A computer vision-based steel bar processing intelligent optimization method and system

Abstract

The embodiment of the specification provides a steel bar processing intelligent optimization method and system based on computer vision, wherein the method comprises the following steps: acquiring a cross-section image and a transverse image of a steel bar pile through a camera; preprocessing the end face image and the transverse image, acquiring the number of steel bars and the length of steel bars based on the end face image and the transverse image respectively, and obtaining steel bar data; inputting a trained dynamic programming model based on existing material order requirements and the steel bar data, and obtaining a steel bar cutting scheme; judging whether the steel bar cutting scheme exceeds the limit based on the transverse image, optimizing the cutting scheme according to the judgment result, and obtaining a final cutting scheme to realize precise cutting. The application can more efficiently and accurately complete the steel bar processing and cutting project order, improve the efficiency, reduce the surplus material and reduce the labor cost.

Description

Technical Field

[0001] This document relates to the field of computer vision technology, and in particular to a computer vision-based intelligent optimization method and system for steel bar processing. Background Technology

[0002] Building materials, as the material foundation of the construction industry, have a significant impact on the cost of civil engineering projects. Steel reinforcement, as one of the most important building materials, accounts for over 30% of the cost of civil engineering projects. Therefore, optimizing the cutting and combination methods of steel reinforcement, while meeting the requirements of structural design codes, is of great significance for improving the utilization rate of steel reinforcement materials and reducing the cost of civil engineering projects.

[0003] Currently, in practical engineering, manual rebar cutting and assembly calculations are complex. Workers often only assemble rebar within single components and simply cut it sequentially, leading to significant rebar waste. To address the functional requirements of rebar processing, cutting, and quality monitoring for rebar equipment manufacturers, an automated intelligent optimization method and system for rebar cutting is needed. This system should be able to monitor equipment operation status in real time, modify rebar processing equipment parameters, remotely download equipment control programs, and perform remote equipment location tracking. This would enable real-time monitoring of key parameters during rebar processing equipment operation, facilitating equipment maintenance and management, improving the intelligence level of rebar processing equipment, and ultimately increasing rebar processing efficiency and quality. Summary of the Invention

[0004] This specification provides one or more embodiments of a computer vision-based intelligent optimization method for rebar processing, including:

[0005] S1. Capture cross-sectional and transverse images of the steel reinforcement pile using a camera;

[0006] S2. Preprocess the end face image and the transverse image, and obtain the number of steel bars and the length of steel bars based on the end face image and the transverse image respectively to obtain steel bar data;

[0007] S3. Based on the existing material list requirements and the steel bar data, input the trained dynamic programming model to obtain the steel bar cutting scheme;

[0008] S4. Based on the horizontal image, the steel bar cutting scheme is judged to exceed the limit. The cutting scheme is optimized according to the judgment result to obtain the final cutting scheme and achieve precise cutting.

[0009] Furthermore, the quantity of reinforcing bars is obtained based on the end face image, specifically using the following method:

[0010] The YOLOv5 algorithm is used to classify the end face image, identify and extract the profile of the steel bar section;

[0011] Detect and locate the position of the reinforcing bars using rectangular frames, and calculate the number of rectangular frames for the reinforcing bars;

[0012] The number of rebars is obtained from the number of rebar rectangles.

[0013] Furthermore, the length of the reinforcing bar is obtained based on the horizontal image, specifically using the following method:

[0014] Image segmentation technology is used to extract the rebar mask and mark the location and extent of the rebar;

[0015] The length limit is determined by obtaining the position and angle of the camera from the horizontal image, and the length of the rebar is calculated by combining the geometric relationship of the rebar segmentation range.

[0016] Furthermore, the specific method for obtaining the rebar cutting scheme by inputting the trained dynamic programming model based on the existing material list requirements and the rebar data is as follows:

[0017] An objective function is established to minimize the use of raw materials for steel bars while meeting the requirements for steel bar cutting. The optimal cutting method is achieved when the remaining material after cutting is no greater than the minimum cutting length.

[0018] L-[a1×c(j,1)+a2×(j,2)+...+an×c(j,n)]≤min(an);

[0019] The objective function is defined as follows:

[0020]

[0021] Where L is the length of the steel bar, a1, a2, ..., an are the cutting lengths, and the corresponding cutting quantities of steel bars are b1, b2, ..., bn bars respectively; c(j,i) is the number of corresponding cutting lengths in the single raw material cutting method; x1, x2, ..., xn represent the number of times each cutting method is used.

[0022] Furthermore, the constraint equations for the objective function are as follows:

[0023] AX≥b;

[0024] In this context, matrix A and matrix X represent the number of times each segmentation method is used, and matrix b represents the corresponding number of steel bar cutting requirements.

[0025] Furthermore, the method further includes:

[0026] First, sort the cutting lengths from largest to smallest, and prioritize cutting the longest cutting lengths.

[0027] Furthermore, the specific method for judging the over-limit of the rebar cutting scheme based on the horizontal image is as follows:

[0028] The horizontal image is identified and classified, and the steel reinforcement region in the horizontal image is segmented. The steel reinforcement segmentation result is then masked and processed by the maximum connected component to realize the steel reinforcement exceeding the limit.

[0029] This specification provides one or more embodiments of a computer vision-based intelligent optimization system for rebar processing, including:

[0030] Image acquisition module: used to acquire cross-sectional and transverse images of the steel reinforcement pile via a camera;

[0031] Image processing module: used to preprocess the end face image and the horizontal image, and obtain the number and length of the reinforcing bars based on the end face image and the horizontal image respectively, to obtain the reinforcing bar data;

[0032] Solution planning module: Based on the existing material list requirements and the rebar data, input a trained dynamic programming model to obtain the rebar cutting solution;

[0033] Solution optimization module: It is used to make a limit judgment on the steel bar cutting scheme based on the horizontal image, optimize the cutting scheme according to the judgment result, and obtain the final cutting scheme to achieve precise cutting.

[0034] This specification provides one or more embodiments of an electronic device, including:

[0035] A processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to implement the steps of the above-described intelligent optimization method for rebar processing based on computer vision.

[0036] This specification provides one or more embodiments of a storage medium for storing computer-executable instructions, which, when executed, implement the steps of the above-described intelligent optimization method for rebar processing based on computer vision.

[0037] This invention automates and optimizes the steel bar cutting process by using camera image acquisition and dynamic programming models, thereby improving work efficiency, reducing costs, enhancing adaptability and manageability, and meeting environmental protection and energy conservation requirements.

[0038] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A flowchart illustrating a computer vision-based intelligent optimization method for rebar processing provided in one or more embodiments of this specification;

[0041] Figure 2 A flowchart illustrating how the YOLOv5 algorithm, provided in one or more embodiments of this specification, processes an input end-face image;

[0042] Figure 3 The image shows the effect of processing an input end face image using the YOLOv5 algorithm provided in one or more embodiments of this specification.

[0043] Figure 4 This diagram illustrates the over-limit judgment of a steel bar cutting scheme based on a horizontal image, provided in one or more embodiments of this specification.

[0044] Figure 5 A screenshot of the rebar processing monitoring intelligent platform provided in one or more embodiments of this specification.

[0045] Figure 6 A diagram of the steel bar quantity report window of the intelligent platform for monitoring steel bar processing provided in one or more embodiments of this specification;

[0046] Figure 7 A schematic diagram illustrating the composition of a computer vision-based intelligent optimization system for steel bar processing, provided for one or more embodiments of this specification.

[0047] Figure 8 This is a schematic diagram of the structure of an electronic device provided for one or more embodiments of this specification. Detailed Implementation

[0048] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0049] Method Implementation Examples

[0050] According to embodiments of the present invention, a computer vision-based intelligent optimization method for rebar processing is provided. Figure 1 A flowchart of a computer vision-based intelligent optimization method for rebar processing provided in one or more embodiments of this specification is shown below. Figure 1 As shown, the intelligent optimization method for rebar processing based on computer vision according to an embodiment of the present invention specifically includes:

[0051] S1. Capture cross-sectional and transverse images of the steel reinforcement pile using a camera.

[0052] Set the camera position and adjust the angle and height of the camera according to the actual situation of the rebar pile to ensure that the cross-section and horizontal image of the rebar pile can be captured completely. When capturing the cross-section image, ensure that the camera capturing the cross-section of the rebar pile is parallel to the cross-section. When capturing the horizontal image, rotate the camera to the horizontal direction of the rebar pile to ensure that the camera is parallel to the horizontal direction. Adjust the camera's focus and exposure. Capture each object three times to ensure that the image is accurately focused and clear.

[0053] S2. Preprocess the end face image and the transverse image, and obtain the number of steel bars and the length of steel bars based on the end face image and the transverse image respectively to obtain steel bar data.

[0054] The acquired end-face and transverse images are synchronized to the intelligent platform, and the quantity of reinforcing bars is obtained based on the end-face images. Figure 2 As shown, the specific method is as follows:

[0055] The YOLOv5 algorithm is used to classify the input end-face image, identify and extract the rebar cross-section contour; the rebar cross-section contour is detected, and the position of each detected rebar is marked with a rectangular bounding box, such as... Figure 3 As shown, calculate the number of marked rectangles; obtain the rebar quantity string based on the number of rebar rectangles, and upload the obtained rebar quantity string to the platform for data interaction.

[0056] The method for obtaining the length of the reinforcing bar based on the horizontal image is as follows:

[0057] Image segmentation technology is used to extract the rebar segmentation mask from the acquired horizontal image, marking the position and range of the rebar; the length limit is determined based on the position and angle of the camera obtained from the horizontal image, and the length of the rebar is calculated by combining the geometric relationship of the rebar segmentation range.

[0058] S3. Based on the existing material list requirements and the steel bar data, input the trained dynamic programming model to obtain the steel bar cutting scheme.

[0059] An objective function is established to minimize the use of raw materials for steel bars while meeting the requirements for steel bar cutting. The optimal cutting method is achieved when the remaining material after cutting is no greater than the minimum cutting length.

[0060] L-[a1×c(j,1)+a2×(j,2)+...+an×c(j,n)]≤min(an);

[0061] The objective function is defined as follows:

[0062]

[0063] Where L is the fixed length of the raw material steel bar, a1, a2, ..., an are the cutting lengths, and the corresponding cutting quantities of steel bars are b1, b2, ..., bn bars respectively; c(j,i) is the number of corresponding cutting lengths in the single raw material cutting method; x1, x2, ..., xn represent the number of times each cutting method is used.

[0064] With a fixed length of L, the maximum number of pieces that can be cut is:

[0065] int(L / ai)

[0066] Here, `int` represents the remainder rounded down, so there are 0 to `int(L / ai)` options for choosing `ai`. Assuming `L = 9` and `ai = 2.3`, there are 4 choices: (0, 1, 2, 3). Assuming `a1` corresponds to choice `c(j, 1)`, `ai` corresponds to `c(j, i)`, and `an` corresponds to `c(j, n)`, then:

[0067] a1×c(j,1)+a2×(j,2)+...+an×c(j,n)≤0.

[0068] For a single steel bar, the process involves segmentation and enumeration. To prevent omissions in the enumeration, a loop is used to list all feasible solutions. First, the cutting lengths a1, a2, ..., an are sorted from largest to smallest, and the longest cutting length is selected first for cutting. This also facilitates the setting of constraints later.

[0069] The constraint equations for the objective function are as follows:

[0070] AX≥b;

[0071] In this context, matrix A and matrix X represent the number of times each segmentation method is used, and matrix b represents the corresponding number of steel bar cutting requirements.

[0072] S4. Based on the horizontal image, the steel bar cutting scheme is judged to exceed the limit. The cutting scheme is optimized according to the judgment result to obtain the final cutting scheme and achieve precise cutting.

[0073] like Figure 4 As shown, the method for judging whether the rebar cutting scheme exceeds the limit is based on the horizontal image: First, the horizontal image is identified and classified, and the rebar region in the horizontal image is segmented. Then, the segmented rebar results are subjected to segmentation masking, and then the rebar exceeds the limit by processing the maximum connected component. Further, the cutting scheme is optimized according to the judgment result to obtain the final cutting scheme, and the flat rebar cross-section is precisely cut to the length.

[0074] A smart platform integrating technologies is used to process data information quickly, synchronize it promptly, and monitor it in real time.

[0075] By integrating the three major functions of YOLOv5 algorithm for real-time detection of rebar quantity, dynamic programming for rebar cutting scheme optimization, and PaddleSeg for precise control of rebar cutting, an intelligent rebar processing platform is established. Based on the data information processed by the three functional modules, the platform enables real-time interaction to optimize rebar processing and cutting in all aspects, thereby achieving the target indicators for rebar processing orders.

[0076] Some renderings of the intelligent platform for monitoring steel bar processing are shown below. Figure 5 , Figure 6 During the steel bar processing, the computer IP and camera IP are changed to be in the same network segment. The size of the monitoring screen and the position of the pan-tilt unit are changed by controlling the adjustment buttons in this interface so that the appearance and shape of the steel bars can be observed more clearly. This facilitates the steel bar quantity identification function based on the YOLO algorithm. The KingSCADA KvdbGrid control is used to generate a report on the steel bar quantity results of each monitoring screen, and the quantity of steel bars used in the steel bar processing is identified and counted.

[0077] The beneficial effects of this invention are as follows:

[0078] By utilizing a trained dynamic programming model, and based on existing material list requirements and rebar data, the optimal rebar cutting scheme is generated. This maximizes the utilization of rebar materials, reduces waste, and lowers costs. The cutting scheme undergoes limit-breaking checks to ensure its feasibility and effectiveness. Rebar detection and cutting are automated, reducing labor costs. The scheme can be adjusted and optimized according to different material list requirements and rebar data to adapt to different production scenarios and changing needs, exhibiting strong adaptability and scalability. In summary, this invention, through the application of camera image acquisition and a dynamic programming model, achieves automation and optimization of rebar cutting schemes, improving work efficiency, reducing costs, enhancing adaptability and manageability, and meeting environmental protection and energy-saving requirements.

[0079] System Implementation Examples

[0080] According to embodiments of the present invention, a computer vision-based intelligent optimization system for rebar processing is provided. Figure 7 A schematic diagram illustrating the composition of a computer vision-based intelligent optimization system for rebar processing, provided for one or more embodiments of this specification, is shown below. Figure 7 As shown, the intelligent optimization system for rebar processing based on computer vision according to an embodiment of the present invention specifically includes:

[0081] Image acquisition module 710: used to acquire cross-sectional and transverse images of the steel reinforcement pile via a camera;

[0082] Image processing module 720: used to preprocess the end face image and the transverse image, and obtain the number of steel bars and the length of steel bars based on the end face image and the transverse image respectively, to obtain steel bar data;

[0083] Scheme planning module 730: Based on the existing material list requirements and the steel bar data, input the trained dynamic programming model to obtain the steel bar cutting scheme;

[0084] Scheme optimization module 740: is used to make a limit judgment on the steel bar cutting scheme based on the horizontal image, optimize the cutting scheme according to the judgment result, and obtain the final cutting scheme to achieve precise cutting.

[0085] The embodiments of the present invention are system embodiments corresponding to the above method embodiments. The specific operation of each module can be understood by referring to the description of the method embodiments, and will not be repeated here.

[0086] Device Example 1

[0087] This invention provides an electronic device, such as... Figure 8As shown, it includes: a memory 80, a processor 82, and a computer program stored in the memory 80 and executable on the processor 82. When the computer program is executed by the processor 82, it performs the following method steps:

[0088] S1. Capture cross-sectional and transverse images of the steel reinforcement pile using a camera;

[0089] S2. Preprocess the end face image and the transverse image, and obtain the number of steel bars and the length of steel bars based on the end face image and the transverse image respectively to obtain steel bar data;

[0090] S3. Based on the existing material list requirements and the steel bar data, input the trained dynamic programming model to obtain the steel bar cutting scheme;

[0091] S4. Based on the horizontal image, the steel bar cutting scheme is judged to exceed the limit. The cutting scheme is optimized according to the judgment result to obtain the final cutting scheme and achieve precise cutting.

[0092] Device Example 2

[0093] This invention provides a computer-readable storage medium storing an information transmission implementation program. When executed by a processor 82, the program performs the following method steps:

[0094] S1. Capture cross-sectional and transverse images of the steel reinforcement pile using a camera;

[0095] S2. Preprocess the end face image and the transverse image, and obtain the number of steel bars and the length of steel bars based on the end face image and the transverse image respectively to obtain steel bar data;

[0096] S3. Based on the existing material list requirements and the steel bar data, input the trained dynamic programming model to obtain the steel bar cutting scheme;

[0097] S4. Based on the horizontal image, the steel bar cutting scheme is judged to exceed the limit. The cutting scheme is optimized according to the judgment result to obtain the final cutting scheme and achieve precise cutting.

[0098] The computer-readable storage media described in this embodiment include, but are not limited to, ROM, RAM, disk, or optical disk.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A computer vision-based intelligent optimization method for rebar processing, characterized in that, include: S1. Acquire end-face and transverse images of the steel reinforcement pile using a camera; S2. Preprocess the end face image and the transverse image, and obtain the number of steel bars and the length of steel bars based on the end face image and the transverse image respectively to obtain steel bar data; The method for obtaining the length of the reinforcing bar based on the horizontal image is as follows: Image segmentation technology is used to extract the rebar mask and mark the location and extent of the rebar; The length limit is determined by obtaining the position and angle of the camera from the horizontal image, and the length of the rebar is calculated by combining the geometric relationship of the rebar segmentation range. S3. Based on the existing material list requirements and the steel bar data, input the trained dynamic programming model to obtain the steel bar cutting scheme; S4. Based on the horizontal image, the rebar cutting scheme is judged to be out of limit. The cutting scheme is optimized according to the judgment result to obtain the final cutting scheme, thereby achieving precise cutting. The specific method is as follows: The horizontal image is identified and classified, and the steel reinforcement region in the horizontal image is segmented. The steel reinforcement segmentation result is then masked and processed by the maximum connected component to realize the steel reinforcement exceeding the limit.

2. The method according to claim 1, characterized in that, The method for obtaining the number of reinforcing bars based on the end face image is as follows: The YOLOv5 algorithm is used to classify the end face image, identify and extract the profile of the steel bar section; Detect and locate the position of the reinforcing bars using rectangular frames, and calculate the number of rectangular frames for the reinforcing bars; The number of rebars is obtained from the number of rebar rectangles.

3. The method according to claim 1, characterized in that, The specific method for obtaining the rebar cutting scheme by inputting the trained dynamic programming model based on the existing material list requirements and the rebar data is as follows: An objective function is established to minimize the use of raw materials for steel bars while meeting the requirements for steel bar cutting. The optimal cutting method is achieved when the remaining material after cutting is no greater than the minimum cutting length. ； The objective function is defined as follows: ； Where L is the length of the steel bar, a1, a2, ..., an are the cutting lengths, and the corresponding cutting quantities of steel bars are b1, b2, ..., bn bars respectively; c(j,i) is the number of corresponding cutting lengths in the single raw material cutting method; x1, x2, ..., xn represent the number of times each cutting method is used.

4. The method according to claim 3, characterized in that, The constraint equations for the objective function are as follows: ； In this context, matrix A and matrix X represent the number of times each segmentation method is used, and matrix b represents the corresponding number of steel bar cutting requirements.

5. The method according to claim 4, characterized in that, The method further includes: First, sort the cutting lengths from largest to smallest, and prioritize cutting the longest cutting lengths.

6. A computer vision-based intelligent optimization system for steel bar processing, characterized in that, include: Image acquisition module: used to acquire end face and transverse images of the steel reinforcement pile via a camera; Image processing module: used to preprocess the end face image and the horizontal image, and obtain the number and length of the reinforcing bars based on the end face image and the horizontal image respectively, to obtain the reinforcing bar data; The method for obtaining the length of the reinforcing bar based on the horizontal image is as follows: Image segmentation technology is used to extract the rebar mask and mark the location and extent of the rebar; The length limit is determined by obtaining the position and angle of the camera from the horizontal image, and the length of the rebar is calculated by combining the geometric relationship of the rebar segmentation range. Solution planning module: Based on the existing material list requirements and the rebar data, input a trained dynamic programming model to obtain the rebar cutting solution; The scheme optimization module is used to determine whether the rebar cutting scheme exceeds the limit based on the horizontal image, optimize the cutting scheme according to the determination result, and obtain the final cutting scheme to achieve precise cutting; the specific method is as follows: The horizontal image is identified and classified, and the steel reinforcement region in the horizontal image is segmented. The steel reinforcement segmentation result is then masked and processed by the maximum connected component to realize the steel reinforcement exceeding the limit.

7. An electronic device, characterized in that, include: processor; And a memory arranged to store computer-executable instructions, which, when executed, cause the processor to implement the steps of the computer vision-based intelligent optimization method for rebar processing as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, Used to store computer-executable instructions, which, when executed, are implemented to carry out the steps of the computer vision-based intelligent optimization method for rebar processing as described in any one of claims 1 to 5.

Images