Steel bar beam detection method, system, equipment and medium

Abstract

The invention discloses a steel bar beam detection method, system, equipment and medium, which relate to the technical field of engineering quality detection, wherein the steel bar beam detection method comprises collecting a plurality of first-scene images under different viewpoints of the steel bar beam to be detected and respectively obtaining environmental data when the plurality of first-scene images are collected, and according to the environmental data corresponding to the plurality of first-scene images, respectively obtaining global optimal thresholds matching the plurality of first-scene images from a pre-constructed steel bar beam database; according to the global optimal thresholds of the plurality of first-scene images, respectively converting the plurality of first-scene images into three-dimensional images; obtaining first feature data of various types of steel bars in the three-dimensional images, and obtaining feature data corresponding to the steel bar beam to be detected; comparing the feature data of the steel bar beam to be detected with the feature data of the engineering drawing corresponding to the steel bar beam to be detected, identifying the steel bars in the steel bar beam to be detected that do not meet the building specifications, thereby improving the detection efficiency and accuracy, and reducing the manpower cost and time cost.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering quality inspection, and in particular to a steel bar beam inspection method, system, equipment and medium. Background Art

[0002] Steel beams are the key load-bearing parts of building structures. Checking whether the construction meets the requirements of the drawings can ensure the quality and performance of the steel beams, thereby ensuring the safety and durability of the entire building structure. Any deviation in the construction process may lead to structural defects, such as uneven spacing between steel bars, steel bar models that do not match the drawings, etc., which may affect the bearing capacity and service life of the structure. Inspections can promptly discover and correct these problems and avoid potential structural problems.

[0003] In the construction and use of large-scale projects such as new building construction, renovation and reinforcement of old buildings, bridge projects, tunnel projects, etc., steel beams are like the skeleton of the entire structure. The detection of steel beams is very important for the identification of the safety of the overall concrete structure, so higher requirements are placed on the accuracy of steel bar parameter detection.

[0004] The existing steel beam inspection scheme has the following defects:

[0005] It is greatly affected by environmental factors, resulting in reduced accuracy and low efficiency of test results.

[0006] To sum up, in order to better meet the needs of social development, it is urgent to develop more advanced steel beam detection solutions to achieve better social and economic benefits. Summary of the invention

[0007] In order to solve the defects in the prior art, the embodiments of the present invention provide a steel bar beam detection method, system, equipment and medium.

[0008] In a first aspect, a steel bar beam detection method provided by an embodiment of the present invention comprises the following steps:

[0009] Collecting multiple first scene images from different viewpoints of the steel bar beam to be inspected and respectively acquiring environmental data when collecting the multiple first scene images, wherein the environmental data includes shooting distance, light intensity, ambient temperature, ambient humidity and resolution of the multiple first scene images when collecting the multiple first scene images;

[0010] According to the environmental data corresponding to the plurality of first scene images, respectively obtaining global optimal thresholds matching the plurality of first scene images from a pre-built steel beam database;

[0011] converting the plurality of first scene images into three-dimensional images respectively according to a global optimal threshold of the plurality of first scene images;

[0012] Acquire first feature data of various types of steel bars in the three-dimensional image to obtain feature data corresponding to the steel bar beam to be detected, wherein the first feature data includes the position, specification and quantity of various types of steel bars in the three-dimensional space;

[0013] The characteristic data of the steel bar beam to be detected is compared with the characteristic data of the engineering drawing corresponding to the steel bar beam to be detected, and the steel bars in the steel bar beam to be detected that do not match the characteristic data of the engineering drawing are identified.

[0014] In some examples, converting the plurality of first scene images into three-dimensional images respectively according to the global optimal threshold of the plurality of first scene images includes:

[0015] Based on the global optimal threshold of the plurality of first scene images, binarizing the plurality of first scene images respectively to obtain the plurality of binarized first scene images;

[0016] Based on a two-dimensional discrete wavelet transform model, the binarized plurality of first scene images are decomposed respectively to obtain a plurality of decomposed first scene images.

[0017] In some examples, converting the plurality of first scene images into three-dimensional images according to the global optimal threshold of the plurality of first scene images further includes:

[0018] Based on a two-dimensional discrete wavelet inverse transform model, denoising the decomposed plurality of first scene images to obtain a plurality of denoised first scene images;

[0019] Based on a multi-view stereo matching algorithm, three-dimensional images corresponding to the plurality of denoised first scene images are generated.

[0020] In some examples, after generating the denoised three-dimensional images corresponding to the plurality of first scene images, the method further includes:

[0021] Different types of steel bars are marked with different type and quantity labels.

[0022] In some examples, the process of constructing the pre-built steel beam database includes:

[0023] Acquire second characteristic data of various types of steel bars in historical engineering drawings, wherein the second characteristic data includes positions, specifications, and quantities of various types of steel bars in three-dimensional space;

[0024] Under different environments, the on-site images corresponding to the historical engineering drawings are respectively collected to obtain a plurality of second on-site images, wherein the plurality of second on-site images are a plurality of on-site images that completely match the feature data of the historical engineering drawings;

[0025] An association relationship is established between the historical engineering drawing and the second characteristic data.

[0026] In some examples, the process of constructing the pre-constructed steel beam database further includes:

[0027] Using an automatic threshold algorithm, respectively obtaining a global optimal threshold of a plurality of the second scene images;

[0028] Respectively acquiring environmental data when the plurality of second scene images are collected, wherein the environmental data includes shooting distance, light intensity, ambient temperature, ambient humidity, and resolution of the plurality of second scene images when the plurality of second scene images are collected;

[0029] A one-to-one association relationship between the environmental data corresponding to the plurality of second scene images and the global optimal threshold is established respectively.

[0030] In some examples, the process of constructing the pre-constructed steel beam database further includes:

[0031] A steel beam database is constructed based on the association relationship between the historical engineering drawings and the second feature data, and the one-to-one association relationship between the environmental data corresponding to multiple second site images and the global optimal threshold.

[0032] In a second aspect, a reinforcement beam detection system provided by an embodiment of the present invention includes:

[0033] A first acquisition module is configured to acquire a plurality of first scene images at different viewpoints of the steel bar beam to be detected and respectively acquire environmental data when the plurality of first scene images are acquired, wherein the environmental data includes a shooting distance, light intensity, ambient temperature, ambient humidity, and resolution of the plurality of first scene images when the plurality of first scene images are acquired;

[0034] A second acquisition module is configured to respectively acquire global optimal thresholds matching the plurality of first scene images from a pre-built steel beam database according to the environmental data corresponding to the plurality of first scene images;

[0035] a conversion module, configured to convert the plurality of first scene images into three-dimensional images respectively according to a global optimal threshold of the plurality of first scene images;

[0036] A third acquisition module is configured to acquire first feature data of various types of steel bars in the three-dimensional image to obtain feature data corresponding to the steel bar beam to be detected, wherein the first feature data includes the position, specification and quantity of various types of steel bars in the three-dimensional space;

[0037] The comparison module is configured to compare the characteristic data of the steel beam to be detected with the characteristic data of the engineering drawing matching the steel beam to be detected, and identify the steel bars in the steel beam to be detected that do not meet the building specifications.

[0038] In a third aspect, an electronic device provided by an embodiment of the present invention includes a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the steel beam detection method disclosed in the first aspect is implemented.

[0039] In a fourth aspect, a computer-readable storage medium provided by an embodiment of the present invention stores computer program instructions, and when the computer program instructions are executed by a processor, the steel beam detection method disclosed in the first aspect is implemented.

[0040] Compared with the prior art, the embodiments of the present invention provide the following beneficial effects:

[0041] The present invention combines image processing technology and deep learning technology to realize automatic recognition and detection of various types of steel bars. Through the pre-constructed steel beam database (trained deep learning model), steel bars that do not meet building specifications can be accurately identified, thereby improving detection efficiency and accuracy, and reducing labor and time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 The figure is a schematic flow chart of a reinforcement beam detection method disclosed according to an embodiment of the present invention.

[0044] Figure 2 The figure is a schematic diagram of the structure of a reinforcement beam detection system disclosed according to an embodiment of the present invention.

[0045] Figure 3 This is a schematic diagram of the shape identification of various types of steel bars in reinforced beams.

[0046] Figure 4 A principle block diagram of an electronic device serving as a classical computing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following is a further detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings and examples. The detailed descriptions and drawings of the following embodiments are used to exemplarily illustrate the principles of the present disclosure, but cannot be used to limit the scope of the present disclosure. The present disclosure can be implemented in many different forms, not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

[0048] Example 1

[0049] like Figure 1 As shown, the steel bar beam detection method provided by the embodiment of the present invention comprises the following steps:

[0050] S101, collecting multiple first-scene images from different viewpoints of the steel beam to be inspected and respectively obtaining environmental data when collecting the multiple first-scene images, wherein the environmental data includes the shooting distance, light intensity, ambient temperature, ambient humidity and resolution of the multiple first-scene images when collecting the multiple first-scene images.

[0051] Specifically, collecting data from different viewpoints can ensure that the entire steel beam to be inspected is covered from multiple angles to obtain a complete steel beam structure.

[0052] S102, according to the environmental data corresponding to the plurality of first scene images, respectively obtaining global optimal thresholds matching the plurality of first scene images from a pre-built steel beam database.

[0053] Specifically, there is a correlation between the global optimal threshold of the image and the environmental data, that is, one global optimal threshold corresponds to one environmental data. By directly obtaining the global optimal thresholds that match multiple first-site images from the pre-built steel beam database, the step of calculating the global optimal threshold is omitted, thereby improving efficiency. Specifically, the segmentation threshold is adjusted and optimized according to the feedback result of the global optimal threshold to ensure the coordination and unification of the global optimal threshold and the segmentation threshold. When performing image segmentation, if the global optimal threshold is not selected properly, it may lead to poor segmentation effect or inaccurate segmentation results.

[0054] The global optimal threshold is a key parameter used to segment an image into different regions or objects. The role of the global optimal threshold is mainly to help segment the target area of ​​interest from the image, providing a basis for subsequent image processing and analysis. Selecting an appropriate global optimal threshold is a key step in achieving accurate and effective image processing. The global optimal threshold is used to determine the light and dark boundaries in the image, thereby improving the clarity and contrast of the image. By selecting an appropriate threshold, the details in the image can be effectively highlighted, making the image look clearer and more vivid, which can further improve the quality and accuracy of image processing.

[0055] In some examples, the process of building a pre-built library of reinforced beams includes:

[0056] Acquire second characteristic data of various types of steel bars in historical engineering drawings, wherein the second characteristic data includes positions, specifications, and quantities of various types of steel bars in three-dimensional space;

[0057] Under different environments, the on-site images corresponding to the historical engineering drawings are respectively collected to obtain a plurality of second on-site images, wherein the plurality of second on-site images are a plurality of on-site images that completely match the feature data of the historical engineering drawings;

[0058] Establish an association relationship between the historical engineering drawings and the second characteristic data.

[0059] Specifically, the camera used to collect the plurality of second scene images has the same parameters as the camera used to collect the plurality of first scene images. Therefore, for different steel beams, when the parameters of the camera used and the environmental data are the same, the global optimal threshold of the collected scene images is also the same.

[0060] In some examples, the process of building a pre-built library of reinforced beams also includes:

[0061] Using an automatic threshold algorithm, respectively obtaining global optimal thresholds of a plurality of second scene images;

[0062] Respectively acquiring environmental data when the plurality of second scene images are collected, wherein the environmental data includes shooting distance, light intensity, environmental temperature, environmental humidity, and resolution of the plurality of second scene images when the plurality of second scene images are collected;

[0063] A one-to-one association relationship between the environmental data corresponding to the plurality of second scene images and the global optimal threshold is established respectively.

[0064] Specifically, the automatic threshold algorithm is the Otsu threshold method. Specifically, the light contrast technology calculates the grayscale histogram corresponding to the scene image and obtains the global optimal threshold , including the following steps:

[0065] (1) For each possible threshold t, the approximation coefficient LL is divided into two categories: the on-site image of the steel beam to be detected and the background of the on-site image.

[0066] (2) Calculate the total number of pixels and the total grayscale value of pixels in the field image of each category of steel beam to be tested. , thereby calculating the average gray value of the category.

[0067] (3) For each threshold, calculate the intra-class variance , between-class variance .

[0068] (4) Calculate the inter-class variance The sum of , find the threshold that maximizes the sum as the global optimal threshold ,in:

[0069] (1)

[0070] In formula (1), k represents the number of pixels; represents the average gray value; is the average gray value of the category below the threshold t; The average gray value of the category at and above threshold t;

[0071] (5) Choose the between-class variance The largest threshold is taken as the global optimal threshold ,Right now

[0072] (2)

[0073] In some examples, the process of building a pre-built library of reinforced beams also includes:

[0074] A steel beam database is constructed based on the association relationship between the historical engineering drawings and the second characteristic data, and the one-to-one association relationship between the environmental data corresponding to the multiple second on-site images and the global optimal threshold.

[0075] In particular, if a global optimal threshold matching a certain scene image among the multiple first scene images is not found in the pre-constructed steel beam database, the automatic threshold algorithm is used to obtain the global optimal threshold of the scene image, and the environmental data corresponding to the global image and the global optimal threshold are written into the steel beam database.

[0076] S103, converting the plurality of first scene images into three-dimensional images respectively according to the global optimal threshold of the plurality of first scene images.

[0077] In some examples, step S103 specifically includes the following steps:

[0078] Based on the global optimal threshold of the multiple first scene images, the multiple first scene images are binarized respectively to obtain the multiple binarized first scene images.

[0079] Specifically, the multiple first scene images are decomposed into two categories, namely, steel beams and background, by using their respective global optimal thresholds, so that the steel beams in the multiple first scene images can be separated from the corresponding scene images later. Binarize the low-frequency coefficient LL, and set the approximate coefficient after binarization to ,in:

[0080] (3)

[0081] Based on a two-dimensional discrete wavelet transform model, the binarized multiple first scene images are decomposed respectively to obtain multiple decomposed first scene images.

[0082] Specifically, the two-dimensional discrete wavelet transform model is used to decompose the on-site image into low-frequency coefficients (LL subband) and high-frequency coefficients (LH subband, HL subband and HH subband), retain the LL subband, discard the LH subband, HL subband and HH subband, and retain the LL subband. Among them, eliminating or weakening the LH subband, HL subband and HH subband helps to remove high-frequency noise and unimportant information in each on-site image. The discrete wavelet transform model can perform layered processing on the on-site image and extract the detailed features of various types of steel bars, which helps to more accurately identify the position and shape of various types of steel bars. Among them, the two-dimensional discrete wavelet transform model is expressed as:

[0083] , where DWT() is the discrete wavelet transform function.

[0084] In some examples, step S103 specifically further includes the following steps:

[0085] Based on a two-dimensional inverse discrete wavelet transform model, the decomposed multiple first scene images are denoised to obtain multiple denoised first scene images.

[0086] Specifically, the approximate coefficients after binarization are Perform inverse discrete wavelet transform to reconstruct the binary scene image , the low frequency coefficient LL Convert to the original live image space, where

[0087] (4)

[0088] In formula (4), IDWT () is the inverse discrete wavelet transform function. This process retains the important features of the steel beam to be detected, while reducing the influence of noise and illumination inhomogeneity, and obtains the final binary image, which enhances the contrast of the on-site image, making the various types of steel bars in the steel beam to be detected more clearly visible, and enhancing the accuracy of steel beam detection.

[0089] Based on a multi-view stereo matching algorithm, a three-dimensional image corresponding to the multiple first scene images after denoising is generated.

[0090] Specifically, the multi-view stereo matching algorithm extracts and matches feature points from multiple two-dimensional images (field images) collected from different angles, performs triangulation in combination with known camera parameters, generates a feature point cloud in three-dimensional space, and then constructs a three-dimensional model through point cloud processing and surface reconstruction technology, thereby automatically constructing corresponding three-dimensional images based on two-dimensional images from multiple viewpoints, providing an accurate three-dimensional model for steel beam detection and improving the accuracy of detection. Among them, the two-dimensional images from each viewpoint have a uniform size and pixel. According to the matched feature points and known camera parameters (focal length, position, etc.), the triangulation method is used to calculate the position of the feature points in three-dimensional space to form a feature point cloud, which is optimized through various algorithms (iterative closest point algorithm) to improve the accuracy of the feature point cloud.

[0091] S104, obtaining first feature data of each type of steel bar in the three-dimensional image, and obtaining feature data corresponding to the steel bar beam to be detected, wherein the first feature data includes the position, specification and quantity of each type of steel bar in the three-dimensional space.

[0092] S105, comparing the characteristic data of the steel beam to be detected with the characteristic data of the engineering drawing corresponding to the steel beam to be detected, and identifying the steel bars in the steel beam to be detected that do not match the characteristic data in the engineering drawing.

[0093] In some examples, after step S103, the method further includes:

[0094] Different types of steel bars are marked with different type and quantity labels.

[0095] Specifically, Figure 2 As shown, the various types of steel bars include longitudinal bars 4, stirrups 2, hanger bars 3 and axillary bars 1, among which the longitudinal bars 4 are marked in red and represented by the letter R; stirrups 2 are marked in yellow and represented by the letter Y; hanger bars 3 are marked in green and represented by the letter G; axillary bars 1 are marked in blue and represented by the letter B; and the quantity of each type of steel bar is also marked.

[0096] The present invention combines image processing technology and deep learning technology to realize automatic recognition and detection of various types of steel bars. Through the pre-constructed steel beam database (trained deep learning model), steel bars that do not meet building specifications can be accurately identified, thereby improving detection efficiency and accuracy, and reducing labor and time costs.

[0097] like Figure 3 As shown, the steel bar beam detection system provided by the embodiment of the present invention includes:

[0098] A first acquisition module is configured to collect multiple first scene images under different viewpoints of the steel bar beam to be detected and respectively obtain environmental data corresponding to the collected multiple first scene images, wherein the environmental data includes a shooting distance, light intensity, ambient temperature, ambient humidity when collecting the multiple first scene images, and a resolution of the multiple first scene images;

[0099] A second acquisition module is configured to respectively acquire global optimal thresholds matching the plurality of first scene images from a pre-built steel beam database according to the environmental data corresponding to the plurality of first scene images;

[0100] a conversion module, configured to convert the plurality of first scene images into three-dimensional images respectively according to a global optimal threshold of the plurality of first scene images;

[0101] A third acquisition module is configured to acquire first feature data of various types of steel bars in the three-dimensional image to obtain feature data corresponding to the steel bar beam to be detected, wherein the first feature data includes the position, specification and quantity of various types of steel bars in the three-dimensional space;

[0102] The comparison module is configured to compare the characteristic data of the steel beam to be detected with the characteristic data of the engineering drawing that matches the steel beam to be detected, and identify the steel bars in the steel beam to be detected that do not match the characteristic data of the engineering drawing.

[0103] Figure 4 The hardware structure principle block diagram of an embodiment of the electronic device provided by the present invention is shown. The electronic device includes a processor 601 and a memory 602 storing computer program instructions. When the processor executes the computer program instructions, the method disclosed in the above embodiment of the present invention is implemented.

[0104] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0105] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0106] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0107] In some examples, such as Figure 4 As shown, the electronic device may further include a communication interface 603 and a bus 610. Figure 4 As shown, the processor 601, the memory 602, and the communication interface 603 are connected and communicate with each other via a bus 610. The electronic device in the embodiment of the present invention may be a server or other computing device, or may be a cloud server.

[0108] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiment of the present invention.

[0109] Bus 610 includes hardware, software or both, and couples the components of online data traffic billing equipment to each other. For example, but not limitation, the bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnect (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. Where appropriate, bus 610 may include one or more buses. Although the embodiment of the present invention describes and shows a specific bus, the present invention considers any suitable bus or interconnection.

[0110] The present invention also provides a computer program product, which includes computer program instructions, and when the computer program instructions are executed by a processor, the method provided by the embodiment of the present invention is implemented. The computer program product is, for example, a software installation package, a plug-in compatible with a related software system, etc.

[0111] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0112] In addition, the words “first”, “second” and the like used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts.

[0113] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, module and unit can refer to the process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A steel bar beam detection method, characterized in that: The following steps are involved: Collecting multiple first scene images from different viewpoints of the steel bar beam to be inspected and respectively acquiring environmental data when collecting the multiple first scene images, wherein the environmental data includes shooting distance, light intensity, ambient temperature, ambient humidity and resolution of the multiple first scene images when collecting the multiple first scene images; According to the environmental data corresponding to the plurality of first scene images, respectively obtaining global optimal thresholds matching the plurality of first scene images from a pre-built steel beam database, wherein the global optimal threshold is used to determine the light and dark boundary in the image, improve the clarity and contrast of the image, and help segment the target area of ​​interest from the image; According to the global optimal threshold of the plurality of first scene images, the plurality of first scene images are respectively converted into three-dimensional images, including: Based on the global optimal threshold of the plurality of first scene images, binarizing the plurality of first scene images respectively to obtain the plurality of binarized first scene images; Based on a two-dimensional discrete wavelet transform model, the binarized plurality of first scene images are respectively decomposed to obtain a plurality of decomposed first scene images; Based on a two-dimensional discrete wavelet inverse transform model, denoising the decomposed plurality of first scene images to obtain a plurality of denoised first scene images; Based on a multi-view stereo matching algorithm, generating a 3D image corresponding to the plurality of first scene images after denoising; Acquire first feature data of various types of steel bars in the three-dimensional image to obtain feature data corresponding to the steel bar beam to be detected, wherein the first feature data includes the position, specification and quantity of various types of steel bars in the three-dimensional space; The characteristic data of the steel bar beam to be detected is compared with the characteristic data of the engineering drawing corresponding to the steel bar beam to be detected, and the steel bars in the steel bar beam to be detected that do not match the characteristic data of the engineering drawing are identified.

2. The steel bar beam detection method according to claim 1, characterized in that: After generating the denoised three-dimensional images corresponding to the plurality of first scene images, the method further includes: Different types of steel bars are marked with different type and quantity labels.

3. The steel bar beam detection method according to claim 1, characterized in that: The construction process of the pre-constructed reinforced beam database includes: Acquire second characteristic data of various types of steel bars in historical engineering drawings, wherein the second characteristic data includes positions, specifications, and quantities of various types of steel bars in three-dimensional space; Under different environments, the on-site images corresponding to the historical engineering drawings are respectively collected to obtain a plurality of second on-site images, wherein the plurality of second on-site images are a plurality of on-site images that completely match the feature data of the historical engineering drawings; An association relationship is established between the historical engineering drawing and the second characteristic data.

4. The steel bar beam detection method according to claim 3, characterized in that: The process of constructing the pre-constructed steel beam database further includes: Using an automatic threshold algorithm, respectively obtaining a global optimal threshold of a plurality of the second scene images; Respectively acquiring environmental data when the plurality of second scene images are collected, wherein the environmental data includes shooting distance, light intensity, ambient temperature, ambient humidity, and resolution of the plurality of second scene images when the plurality of second scene images are collected; A one-to-one association relationship between the environmental data corresponding to the plurality of second scene images and the global optimal threshold is established respectively.

5. The steel bar beam detection method according to claim 4, characterized in that: The process of constructing the pre-constructed steel beam database further includes: A steel beam database is constructed based on the association relationship between the historical engineering drawings and the second feature data, and the one-to-one association relationship between the environmental data corresponding to multiple second site images and the global optimal threshold.

6. A steel bar beam detection system, characterized in that: include: A first acquisition module is configured to acquire a plurality of first scene images at different viewpoints of the steel bar beam to be detected and respectively acquire environmental data when the plurality of first scene images are acquired, wherein the environmental data includes a shooting distance, light intensity, ambient temperature, ambient humidity, and resolution of the plurality of first scene images when the plurality of first scene images are acquired; A second acquisition module is configured to respectively acquire global optimal thresholds matching the plurality of first scene images from a pre-built steel beam database according to the environmental data corresponding to the plurality of first scene images, wherein the global optimal threshold is used to determine the light and dark boundary in the image, improve the clarity and contrast of the image, and help segment the target area of ​​interest from the image; A conversion module is configured to convert the plurality of first scene images into three-dimensional images respectively according to a global optimal threshold of the plurality of first scene images, wherein the conversion module comprises: A binarization unit is configured to binarize the plurality of first scene images respectively based on a global optimal threshold of the plurality of first scene images to obtain a plurality of binarized first scene images; A decomposition unit is configured to decompose the plurality of binarized first scene images respectively based on a two-dimensional discrete wavelet transform model to obtain a plurality of decomposed first scene images; a denoising unit configured to denoise the decomposed plurality of first scene images based on a two-dimensional discrete wavelet inverse transform model to obtain a plurality of denoised first scene images; A generating unit configured to generate, based on a multi-view stereo matching algorithm, three-dimensional images corresponding to the plurality of first scene images after denoising; A third acquisition module is configured to acquire first feature data of various types of steel bars in the three-dimensional image to obtain feature data corresponding to the steel bar beam to be detected, wherein the first feature data includes the position, specification and quantity of various types of steel bars in the three-dimensional space; The comparison module is configured to compare the characteristic data of the steel beam to be detected with the characteristic data of the engineering drawing that matches the steel beam to be detected, and identify the steel bars in the steel beam to be detected that do not match the characteristic data of the engineering drawing.

7. An electronic device comprising a processor and a memory storing computer program instructions, characterized in that: When the processor executes the computer program instructions, the steel bar beam detection method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the steel bar beam detection method as described in any one of claims 1 to 5 is implemented.

Images