Method and system for obtaining length of approximately rectangular large high-temperature forging
Through binocular vision system and three-dimensional reconstruction technology, high-precision non-contact measurement of the length of large high-temperature forgings is achieved, solving the problems of low measurement accuracy and safety hazards in the prior art.
Patent Information
- Application Number
- CN202411663322.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-20
- Publication Date
- 2025-02-25
AI Technical Summary
In the prior art, when measuring large high-temperature forgings, it is difficult to ensure high accuracy and operators need to get close contact with hot forgings, which poses safety hazards.
Using a binocular vision system, the horizontal light bar images and vertical light bar images of the surface of the high-temperature forging are obtained, sub-pixel center extraction, matching and three-dimensional reconstruction are performed, the edges of the forging are determined, and the forging length is calculated through projection and fitting.
High-precision non-contact measurement of the length of large high-temperature forgings with a rectangle shape is achieved, ensuring the stability and safety of the measurement process.
Smart Images

Figure CN119515955A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of computer vision detection, and in particular to a method and system for obtaining the length of a large high-temperature forging piece that is approximately rectangular. Background Art
[0002] Large high-temperature forgings are important blank parts required for manufacturing key fields such as petrochemicals, ships, electricity, and aerospace. They are usually made from giant steel ingots weighing more than ten tons or even hundreds of tons. After being heated to a high temperature of 1200-1400℃, they are carefully crafted through a free forging process. In order to ensure the accurate size of the free forgings after forging, the size measurement of the high-temperature forgings must be carried out during the forging process. At present, the mainstream measurement method still relies on contact means, which requires the operator to personally hold the measuring tool and get close to the hot forgings to obtain data. However, given that large high-temperature forgings have strong thermal radiation, the measurement personnel often suffer from a strong sense of burning when approaching, and have to use protective measures such as arms or helmets to cover their faces to protect their eyes from high-temperature burns, and strive to complete the measurement task quickly under such conditions. However, this contact measurement method is often difficult to ensure high measurement accuracy when dealing with large high-temperature forgings produced by the free forging process. Summary of the invention
[0003] The purpose of the present invention is to propose a method for measuring the length of large high-temperature forgings with a shape similar to a rectangle using a binocular vision system, which is particularly suitable for such forgings weighing more than ten tons or even hundreds of tons; it has the advantages of high precision and stable calculation process.
[0004] According to a first aspect of an embodiment of the present disclosure, a method for obtaining the length of a large high-temperature forging that is approximately rectangular is provided, comprising the following steps:
[0005] Acquire horizontal and vertical light stripe images of the surface of the high-temperature forging;
[0006] The sub-pixel center of the horizontal light strip image is extracted, and after matching and 3D reconstruction, the left and right edges of the high-temperature forging are determined on the 3D reconstructed point cloud of the horizontal light strip;
[0007] The sub-pixel center of the vertical light strip image is extracted, and after matching and 3D reconstruction, the upper and lower edges of the high-temperature forging are determined on the 3D reconstructed point cloud of the vertical light strip;
[0008] The left edge, right edge, upper edge and lower edge are projected onto the plane of the vertical light strip three-dimensional reconstruction point cloud fitting, and the distances between the intersections of the upper edge projection point fitting line, the lower edge projection point fitting line and the left edge projection point fitting line and the right edge projection point fitting curve are obtained respectively; the average of the two distances is the length of the high-temperature forging.
[0009] In one of the embodiments, a high temperature forging image acquisition system composed of binocular vision is used to capture horizontal and vertical light strip images projected on the surface of the high temperature forging when the high temperature forging is temporarily in a stationary state.
[0010] In one embodiment, the horizontal light strip SP on the surface of the high temperature forging i , SPL is used in the left image and the right image respectively i and SPR i Indicates; Get the light bar SPL i and SPR i The sub-pixel centers are sorted in ascending order according to their horizontal coordinate values. After sorting, the SPL of the light bar in the left image i The sub-pixel center is C_SPL i (kL i ) indicates that the light bar SPR in the right image i The sub-pixel center is C_SPR i (kR i ) indicates that: The SPL of the light bar in the left image i The number of sub-pixel centers, The SPR of the light bar in the right image i The number of sub-pixel centers;
[0011] In the left image, press the light bar SPL i Sub-pixel center C_SPL i (kL i ) are stored in the order of taking the sub-pixel center points one by one, and using the epipolar constraint method in C_SPR i (kR i ) to determine the matching points, and obtain the light strip SPL after 3D reconstruction of the matching point pairs i 3D point cloud P_SP i (km i ); 3D point cloud P_SP i (km i ) is located in the world coordinate system O W X W Y W Z W .in, For light bar SP i The number of 3D point clouds.
[0012] In one embodiment, the light strip SP i 3D reconstructed point cloud P_SP i (km i) to obtain the three-dimensional points P corresponding to the left and right edges of the high-temperature forging L_Spi and P R_Spi The steps are as follows:
[0013] Using light strip SP i 3D reconstructed point cloud P_SP i (km i ) Fitting plane Plane_P_SP i , the three-dimensional point cloud P_SP i (km i ) projected on the fitting plane Plane_P_SP i On the top, the projection point uses P2D_SP i (km i )express;
[0014] By 2D point P2D_SP i (km i ) is stored in the order w t points, and the points extracted by curve fitting represented by a quartic polynomial; the wth q Points P2D_SP i (w q ) curvature, if the curvature is greater than the set value q wq Then stop the calculation, and the three-dimensional point corresponding to this point is the light strip SP i The right edge P R_Spi , 3D point P_SP i (1) Light strip SP i The left edge P L_Spi .
[0015] In one embodiment, the vertical light strip SZ on the surface of the high temperature forging is j , SZL is used in the left image and the right image respectively j and SZR j Indicates; Get the light bar SZL j and SZR j The sub-pixel center C_SZL j and C_SZR j And sort the sub-pixel centers of each light strip in descending order according to the ordinate value; take the light strips SZL in the left image one by one in the storage order j The sub-pixel center C_SZL j , using the epipolar constraint method in the right image SZR j The sub-pixel center C_SZR j Determine the matching points in the 3D reconstruction, and obtain the 3D point cloud of the vertical light strip using P_SZ j (kn j ) indicates that, among which, kn j=1,2,3,…,n knj , n knj For light bar SZ j The number of point clouds after sub-pixel center 3D reconstruction; point cloud P_SZ j (kn j ) is located in the world coordinate system O W X W Y W Z W ; then P_SZ j (1) Light strip SZ j The upper edge P U_SZj , For light bar SZ j The lower edge point P D_SZj .
[0016] In one embodiment, the three-dimensional point cloud P_SZ of the vertical light strip is used. j (kn j ) Fitting plane Plane_SZ, establish coordinate system O in fitting plane Plane_SZ N X N Y N , coordinate origin O N O is the origin of the world coordinate system W Projection on the fitting plane Plane_SZ, X N Axis and Y N The axis is the X axis of the world coordinate system. W Axis and Y W The projection line of the axis on the fitting plane.
[0017] In one embodiment, the left edge P in the three-dimensional point cloud is L_Spi and the right edge P R_Spi Projected on plane Plane_SZ, the projection points are TP L_Spi and TP R_Spi Indicates; left edge TP L_Spi The fitting straight line is l L Indicates that the right edge TP R_Spi The fitting curve C represented by a cubic polynomial R ;
[0018] The upper edge P in the 3D point cloud U_SZj and the lower edge P D_SZj Projected on plane Plane_SZ, the projection points are TP U_SZj and TP D_SZj Indicates; in the plane Plane_SZ, the upper edge TP U_SZj The fitting straight line is l u Indicates that the lower edge fitting line is l d express;
[0019] Straight line L With straight line l u and straight line l d The intersection points are denoted by P LU and P LD Indicates that curve C R With straight line l u and straight line l d The intersection points are denoted by P CU and P CD Indicates; intersection point P LU and P CU The distance between them is represented by L1, and the intersection point P LD and P CD The distance between them is represented by L2; the length of the high temperature forging is represented by L, and L is the average of the sum of L1 and L2, that is, L = (L1 + L2) / 2.
[0020] According to a second aspect of an embodiment of the present disclosure, a system for obtaining the length of a large high-temperature forging approximately in a rectangular shape is provided, comprising:
[0021] An image acquisition module is used to acquire horizontal and vertical light strip images on the surface of the high-temperature forging;
[0022] The left and right edge extraction module is used to extract the sub-pixel center of the horizontal light strip image, and after matching and 3D reconstruction, determine the left and right edges of the high-temperature forging on the 3D reconstructed point cloud of the horizontal light strip;
[0023] The upper and lower edge extraction module is used to extract the sub-pixel center of the vertical light strip image, and after matching and 3D reconstruction, determine the upper and lower edges of the high-temperature forging on the 3D reconstructed point cloud of the vertical light strip;
[0024] The length calculation module projects the left edge, right edge, upper edge and lower edge onto the plane of the vertical light strip three-dimensional reconstruction point cloud fitting, and obtains the distances between the intersections of the upper edge projection point fitting line, the lower edge projection point fitting line and the left edge projection point fitting line and the right edge projection point fitting curve; the average of the two distances is the length of the high-temperature forging.
[0025] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device comprising a memory, a processor and a computer program stored and running on the memory, wherein when the processor executes the program, a method for obtaining the length of a large high-temperature forging of an approximate rectangular shape is implemented.
[0026] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for obtaining the length of a large high-temperature forging that is approximately rectangular is implemented.
[0027] Compared with the prior art, the above technical solution adopted by the present invention has the following advantages: the present invention can convert the horizontal light strips and vertical light strips projected on the high-temperature forging into three-dimensional information through three-dimensional reconstruction technology, thereby obtaining the three-dimensional coordinates of the edge of the forging at the horizontal and vertical light strip positions. Next, these edge points are projected onto the plane obtained by fitting the vertical light strips. Then, based on the straight line fitted by the left edge projection point of the horizontal light strip, the curve fitted by the right edge projection point, and the straight line fitted by the upper edge projection point of the vertical light strip, and the straight line fitted by the lower edge projection point. Using these intersection points, the length of the high-temperature forging can be obtained. This method has the advantage of non-contact measurement when measuring the length of a high-temperature forging that is approximately rectangular in shape, and the calculation process is stable and reliable. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The drawings in the specification, which constitute a part of the present application, are used to provide further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.
[0029] Figure 1 This is a schematic diagram of projecting horizontal light strips onto a high-temperature forging;
[0030] Figure 2 This is a schematic diagram of projecting vertical light strips onto a high-temperature forging;
[0031] Figure 3 For horizontal light strip SP i On the point cloud of 3D reconstruction, the left edge P of the high temperature forging L_Spi and the right edge P R_Spi Location diagram;
[0032] Figure 4 For the horizontal light strip SP i On the point cloud of 3D reconstruction, obtain the left edge P of the high temperature forging L_Spi and the right edge P R_Spi Flowchart of
[0033] Figure 5 For vertical light strip SZ j On the point cloud of 3D reconstruction, the upper edge P of the high temperature forging U_SZj and the lower edge P D_SZj Location diagram;
[0034] Figure 6 For the vertical light strip SZ j The upper edge P of the high temperature forging is obtained from the 3D reconstructed point cloud. U_SZj and the lower edge P D_SZj Flowchart of
[0035] Figure 7 It is the projection point position on the plane Plane_SZ and the schematic diagram of obtaining the length of the high temperature forging;
[0036] Figure 8 Flow chart of the method for obtaining the approximate length of a rectangular large high-temperature forging.
[0037] 1. High-temperature forgings; 11. Horizontal light strips; 12. Vertical light strips; 2. Vibration reduction platform; 3. Short-wave filter; 41. Left CCD camera; 42. Right CCD camera; 5. Guide rails; 6. Light strip projection equipment. DETAILED DESCRIPTION
[0038] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.
[0039] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.
[0040] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.
[0041] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and systems according to various embodiments of the present disclosure. It should be noted that each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of a code may include one or more executable instructions for implementing the logical functions specified in each embodiment. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the flowchart and / or block diagram, and the combination of boxes in the flowchart and / or block diagram can be implemented using a dedicated hardware-based system that performs a specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.
[0042] Embodiment 1:
[0043] like Figure 8 As shown, this embodiment provides a method for obtaining the length of a large high-temperature forging of an approximately rectangular shape, comprising the following steps:
[0044] The first step is to obtain horizontal and vertical light strip images of the surface of the high-temperature forging;
[0045] Specifically, a high-temperature forging image acquisition system composed of binocular vision is used to acquire images. The high-temperature forging image acquisition system arranged on the vibration reduction platform includes a left CCD camera and a right CCD camera. Short-wave pass filters are installed in front of the lenses of the left CCD camera and the right CCD camera to filter out the radiation light of the forging and allow the projected light strip reflected by the forging to pass through;
[0046] When the high temperature forging is in a temporary static state, use the light bar projection equipment to project horizontal and vertical light bars onto the surface of the high temperature forging. Figure 1-2 As shown, and images of high temperature forgings were taken.
[0047] The second step is to extract the sub-pixel center of the horizontal light strip image, and after matching and 3D reconstruction, determine the left and right edges of the high-temperature forging on the 3D reconstructed point cloud of the horizontal light strip;
[0048] Figure 1 SP for projecting horizontal light strips on medium and large high temperature forgings i Indicates, i = 1, 2, 3, 4, 5. The light strips are numbered from top to bottom, and SP1 represents the top horizontal light strip.
[0049] Figure 1 The images captured by the left CCD camera and the right CCD camera are called the left image and the right image respectively. i In the left image and right image, SPL is used i and SPR i Get the SPL of the light bar i and SPR i The sub-pixel centers of the left image are sorted in ascending order according to their horizontal coordinate values. i The sub-pixel center is C_SPL i (kL i ) indicates that the light bar SPR in the right image i The sub-pixel center is C_SPR i (kR i ) indicates. Among them, The SPL of the light bar in the left image i The number of sub-pixel centers, The SPR of the light bar in the right image i The number of sub-pixel centers.
[0050] like Figure 3 As shown, in the left image, press the light bar SPL i Sub-pixel center C_SPL i (kL i ) are stored in the order of taking the sub-pixel center points one by one, and using the epipolar constraint method in C_SPR i (kR i ) is used to determine the matching points. The light strip SPL is obtained by 3D reconstruction of the matching point pairs through the calibrated internal and external parameters of the left and right CCD cameras. i 3D point cloud P_SP i (km i ); 3D point cloud P_SP i (km i ) is located in the world coordinate system O W X W Y W Z W The world coordinate system is determined when calibrating the internal and external parameters of the two CCD cameras. For light bar SP i The number of 3D point clouds.
[0051] On the point cloud of each light strip 3D reconstruction, determine the left and right edges of the forging: Figure 4 As shown, in the light bar SP i 3D reconstructed point cloud P_SP i (km i ) to obtain the three-dimensional points P corresponding to the left and right edges of the forging L_Spi and P R_Spi The steps are as follows:
[0052] S2.1 uses light strip SP i 3D reconstructed point cloud P_SP i (km i ) Fitting plane Plane_P_SP i , the three-dimensional point cloud P_SP i (km i ) projected on the fitting plane Plane_P_SP i On the top, the projection point uses P2D_SP i (km i )express;
[0053] S2.2 By 2D point P2D_SP i (km i ) is stored in the order w t points, and the points extracted by curve fitting represented by a quartic polynomial; the wthq Points P2D_SP i (w q ) curvature, if the curvature is greater than the set value q wq Then stop the calculation, and the three-dimensional point corresponding to this point is the light strip SP i The right edge P R_Spi ; 3D point P_SP i (1) Light strip SP i The left edge P L_Spi .q wq The value of is set according to the geometric shape of the forging at the projection position of the light strip. t ∈[100·n nh +1,100·n nh +150], w q ∈[100·n nh +50,100·n nh +100],n nh =0,1,2,…, and
[0054] The third step is to extract the sub-pixel center of the vertical light strip image, and after matching and 3D reconstruction, determine the upper and lower edges of the high-temperature forging on the 3D reconstructed point cloud of the vertical light strip;
[0055] Figure 2 The vertical light strips projected on the medium and high temperature forgings are SZ j Indicated by. Where j = 1, 2, 3, 4, 5, 6, the light strips are numbered from left to right, SZ1 represents the leftmost light strip, such as Figure 5 shown.
[0056] The vertical light stripes in the left and right images are represented by SZL j and SZR j Indicates. Figure 6 As shown, get the light bar SZL j and SZR j The sub-pixel center C_SZL j and C_SZR j And sort the sub-pixel centers of each light strip in descending order according to the ordinate value. Take the light strips SZL in the left image one by one in the storage order j The sub-pixel center C_SZL j , using the epipolar constraint method in the right image SZR j The sub-pixel center C_SZR j Using the calibrated internal and external parameters of the left and right CCD cameras, the three-dimensional reconstruction of the matching point pairs is used to obtain the three-dimensional point cloud of the vertical light strip. j (knj ) indicates. Among them, For light bar SZ j The number of point clouds after sub-pixel center 3D reconstruction; point cloud P_SZi(kn j ) is located in the world coordinate system O W X W Y W Z W Then, P_SZ j (1) Light strip SZ j The upper edge P U_SZj , For light bar SZ j The lower edge point P D_SZj .
[0057] The fourth step is to project the left edge, right edge, upper edge and lower edge onto the plane of the vertical light strip 3D reconstruction point cloud fitting, and obtain the distances between the intersections of the upper edge projection point fitting line, the lower edge projection point fitting line and the left edge projection point fitting line and the right edge projection point fitting curve; the average of the two distances is the length of the high temperature forging;
[0058] Specifically, the three-dimensional point cloud P_SZ of the vertical light strip is used j (kn j ) Fitting plane Plane_SZ, establish coordinate system O in fitting plane Plane_SZ N X N Y N , coordinate origin O N O is the origin of the world coordinate system W Projection on the fitting plane Plane_SZ, X N Axis and Y N The axis is the X axis of the world coordinate system. W Axis and Y W The projection line of the axis on the fitting plane.
[0059] Will Figure 3 The left edge P in the 3D point cloud shown L_Spi and the right edge P R_Spi Projected on plane Plane_SZ, the projection points are TP L_Spi and TP R_Spi Indicates. Left edge TP L_Spi The fitted straight line is l L Indicates; right edge TP R_Spi The fitting curve C represented by a cubic polynomial R Indicates. Figure 5 The upper edge P in the 3D point cloud shown U_SZj and the lower edge P D_SZjProjected on plane Plane_SZ, the projection points are TP U_SZj and TP D_SZj Indicates. Figure 7 As shown, in the plane Plane_SZ, the upper edge TP U_SZj The fitted straight line is l u Indicates that the straight line of the lower edge fitting is l d Indicates. Straight line l L With straight line l u and l d The intersection points are denoted by P LU and P LD Indicates that curve C R With straight line l u and l d The intersection points are denoted by P CU and P CD Indicates. The intersection point P LU and P CU The distance between them is represented by L1, and the intersection point P LD and P CD The distance between the two parts is represented by L2. The length of the high temperature forging is represented by L. L is the average of the sum of L1 and L2, that is, L = (L1 + L2) / 2.
[0060] The present invention uses three-dimensional reconstruction technology to accurately determine the edge position of the high-temperature forging in the point cloud data of the horizontal light strip and the vertical light strip, thereby realizing the measurement of its length. This method is particularly suitable for large high-temperature forgings with a shape similar to a rectangle, and can realize non-contact length measurement.
[0061] Embodiment 2:
[0062] This embodiment provides a system for obtaining the length of a large high-temperature forging of an approximately rectangular shape, comprising:
[0063] An image acquisition module is used to acquire horizontal and vertical light strip images on the surface of the high-temperature forging;
[0064] The left and right edge extraction module is used to extract the sub-pixel center of the horizontal light strip image, and after matching and 3D reconstruction, determine the left and right edges of the high-temperature forging on the 3D reconstructed point cloud of the horizontal light strip;
[0065] The upper and lower edge extraction module is used to extract the sub-pixel center of the vertical light strip image, and after matching and 3D reconstruction, determine the upper and lower edges of the high-temperature forging on the 3D reconstructed point cloud of the vertical light strip;
[0066] The length calculation module projects the left edge, right edge, upper edge and lower edge onto the plane of the vertical light strip three-dimensional reconstruction point cloud fitting, and obtains the distances between the intersections of the upper edge projection point fitting line, the lower edge projection point fitting line and the left edge projection point fitting line and the right edge projection point fitting curve; the average of the two distances is the length of the high-temperature forging.
[0067] Embodiment three:
[0068] An electronic device includes a memory, a processor, and a computer program stored and running on the memory, wherein the processor implements the above-mentioned method for obtaining the length of an approximately rectangular large high-temperature forging when executing the program, including:
[0069] Acquire horizontal and vertical light stripe images of the surface of the high-temperature forging;
[0070] The sub-pixel center of the horizontal light strip image is extracted, and after matching and 3D reconstruction, the left and right edges of the high-temperature forging are determined on the 3D reconstructed point cloud of the horizontal light strip;
[0071] The sub-pixel center of the vertical light strip image is extracted, and after matching and 3D reconstruction, the upper and lower edges of the high-temperature forging are determined on the 3D reconstructed point cloud of the vertical light strip;
[0072] The left edge, right edge, upper edge and lower edge are projected onto the plane of the vertical light strip three-dimensional reconstruction point cloud fitting, and the distances between the intersections of the upper edge projection point fitting line, the lower edge projection point fitting line and the left edge projection point fitting line and the right edge projection point fitting curve are obtained respectively; the average of the two distances is the length of the high-temperature forging.
[0073] Embodiment 4:
[0074] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for obtaining the length of an approximately rectangular large high-temperature forging, comprising:
[0075] Acquire horizontal and vertical light stripe images of the surface of the high-temperature forging;
[0076] The sub-pixel center of the horizontal light strip image is extracted, and after matching and 3D reconstruction, the left and right edges of the high-temperature forging are determined on the 3D reconstructed point cloud of the horizontal light strip;
[0077] The sub-pixel center of the vertical light strip image is extracted, and after matching and 3D reconstruction, the upper and lower edges of the high-temperature forging are determined on the 3D reconstructed point cloud of the vertical light strip;
[0078] The left edge, right edge, upper edge and lower edge are projected onto the plane of the vertical light strip three-dimensional reconstruction point cloud fitting, and the distances between the intersections of the upper edge projection point fitting line, the lower edge projection point fitting line and the left edge projection point fitting line and the right edge projection point fitting curve are obtained respectively; the average of the two distances is the length of the high-temperature forging.
[0079] Those skilled in the art should understand that the modules or steps of the present disclosure can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present disclosure is not limited to any specific combination of hardware and software.
[0080] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
[0081] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.
Claims
1. A method for obtaining the length of a large high-temperature forging that is approximately rectangular, characterized in that: The following steps are involved: Acquire horizontal and vertical light stripe images of the surface of the high-temperature forging; The sub-pixel center of the horizontal light strip image is extracted, and after matching and 3D reconstruction, the left and right edges of the high-temperature forging are determined on the 3D reconstructed point cloud of the horizontal light strip; The sub-pixel center of the vertical light strip image is extracted, and after matching and 3D reconstruction, the upper and lower edges of the high-temperature forging are determined on the 3D reconstructed point cloud of the vertical light strip; The left edge, right edge, upper edge and lower edge are projected onto the plane of the vertical light strip three-dimensional reconstruction point cloud fitting, and the distances between the intersections of the upper edge projection point fitting line, the lower edge projection point fitting line and the left edge projection point fitting line and the right edge projection point fitting curve are obtained respectively; the average of the two distances is the length of the high-temperature forging.
2. A method for obtaining the length of a large high-temperature forging approximately in a rectangular shape according to claim 1, characterized in that: A high-temperature forging image acquisition system composed of binocular vision is used to capture horizontal and vertical light strip images projected on the surface of the high-temperature forging when the high-temperature forging is temporarily in a stationary state.
3. The method for obtaining the length of a large high-temperature forging approximately in a rectangular shape according to claim 1, characterized in that: The horizontal light strip SP on the surface of the high temperature forging i , SPL is used in the left image and the right image respectively i and SPR i Indicates; Get the light bar SPL i and SPR i The sub-pixel centers are sorted in ascending order according to their horizontal coordinate values. After sorting, the SPL of the light bar in the left image i The sub-pixel center is C_SPL i (kL i ) indicates that the light bar SPR in the right image i The sub-pixel center is C_SPR i (kR i ) indicates that: The SPL of the light bar in the left image i The number of sub-pixel centers, The SPR of the light bar in the right image i The number of sub-pixel centers; In the left image, press the light bar SPL i Sub-pixel center C_SPL i (kL i ) are stored in the order of taking the sub-pixel center points one by one, and using the epipolar constraint method in C_SPR i (kR i ) to determine the matching points, and obtain the light strip SPL after 3D reconstruction of the matching point pairs i 3D point cloud P_SP i (km i ); 3D point cloud P_SP i (km i ) is located in the world coordinate system O W X W Y W Z W ;in, For light bar SP i The number of 3D point clouds.
4. A method for obtaining the length of a large high-temperature forging approximately in a rectangular shape according to claim 3, characterized in that: In light bar SP i 3D reconstructed point cloud P_SP i (km i ) to obtain the three-dimensional points P corresponding to the left and right edges of the high-temperature forging L_Spi and P R_Spi The steps are as follows: Using light strip SP i 3D reconstructed point cloud P_SP i (km i ) Fitting plane Plane_P_SP i , the three-dimensional point cloud P_SP i (km i ) projected on the fitting plane Plane_P_SP i On the top, the projection point uses P2D_SP i (km i )express; By 2D point P2D_SP i (km i ) is stored in the order w t points, and the points extracted by curve fitting represented by a quartic polynomial; the wth q Points P2D_SP i (w q ) curvature, if the curvature is greater than the set value q wq Then stop the calculation, and the three-dimensional point corresponding to this point is the light strip SP i The right edge P R_Spi , 3D point P_SP i (1) Light strip SP i The left edge P L_Spi .
5. The method for obtaining the length of a large high-temperature forging approximately in a rectangular shape according to claim 1, characterized in that: The vertical light strip SZ on the surface of the high temperature forging j , SZL is used in the left image and the right image respectively j and SZR j Indicates; Get the light bar SZL j and SZR j The sub-pixel center C_SZL j and C_SZR j And sort the sub-pixel centers of each light strip in descending order according to the ordinate value; take the light strips SZL in the left image one by one in the storage order j The sub-pixel center C_SZL j , using the epipolar constraint method in the right image SZR j The sub-pixel center C_SZR j Determine the matching points in the 3D reconstruction, and obtain the 3D point cloud of the vertical light strip using P_SZ j (kn j ) indicates that, For light bar SZ j The number of point clouds after sub-pixel center 3D reconstruction; point cloud P_SZ j (kn j ) is located in the world coordinate system O W X W Y W Z W ; then P_SZ j (1) Light strip SZ j The upper edge P U_SZj , For light bar SZ j The lower edge point P D_SZj .
6. A method for obtaining the length of a large high-temperature forging approximately in a rectangular shape according to claim 5, characterized in that: 3D point cloud P_SZ using vertical light strips j (kn j ) Fitting plane Plane_SZ, establish coordinate system O in fitting plane Plane_SZ N X N Y N , coordinate origin O N is the origin of the world coordinate system O W Projection on the fitting plane Plane_SZ, X N Axis and Y N The axis is the X axis of the world coordinate system. W Axis and Y W The projection line of the axis on the fitting plane.
7. A method for obtaining the length of a large high-temperature forging approximately in a rectangular shape according to claim 6, characterized in that: The left edge P in the 3D point cloud L_Spi and the right edge P R_Spi Projected on plane Plane_SZ, the projection points are TP L_Spi and TP R_Spi Indicates; left edge TP L_Spi The fitting straight line is l L Indicates that the right edge TP R_Spi The fitting curve C represented by a cubic polynomial R ; The upper edge P in the 3D point cloud U_SZj and the lower edge P D_SZj Projected on plane Plane_SZ, the projection points are TP U_SZj and TP D_SZj Indicates; in the plane Plane_SZ, the upper edge TP U_SZj The fitting straight line is l u Indicates that the lower edge fitting line is l d express; Straight line L With straight line l u and straight line l d The intersection points are denoted by P LU and P LD Indicates that curve C R With straight line l u and straight line l d The intersection points are denoted by P CU and P CD Indicates; intersection point P LU and P CU The distance between them is represented by L1, and the intersection point P LD and P CD The distance between them is represented by L2; the length of the high temperature forging is represented by L, and L is the average of the sum of L1 and L2, that is, L = (L1 + L2) / 2.
8. A system for obtaining the length of a large high-temperature forging approximately in a rectangular shape, characterized in that: include: An image acquisition module is used to acquire horizontal and vertical light strip images on the surface of the high-temperature forging; The left and right edge extraction module is used to extract the sub-pixel center of the horizontal light strip image, and after matching and 3D reconstruction, determine the left and right edges of the high-temperature forging on the 3D reconstructed point cloud of the horizontal light strip; The upper and lower edge extraction module is used to extract the sub-pixel center of the vertical light strip image, and after matching and 3D reconstruction, determine the upper and lower edges of the high-temperature forging on the 3D reconstructed point cloud of the vertical light strip; The length calculation module projects the left edge, right edge, upper edge and lower edge onto the plane of the vertical light strip three-dimensional reconstruction point cloud fitting, and obtains the distances between the intersections of the upper edge projection point fitting line, the lower edge projection point fitting line and the left edge projection point fitting line and the right edge projection point fitting curve; the average of the two distances is the length of the high-temperature forging.
9. An electronic device comprising a memory, a processor and a computer program stored and running on the memory, characterized in that: When the processor executes the program, the method for obtaining the length of a large high-temperature forging part having an approximate rectangular shape as described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a method for obtaining the length of a large high-temperature forging part having an approximate rectangular shape as described in any one of claims 1 to 7 is implemented.