Bridge deck quality monitoring method and system based on edge detection

Abstract

The application relates to the technical field of image processing, in particular to a bridge deck quality monitoring method and system based on edge detection, which comprises the following steps: acquiring a bridge grayscale image; acquiring a plurality of bridge edge images through threshold iteration based on the bridge grayscale image; acquiring the possibility that a suspected crack edge in all bridge edge images is a crack edge according to the change of edge pixel points in adjacent bridge edge images; further acquiring a plurality of reference edges and pixel points to be recognized; acquiring a suspected spliced edge of each reference edge; acquiring a spliced edge of each reference edge according to the shape of each reference edge and the suspected spliced edge thereof; and taking all spliced edges and reference edges as final crack edges in the bridge. The application can accurately recognize crack edges by analyzing the similar characteristics of crack edge extension directions under different thresholds and the characteristics that two edges of a crack are consistent, so that the accuracy of bridge deck quality monitoring is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a bridge deck quality monitoring method and system based on edge detection. BACKGROUND

[0002] Cracks in the bridge may affect the structural safety and carrying capacity of the bridge, increase the risk of corrosion, cause the deterioration of steel and concrete, and thus endanger traffic safety, so it is necessary to detect cracks in the bridge in a timely manner to develop a reasonable maintenance and reinforcement scheme and prolong the service life of the bridge, but in the process of identifying crack edges through machine vision in the traditional way, it is necessary to collect bridge surface images, and the collection of bridge surface images will be affected by external light, resulting in that the traditional edge detection operator cannot accurately identify the crack edges in the bridge. SUMMARY

[0003] The present application provides a bridge deck quality monitoring method and system based on edge detection to solve the existing problem that the traditional edge detection operator cannot accurately identify the crack edges in the bridge.

[0004] The bridge deck quality monitoring method and system based on edge detection of the present application adopt the following technical solutions:

[0005] One embodiment of the present application provides a bridge deck quality monitoring method based on edge detection, which comprises the following steps:

[0006] Obtain a bridge grayscale image;

[0007] Obtain a plurality of bridge edge images through threshold iteration based on the bridge grayscale image; obtain part of crack edge pixels according to the gradient values of the edge pixel points in the bridge edge images; obtain suspected crack edges in all bridge edge images according to the changes of the edge pixel points in adjacent bridge edge images; obtain the possibility of the suspected crack edges in all bridge edge images being crack edges according to the suspected crack edges in all bridge edge images and the part of crack edge pixels; obtain a plurality of reference edges and to-be-identified pixel points according to the possibility of the suspected crack edges in all bridge edge images being crack edges, wherein the pixel points in the reference edges are reference pixel points;

[0008] Obtain the standard crack width of each reference edge according to the gradient direction of the reference pixel points in the same reference edge; obtain the suspected spliced edges of each reference edge according to the reference edges and their standard crack widths; obtain the similarity between each suspected spliced edge and the corresponding reference edge according to the shape of the reference edge and its suspected spliced edge;

[0009] Obtain the spliced edges according to the similarity between the suspected spliced edges and the corresponding reference edges; and take all the spliced edges and the reference edges as the final crack edges in the bridge.

[0010] Preferably, the bridge gray scale-based threshold iteration is used to obtain several bridge edge maps, and the specific method comprises the following steps:

[0011] An initial threshold value α, a termination threshold value β and a threshold iteration step size γ are preset; the threshold value of an edge detection operator is set to α, the edge detection operator is used to detect the edges in the bridge gray scale map, and a first bridge edge map is obtained;

[0012] The threshold value of the edge detection operator is set to α-γ, the edge detection operator is used to detect the edges in the bridge gray scale map, and a second bridge edge map is obtained;

[0013] Until the threshold value of the edge detection operator is set to β, the edge detection operator is used to detect the edges in the bridge gray scale map, and an xth bridge edge map is obtained, wherein

[0014] Preferably, the bridge edge gradient value-based partial crack edge pixel point acquisition comprises the following steps:

[0015] A crack edge gradient threshold value coefficient δ is preset, the maximum gradient value in the first bridge edge map is obtained, and the pixel points in the first bridge edge map with a gradient value greater than δ times the maximum gradient value are taken as crack edge pixel points.

[0016] Preferably, the adjacent bridge edge map-based change of the edge pixel points is used to obtain the suspected crack edges in all bridge edge maps, and the specific method comprises the following steps:

[0017] For any edge pixel point in the second bridge edge map, the edge pixel point is recorded as a target point, the pixel point with the same position coordinates as the target point in the first bridge edge map is recorded as a corresponding point of the target point, if the corresponding point is a crack edge pixel point, the target point is a crack edge pixel point, if the corresponding point is not a crack edge pixel point, the target point is a suspected crack edge pixel point, the adjacent suspected crack edge pixel points in the eight adjacent domains are classified into the same suspected crack edge, and several suspected crack edges are obtained; the adjacent crack edge pixel points in the eight adjacent domains are classified into the same crack edge, and several crack edges are obtained.

[0018] Preferably, the suspected crack edge in all bridge edge maps is used to obtain the possibility of the suspected crack edge being a crack edge, and the specific method comprises the following steps:

[0019] For any suspected crack edge, obtain the crack edge closest to the suspected crack edge and mark it as a target edge; mark all pixel points in the suspected crack edge and the target edge as feature points, and obtain the possibility of the suspected crack edge being a crack edge according to the gradient direction of the pixel points corresponding to all the feature points in the bridge grayscale image and the distance between the suspected crack edge and the target edge, and the specific calculation formula is:

[0020] P = exp[-(σ x L)]

[0021] In the formula, P represents the possibility of the suspected crack edge being a crack edge; σ represents the standard deviation of the gradient direction of the pixel points corresponding to all the feature points in the bridge grayscale image; L represents the distance between the suspected crack edge and the target edge; and exp[] represents an exponential function with a natural constant as the base number.

[0022] Preferably, the method for obtaining a plurality of reference edges and pixel points to be identified according to the possibility of the suspected crack edge in all bridge edge images being a crack edge comprises the following specific method:

[0023] A possibility threshold μ of the suspected crack edge being a crack edge is preset, if the possibility of the suspected crack edge being a crack edge is greater than or equal to the possibility threshold, the suspected crack edge is a crack edge; if the possibility of the suspected crack edge being a crack edge is less than the possibility threshold, the suspected crack edge is not a crack edge; and all pixel points in the crack edge are taken as crack edge pixel points.

[0024] For any edge pixel point in the third bridge edge image, the edge pixel point is marked as a target point, and the pixel point with the same position coordinates as the target point in the second bridge edge image is marked as a corresponding point, if the corresponding point is a crack edge pixel point, the target point is a crack edge pixel point, if the corresponding point is not a crack edge pixel point, the target point is a suspected crack edge pixel point, the suspected crack edge pixel points adjacent on the eight-neighbor domain are classified into the same suspected crack edge, and a plurality of suspected crack edges are obtained; the crack edge pixel points adjacent on the eight-neighbor domain are classified into the same crack edge, and a plurality of crack edges are obtained.

[0025] The possibility of the suspected crack edge in the third bridge edge image being a crack edge is calculated, and a plurality of crack edges are obtained.

[0026] By analogy, all crack edges in the xth bridge edge image are obtained, the crack edges are marked as reference edges, the pixel points on the reference edges are marked as reference pixel points, and the edge pixel points in the xth bridge edge image that are not reference pixel points are marked as pixel points to be identified.

[0027] Preferably, the method for obtaining the suspected spliced edges of each reference edge according to the reference edge and its standard crack width comprises the following specific steps:

[0028] For any reference edge, a magnification coefficient τ is preset; all to-be-identified pixel points with a standard crack width less than τ times the distance from the reference edge are recorded as suspected spliced pixel points of the reference edge, and the eight-neighbor suspected spliced pixel points are grouped into the same suspected spliced edge, thereby obtaining several suspected spliced edges of the reference edge.

[0029] Preferably, the method for obtaining the similarity between each suspected spliced edge and the corresponding reference edge according to the shape of the reference edge and its suspected spliced edge comprises the following specific steps:

[0030] For any suspected spliced edge of any reference edge, the reference edge and the suspected spliced edge are subjected to DTW matching to obtain several matching pairs; the similarity between the suspected spliced edge and the reference edge is obtained according to the difference between the gradient directions of two pixel points in each matching pair, and the specific calculation formula is as follows:

[0031]

[0032] In the formula, S represents the similarity between the suspected spliced edge and the reference edge; m represents the number of matching pairs; θ i,1,2 represents the included angle between the first pixel point and the second pixel point in the i th matching pair in the gradient direction; cos( ) represents the cosine trigonometric function; | | represents the absolute value function; and exp[ ] represents the exponential function with a natural constant as the base number.

[0033] Preferably, the method for obtaining the spliced edge according to the similarity between the suspected spliced edge and the corresponding reference edge comprises the following specific steps:

[0034] A similarity threshold value is preset For any suspected spliced edge of any reference edge, if the similarity between the suspected spliced edge and the reference edge is greater than or equal to the suspected spliced edge is a spliced edge.

[0035] Another embodiment of the present application provides a bridge deck quality monitoring system based on edge detection, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps of any one of the above-mentioned bridge deck quality monitoring methods based on edge detection when executing the computer program.

[0036] The beneficial effects of the technical solutions of the present application are as follows: the present application obtains a plurality of bridge edge maps through threshold iteration based on a bridge grayscale map; according to the changes of edge pixel points in adjacent bridge edge maps, the possibility of a suspected crack edge in all bridge edge maps being a crack edge is obtained, a plurality of reference edges and a pixel point to be recognized are obtained; since the pixel point with the maximum gradient value in the bridge grayscale map is always located at the bridge crack edge, the crack edge pixel points are first obtained through the bridge edge map under the maximum threshold, and then the crack edge pixel points in each bridge edge map are obtained according to the similar characteristics of the extension direction of the crack edge.

[0037] The suspected spliced edges of each reference edge are obtained; the spliced edges of each reference edge are obtained according to the shapes of each reference edge and its suspected spliced edge; all the spliced edges and the reference edges are taken as the final crack edges in the bridge; the crack edge pixel points in the pixel point to be recognized are further obtained according to the similarity of the trend of the pixel point to be recognized and the recognized crack edge. The crack edges in the bridge are obtained according to the similarity between the suspected spliced edges and the reference edges. The crack edges are accurately recognized by analyzing the similar characteristics of the extension direction of the crack edge under different thresholds and the characteristics that the two edges of the crack are consistent, so as to improve the accuracy of the bridge deck quality monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0039] Figure 1 The step flow chart of the bridge deck quality monitoring method based on edge detection of the present application;

[0040] Figure 2 The example diagram of the bridge grayscale map;

[0041] Figure 3 The example diagram of the first bridge edge map. DETAILED DESCRIPTION

[0042] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined inventive purpose, the specific implementation, structure, features and effects of the bridge deck quality monitoring method and system based on edge detection according to the present application are described in detail as follows in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0044] The specific scheme of the bridge deck quality monitoring method and system based on edge detection provided by the present application is described in detail below in combination with the drawings.

[0045] Please refer to Figure 1 which shows the step flowchart of the bridge deck quality monitoring method based on edge detection provided by one embodiment of the present application, which includes the following steps:

[0046] Step S001: Obtain a bridge grayscale image.

[0047] It should be noted that the cracks in the bridge may affect the structural safety and carrying capacity of the bridge, increase the corrosion risk, cause the deterioration of the steel and concrete, and thus endanger the traffic safety. Therefore, timely detection of the cracks in the bridge can help develop a reasonable maintenance and reinforcement scheme to prolong the service life of the bridge. The present embodiment is a bridge deck quality monitoring method based on edge detection, which specifically accurately detects the crack edges in the bridge by machine vision. Therefore, it is necessary to first collect a bridge grayscale image.

[0048] Specifically, the camera is used to collect a bridge surface image, the bridge surface image is subjected to grayscale processing, and the grayscale result is subjected to Gaussian filter denoising processing to obtain a bridge grayscale image, as shown in Figure 2 Figure 2 which is an example of the bridge grayscale image. Since the grayscale processing and Gaussian filter denoising processing are both well-known prior art, they will not be described in detail in the present embodiment.

[0049] ​Step S002: obtaining a plurality of bridge edge maps based on the bridge grayscale map through threshold iteration; obtaining part of crack edge pixel points according to gradient values of edge pixel points in the bridge edge maps; obtaining suspected crack edges in all bridge edge maps according to changes of edge pixel points in adjacent bridge edge maps; obtaining likelihoods of suspected crack edges in all bridge edge maps being crack edges according to the suspected crack edges and the part of crack edge pixel points; and obtaining a plurality of reference edges and the pixel points to be recognized according to the likelihoods of the suspected crack edges in all bridge edge maps being crack edges, wherein the pixel points in the reference edges are reference pixel points.

[0050] It should be noted that when the camera collects the bridge surface image, it will be affected by external light, and there will be a shadow area in the bridge grayscale map. The gradient value of the crack edge in the shadow area will be affected by the shadow area, which will cause the crack edge under the shadow position to be unable to be detected when the edge detection operator is used to monitor the crack edge. Since the grayscale difference between the shadow area and the light area is large, the edge detection operator will identify the edge between the shadow area and the light area when detecting the crack edge, i.e., the crack edge in the bridge cannot be accurately obtained. Therefore, the embodiment proposes a bridge deck quality monitoring method based on edge detection.

[0051] It should be further noted that since the pixel point with the maximum gradient value in the bridge grayscale map is always located at the bridge crack edge, the edge detection operator is used to detect the edge in the bridge grayscale map with a plurality of threshold values. The greater the threshold value of the edge detection operator, the more the number of crack edge pixel points identified by the edge detection operator. The crack edge pixel points are obtained by analyzing the morphological characteristics of the crack edge formed by the crack edge pixel points and the morphological characteristics of the edge pixel points detected under other threshold values, and the crack edge pixel points are further obtained.

[0052] Preferably, in one specific embodiment of the present application, an initial threshold value α, a termination threshold value β and a threshold iteration step size γ are preset. The specific values of α, β and γ can be set by the actual situation, and the present embodiment does not make hard requirements. In the present embodiment, α=0.14, β=0.04 and γ=0.02 are taken as examples for description. The threshold value of the edge detection operator is set to α, the edge in the bridge grayscale map is detected by using the edge detection operator, and a first bridge edge map is obtained, as shown in FIG. 1. Figure 3 Figure 3 In the present embodiment, the edge detection operator detects the edge by using a sobel operator, which is a well-known prior art, and thus will not be described in detail in the present embodiment.

[0053] ​Further, the threshold of the edge detection operator is set as a-gamma, the edge in the bridge gray scale image is detected by using the edge detection operator, and a second bridge edge image is obtained;

[0054] By analogy, until the threshold of the edge detection operator is set as beta, the edge in the bridge gray scale image is detected by using the edge detection operator, and an xth bridge edge image is obtained.

[0055] It should be noted that, since the crack in the bridge has the characteristics of being long and deep, external light is difficult to enter the inside of the crack, so the gradient value of the pixel point at the crack edge in the bridge gray scale image is much larger than the gradient value at other positions, and since the threshold of the edge detection operator for obtaining the first bridge edge image is large, most of the edge pixel points in the first bridge edge image are crack edge pixel points; and the greater the gradient value, the more likely it is a crack edge pixel point, so the crack edge pixel points can be obtained based on this.

[0056] Preferably, in a specific embodiment of the present application, a crack edge gradient threshold coefficient δ is preset, the specific value of δ can be set by oneself in combination with the actual situation, and the present embodiment does not make a hard requirement, and in the present embodiment, δ=0.9 is taken as an example for description, the maximum gradient value in the first bridge edge image is obtained, and the pixel point with a gradient value greater than δ times the maximum gradient value in the first bridge edge image is taken as a crack edge pixel point.

[0057] It should be noted that each bridge edge image will add several edge pixel points compared with the previous bridge edge image, and the added edge pixel points include crack edge pixel points and non-crack edge pixel points; and since the bridge will produce stress concentration when subjected to load, and the crack usually occurs along the direction with the maximum stress, and since the distribution of stress in the bridge is relatively uniform, the extension directions of various positions in the crack are similar, so the crack edge pixel points in each bridge edge image can be obtained by analyzing whether the added edge pixel points in each bridge edge image are similar to the crack edge pixel points in the previous bridge edge image in the extension direction.

[0058] Further, for any edge pixel point in the second bridge edge image, the edge pixel point is recorded as a target point, the pixel point with the same position coordinates as the target point in the first bridge edge image is recorded as a corresponding point of the target point, if the corresponding point is a crack edge pixel point, the target point is a crack edge pixel point, if the corresponding point is not a crack edge pixel point, the target point is a suspected crack edge pixel point, the suspected crack edge pixel points adjacent to each other on the eight-neighbor domain are classified into the same suspected crack edge, and a plurality of suspected crack edges are obtained; the crack edge pixel points adjacent to each other on the eight-neighbor domain are classified into the same crack edge, and a plurality of crack edges are obtained.

[0059] For any suspected crack edge, the crack edge closest to the suspected crack edge is obtained and recorded as a target edge; all pixel points in the suspected crack edge and the target edge are recorded as feature points, and the possibility that the suspected crack edge is a crack edge is obtained according to the gradient direction of the pixel points corresponding to all the feature points in the bridge gray image and the distance between the suspected crack edge and the target edge, and the specific calculation formula is:

[0060] P = exp[-(σ x L)]

[0061] In the formula, P represents the possibility that the suspected crack edge is a crack edge; σ represents the standard deviation of the gradient direction of the pixel points corresponding to all the feature points in the bridge gray image; L represents the distance between the suspected crack edge and the target edge; exp[] represents an exponential function with a natural constant as the base number, and the exp(-ε) model is used in the embodiment to present an inverse proportional relationship and normalization processing, and ε is the input of the model, and the implementer can set the inverse proportional function and the normalization function according to the actual situation.

[0062] It should be noted that σ represents the standard deviation of the gradient direction of the pixel points corresponding to all the feature points in the bridge gray image, and the smaller the standard deviation is, the more similar the suspected edge and the target edge are in the extension direction, and since the stress distribution in the bridge is relatively uniform and the crack is an external manifestation of the stress distribution, the gradient values of the pixel points in the local range at each position in the crack are similar, and the smaller the distance between the suspected edge and the target edge is, the more similar the gradient values are, so the value of P is larger, and the suspected crack edge is more likely to be a crack edge.

[0063] Specifically, a possibility threshold μ of a suspected crack edge being a crack edge is preset, and the specific value of μ can be set by the implementer according to the actual situation, and the embodiment does not make a hard requirement that μ = 0.6 in the embodiment; if the possibility of the suspected crack edge being a crack edge is greater than or equal to the possibility threshold, the suspected crack edge is a crack edge; if the possibility of the suspected crack edge being a crack edge is less than the possibility threshold, the suspected crack edge is not a crack edge; and all pixel points in the crack edge are taken as crack edge pixel points.

[0064] Further, for any edge pixel point in the third bridge edge map, the edge pixel point is recorded as a target point, a pixel point in the second bridge edge map with the same position coordinates as the target point is recorded as a corresponding point, if the corresponding point is a crack edge pixel point, the target point is a crack edge pixel point, if the corresponding point is not a crack edge pixel point, the target point is a suspected crack edge pixel point, suspected crack edges adjacent to each other in the eight-neighbor domain are classified into the same suspected crack edge, and a plurality of suspected crack edges are obtained; crack edges adjacent to each other in the eight-neighbor domain are classified into the same crack edge, and a plurality of crack edges are obtained.

[0065] The possibility of the suspected crack edge in the third bridge edge map being a crack edge is calculated, and a plurality of crack edges are obtained.

[0066] By analogy, all crack edges in the xth bridge edge map are obtained, the crack edges are recorded as reference edges, the pixel points on the reference edges are recorded as reference pixel points, and the edge pixel points in the xth bridge edge map that are not reference pixel points are recorded as to-be-identified pixel points.

[0067] It should be noted that the specific process of obtaining the third bridge edge map and the crack edges in all bridge edge maps after the third bridge edge map is the same as that of obtaining the crack edges in all suspected crack edges in the second bridge edge map, and thus will not be described again.

[0068] It should be further noted that the edges in the xth bridge edge map in this step include edges between all shadow regions and light regions, and all crack edges, which are obtained by analyzing bridge edge maps under different thresholds, and the characteristics of similar extension directions of edge pixel points, but due to the influence of external light and shadow, there are crack edges that are not identified, and whether the remaining edge pixel points are crack edge pixel points needs to be judged according to the identified crack edge pixel points, so all crack edge pixel points identified in this step are recorded as reference pixel points; the remaining edge pixel points are recorded as to-be-identified pixel points.

[0069] At this point, the reference edges, the reference pixel points, and the to-be-identified pixel points are obtained.

[0070] Step S003: obtaining the standard crack width of each reference edge according to the gradient direction of the reference pixel points in the same reference edge; obtaining the suspected spliced edge of each reference edge according to the reference edge and the standard crack width thereof; obtaining the similarity degree between each suspected spliced edge and the corresponding reference edge according to the shape of the reference edge and the suspected spliced edge thereof.

[0071] It should be noted that, since the two edges of the crack in the bridge have the characteristics of matching, i.e. the trend of one edge in the crack is highly similar to the trend of the other edge, therefore, based on the partial crack edges obtained in step S002, the crack edge pixels in the to-be-identified pixel points can be further obtained according to the similarity in the trend between the to-be-identified pixel points and the identified crack edges.

[0072] Preferably, in a specific embodiment of the present application, any reference pixel point on any reference edge is recorded as a measurement point, and the distance between the measurement point and the reference pixel point closest to the measurement point in the gradient direction of the measurement point is recorded as the crack width of the measurement point.

[0073] Similarly, the crack widths of all reference pixel points on the reference edge line are obtained, and the average of the crack widths of all reference pixel points on the reference edge line is recorded as the standard crack width of the reference edge.

[0074] For any reference edge, a magnification coefficient τ greater than 2 is preset, the specific value of τ can be set by oneself in combination with the actual situation, and the present embodiment does not make hard requirements, and τ = 3 is described in the present embodiment; all to-be-identified pixel points with a standard crack width less than τ times the distance from the reference edge are recorded as suspected spliced pixel points of the reference edge, and the suspected spliced pixel points in the eight-neighborhood are classified into the same suspected spliced edge, and a plurality of suspected spliced edges of the reference edge are obtained.

[0075] It should be noted that, since the crack of the bridge has a certain width, when the crack edge pixels in the to-be-identified pixel points are obtained according to the similarity in the trend between the to-be-identified pixel points and the identified crack edges, the approximate width of the crack is obtained according to the identified crack edges, and a magnification coefficient is preset to ensure that all un-identified crack edge pixels can calculate the similarity in the trend with the identified crack edge pixels.

[0076] Further, for any suspected spliced edge of any reference edge; the reference edge and the suspected spliced edge are subjected to DTW matching to obtain a plurality of matching pairs, since DTW matching is a known prior art, therefore, it will not be described again in the present embodiment; the similarity between the suspected spliced edge and the reference edge is obtained according to the difference between the gradient directions of the two pixel points in each matching pair, and the specific calculation formula is:

[0077]

[0078] In the formula, S represents the similarity between the suspected spliced edge and the reference edge; m represents the number of matching pairs; θ i,1,2represents the angle between the first pixel and the second pixel in the i-th matching pair in the gradient direction; cos() represents the cosine trigonometric function; || represents the absolute value function; exp[] represents an exponential function with a natural constant as the base. This embodiment adopts the exp(-ε) model to present the inverse proportional relationship and normalization processing, and ε is the input of the model. The implementer can set the inverse proportional function and normalization function according to the actual situation.

[0079] It should be noted that, since the inside of the crack is dark and the outside of the crack is bright, the gradient direction of the pixel points at the edge of the crack always points vertically from the outside of the crack to the inside of the crack. Therefore, when the suspected stitching edge is the crack edge, since the suspected stitching edge and the reference edge have similar trends, the angle between the pixel points in the matching pair in the gradient direction approaches 180°. Therefore, the closer the angle between the pixel points in each matching pair in the gradient direction approaches 180°, the more similar the suspected stitching edge and the reference edge are in trend. The higher the degree of similarity between the suspected stitching edge and the reference edge, the more likely the suspected stitching edge is the crack edge identified in step S002.

[0080] At this point, the similarity between the suspected stitching edge and the reference edge is obtained.

[0081] Step S004: obtaining a splicing edge based on the similarity between the suspected splicing edge and the corresponding reference edge; and taking all the splicing edges and the reference edge as the final crack edge in the bridge.

[0082] It should be noted that after obtaining the degree of similarity between the suspected spliced ​​edge and the reference edge through step S003, the degree of similarity between the suspected spliced ​​edge and the reference edge can be used as a basis to accurately obtain the crack edge identified in step S002; further, combined with the crack edge identified in step S002, the crack edge in the bridge can be accurately obtained, thereby accurately identifying the crack in the bridge.

[0083] Specifically, a similarity threshold is preset The specific value of can be set according to the actual situation. This embodiment does not make a hard requirement. For any suspected splicing edge of any reference edge, if the similarity between the suspected splicing edge and the reference edge is greater than or equal to Then the suspected splicing edge is the splicing edge; all the reference edges and all the splicing edges in the x-th bridge edge map are taken as the final crack edges in the bridge.

[0084] At this point, this embodiment is completed.

[0085] Another embodiment of the present application provides a bridge deck quality monitoring system based on edge detection, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the bridge deck quality monitoring method based on edge detection in steps S001 to S004 when executing the computer program.

[0086] The above merely provides the preferred embodiment of the present application, but should not be used to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for bridge deck quality monitoring based on edge detection, characterized in that, The method comprises the following steps: Obtaining a bridge gray image; Based on the bridge gray image, a plurality of bridge edge images are obtained through threshold iteration; based on the gradient value of the edge pixel points in the bridge edge image, part of the crack edge pixel points are obtained; based on the change of the edge pixel points in the adjacent bridge edge image, the suspected crack edges in all bridge edge images are obtained; based on the suspected crack edges in all bridge edge images and part of the crack edge pixel points, the possibility that the suspected crack edges in all bridge edge images are crack edges is obtained; based on the possibility that the suspected crack edges in all bridge edge images are crack edges, a plurality of reference edges and pixel points to be identified are obtained, the pixel points in the reference edges are reference pixel points; Based on the gradient direction of the reference pixel points in the same reference edge, the standard crack width of each reference edge is obtained; based on the reference edge and its standard crack width, the suspected spliced edge of each reference edge is obtained; based on the shape of the reference edge and its suspected spliced edge, the similarity between each suspected spliced edge and the corresponding reference edge is obtained; Based on the similarity between the suspected spliced edge and the corresponding reference edge, the spliced edge is obtained; all the spliced edges and the reference edges are taken as the final crack edges in the bridge.

2. The method for monitoring the quality of a bridge deck based on edge detection according to claim 1, characterized in that, The specific method for obtaining a plurality of bridge edge images based on the bridge gray image through threshold iteration comprises: An initial threshold α, a termination threshold β and a threshold iteration step γ are preset; the threshold of the edge detection operator is set to α, and the edge in the bridge gray image is detected by using the edge detection operator to obtain a first bridge edge image; The threshold of the edge detection operator is set to α-γ, and the edge in the bridge gray image is detected by using the edge detection operator to obtain a second bridge edge image; Until the threshold value of the edge detection operator is set as β, the edge in the bridge gray image is detected by using the edge detection operator, and the xth bridge edge image is obtained, wherein 3. The method for monitoring the quality of a bridge deck based on edge detection according to claim 1, characterized in that, The specific method for obtaining part of the crack edge pixel points based on the gradient value of the edge pixel points in the bridge edge image comprises: A crack edge gradient threshold coefficient δ is preset, the maximum gradient value in the first bridge edge image is obtained, and the pixel points with a gradient value greater than δ times the maximum gradient value in the first bridge edge image are taken as the crack edge pixel points.

4. The method for monitoring the quality of a bridge deck based on edge detection according to claim 2, wherein, The specific method for obtaining the suspected crack edges in all bridge edge images based on the change of the edge pixel points in the adjacent bridge edge image comprises: For any edge pixel point in the second bridge edge image, the edge pixel point is recorded as a target point, and the pixel point with the same position coordinates as the target point in the first bridge edge image is recorded as the corresponding point of the target point; if the corresponding point is a crack edge pixel point, the target point is a crack edge pixel point; if the corresponding point is not a crack edge pixel point, the target point is a suspected crack edge pixel point; the adjacent suspected crack edge pixel points in the eight adjacent domains are classified into the same suspected crack edge to obtain a plurality of suspected crack edges; the adjacent crack edge pixel points in the eight adjacent domains are classified into the same crack edge to obtain a plurality of crack edges.

5. The method for monitoring the quality of a bridge deck based on edge detection according to claim 4, characterized in that, The specific method for obtaining the possibility that the suspected crack edges in all bridge edge images are crack edges based on the suspected crack edges in all bridge edge images and part of the crack edge pixel points comprises: For any suspected crack edge, obtain the crack edge closest to the suspected crack edge and mark it as a target edge; mark all pixel points in the suspected crack edge and the target edge as feature points, and obtain the possibility of the suspected crack edge being a crack edge according to the gradient direction of the pixel points corresponding to all the feature points in the bridge grayscale image and the distance between the suspected crack edge and the target edge, and the specific calculation formula is: P = exp[-(σ×L)] In the formula, P represents the possibility of the suspected crack edge being a crack edge; σ represents the standard deviation of the gradient direction of the pixel points corresponding to all the feature points in the bridge grayscale image; L represents the distance between the suspected crack edge and the target edge; and exp[] represents an exponential function with a natural constant as the base.

6. The method for monitoring the quality of a bridge deck based on edge detection according to claim 5, wherein, The specific method for obtaining a plurality of reference edges and pixel points to be recognized according to the possibility of the suspected crack edge in all bridge edge images being a crack edge comprises the following steps: A possibility threshold μ of the suspected crack edge being a crack edge is preset, if the possibility of the suspected crack edge being a crack edge is greater than or equal to the possibility threshold, the suspected crack edge is a crack edge; if the possibility of the suspected crack edge being a crack edge is less than the possibility threshold, the suspected crack edge is not a crack edge; and all pixel points in the crack edge are regarded as crack edge pixel points. For any edge pixel point in the third bridge edge image, the edge pixel point is marked as a target point, and a pixel point in the second bridge edge image with the same position coordinates as the target point is marked as a corresponding point, if the corresponding point is a crack edge pixel point, the target point is a crack edge pixel point, if the corresponding point is not a crack edge pixel point, the target point is a suspected crack edge pixel point, suspected crack edge pixel points adjacent to each other in an eight-neighbor domain are grouped into a suspected crack edge, and a plurality of suspected crack edges are obtained; crack edge pixel points adjacent to each other in an eight-neighbor domain are grouped into a crack edge, and a plurality of crack edges are obtained. The possibility of the suspected crack edge in the third bridge edge image being a crack edge is calculated, and a plurality of crack edges are obtained. In this way, all crack edges in the xth bridge edge image are obtained, the crack edges are marked as reference edges, the pixel points on the reference edges are marked as reference pixel points, and the edge pixel points in the xth bridge edge image that are not reference pixel points are marked as pixel points to be recognized.

7. The method for monitoring the quality of a bridge deck based on edge detection according to claim 1, wherein, The specific method for obtaining the suspected spliced edge of each reference edge according to the reference edge and the standard crack width thereof comprises the following steps: For any reference edge, a magnification coefficient τ is preset; all pixel points to be recognized with a standard crack width smaller than τ times the distance from the reference edge are marked as suspected spliced pixel points of the reference edge, and suspected spliced pixel points adjacent to each other in an eight-neighbor domain are grouped into a suspected spliced edge, and a plurality of suspected spliced edges of the reference edge are obtained.

8. The method for bridge deck quality monitoring based on edge detection according to claim 1, wherein, The specific method for obtaining the similarity degree between each suspected spliced edge and the corresponding reference edge according to the shape of the reference edge and the suspected spliced edge thereof comprises the following steps: For any reference edge and any suspected spliced edge; performing DTW matching on the reference edge and the suspected spliced edge to obtain a plurality of matching pairs; obtaining a similarity between the suspected spliced edge and the reference edge according to a difference between gradient directions of two pixel points in each matching pair, and a specific calculation formula is: In the formula, S represents the similarity between the suspected spliced edge and the reference edge; m represents the number of matching pairs; θ i,1,2 represents the included angle between the first pixel point and the second pixel point in the gradient direction in the ith matching pair; cos() represents the cosine trigonometric function; || represents the absolute value function; and exp[] represents the exponential function with the natural constant as the base number.

9. The method for monitoring the quality of a bridge deck based on edge detection according to claim 1, wherein, The specific method for obtaining the spliced edge according to the similarity between the suspected spliced edge and the corresponding reference edge comprises: A similarity degree threshold is preset For any suspect spliced edge of any reference edge, if the similarity degree between the suspect spliced edge and the reference edge is greater than or equal to the similarity degree threshold The suspect spliced edge is a spliced edge.

10. A bridge deck quality monitoring system based on edge detection, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The computer program is executed by the processor to realize the steps of the bridge deck quality monitoring method based on edge detection according to any one of claims 1-9.

Images