabricated bridge according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that when the terms "first," "second," and the like are used in the claims, the specification and the drawings of the present invention, they are used merely for distinguishing between different objects and not for describing a particular sequential order. The terms "comprises" and "comprising" when used in the specification and claims of the present invention are taken to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The invention provides a prefabricated bridge hinge joint damage detection method based on image processing. As shown in fig. 1, a method for detecting a hinge joint breakage of a prefabricated bridge based on image processing includes steps S1 to S7, which are described in detail below.
S1, acquiring a pretreated hinge joint surface gray scale map, and obtaining a defect area.
In one embodiment, a high-definition camera loaded on the unmanned aerial vehicle is used for shooting a prefabricated bridge hinge joint to obtain a surface RGB (Red Green Blue) image, the surface RGB image is subjected to gray scale processing to obtain an initial hinge joint surface gray scale map, and Gaussian filtering and histogram equalization are performed on the initial hinge joint surface gray scale map to obtain the hinge joint surface gray scale map. The gaussian filtering and histogram equalization are used to remove noise from the original hinge surface gray level map, and enhance the contrast of the original hinge surface gray level map, so that the original hinge surface gray level map is clearer, as shown in fig. 2.
The method comprises the steps of calculating a gradient value of each pixel point in a hinge joint surface gray level map, obtaining edge pixel points in the hinge joint surface gray level map according to a preset edge detection algorithm, wherein the preset edge detection algorithm comprises a Roberts operator, a Prewitt operator, a Sobel operator, a Laplacian operator and a Canny operator. It should be noted that, the defect area includes a hinge crack area, a hinge water seepage area and an erosion alkalization area, and the damage degree indicated by the different types of areas (hinge crack area, hinge water seepage area and erosion alkalization area) in the defect area is different, so, in order to accurately obtain the damage degree of the hinge joint of the precast bridge, when the hinge joint of the precast bridge is damaged and detected by an image processing method, the hinge joint damage area needs to be accurately divided, and the different types of areas need to be divided in the hinge joint damage area.
Because the edge of the defect area is in a curve shape, bezier curve fitting is carried out on the obtained edge pixel points, discrete edge pixel points are connected into a smooth curve, and a closed area surrounded by the curve is obtained and is recorded as the defect area.
S2, calculating a gray value difference value of two adjacent pixel points in the horizontal direction in the defect area by taking the edge pixel point of the defect area as a starting point, stopping calculation when the gray value difference value is larger than a preset difference value threshold value, and taking the pixel point at the stopping position as a cut-off pixel point.
S3, taking the area between the edge pixel point and the cut pixel point of the defect area as an erosion alkalization area, and taking the area of the defect area except the erosion alkalization area as an analysis area.
S4, taking the pixel points selected based on the preset interval in the analysis area as seed points, calculating the suboptimal probability of the target pixel points in the search range of the target seed points, wherein the target seed points are any one seed point in the analysis area, the target pixel points are any one pixel point in the search range of the target seed points, traversing all the pixel points, and constructing a super pixel block, wherein the super pixel block comprises one seed point and at least one pixel point.
In one embodiment, pixel points selected based on a preset interval in an analysis area are taken as seed points, the area of the analysis area and the number of the seed points in the analysis area are obtained, and the side length of a search range is calculated:
wherein, the method comprises the steps of, wherein, Indicating the side length of the search range,Indicating the area of the analysis region,Indicating the number of seed points in the analysis area.
The search range of the target seed point is obtained by taking the target seed point as the center, the size of the search range is square of the side length multiple, and the size of the search range is set to be 2S multiplied by 2S, and it is noted that the setting of a large search range can contain more information of the pixel points, so that the calculated subordinate probability is more accurate.
Calculating the subordinate probability of a target pixel point in the search range of the target seed point, wherein the target seed point is any one seed point in the analysis area, and the subordinate probability satisfies the relation expression:
wherein, the method comprises the steps of, wherein, Represent the firstThe pixel point is at the firstThe subordinate probabilities in the search range of the individual seed points,Represent the firstThe average value of the gray values of all the pixel points in the searching range of the seed points,Represent the firstThe gray value of each pixel point,Represent the firstPixel dot and the firstThe euclidean distance of the individual seed points,The gray scale difference weight is represented as,Represents distance weights, satisfies，Indicating the side length of the search range,A sequence number representing a seed point,A sequence number representing a pixel point in the search range of the seed point,Represents an exponential function, in the subordinate probability relation, the thThe seed points are target seed points, the firstThe individual pixels are target pixels.
If the target pixel point exists in the search ranges of the seed points, calculating the subordinate probabilities of the target pixel point in each search range respectively, and selecting the largest subordinate probability as the subordinate probability of the target pixel point.
Traversing all pixel points to construct a super pixel block, wherein the super pixel block comprises a seed point and at least one pixel point.
S5, calculating the deviation degree between the center point of the target super-pixel block and the center point of the super-pixel block adjacent to the target super-pixel block downwards along the vertical direction, wherein the target super-pixel block is any super-pixel block, traversing all super-pixel blocks downwards along the vertical direction by taking the target super-pixel block as a starting point, obtaining the deviation degree between the center points of two adjacent super-pixel blocks, averaging all the deviation degrees to calculate the area probability of the target super-pixel block, and dividing the target super-pixel block into a cracking block belonging to a hinge joint cracking area and a water seepage block belonging to a hinge joint water seepage area by comparing the area probability with a preset probability threshold value.
In one embodiment, calculating the degree of deviation includes: establishing a coordinate system by taking the left upper corner of the gray level graph of the hinge joint surface as an origin, taking the right horizontal direction as a transverse axis and taking the downward vertical direction as a longitudinal axis; taking the intersection point of a first distance line segment and a second distance line segment of the target super-pixel block as a central point of the target super-pixel block, and obtaining the central point coordinate of the target super-pixel block, wherein the first distance line segment is a connecting line of the maximum Euclidean distance between all contour pixel points of the target super-pixel block in the horizontal direction, and the second distance line segment is a connecting line of the maximum Euclidean distance between all contour pixel points of the target super-pixel block in the vertical direction; traversing all the super pixel blocks to obtain the center point coordinates corresponding to each super pixel block; taking the difference value between the abscissa of the center point of the target superpixel block and the abscissa of the center point of the superpixel block adjacent to the target superpixel block downwards along the vertical direction as a first difference value, taking the difference value between the ordinate of the center point of the target superpixel block and the ordinate of the center point of the superpixel block adjacent to the target superpixel block downwards along the vertical direction as a second difference value, and normalizing the ratio of the first difference value to the second difference value to obtain the deviation degree.
In one embodiment, by calculating the deviation degree, traversing all the superpixel blocks taking the target superpixel block as a starting point and downward along the vertical direction to obtain the deviation degree between the center points of two adjacent superpixel blocks, and averaging all the deviation degrees to calculate the region probability of the target superpixel block, wherein the region probability satisfies the relation:
wherein, the method comprises the steps of, wherein, Represent the firstThe region probabilities of the individual super-pixel blocks,Represent the firstThe average value of the gray values of all pixel points in the super pixel blocks,Represent the firstThe variance of gray values of all pixel points in each super pixel block,Expressed by the firstEach super pixel block is taken as the average of all deviation degrees of the starting point in the vertical direction downwards,Represents an exponential function, in the regional probability relation, the thThe super pixel blocks are target super pixel blocks.
By comparing the region probability with a preset probability threshold, when the region probability is larger than the preset probability threshold, the target super-pixel block belongs to a cracking block of a hinge joint cracking region, and when the region probability is smaller than or equal to the preset probability threshold, the target super-pixel block belongs to a water seepage block of a hinge joint water seepage region.
S6, calculating the hinge joint cracking degree of the hinge joint cracking region, calculating the hinge joint water seepage degree of the hinge joint water seepage region, and calculating the erosion alkalization degree of the erosion alkalization region.
In one embodiment, the degree of hinge cracking satisfies the relationship:
wherein, the method comprises the steps of, wherein, Indicating the degree of cracking of the hinge joint,Indicating the total number of pieces of the crack,Represent the firstThe area of the individual pieces of the crack,Indicating the area of the hinge joint cracking zone,Represent the firstThe average value of the gray values of all the pixels in each split block,The serial number of the crack block is indicated,Representing the normalization function.
The water seepage degree of the hinge joint meets the relation:
wherein, the method comprises the steps of, wherein, The water seepage degree of the hinge joint is indicated,Indicating the total number of water seepage blocks,Represent the firstThe area of each water seepage block is equal to the area of each water seepage block,Represents the area of the hinge joint water seepage area,Represent the firstThe average value of the gray values of all pixel points in each water seepage block,The serial number of the seepage block is indicated,Representing the normalization function.
The step of obtaining the erosion alkalization degree of the erosion alkalization region comprises the following steps: taking the edge pixel point and the truncated pixel point as erosion alkalization points of the erosion alkalization area; taking Euclidean distance between two adjacent corrosion alkalization points as a third distance; traversing all the erosion alkalization points, and normalizing the average value of all the third distances to obtain the erosion alkalization degree.
And S7, weighting and calculating the hinge joint cracking degree, the hinge joint water seepage degree and the corrosion alkalization degree, and generating and transmitting a repair detection signal when the hinge joint cracking degree is larger than a preset damage threshold value.
The hinge joint damage degree satisfies the relation:
wherein, the method comprises the steps of, wherein, The damage degree of the hinge joint is indicated,Represents the weight of the degree of cracking of the hinge joint,Indicating the degree of cracking of the hinge joint,The weight of the water seepage degree of the hinge joint is expressed,The water seepage degree of the hinge joint is indicated,Indicating the weight of the degree of erosion alkalization,Indicating the degree of aggressive basification,Representing the normalization function. By way of example only, and not by way of limitation,The setting is made to be 0.6,The setting is made to be 0.3,The weight of the hinge joint cracking degree, the weight of the hinge joint water seepage degree and the weight of the corrosion alkalization degree are set to be 0.1 according to the probability of occurrence of hinge joint breakage, and the more easily-occurring breakage is set to be larger and more sensitive to the occurrence of breakage.
And comparing the hinge joint damage degree with a preset damage threshold value, and generating and transmitting a repair detection signal when the hinge joint damage degree is larger than the preset damage threshold value. Illustratively, the preset breakage threshold value may be set by one skilled in the art, and the present invention sets the preset breakage threshold value to 0.5.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
The above embodiments are not intended to limit the scope of the present invention, so: all equivalent changes in structure, shape and principle of the invention should be covered in the scope of protection of the invention.
Claims (9)
1. The prefabricated bridge hinge joint damage detection method based on image processing is characterized by comprising the following steps of:
Obtaining a pretreated hinge joint surface gray level map, obtaining a defect area, wherein the obtaining of the defect area comprises the following steps:
Calculating a gradient value of each pixel point in the gray level map of the hinge joint surface, obtaining edge pixel points in the gray level map of the hinge joint surface according to a preset edge detection algorithm, and performing Bezier curve fitting on all the edge pixel points to obtain a defect region;
calculating gray value difference values of two adjacent pixel points in the horizontal direction in the defect area by taking the edge pixel points of the defect area as starting points, stopping calculation when the gray value difference values are larger than a preset difference value threshold value, and taking the pixel points at the stopping positions as cut-off pixel points;
Taking the area between the edge pixel point and the cut pixel point of the defect area as an erosion alkalization area, and taking the area of the defect area except the erosion alkalization area as an analysis area;
Taking pixel points selected based on a preset interval in an analysis area as seed points, calculating the subordinate probability of a target pixel point in a search range of the target seed point, wherein the target seed point is any one seed point in the analysis area, the target pixel point is any one pixel point in the search range of the target seed point, traversing all the pixel points, and constructing a super pixel block, wherein the super pixel block comprises one seed point and at least one pixel point;
Calculating the deviation degree between the center point of a target super-pixel block and the center point of a super-pixel block adjacent to the target super-pixel block downwards in the vertical direction, wherein the target super-pixel block is any super-pixel block, traversing all super-pixel blocks downwards in the vertical direction with the target super-pixel block as a starting point to obtain the deviation degree between the center points of two adjacent super-pixel blocks, averaging all the deviation degrees to calculate the region probability of the target super-pixel block, and dividing the target super-pixel block into a cracking block belonging to a hinge joint cracking region and a water seepage block belonging to a hinge joint water seepage region by comparing the region probability with a preset probability threshold;
Calculating the hinge joint cracking degree of a hinge joint cracking region, calculating the hinge joint water seepage degree of a hinge joint water seepage region, and calculating the erosion alkalization degree of an erosion alkalization region;
And weighting and calculating the hinge joint cracking degree, the hinge joint water seepage degree and the corrosion alkalization degree, and generating and sending a repair detection signal when the hinge joint cracking degree is larger than a preset damage threshold value.
2. The method for detecting hinge joint breakage of a precast bridge based on image processing according to claim 1, wherein the step of obtaining the search range comprises the steps of:
Acquiring the area of an analysis area and the number of seed points in the analysis area, and calculating the side length of a search range:
Wherein/> Representing the side length of the search range,/>Representing the area of the analysis region,/>Representing the number of seed points in the analysis area;
and acquiring a search range of the target seed point by taking the target seed point as a center, wherein the size of the search range is the square of the side length multiple.
3. The method for detecting hinge joint breakage of a precast bridge based on image processing according to claim 1, wherein the step of obtaining the slave probability comprises the steps of:
Calculating the subordinate probability of the target pixel point in the search range of the target seed point, wherein the subordinate probability satisfies the relation:
Wherein/> Represents the/>The pixel point is at the/>Subordinate probabilities in search range of individual seed points,/>Represents the/>Average value of gray values of all pixel points in search range of each seed point,/>Represents the/>Gray value of each pixel/(Represents the/>Individual pixel dot and/>Euclidean distance of individual seed points,/>Representing gray scale difference weights,/>Represents distance weights, satisfies/>，/>Representing the side length of the search range,/>Sequence number representing seed Point,/>Number of pixel points in search range of seed points,/>Represents an exponential function, in the dependent probability relation, the/>The seed points are target seed points, the/>The pixel points are target pixel points;
If the target pixel point exists in the search ranges of the seed points, calculating the subordinate probabilities of the target pixel point in each search range respectively, and selecting the largest subordinate probability as the subordinate probability of the target pixel point.
4. The method for detecting hinge joint breakage of a precast bridge based on image processing according to claim 1, wherein calculating the degree of deviation comprises the steps of:
Establishing a coordinate system by taking the left upper corner of the gray level graph of the hinge joint surface as an origin, taking the right horizontal direction as a transverse axis and taking the downward vertical direction as a longitudinal axis;
Taking the intersection point of a first distance line segment and a second distance line segment of the target super-pixel block as a central point of the target super-pixel block, and obtaining the central point coordinate of the target super-pixel block, wherein the first distance line segment is a connecting line of the maximum Euclidean distance between all contour pixel points of the target super-pixel block in the horizontal direction, and the second distance line segment is a connecting line of the maximum Euclidean distance between all contour pixel points of the target super-pixel block in the vertical direction;
Traversing all the super pixel blocks to obtain the center point coordinates corresponding to each super pixel block;
Taking the difference value between the abscissa of the center point of the target superpixel block and the abscissa of the center point of the superpixel block adjacent to the target superpixel block downwards along the vertical direction as a first difference value, taking the difference value between the ordinate of the center point of the target superpixel block and the ordinate of the center point of the superpixel block adjacent to the target superpixel block downwards along the vertical direction as a second difference value, and normalizing the ratio of the first difference value to the second difference value to obtain the deviation degree.
5. The method for detecting damage to a hinge joint of a precast bridge based on image processing according to claim 1, wherein the step of dividing the target super pixel block into a crack block belonging to a hinge joint crack region and a water penetration block belonging to a hinge joint water penetration region comprises the steps of:
calculating the region probability of the target super-pixel block, wherein the region probability meets the relation:
Wherein/> Represents the/>Regional probability of a block of superpixels,/>Represents the/>Average value of gray values of all pixel points in super pixel blocks,/>Represents the/>Variance of gray values of all pixel points in each super pixel block,/>Expressed as/>All the deviation degrees of each super pixel block downward along the vertical direction are taken as the average value of the starting point,/>Represents an exponential function, in the regional probability relation, the/>The super pixel blocks are target super pixel blocks;
By comparing the region probability with a preset probability threshold, when the region probability is larger than the preset probability threshold, the target super-pixel block belongs to a cracking block of a hinge joint cracking region, and when the region probability is smaller than or equal to the preset probability threshold, the target super-pixel block belongs to a water seepage block of a hinge joint water seepage region.
6. The method for detecting the hinge joint damage of the prefabricated bridge based on image processing according to claim 1, wherein the degree of hinge joint cracking satisfies the relation:
Wherein/> Indicating the degree of hinge joint cracking,/>Representing the total number of cracked blocks,/>Represents the/>Area of individual crack pieces,/>Representing the area of the hinge joint cracking zone,/>Represents the/>Average value of gray values of all pixel points in each crack block,/>Number indicating crack block,/>Representing the normalization function.
7. The method for detecting the hinge joint damage of the prefabricated bridge based on image processing according to claim 1, wherein the degree of water seepage of the hinge joint meets the relation:
Wherein/> Indicates the water seepage degree of the hinge joint,/>Representing the total number of water seepage blocks,/>Represents the/>Area of each water seepage block,/>Representing the area of the hinge joint water seepage area,/>Represents the/>Average value of gray values of all pixel points in each water seepage block,/>Number indicating water seepage block,/>Representing the normalization function.
8. The method for detecting the hinge joint damage of the prefabricated bridge based on image processing according to claim 1, wherein the step of obtaining the erosion alkalization degree comprises the following steps:
taking the edge pixel point and the truncated pixel point as erosion alkalization points of the erosion alkalization area;
taking Euclidean distance between two adjacent corrosion alkalization points as a third distance;
traversing all the erosion alkalization points, and normalizing the average value of all the third distances to obtain the erosion alkalization degree.
9. The method for detecting the hinge joint damage of the prefabricated bridge based on image processing according to claim 1, wherein the hinge joint damage degree satisfies the relation:
Wherein/> Indicate the damage degree of the hinge joint,/>Represents the weight of the hinge joint cracking degree,/>Indicating the degree of hinge joint cracking,/>Weight indicating degree of hinge joint water seepage,/>Indicates the water seepage degree of the hinge joint,/>Indicating the erosion alkalization degree weight,/>Indicating the degree of erosion alkalization,/>Representing the normalization function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410529570.3A CN118097384B (en) | 2024-04-29 | 2024-04-29 | Prefabricated bridge hinge joint damage detection method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410529570.3A CN118097384B (en) | 2024-04-29 | 2024-04-29 | Prefabricated bridge hinge joint damage detection method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118097384A true CN118097384A (en) | 2024-05-28 |
| CN118097384B CN118097384B (en) | 2024-07-23 |
Family
ID=91165700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410529570.3A Active CN118097384B (en) | 2024-04-29 | 2024-04-29 | Prefabricated bridge hinge joint damage detection method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118097384B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005069220A2 (en) * | 2003-12-26 | 2005-07-28 | Centre Technique Cuir Chaussure Maroquinerie | Method for mapping defects on leather |
| CN205557323U (en) * | 2016-04-25 | 2016-09-07 | 山东畅通路桥股份有限公司 | Hinge joint drainage structures |
| US20200034972A1 (en) * | 2018-07-25 | 2020-01-30 | Boe Technology Group Co., Ltd. | Image segmentation method and device, computer device and non-volatile storage medium |
| WO2023083059A1 (en) * | 2021-11-15 | 2023-05-19 | 中移(上海)信息通信科技有限公司 | Road surface defect detection method and apparatus, and electronic device and readable storage medium |
| CN116758059A (en) * | 2023-08-10 | 2023-09-15 | 吉林交通职业技术学院 | Visual nondestructive testing method for roadbed and pavement |
| CN116993719A (en) * | 2023-09-25 | 2023-11-03 | 惠州艺都宇正数码科技有限公司 | OCA optical film surface defect visual detection method and system |
| CN117237368A (en) * | 2023-11-16 | 2023-12-15 | 临沂市公路事业发展中心兰陵县中心 | Bridge crack detection method and system |
| CN117437223A (en) * | 2023-12-20 | 2024-01-23 | 连兴旺电子(深圳)有限公司 | Intelligent defect detection method for high-speed board-to-board connector |
| CN117764986A (en) * | 2024-02-22 | 2024-03-26 | 宝鸡世邦钛制品有限公司 | titanium plate surface defect detection method based on image processing |
-
2024
- 2024-04-29 CN CN202410529570.3A patent/CN118097384B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005069220A2 (en) * | 2003-12-26 | 2005-07-28 | Centre Technique Cuir Chaussure Maroquinerie | Method for mapping defects on leather |
| CN205557323U (en) * | 2016-04-25 | 2016-09-07 | 山东畅通路桥股份有限公司 | Hinge joint drainage structures |
| US20200034972A1 (en) * | 2018-07-25 | 2020-01-30 | Boe Technology Group Co., Ltd. | Image segmentation method and device, computer device and non-volatile storage medium |
| WO2023083059A1 (en) * | 2021-11-15 | 2023-05-19 | 中移(上海)信息通信科技有限公司 | Road surface defect detection method and apparatus, and electronic device and readable storage medium |
| CN116758059A (en) * | 2023-08-10 | 2023-09-15 | 吉林交通职业技术学院 | Visual nondestructive testing method for roadbed and pavement |
| CN116993719A (en) * | 2023-09-25 | 2023-11-03 | 惠州艺都宇正数码科技有限公司 | OCA optical film surface defect visual detection method and system |
| CN117237368A (en) * | 2023-11-16 | 2023-12-15 | 临沂市公路事业发展中心兰陵县中心 | Bridge crack detection method and system |
| CN117437223A (en) * | 2023-12-20 | 2024-01-23 | 连兴旺电子(深圳)有限公司 | Intelligent defect detection method for high-speed board-to-board connector |
| CN117764986A (en) * | 2024-02-22 | 2024-03-26 | 宝鸡世邦钛制品有限公司 | titanium plate surface defect detection method based on image processing |
Non-Patent Citations (1)
| Title |
|---|
| 王道峰;周传林;: "图像分析技术在混凝土桥梁裂缝识别与计算中的应用", 筑路机械与施工机械化, no. 11, 10 November 2015 (2015-11-10) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118097384B (en) | 2024-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107679520B (en) | Lane line visual detection method suitable for complex conditions | |
| CN108038883B (en) | Crack detection and identification method applied to highway pavement video image | |
| CN109191459B (en) | Automatic identification and rating method for continuous casting billet macrostructure center segregation defect | |
| CN110264459A (en) | A kind of interstices of soil characteristics information extraction method | |
| CN106404793B (en) | Bearing sealing element defect detection method based on vision | |
| CN107239742B (en) | Method for calculating scale value of instrument pointer | |
| CN115345885A (en) | Method for detecting appearance quality of metal fitness equipment | |
| CN103051872B (en) | Based on the belt deflection detection method of Edge extraction | |
| CN105160682B (en) | Method for detecting image edge and device | |
| CN113379712B (en) | Steel bridge bolt disease detection method and system based on computer vision | |
| CN110619328A (en) | Intelligent ship water gauge reading identification method based on image processing and deep learning | |
| CN107798293A (en) | A kind of crack on road detection means | |
| CN112580447B (en) | Edge second-order statistics and fusion-based power line detection method | |
| CN102750538A (en) | Go competition result analysis method based on image processing technique | |
| CN110807765A (en) | Suspension insulator string inclination detection method and system based on image processing | |
| CN113989266A (en) | Mechanical part surface defect detection method based on image processing | |
| CN113487722A (en) | Automatic concrete member detection method based on three-dimensional laser scanning method | |
| CN115797473B (en) | Concrete forming evaluation method for civil engineering | |
| CN110610516A (en) | Railway fastener nut center positioning method | |
| CN103927553A (en) | Coal and rock recognition method based on multi-scale micro-lamination and contrast ratio joint distribution | |
| CN110717900A (en) | Pantograph abrasion detection method based on improved Canny edge detection algorithm | |
| CN113192126A (en) | Distance measurement positioning method based on image circular object recognition | |
| CN116883408A (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN118097384B (en) | Prefabricated bridge hinge joint damage detection method based on image processing | |
| CN109767426B (en) | Shield tunnel water leakage detection method based on image feature recognition |
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 | ||
| GR01 | Patent grant |