Bridge Deep Water Cofferdam Construction Quality Detection Method and System Based on Machine Vision

Abstract

The present invention relates to the technical field of image data processing, and proposes a machine vision-based method and system for inspecting the construction quality of deep-water cofferdams for bridges. The method comprises: obtaining scale features of edge lines based on a cofferdam image and its scale-transformed image; obtaining joint edge features based on the edge lines and their scale features; obtaining a joint probability based on the edge lines and the joint edge features; obtaining a deformation degree based on the edge lines; obtaining a temporary deformation degree and a temporary deformation index based on the deformation degree, a water pressure index, and the joint probability; obtaining sealing properties based on the temporary deformation index, the temporary deformation degree, and the deformation degree; and obtaining a construction quality inspection result of a deep-water cofferdam for bridges based on the sealing properties. The present invention obtains accurate quality inspection results based on the sealing properties of edge lines, thereby improving the accuracy of the construction quality inspection results of deep-water cofferdams for bridges.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a method and system for detecting the construction quality of a bridge deep-water cofferdam based on machine vision. Background Art

[0002] A deepwater bridge cofferdam is a temporary structure used for underwater construction. By establishing a closed cofferdam area underwater, construction workers can facilitate foundation construction within it. Construction quality inspections are necessary to ensure the cofferdam's tightness and structural stability, and to guarantee the safety and quality of bridge foundation construction. In underwater construction environments, traditional manual inspection methods struggle to achieve efficient and accurate quality assessments due to factors such as water flow and turbid water. Therefore, the use of machine vision technology, through high-precision image acquisition and processing, can accurately identify cofferdam structure defects, joint sealing, and deformation in real time, effectively reducing human error, improving inspection efficiency, and meeting the high standards for construction quality in deepwater construction environments.

[0003] In the existing technology, when using image processing methods to detect the construction quality of cofferdams, when detecting the sealing of cofferdam joints, the underwater construction environment is complex, and the impact of water flow will not only have a physical effect on the cofferdam structure, but may also cause bending, dislocation or temporary deformation at the joints. Temporary deformation is dynamic and local, and changes with the fluctuation of water flow. Traditional image processing methods may not be able to accurately identify the actual state of the joints, resulting in the system being unable to distinguish between normal deformation and actual structural cracks, and mistakenly judging temporary deformation areas as cracks or unqualified parts, which may lead to erroneous quality assessments and reduce the accuracy of the quality inspection results of deep-water cofferdam construction of bridges. Summary of the Invention

[0004] The present invention provides a method and system for detecting the construction quality of deep-water cofferdams of bridges based on machine vision to solve the problem of low accuracy of existing detection results of the construction quality of deep-water cofferdams of bridges. The technical solutions adopted are as follows:

[0005] The present invention proposes a method for detecting the construction quality of a deep-water cofferdam of a bridge based on machine vision, which comprises the following steps:

[0006] Obtain several cofferdam images and their water pressure indices;

[0007] Acquire several cofferdam scale-transformed images of each cofferdam image, and acquire several edge lines in each cofferdam image and its cofferdam scale-transformed image; obtain the scale feature of each edge line in each cofferdam image based on the positional relationship of the edge lines between each cofferdam image and its cofferdam scale-transformed image; obtain the seam edge feature of each edge line in each cofferdam image based on the extension offset relationship and the scale feature of each edge line in each cofferdam image; obtain the seam probability of each edge line in each cofferdam image based on the overall gradient relationship between the edge lines in each cofferdam image and the seam edge feature of each edge line;

[0008] Based on the extension and bending relationship of each edge line in each cofferdam image, the deformation degree of each edge line in each cofferdam image is obtained; based on the correlation between the deformation degree of the edge line in the cofferdam image and the water pressure index of the cofferdam image, as well as the seam probability of the edge lines in the cofferdam image, the temporary deformation degree of each edge line in each cofferdam image and the temporary deformation index of each cofferdam image are obtained;

[0009] According to the temporary deformation index of the cofferdam image and the difference in the temporary deformation degree of the edge lines in the cofferdam image, as well as the deformation degree of the edge lines, the sealing property of each edge line in each cofferdam image is obtained;

[0010] The construction quality inspection results of the bridge deepwater cofferdam are obtained based on the sealing of all edge lines in all cofferdam images.

[0011] Furthermore, the scale feature of each edge line in each cofferdam image is obtained based on the positional relationship of the edge lines between each cofferdam image and its cofferdam scale-transformed image, including the following specific methods:

[0012] For any edge line in any cofferdam image, the edge lines whose positions in all the cofferdam scale transformation images of the cofferdam image intersect with the position of the edge line are recorded as the reference lines of the edge line;

[0013] The scale feature of the bth edge line in the ath cofferdam image is calculated as follows:

[0014]

[0015] Where A a,b is the scale feature of the bth edge line in the ath cofferdam image; B a,b is the number of reference lines of the bth edge line in the ath cofferdam image; C a,b,c is the DTW distance between the bth edge line in the ath cofferdam image and its cth reference line; exp() is an exponential function with a natural constant as the base.

[0016] Furthermore, the method of obtaining the seam edge feature of each edge line in each cofferdam image according to the extension offset relationship and scale feature of each edge line in each cofferdam image includes the following specific methods:

[0017] For any edge pixel point in any edge line in any cofferdam image, any endpoint of the edge line is recorded as the characteristic endpoint of the edge line, and the next adjacent pixel point on the shortest path from the edge pixel point along the edge line to the characteristic endpoint is recorded as the characteristic adjacent point of the edge pixel point; the direction from the edge pixel point to its characteristic adjacent point is recorded as the characteristic direction of the edge pixel point;

[0018] The minimum angle between the characteristic direction of the edge pixel point and the characteristic direction of its adjacent feature point is recorded as the offset angle of the edge pixel point;

[0019] The calculation method of the seam edge feature of the bth edge line in the ath cofferdam image is:

[0020]

[0021] Where D a,b A is the seam edge feature of the bth edge line in the ath cofferdam image; a,b is the scale feature of the bth edge line in the ath cofferdam image; E a,b is the number of edge pixels on the bth edge line in the ath cofferdam image; θ a,b,d is the offset angle of the d-th edge pixel on the b-th edge line in the a-th cofferdam image; || is the absolute value function; exp() is the exponential function with a natural constant as the base; cos() is the cosine function.

[0022] Furthermore, the seam probability of each edge line in each cofferdam image is obtained according to the overall gradient relationship between the edge lines in each cofferdam image and the seam edge feature of each edge line, including the specific method of:

[0023] Record any edge line in any cofferdam image as a target edge line; obtain the gradient vector of each edge pixel point on the target edge line; record the sum vector of the gradient vectors of all edge pixels on the target edge line as the overall gradient vector of the target edge line;

[0024] The modulus of the difference vector between the overall gradient vector of the target edge line and the overall gradient vector of any edge line in the cofferdam image other than the target edge line is recorded as the degree of difference between the target edge line and the edge line; the inverse proportional normalization result of the mean of the degree of difference between the target edge line and all edge lines in the cofferdam image other than the target edge line is recorded as the degree of regularity of the target edge line;

[0025] The product of the seam edge feature and the regularity of the target edge line is recorded as the seam probability of the target edge line.

[0026] Furthermore, the deformation degree of each edge line in each cofferdam image is obtained according to the extension and bending relationship of each edge line in each cofferdam image, including the specific method of:

[0027] Obtain the gradient vector of each edge pixel on each edge line in each cofferdam image;

[0028]

[0029] Where, F a,b is the deformation degree of the bth edge line in the ath cofferdam image; G a,b is the maximum value of the angle difference between the directions of the gradient vectors of all edge pixels in the bth edge line in the ath cofferdam image; E a,b is the number of edge pixels on the bth edge line in the ath cofferdam image; a,b,f It is the minimum angle between the direction of the gradient vector of the f-th edge pixel on the b-th edge line in the a-th cofferdam image and the direction of the gradient vector of its feature adjacent point; norm() is the linear normalization function; cos() is the cosine function.

[0030] Furthermore, the specific method for obtaining the temporary deformation degree of each edge line in each cofferdam image is as follows:

[0031] Record any cofferdam image as the main image; record any edge line in the main image as the main edge line; obtain all edge lines of any cofferdam image except the main image, and the edge lines whose number of pixel points overlapping with the pixel point position of the main edge line is greater than a preset overlap threshold, and record them as matching lines of the main edge line;

[0032] The sequence of deformation degrees of the main edge line and its matching lines is recorded as the deformation sequence of the main edge line;

[0033] According to the order of edge lines corresponding to the deformation degree in the deformation sequence of the main edge lines, the sequence consisting of the water pressure index of the cofferdam image where the main edge lines and their matching lines are located is recorded as the water pressure sequence of the main edge lines;

[0034] The Pearson correlation coefficient between the deformation sequence and the water pressure sequence of the main edge line is recorded as the water pressure influence index of the main edge line;

[0035] The product of the joint probability of the main edge line and the water pressure influence index is recorded as the temporary deformation degree of the main edge line.

[0036] Furthermore, the specific method for obtaining the temporary deformation index of each cofferdam image is as follows:

[0037] The average of the temporary deformation degrees of all edge lines in the main image is recorded as the temporary deformation index of the main image.

[0038] Furthermore, the sealing property of each edge line in each cofferdam image is obtained based on the temporary deformation index of the cofferdam image and the difference in the temporary deformation degree of the edge lines in the cofferdam image, as well as the deformation degree of the edge lines, including the specific method of:

[0039] For any edge line in any cofferdam image, the linear normalization result of the difference between the temporary deformation degree of the edge line and the temporary deformation index of the cofferdam image is recorded as the water flow index of the edge line;

[0040] The product of the inversely proportional normalized result of the deformation degree of the edge line and the water flow index is recorded as the sealing performance of the edge line.

[0041] Furthermore, the construction quality inspection result of the deep-water cofferdam of the bridge is obtained based on the sealing of all edge lines in all cofferdam images, including the specific method of:

[0042] If there are edge lines with sealing properties less than or equal to the sealing threshold in all cofferdam images, the cofferdam construction quality is unqualified; if there are edge lines with sealing properties greater than the sealing threshold in all cofferdam images, the cofferdam construction quality is qualified.

[0043] The present invention also proposes a machine vision-based bridge deep-water cofferdam construction quality inspection system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0044] The beneficial effects of the present invention are as follows: when inspecting the construction quality of deep-water cofferdams of bridges, the underwater environment shooting of deep-water cofferdams of bridges is easily affected by the environment, resulting in inaccurate acquisition of joint edges. The present invention obtains the joint probability of each edge line through the position relationship of edge lines in images of different scales, as well as the extension offset relationship of edge lines, combined with the overall gradient relationship between edge lines, and judges the possibility that each edge line is a joint edge; since the impact of water flow will cause deformation in the joint area of deep-water cofferdams of bridges, and the deformation types are divided into temporary deformation and permanent deformation, it is necessary to distinguish between temporary deformation and permanent deformation. In particular, the present invention obtains the degree of deformation of each edge line, and then obtains the temporary deformation degree of each edge line in each cofferdam image and the temporary deformation index of each cofferdam image based on the correlation between the deformation degree of the edge line in the cofferdam image and the water pressure index of the cofferdam image, thereby judging the degree to which the edge line is affected by the water flow; when inspecting the construction quality of the deep-water cofferdam of a bridge, the main focus is on judging the sealing performance at each joint. The present invention obtains the sealing performance of each edge line in each cofferdam image by measuring the temporary deformation index of the cofferdam image and the difference in the temporary deformation degree of the edge lines in the cofferdam image, as well as the deformation degree of the edge lines. Thus, the present invention obtains accurate inspection results of the construction quality of the deep-water cofferdam of a bridge by measuring the sealing performance of all edge lines in all cofferdam images. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A schematic flow chart of a method for detecting the construction quality of a deep-water cofferdam of a bridge based on machine vision according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0048] See also Figure 1 , which shows a flow chart of a method for detecting the construction quality of a deep-water cofferdam of a bridge based on machine vision according to an embodiment of the present invention. The method comprises the following steps:

[0049] Step S001: Acquire several cofferdam images and their water pressure indexes.

[0050] It should be noted that the purpose of this embodiment is to perform machine vision-based construction quality inspection of a bridge's deepwater cofferdam, so it is necessary to first collect images of the cofferdam. Since the bridge's deepwater cofferdam needs to surround the entire construction site, it is necessary to collect images of the cofferdam from multiple angles.

[0051] Specifically, an industrial underwater camera is arranged underwater so that any complete surface of the cofferdam is included in the lens of the industrial underwater camera; LED underwater lights are arranged so that the light of the LED underwater lights evenly covers the surface of the cofferdam; a pressure sensor is arranged at the center of the complete surface in the lens of the industrial underwater camera;

[0052] An industrial underwater camera is used to collect the initial RGB image of the cofferdam every 1 second. At the same time, a pressure sensor is used to collect the water pressure value. The collection of the initial RGB image of the cofferdam and the water pressure value lasts for one minute.

[0053] It should be noted that since the deepwater cofferdam of the bridge surrounds the entire construction site, it is necessary to capture multiple complete surfaces of the cofferdam when conducting construction quality inspection of the cofferdam to ensure that each complete surface of the cofferdam is reliable and stable. This embodiment uses the initial RGB images of all cofferdams obtained from one complete surface as an example for analysis.

[0054] It should be noted that due to the high noise interference in the underwater environment, in order to make the features of the cofferdam clearer, it is necessary to use the image enhancement algorithm to further enhance the initial RGB image of the cofferdam.

[0055] Specifically, all initial RGB images of the cofferdam are grayscaled to obtain a plurality of cofferdam grayscale images; all cofferdam grayscale images are subjected to median filtering and contrast enhancement to obtain a plurality of cofferdam images; grayscale, median filtering, and contrast enhancement are well-known technologies, and the specific methods are not described here;

[0056] For any cofferdam image, the water pressure value collected at the same time as the initial RGB image of the cofferdam corresponding to the cofferdam image is recorded as the water pressure index of the cofferdam image.

[0057] Step S002: Obtain several cofferdam scale-transformed images of each cofferdam image, and obtain several edge lines in each cofferdam image and its cofferdam scale-transformed image; obtain the scale feature of each edge line in each cofferdam image based on the positional relationship between the edge lines between each cofferdam image and its cofferdam scale-transformed image; obtain the seam edge feature of each edge line in each cofferdam image based on the extension offset relationship and scale feature of each edge line in each cofferdam image; obtain the seam probability of each edge line in each cofferdam image based on the overall gradient relationship between the edge lines in each cofferdam image and the seam edge feature of each edge line.

[0058] It should be noted that during the construction of a deepwater cofferdam for a bridge, a foundation support structure, namely the cofferdam's pile foundation, is built underwater. After transporting the cofferdam, the various parts are connected by joints, typically using steel plate welding and bolting. The main function of a cofferdam is to isolate the water and provide a dry environment for bridge construction. The joints are the weak links in the cofferdam structure. If the joints are not properly sealed, they may shift, misalign, or break under the action of water pressure, affecting the stability of the cofferdam and even causing it to fail, compromising the safety of the bridge construction. Therefore, it is necessary to test the sealing of the cofferdam joints. To do this, it is necessary to capture the joint area in the cofferdam image collected in the underwater environment.

[0059] It should be further explained that underwater photography of deep-water cofferdams of bridges is easily affected by the environment, resulting in inaccurate acquisition of joint edges. Therefore, multi-scale edge detection is used to obtain the scale features of the edge lines in the cofferdam image.

[0060] Specifically, a Gaussian pyramid is used to obtain several scale images of any cofferdam image; all scale images are restored to the same size as the cofferdam image using a bilinear interpolation algorithm to obtain several cofferdam scale-transformed images of the cofferdam image; Canny edge detection is performed on the cofferdam image and all of its scale-transformed images to obtain several edge lines in the cofferdam image and each of its scale-transformed images; the process of Canny edge detection and Gaussian pyramid to obtain scale images is a well-known technology, and the specific method will not be introduced here.

[0061] It should be noted that, in addition to the edge of the cofferdam joint, the edge lines in the cofferdam image also include interference edges generated by the underwater environment and caused by the cofferdam surface texture. Compared with the edge of the cofferdam joint, the interference edge is more blurred in the image, that is, in the cofferdam scale transformation image, the interference edge may disappear due to the different scales.

[0062] Specifically, for any edge line in any cofferdam image, edge lines whose positions in all cofferdam scale-transformed images of the cofferdam image intersect with the position of the edge line are recorded as reference lines of the edge line; wherein each cofferdam image contains multiple edge lines, and each edge line corresponds to multiple reference lines;

[0063] The scale feature of the bth edge line in the ath cofferdam image is calculated as follows:

[0064]

[0065] Where A a,b is the scale feature of the bth edge line in the ath cofferdam image; B a,b is the number of reference lines of the bth edge line in the ath cofferdam image; C a,b,c is the DTW distance between the bth edge line and its cth reference line in the ath cofferdam image (the DTW distance between the position of the edge line and the position of the reference line); exp() is an exponential function with a natural constant as the base.

[0066] What needs to be explained is that B a,b The larger the value is, the clearer the bth edge line in the ath cofferdam image is, and the more likely it is to be a joint edge. The larger the value is, the higher the correlation between the bth edge line in the ath cofferdam image and its reference line is, and the more likely the reference line belongs to the same edge before and after the scale transformation.

[0067] It should be noted that since the joints of the cofferdams are approximately straight lines, the extension directions of all joint edges are relatively uniform. Therefore, the joint edge features of the edge lines are determined according to the extension rules of the edge lines in the cofferdam image.

[0068] Specifically, for any edge pixel point in any edge line in any cofferdam image, any endpoint of the edge line is recorded as the characteristic endpoint of the edge line (only one endpoint of the edge line is used as the characteristic endpoint, and the other endpoints are no longer used as characteristic endpoints and are subsequently analyzed in the same way as other edge pixels), and the next adjacent pixel point on the shortest path from the edge pixel point along the edge line to the characteristic endpoint is recorded as the characteristic adjacent point of the edge pixel point; the direction from the edge pixel point to its characteristic adjacent point is recorded as the characteristic direction of the edge pixel point; it should be noted that the characteristic endpoint of the edge line has no characteristic adjacent point and characteristic direction;

[0069] The minimum angle between the characteristic direction of the edge pixel point and the characteristic direction of its adjacent characteristic point is recorded as the offset angle of the edge pixel point; it should be noted that the offset angle of the characteristic endpoint of the edge line is recorded as 0;

[0070] The calculation method of the seam edge feature of the bth edge line in the ath cofferdam image is:

[0071]

[0072] Where D a,b A is the seam edge feature of the bth edge line in the ath cofferdam image; a,b is the scale feature of the bth edge line in the ath cofferdam image; E a,b is the number of edge pixels on the bth edge line in the ath cofferdam image; θ a,b,d is the offset angle of the d-th edge pixel on the b-th edge line in the a-th cofferdam image; || is the absolute value function; exp() is the exponential function with a natural constant as the base; cos() is the cosine function.

[0073] What needs to be explained is that The larger the value is, the smaller the curvature of the bth edge line in the ath cofferdam image is, the less the deviation occurs when extending on the edge line, and the more likely it is to be a seam edge.

[0074] It should be noted that the joints of the cofferdams are parallel, so based on this, we can further judge the possibility that the edge lines in the cofferdam image are the joint edges.

[0075] Specifically, for any edge line in any cofferdam image, the Sobel operator is used to obtain the gradient vector of each edge pixel on the edge line; the sum vector of the gradient vectors of all edge pixels on the edge line is recorded as the overall gradient vector of the edge line; wherein, the Sobel method of obtaining pixel gradient vectors is a well-known technology, and the specific method is not introduced here.

[0076] It should be noted that, since the seams of the cofferdams are parallel, for the edge of any seam, there will be many edges with similar overall gradient vectors in the cofferdam image.

[0077] Specifically, any edge line in any cofferdam image is recorded as a target edge line, and the modulus of the difference vector between the overall gradient vector of the target edge line and the overall gradient vector of any edge line in the cofferdam image other than the target edge line is recorded as the degree of difference between the target edge line and the edge line; the inverse proportional normalization result of the mean of the degree of difference between the target edge line and all edge lines in the cofferdam image other than the target edge line is recorded as the degree of regularity of the target edge line;

[0078] Furthermore, the product of the seam edge feature and the regularity degree of the target edge line is recorded as the seam probability of the target edge line.

[0079] Step S003: Obtain the degree of deformation of each edge line in each cofferdam image based on the extension and bending relationship of each edge line in each cofferdam image; obtain the temporary deformation degree of each edge line in each cofferdam image and the temporary deformation index of each cofferdam image based on the correlation between the deformation degree of the edge line in the cofferdam image and the water pressure index of the cofferdam image, as well as the seam probability of the edge lines in the cofferdam image.

[0080] It's important to note that the force of water flow can cause deformation in the joints of deepwater cofferdams on bridges. This deformation can be classified as temporary or permanent. Temporary deformation is caused by the force of water flow and is minor and reversible. Once the flow subsides, the joints return to their original state. Temporary deformation is considered normal, while permanent deformation is caused by water flow damage to the cofferdam structure and is considered abnormal. Therefore, it's necessary to determine the type of deformation in the cofferdam image to avoid misjudgment and ensure the accuracy of the detection results.

[0081] It should be further explained that when water exerts pressure on the cofferdam, the joints of the cofferdam exhibit bending features. Therefore, the degree of deformation of the edge lines is obtained according to the degree of bending of the edge lines in the cofferdam image.

[0082] Specifically, the deformation degree of the bth edge line in the ath cofferdam image is calculated as follows:

[0083]

[0084] Where, F a,b is the deformation degree of the bth edge line in the ath cofferdam image; G a,b is the maximum value of the angle difference between the directions of the gradient vectors of all edge pixels in the bth edge line in the ath cofferdam image; E a,b is the number of edge pixels on the bth edge line in the ath cofferdam image; a,b,f is the minimum angle between the direction of the gradient vector of the fth edge pixel on the bth edge line in the ath cofferdam image and the direction of the gradient vector of its feature neighboring point; norm() is a linear normalization function, and the normalization object is (cos(G a,b )); cos() is the cosine function.

[0085] It should be noted that norm(cos(G a,b )) is larger, indicating that the overall deformation degree of the bth edge line in the ath cofferdam image is greater; The larger it is, the greater the local deformation of the bth edge line in the ath cofferdam image.

[0086] It should be noted that when the edge line deforms, it is necessary to determine whether the deformation is temporary or permanent. If the deformation is temporary, the degree of deformation is highly correlated with the water pressure.

[0087] Specifically, any cofferdam image is recorded as the main image; any edge line in the main image is recorded as the main edge line; among all edge lines of any cofferdam image other than the main image, the edge line whose number of pixel points overlapping with the pixel point position of the main edge line is greater than a preset overlap threshold is obtained and recorded as the matching line of the main edge line; wherein the preset overlap threshold is 30, which is used as an example in this embodiment;

[0088] The sequence of deformation degrees of the main edge line and its matching lines is recorded as the deformation sequence of the main edge line;

[0089] Arrange the water pressure indexes of the cofferdam images where the main edge lines and their matching lines are located according to the order of the edge lines corresponding to the deformation degrees in the deformation sequence of the main edge lines to form a water pressure sequence of the main edge lines;

[0090] The Pearson correlation coefficient between the deformation sequence and the water pressure sequence of the main edge line is recorded as the water pressure influence index of the main edge line. The method for obtaining the Pearson correlation coefficient is a well-known technique and the specific method is not introduced here.

[0091] The product of the joint probability of the main edge line and the water pressure influence index is recorded as the temporary deformation degree of the main edge line;

[0092] The average of the temporary deformation degrees of all edge lines in the main image is recorded as the temporary deformation index of the main image.

[0093] Step S004: Obtain the sealing property of each edge line in each cofferdam image according to the temporary deformation index of the cofferdam image, the difference in temporary deformation degree of the edge lines in the cofferdam image, and the deformation degree of the edge lines.

[0094] It should be noted that, for any edge line, the greater the influence of the water flow on the edge line, that is, the greater the temporary deformation degree of the edge line, and the smaller the deformation degree, the better the sealing performance of the edge line.

[0095] Specifically, for any edge line in any cofferdam image, the linear normalization result of the difference between the temporary deformation degree of the edge line and the temporary deformation index of the cofferdam image is recorded as the water flow index of the edge line; the normalization object is the difference between the temporary deformation degree of all edge lines in the cofferdam image and the temporary deformation index of the cofferdam image;

[0096] The product of the inversely proportional normalized result of the deformation degree of the edge line and the water flow index is recorded as the sealing performance of the edge line.

[0097] Step S005: Obtain the construction quality inspection result of the bridge deepwater cofferdam based on the sealing performance of all edge lines in all cofferdam images.

[0098] It should be noted that after obtaining the sealing of the edge lines, it is necessary to conduct a construction quality inspection based on the sealing of the edge lines.

[0099] Specifically, if any edge lines with a sealing degree less than or equal to a sealing threshold exist in all cofferdam images, it indicates that the cofferdam construction quality is unqualified and further construction of the cofferdam is required; if any edge lines with a sealing degree greater than the sealing threshold exist in all cofferdam images, it indicates that the cofferdam construction quality is qualified. The sealing threshold is set to 0.5, which is used as an example in this embodiment.

[0100] This embodiment uses the exp(-MX) model to present the inverse proportional relationship and normalization processing. MX is the input of the model. The implementer can set the inverse proportional function and normalization function according to actual conditions.

[0101] Another embodiment of the present invention provides a machine vision-based bridge deep-water cofferdam construction quality inspection system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, steps S001 to S005 of the above method are implemented.

[0102] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting the construction quality of deep-water cofferdams of bridges based on machine vision, characterized in that: The method comprises the following steps: Obtain several cofferdam images and their water pressure indices; Acquire several cofferdam scale-transformed images of each cofferdam image, and acquire several edge lines in each cofferdam image and its cofferdam scale-transformed image; obtain the scale feature of each edge line in each cofferdam image based on the positional relationship of the edge lines between each cofferdam image and its cofferdam scale-transformed image; obtain the seam edge feature of each edge line in each cofferdam image based on the extension offset relationship and the scale feature of each edge line in each cofferdam image; obtain the seam probability of each edge line in each cofferdam image based on the overall gradient relationship between the edge lines in each cofferdam image and the seam edge feature of each edge line; Based on the extension and bending relationship of each edge line in each cofferdam image, the deformation degree of each edge line in each cofferdam image is obtained; based on the correlation between the deformation degree of the edge line in the cofferdam image and the water pressure index of the cofferdam image, as well as the seam probability of the edge lines in the cofferdam image, the temporary deformation degree of each edge line in each cofferdam image and the temporary deformation index of each cofferdam image are obtained; According to the temporary deformation index of the cofferdam image and the difference in the temporary deformation degree of the edge lines in the cofferdam image, as well as the deformation degree of the edge lines, the sealing property of each edge line in each cofferdam image is obtained; The construction quality inspection results of the bridge deepwater cofferdam are obtained based on the sealing of all edge lines in all cofferdam images.

2. The method for detecting the construction quality of a bridge deepwater cofferdam based on machine vision according to claim 1 is characterized in that: The method of obtaining the scale feature of each edge line in each cofferdam image based on the positional relationship of the edge lines between each cofferdam image and its cofferdam scale-transformed image includes the following specific methods: For any edge line in any cofferdam image, the edge lines whose positions in all the cofferdam scale transformation images of the cofferdam image intersect with the position of the edge line are recorded as the reference lines of the edge line; The scale feature of the bth edge line in the ath cofferdam image is calculated as follows: Where A a,b is the scale feature of the bth edge line in the ath cofferdam image; B a,b is the number of reference lines of the bth edge line in the ath cofferdam image; C a,b,c is the DTW distance between the bth edge line in the ath cofferdam image and its cth reference line; exp() is an exponential function with a natural constant as the base.

3. The method for detecting the construction quality of a deep-water cofferdam of a bridge based on machine vision according to claim 1 is characterized in that: The method of obtaining the seam edge feature of each edge line in each cofferdam image according to the extension offset relationship and scale feature of each edge line in each cofferdam image includes the following specific methods: For any edge pixel point in any edge line in any cofferdam image, any endpoint of the edge line is recorded as the characteristic endpoint of the edge line, and the next adjacent pixel point on the shortest path from the edge pixel point along the edge line to the characteristic endpoint is recorded as the characteristic adjacent point of the edge pixel point; the direction from the edge pixel point to its characteristic adjacent point is recorded as the characteristic direction of the edge pixel point; The minimum angle between the characteristic direction of the edge pixel point and the characteristic direction of its adjacent feature point is recorded as the offset angle of the edge pixel point; The calculation method of the seam edge feature of the bth edge line in the ath cofferdam image is: Where D a,b A is the seam edge feature of the bth edge line in the ath cofferdam image; a,b is the scale feature of the bth edge line in the ath cofferdam image; E a,b is the number of edge pixels on the bth edge line in the ath cofferdam image; θ a,b,d is the offset angle of the d-th edge pixel on the b-th edge line in the a-th cofferdam image; || is the absolute value function; exp() is the exponential function with a natural constant as the base; cos() is the cosine function.

4. The method for detecting the construction quality of a bridge deepwater cofferdam based on machine vision according to claim 1 is characterized in that: The method of obtaining the seam probability of each edge line in each cofferdam image according to the overall gradient relationship between the edge lines in each cofferdam image and the seam edge feature of each edge line includes the following specific methods: Record any edge line in any cofferdam image as a target edge line; obtain the gradient vector of each edge pixel point on the target edge line; record the sum vector of the gradient vectors of all edge pixels on the target edge line as the overall gradient vector of the target edge line; The modulus of the difference vector between the overall gradient vector of the target edge line and the overall gradient vector of any edge line in the cofferdam image other than the target edge line is recorded as the degree of difference between the target edge line and the edge line; the inverse proportional normalization result of the mean of the degree of difference between the target edge line and all edge lines in the cofferdam image other than the target edge line is recorded as the degree of regularity of the target edge line; The product of the seam edge feature and the regularity of the target edge line is recorded as the seam probability of the target edge line.

5. The method for detecting the construction quality of deep-water cofferdams of bridges based on machine vision according to claim 3 is characterized in that: The method of obtaining the deformation degree of each edge line in each cofferdam image according to the extension and bending relationship of each edge line in each cofferdam image includes the following specific methods: Obtain the gradient vector of each edge pixel on each edge line in each cofferdam image; Where, F a,b is the deformation degree of the bth edge line in the ath cofferdam image; G a,b is the maximum value of the angle difference between the directions of the gradient vectors of all edge pixels in the bth edge line in the ath cofferdam image; E a,b is the number of edge pixels on the bth edge line in the ath cofferdam image; a,b,f It is the minimum angle between the direction of the gradient vector of the f-th edge pixel on the b-th edge line in the a-th cofferdam image and the direction of the gradient vector of its feature adjacent point; norm() is the linear normalization function; cos() is the cosine function.

6. The method for detecting the construction quality of a bridge deepwater cofferdam based on machine vision according to claim 1 is characterized in that: The specific method for obtaining the temporary deformation degree of each edge line in each cofferdam image is as follows: Record any cofferdam image as the main image; record any edge line in the main image as the main edge line; obtain all edge lines of any cofferdam image except the main image, and the edge lines whose number of pixel points overlapping with the pixel point position of the main edge line is greater than a preset overlap threshold, and record them as matching lines of the main edge line; The sequence of deformation degrees of the main edge line and its matching lines is recorded as the deformation sequence of the main edge line; Arrange the water pressure indexes of the cofferdam images where the main edge lines and their matching lines are located according to the order of the edge lines corresponding to the deformation degrees in the deformation sequence of the main edge lines to form a water pressure sequence of the main edge lines; The Pearson correlation coefficient between the deformation sequence and the water pressure sequence of the main edge line is recorded as the water pressure influence index of the main edge line; The product of the joint probability of the main edge line and the water pressure influence index is recorded as the temporary deformation degree of the main edge line.

7. The method for detecting the construction quality of deep-water cofferdams of bridges based on machine vision according to claim 6 is characterized in that: The specific method for obtaining the temporary deformation index of each cofferdam image is as follows: The average of the temporary deformation degrees of all edge lines in the main image is recorded as the temporary deformation index of the main image.

8. The method for detecting the construction quality of deep-water cofferdams of bridges based on machine vision according to claim 1 is characterized in that: The method of obtaining the sealing property of each edge line in each cofferdam image according to the temporary deformation index of the cofferdam image and the difference in the temporary deformation degree of the edge lines in the cofferdam image, as well as the deformation degree of the edge lines, includes the following specific methods: For any edge line in any cofferdam image, the linear normalization result of the difference between the temporary deformation degree of the edge line and the temporary deformation index of the cofferdam image is recorded as the water flow index of the edge line; The product of the inversely proportional normalized result of the deformation degree of the edge line and the water flow index is recorded as the sealing performance of the edge line.

9. The method for detecting the construction quality of deep-water cofferdams of bridges based on machine vision according to claim 1, characterized in that: The method for obtaining the construction quality inspection result of the deep-water cofferdam of the bridge based on the sealing performance of all edge lines in all cofferdam images includes the following specific steps: If there are edge lines with sealing properties less than or equal to the sealing threshold in all cofferdam images, the cofferdam construction quality is unqualified; if there are edge lines with sealing properties greater than the sealing threshold in all cofferdam images, the cofferdam construction quality is qualified.

10. A machine vision-based bridge deepwater cofferdam construction quality inspection system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for detecting the construction quality of a bridge deep-water cofferdam based on machine vision as described in any one of claims 1 to 9 are implemented.

Images