Defect size calibration method, system and equipment for large structural member and medium

Abstract

The invention discloses a defect size calibration method, system, equipment and medium for a large structural member, the defect size calibration method is suitable for an image acquisition device comprising a camera and a plurality of laser transmitters, and the defect size calibration method comprises the following steps: positioning a surface area of a defect in a to-be-measured large structural member, and forming a plurality of laser points on the surface area; acquiring an area image including the laser point and the surface area, a laser pixel coordinate of the laser point in the area image, a distance between the camera and the surface area and a focal length of the camera, and determining an image acquisition angle of the camera according to the distance, the focal length and the laser pixel coordinate; and cutting a defect image corresponding to the defect from the regional image, and obtaining a defect pixel coordinate of the defect image in the regional image, so as to determine the size of the defect according to the defect pixel coordinate, the image acquisition angle, the distance and the focal length, thereby improving the accuracy of defect size calibration.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of defect detection, in particular to a large structural part defect size calibration method, system, device and medium. BACKGROUND

[0002] In the daily detection of large structures such as bridges, buildings, and tunnels, observing whether there are abnormalities on the surface and measuring the size of the abnormalities to evaluate the safety of the large structure is an important detection process for the use of large structures.

[0003] However, when detecting abnormalities in buildings with high-rise, large-span, and complex structures such as bridges, it is difficult to directly observe due to the large number of components, and auxiliary tools are often used for auxiliary observation. Among them, mechanical arms with cameras are often used in the daily detection of large structures such as river-crossing bridges and viaducts, as personnel are difficult to reach, and mechanical arms + cameras are used for abnormal detection.

[0004] However, the existing camera can only capture image data corresponding to the defect, cannot determine the size information of the defect, and the camera shooting angle and the surface where the defect is located have an angle difference, resulting in a difference between the defect in the camera-captured image and the actual defect on the building, and thus the image information corresponding to the defect cannot be accurately obtained. SUMMARY

[0005] To solve the above technical problems, the present application discloses a large structural part defect size calibration method, system, device and medium, which is used to improve the accuracy of defect size calibration.

[0006] To achieve the above purpose, in a first aspect, the present application discloses a large structural part defect size calibration method, which is suitable for an image acquisition device comprising a camera and a plurality of laser emitters, the defect size calibration method comprising:

[0007] Positioning the surface area where the defect in the large structural part to be measured is located by the camera, and starting each laser emitter to form a plurality of laser points on the surface area to obtain a region image containing the laser points and the surface area;

[0008] Obtaining the laser pixel coordinates of each laser point in the region image, the distance between the camera and the surface area, and the focal length of the camera, to determine the image acquisition angle of the camera according to the distance, the focal length and the laser pixel coordinates;

[0009] Cutting a defect image corresponding to the defect from the region image, and obtaining a defect pixel coordinate of the defect image in the region image, so as to determine the size of the defect according to the defect pixel coordinate, the image acquisition angle, the distance and the focal length.

[0010] The method for calibrating the size of a defect of a large structure disclosed in the application improves the efficiency of defect positioning by using a camera to position a surface region where the defect of the large structure to be measured is located in real time. Then, when a defect image corresponding to the defect is photographed for size calibration, a laser point is projected to the surface region where the defect is located, so that the image acquisition angle of the camera is determined by using the pixel coordinate of the laser point formed at the current photographing angle, the focal length of the current camera and the distance from the surface region, and then the defect image is corrected by using the image acquisition angle, and then the size of the defect is determined according to the defect pixel coordinate, the image acquisition angle, the distance and the focal length in combination with the defect pixel coordinate of the defect image in the region image, thereby improving the accuracy of defect size calibration.

[0011] As a preferred example, the positioning of the surface region where the defect in the large structure to be measured is located by the camera and the formation of a plurality of laser points on the surface region by each laser emitter include:

[0012] The camera is controlled to move and scan the large structure to be measured to obtain a surface image corresponding to each surface region of the large structure to be measured;

[0013] Each surface image is subjected to defect detection, and when it is detected that the surface image has a defect, the camera is controlled to stop the moving and scanning and adjust the focal length of the camera until an image containing the defect is obtained; wherein the image includes a plurality of surface regions; and each surface region has the defect;

[0014] When the image is obtained, the laser emitter is started to form a plurality of center-symmetric laser points on the surface region.

[0015] In the above scheme, each region on the large structure is subjected to defect detection by the camera, thereby improving the efficiency and accuracy of defect detection. Then, when it is detected that a defect exists in an image, the angle of the camera is adjusted in real time to photograph a complete defect, thereby improving the accuracy of defect size calibration. While the defect image is collected, laser points are projected to the surface region where the complete defect is located, so that the image corresponding to the defect is adjusted in angle by using the distortion of the laser points, thereby improving the accuracy of defect size calculation.

[0016] As a preferred example, the acquiring of the laser pixel coordinates of each of the laser spots in the area image, the distance of the camera from the surface area, and the focal length of the camera, so as to determine the image acquisition angle of the camera according to the distance, the focal length, and the laser pixel coordinates, comprises:

[0017] According to the laser pixel coordinates, the interval pixel amount between two laser spots that are centrally symmetric is acquired;

[0018] From the pre-calibration database corresponding to the camera, the standard interval pixel amount corresponding to two laser spots that are centrally symmetric under the distance and the focal length is searched;

[0019] The ratio of the standard interval pixel amount and the interval pixel amount is acquired, so as to determine the image acquisition angle of the camera by the ratio and the inverse cosine function.

[0020] In the above scheme, the interval pixel amount between two laser spots that are centrally symmetric in the image acquired in real time and the standard interval pixel amount corresponding to two laser spots that are centrally symmetric under the distance and the focal length in the pre-calibration database of the camera are utilized to determine the shooting angle of the camera, so as to improve the efficiency and accuracy of angle adjustment, and further improve the accuracy of defect size calibration.

[0021] As a preferred example, the cutting of the defect image corresponding to the defect from the area image comprises:

[0022] According to a preset defect detection algorithm, the defect position in the area image is acquired by defect detection on the area image;

[0023] According to the defect position, the defect image corresponding to the defect is cut from the area image.

[0024] In the above scheme, in order to accurately acquire only the size of the defect and avoid the influence of the background on the defect size calibration, the positioning of the defect from the area image is performed by utilizing the defect detection algorithm, so as to cut the defect image containing only the defect from the area image according to the positioning, and further improve the accuracy of defect size calibration.

[0025] As a preferred example, the determination of the size of the defect according to the defect pixel coordinates, the image acquisition angle, the distance, and the focal length comprises:

[0026] According to the image acquisition angle, each of the defect pixel coordinates in the defect image is corrected to obtain a corrected pixel coordinate;

[0027] According to the corrected pixel coordinate, the number of pixels in the defect image is acquired;

[0028] According to the pixel quantity, the distance and the focal length, a pixel point conversion function pre-calibrated is used to determine the defect size of the defect.

[0029] In the above scheme, the image acquisition angle is obtained to correct the coordinates of each pixel point in the defect image, so as to correct the actual size of the defect image, and further improve the accuracy of defect size calibration. After correction, the pixel point conversion function is used to determine the defect size of the defect, and the efficiency and accuracy of size calibration are improved.

[0030] As a preferred example, the calculation expression of the pixel point conversion function is:

[0031]

[0032] Wherein, the f0 represents the focal length of the laboratory calibration; the d0 represents the distance of the laboratory calibration; the m represents the proportional relationship between the calculated value and the actual value during the laboratory calibration process; the k represents the pixel quantity corresponding to 1 millimeter under the focal length and distance of the laboratory calibration; the f represents the current focal length of the camera; the d represents the current distance of the camera; and the s represents the pixel quantity occupied by each unit length in the picture.

[0033] In a second aspect, the present application discloses a defect size calibration system for large structural parts, which is suitable for an image acquisition device including a camera and a plurality of laser emitters, and the defect size calibration system includes a defect positioning module, an angle correction module and a size calibration module.

[0034] The defect positioning module is used to position the surface area where the defect in the large structural part to be tested is located by the camera, and to start each laser emitter to form a plurality of laser points on the surface area, so as to obtain a region image containing the laser points and the surface area;

[0035] The angle correction module 202 is used to obtain the laser pixel coordinates of each laser point in the region image, the distance between the camera and the surface area and the focal length of the camera, so as to determine the image acquisition angle of the camera according to the distance, the focal length and the laser pixel coordinates;

[0036] The size calibration module is used to crop the defect image corresponding to the defect from the region image, and to obtain the defect pixel coordinates of the defect image in the region image, so as to determine the size of the defect according to the defect pixel coordinates, the image acquisition angle, the distance and the focal length.

[0037] The application discloses a defect size calibration system for large structural members, which uses a camera to real-time locate a surface area where a defect on a large structural member to be measured is located, and improves the defect locating efficiency. Then, when a defect image corresponding to the defect is shot for size calibration, a laser point is projected to the surface area where the defect is located, so that the current image acquisition angle of the camera is determined by using the pixel laser point coordinates formed by the laser point under the current shooting angle, the focal length of the current camera and the distance from the surface area, and then the defect image is corrected by using the image acquisition angle, and then the defect size is determined according to the defect pixel coordinates, the image acquisition angle, the distance and the focal length, so that the precision of defect size calibration is improved.

[0038] As a preferred example, the defect locating module comprises a defect detecting unit and a laser projecting unit.

[0039] The defect detecting unit is used to control the camera to move and scan the large structural member to be measured, and acquire a surface image corresponding to each surface area in the large structural member to be measured; the defect detecting unit is used to detect defects in each surface image, and when it is detected that the surface image has defects, the camera is controlled to stop the moving and scanning, and the focal length of the camera is adjusted until an image containing the defects is acquired; wherein the image comprises a plurality of surface areas; and each surface area has the defects.

[0040] The laser projecting unit is used to start the laser emitter when the image is acquired, so as to form a plurality of center-symmetrical laser points on the surface area.

[0041] In the above scheme, the camera is used to detect defects in each area on the large structural member, so that the defect detection efficiency and precision are improved. When it is detected that a defect exists in an image, the angle of the camera is adjusted in real time, so that the complete defect is shot, and the precision of defect size calibration is improved. While the defect image is acquired, the laser points are projected to the surface area where the complete defect is located, so that the image corresponding to the defect is adjusted in angle by using the distortion of the laser points, and the precision of defect size calculation is improved.

[0042] In a third aspect, the application discloses a terminal device, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, and when the computer program is executed by the processor, the method for calibrating the defect size of the large structural member is realized.

[0043] In a fourth aspect, the present application discloses a computer readable storage medium, comprising: a stored computer program, wherein when the computer program is running, the computer readable storage medium controls the device where the computer readable storage medium is located to execute the defect size calibration method of the large structural member as described in the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0045] Figure 1 is a flowchart of a defect size calibration method of a large structural member provided by an embodiment of the present application;

[0046] Figure 2 is a structural diagram of a defect size calibration system of a large structural member provided by an embodiment of the present application;

[0047] Figure 3 is a structural diagram of a mechanical arm provided by another embodiment of the present application;

[0048] Figure 4 is a rotation diagram of a first rotating arm in a mechanical arm provided by another embodiment of the present application;

[0049] Figure 5 is a vertical rotation diagram of a third rotating arm in a mechanical arm provided by another embodiment of the present application;

[0050] Figure 6 is a horizontal rotation diagram of a third rotating arm in a mechanical arm provided by another embodiment of the present application;

[0051] Figure 7 is a structural diagram of an image acquisition device provided by another embodiment of the present application;

[0052] Figure 8 is a flowchart of a defect size calibration method of a large structural member provided by another embodiment of the present application;

[0053] Figure 9 is a circular diagram of a laser point provided by another embodiment of the present application;

[0054] Figure 10 is an elliptical diagram of a laser point provided by another embodiment of the present application. DETAILED DESCRIPTION

[0055] With reference to the drawings and the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort are within the scope of the present application.

[0056] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described with reference to the drawings and the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort are within the scope of the present application.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this application; the description and claims of this application as well as the above description of the drawings herein are not inclusive of all aspects of the application; and it is understood that the terms "comprises", "comprising", "includes" and "including" as used herein are intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in the claim of this application or in the foregoing description of the application.

[0058] In the description of the embodiments of the present application, the technical terms "first", "second", and the like are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0059] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily independent or alternative embodiments to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0060] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents a "or" relationship between the front and rear associated objects.

[0061] In the description of the embodiments of the present application, the term "a plurality of" refers to two or more (including two), and similarly, "a plurality of groups" refers to two or more groups (including two groups), and "a plurality of pieces" refers to two or more pieces (including two pieces).

[0062] In the description of the embodiments of the present application, unless otherwise explicitly specified and limited, the technical terms "mount", "connect", "connect", "fix" and other terms should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or it can be integrated; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the internal communication of two elements or the interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0063] Reference Figure 1 To solve the problem of unclear defect size calibration in the prior art, the present embodiment provides a defect size calibration method for large structural parts, which is suitable for an image acquisition device comprising a camera and a plurality of laser emitters, and the defect size calibration method comprises:

[0064] Step 301: Position the surface area where the defect in the large structural part to be measured is located by the camera, and start each laser emitter to form a plurality of laser points on the surface area, so as to obtain an area image containing the laser points and the surface area.

[0065] In the present embodiment, this step mainly comprises: controlling the camera to move and scan the large structural part to be measured, and obtaining a surface image corresponding to each surface area in the large structural part to be measured; detecting defects in each surface image, and when detecting that the surface image has defects, controlling the camera to stop the moving and scanning, and adjusting the focal length of the camera until an image containing the defects is obtained; wherein the image comprises a plurality of surface areas; each surface area has the defects; when the image is obtained, the laser emitters are started to form a plurality of center-symmetric laser points on the surface area.

[0066] In the present embodiment, the above step detects defects in each area on the large structural part by the camera, thereby improving the efficiency and accuracy of defect detection. Then, when a defect is detected in an image, the angle of the camera is adjusted in real time to capture the complete defect, thereby improving the accuracy of defect size calibration. At the same time of completing the defect image acquisition, laser points are projected to the surface area where the complete defect is located, so as to adjust the angle of the image corresponding to the defect by using the distortion of the laser points, thereby improving the accuracy of defect size calculation.

[0067] Step 302: Obtain the laser pixel coordinates of each laser point in the area image, the distance of the camera from the surface area, and the focal length of the camera, to determine the image acquisition angle of the camera according to the distance, the focal length, and the laser pixel coordinates.

[0068] In this embodiment, the step mainly includes: obtaining the interval pixel amount between two center-symmetric laser points according to the laser pixel coordinates; searching for the standard interval pixel amount corresponding to the two center-symmetric laser points under the distance and the focal length from the pre-calibration database corresponding to the camera; obtaining the ratio of the standard interval pixel amount to the interval pixel amount, to determine the image acquisition angle of the camera through the ratio and the inverse cosine function.

[0069] In this embodiment, the above step determines the shooting angle of the camera by using the interval pixel amount between the center-symmetric laser points in the image obtained in real time and the standard interval pixel amount corresponding to the two center-symmetric laser points under the distance and the focal length in the pre-calibration database of the camera, thereby improving the efficiency and accuracy of angle adjustment, and further improving the accuracy of defect size calibration.

[0070] Step 303: Crop the defect image corresponding to the defect from the area image, and obtain the defect pixel coordinates of the defect image in the area image, to determine the size of the defect according to the defect pixel coordinates, the image acquisition angle, the distance, and the focal length.

[0071] In this embodiment, the step mainly includes: performing defect detection on the area image according to a preset defect detection algorithm, to obtain the defect position in the area image; cropping the defect image corresponding to the defect from the area image according to the defect position; correcting each defect pixel coordinate in the defect image according to the image acquisition angle, to obtain a corrected pixel coordinate; obtaining the pixel quantity in the defect image according to the corrected pixel coordinate; determining the defect size of the defect through a pre-calibrated pixel point conversion function according to the pixel quantity, the distance, and the focal length; wherein, the calculation expression of the pixel point conversion function is:

[0072]

[0073] wherein, the f0 represents the focal length calibrated in the laboratory; the d0 represents the distance calibrated in the laboratory; the m represents the proportional relationship between the calculated value and the actual value when testing different distances in the laboratory calibration process; the k represents the pixel quantity corresponding to 1 millimeter under the focal length and the distance calibrated in the laboratory; the f represents the current focal length of the camera; the d represents the current distance of the camera; and the s represents the pixel points occupied by each unit length in the picture.

[0074] In this embodiment, the above steps first aim to accurately acquire only the size of the defect, avoiding the influence of the background on the defect size calibration. A defect detection algorithm is used to locate the defect from the region image, and based on this location, a defect image containing only the defect is cropped from the region image, thereby improving the accuracy of the defect size calibration. Secondly, the coordinates of each pixel in the defect image are corrected using the acquired image acquisition angle to correct the actual size of the defect image, further improving the accuracy of the defect size calibration. After correction, the defect size is determined using the number of pixels and a pre-calibrated pixel conversion function, improving the efficiency and accuracy of the size calibration.

[0075] like Figure 2 As shown, based on the above method embodiments, corresponding device embodiments are provided; this embodiment provides a defect size calibration system for large structural components, which is applicable to an image acquisition device including a camera and multiple laser emitters. The defect size calibration system includes a defect positioning module 201, an angle correction module 202 and a size calibration module 203.

[0076] The defect location module 201 is used to locate the surface area where the defect is located in the large structural component under test by using a camera, and to activate each laser emitter to form a number of laser points on the surface area to obtain an image of the area including the laser points and the surface area.

[0077] The angle correction module 202 is used to obtain the laser pixel coordinates of each laser point in the regional image, the distance between the camera and the surface region, and the focal length of the camera, so as to determine the image acquisition angle of the camera based on the distance, the focal length, and the laser pixel coordinates.

[0078] The size calibration module 203 is used to crop the defect image corresponding to the defect from the region image and obtain the defect pixel coordinates of the defect image in the region image, so as to determine the size of the defect based on the defect pixel coordinates, the image acquisition angle, the distance and the focal length.

[0079] In this embodiment, the defect location module 201 includes a defect detection unit and a laser projection unit.

[0080] The defect detection unit is configured to control the camera to perform a moving scan on the large structure to be tested, to obtain a surface image corresponding to each surface region of the large structure to be tested, and to perform defect detection on each surface image, and when a defect is detected in the surface image, to control the camera to stop the moving scan and adjust the focal length of the camera until an image containing the defect is obtained.

[0081] The laser projection unit is configured to start the laser emitter to form a plurality of laser points that are centrally symmetric on the surface region when the image is obtained.

[0082] It can be understood that the above-mentioned device embodiments correspond to the method embodiments, and can implement the large structure defect size calibration method provided by any one of the method embodiments.

[0083] It should be noted that the device embodiments described above are only schematic, and some or all of the modules can be selected to achieve the purpose of the embodiment. In addition, in the device embodiment provided in the drawings, the connection between the modules indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement without creative labor.

[0084] Based on the above-mentioned embodiment of the large structure defect size calibration method, the embodiment further provides a terminal device. The terminal device comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the large structure defect size calibration method is realized.

[0085] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the method embodiment. The one or more modules can be a series of computer program instruction segments that can complete a specific function, which are used to describe the execution process of the computer program in the terminal device.

[0086] The terminal device can be a desktop computer, a notebook computer, a palm computer, a cloud server, and other computing devices. The terminal device can include, but is not limited to, a processor and a memory.

[0087] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The processor is a control center of the terminal device, and connects all parts of the terminal device through various interfaces and lines.

[0088] Based on the above-mentioned device embodiment, the embodiment further provides a computer readable storage medium, including a stored computer program, wherein when the computer program runs, the device where the computer readable storage medium is located executes the method embodiment to control a large structural member defect size calibration method.

[0089] The modules / units integrated in the device / terminal device, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the method embodiments can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer readable storage medium, and when the processor executes the computer program, the steps of each method embodiment can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0090] The method for calibrating the size of a defect of a large structure provided by the embodiment uses a camera to real-time locate the surface area where the defect of the large structure to be measured is located, thereby improving the efficiency of defect locating. Then, when a defect image corresponding to the defect is shot for size calibration, a laser point is projected to the surface area where the defect is located, so as to determine the current image acquisition angle of the camera by means of the pixel laser pixel coordinates formed by the laser point under the current shooting angle, the focal length of the current camera and the distance from the surface area, and then correct the defect image by means of the image acquisition angle, and further determine the size of the defect according to the defect pixel coordinates, the image acquisition angle, the distance and the focal length in combination with the defect pixel coordinates in the area image, thereby improving the accuracy of defect size calibration.

[0091] Embodiment two

[0092] With the free movement of the mechanical arm, the camera is controlled by the mechanical arm to shoot the surface of a large structure at different angles and different heights, such as a bridge, a house, a tunnel and other buildings, and then detect whether the surface of the structure is abnormal, which has become a common technical means. However, the existing mechanical arm can only realize the movement in fixed directions such as straight up and straight down due to the structure setting or cost and other reasons, and cannot move at different angles in time according to the change of the on-site environment to enable the camera to shoot at 360° without dead angle.

[0093] To solve the above technical problems, the embodiment provides a mechanical arm which can support the image shooting device to shoot and rotate flexibly at 360°. Specifically, referring to Figure 3 , a structural schematic diagram of the mechanical arm provided by the embodiment is provided.

[0094] As shown in Figure 3 , the mechanical arm comprises a support body 1, a double rod 2, a first rotatable rod 3, a second rotatable rod 4 and a third rotatable rod 5. Referring to Figure 3 , the double rod 2 is fixedly connected with the support body 1 and is used to stably support the whole mechanical arm. The double rod 2 is rotationally connected with the first rod 3 to realize the rotation of the first rod 3 at different angles. The second rod 4 is rotationally connected with the first rod 3 to realize the rotation of the second rod 4 at different angles. The third rod 5 is rotationally connected with the second rod 4 to realize the rotation of the third rod 5 at different angles. It should be noted that the third rod 5 is a telescopic rod. By controlling the length of the third rod 5, the length of the mechanical arm as shown in Figure 3 can be extended or shortened, so that the mechanical arm reaches different heights or different lengths.

[0095] In an embodiment of the embodiment, referring to Figure 4Fig. 2 is a schematic diagram of the rotation of the first rod 3 to control the shooting angle of the camera. The first rod 3 rotates downward along the rod part of the double rod 2 parallel to the support body 1, so that the extension direction of the second rod 4 is parallel to the extension direction of the support body 1, and the extension direction of the third rod 5 is perpendicular to the extension direction of the support body 1.

[0096] In an embodiment of the present embodiment, referring to Figure 5 Fig. 3 is a schematic diagram of the vertical rotation of the third rod 5 to control the shooting angle of the camera. The third rod 5 rotates downward around the connection point of the third rod 5 and the second rod 4 on the basis of Figure 4 , so that the extension direction of the third rod 5 is parallel to the extension direction of the support body 1.

[0097] In an embodiment of the present embodiment, referring to Figure 6 Fig. 4 is a schematic diagram of the horizontal rotation of the third rod 5 to control the shooting angle of the camera. The third rod 5 rotates right around the connection point of the third rod 5 and the second rod 4 on the basis of Figure 5 , so that the extension direction of the third rod 5 is perpendicular to the extension direction of the support body 1.

[0098] In an embodiment of the present embodiment, in order to improve the portability of the mechanical arm as shown in Figures 3 to 6 , the mechanical arm can be made of light but solid materials to make each component of the mechanical arm, so that the mechanical arm is light and can be folded on a three-wheeled moped or a motorcycle.

[0099] In an embodiment of the present embodiment, an image acquisition device including a camera and a plurality of laser emitters is provided, and the image acquisition device is fixed on the mechanical arm as shown in Figures 3 to 6 to control the image acquisition of the image acquisition device by controlling the movement of the mechanical arm. Referring to the mechanical arm as shown in Figures 3 to 6 , a clamping device is fixed to one end of the third rod 5 which is not connected to the second rod 4; the clamping device is detachably connected to the third rod 5; the image acquisition device is fixed in the clamping device to acquire images; specifically, the specific structure of the image acquisition device is as shown in Figure 7 .

[0100] Referring to Figure 7The image acquisition device comprises a camera 6, a laser range finder 7, a plurality of laser emitters 8, and a machine table 9 for fixing the camera 6, the laser range finder 7, and the laser emitters 8 on the same horizontal plane. The plurality of laser emitters 8 are symmetrically distributed around the camera 6. Figure 7 The shooting device is connected to the mechanical arm through three telescopic rods, and the shooting angle is adjusted by adjusting the length of the three telescopic rods.

[0101] The camera 6 is used for shooting images.

[0102] The laser emitters 8 are used for projecting laser points on the surface of the large structure to form a plurality of continuous laser points.

[0103] The laser range finder 7 is used for detecting the distance between the camera 6 and the large structure being shot.

[0104] In an embodiment of the present embodiment, a turning mechanism can be arranged inside the camera 6 to enable the camera 6 to look around.

[0105] In an embodiment of the present embodiment, an auxiliary lighting + scale auxiliary device can be arranged on the same surface of the machine table 9 as the camera 6 to facilitate image correction, defect size measurement, and rapid image acquisition of the region of interest in cooperation with the focusing camera.

[0106] In an embodiment of the present embodiment, each component is controlled by an electric device, and the rotation angle can be determined.

[0107] In the present embodiment, the mechanical arm shown in Figures 3-6 and the image acquisition device shown in Figure 7 The present embodiment provides a defect size calibration method for large structural parts to improve the accuracy of defect size calibration. Specifically, the specific implementation process of the calibration method is shown in Figure 8 , which comprises:

[0108] Step 801: Control the mechanical arm to rotate and drive the camera to real-time position the surface area of the defect in the large structural part to be measured.

[0109] In the present embodiment, the extension length of the telescopic rod on the mechanical arm and the rotation angle of each rotating arm are controlled to enable the image acquisition device connected to the mechanical arm to obtain image data corresponding to different regions of the large structural part to be measured through the camera.

[0110] For each image data, a defect detection is performed. When a defect is detected in an image, the movement of the image acquisition device is controlled or the position of the image acquisition device when acquiring the image data containing the defect is obtained, so as to control the image acquisition device to return to the position where it is located.

[0111] When the camera is fixed in the position, the focal length of the camera is adjusted, and image data corresponding to different focal lengths is acquired. When the acquired image data shows that the area near the edge of the image is the background, that is, the entire defect area is captured, the focal length adjustment is stopped, and the current focal length of the camera is acquired.

[0112] Step 802: Activate the laser emitter to form a plurality of laser points on the surface area to obtain an image of the area including the laser points and the surface area.

[0113] In this embodiment, when image data capturing the entire defect area is obtained, all laser emitters are activated to form several laser points arranged in a circle on the surface area. At this time, the camera device is controlled to recapture the image to obtain an image of the area including the laser points and the entire defect area.

[0114] Step 803: Obtain the pixel coordinates of the laser point on the regional image, the distance between the camera and the surface region, and the focal length of the camera to determine the image acquisition angle of the camera.

[0115] In this embodiment, refer to Figure 7 As can be seen from the provided image acquisition device, when the laser emitter on the image acquisition device vertically illuminates the surface area, several laser points will form a circle. However, when the camera is at an angle to the surface where the defect is located, the laser points may form different shapes when the laser beam illuminates the defect. For example, when the laser beam illuminates a vertical surface, it may form a shape like... Figure 9 As shown, a circle, or a laser beam irradiating an inclined surface, forms a shape like... Figure 10 The shape shown is an ellipse.

[0116] In the captured image, laser points are identified, and their pixel coordinates are read. This is based on the angle difference between the laser beam identification device mounted on the robotic arm and the inclined surface. Specifically, firstly, based on the focal length of the camera during regional image acquisition, the distance between the camera and the surface area, and the actual interval of the laser emitters on the image acquisition device, the standard laser point interval corresponding to the distance, focal length, and actual interval is obtained from a data table saved according to experimental calibration. The standard laser point interval is as follows: Figure 9The number of pixels between two laser points symmetrical about the center point in the circle shown. In one embodiment, the standard laser point spacing is shown in the table below:

[0117] Standard laser point spacing Focal length Actual spacing of laser emitters Distance 20 pixels 3 15 cm 10 cm

[0118] Referring to the table above, the location of each laser point in the image data is as follows: Figure 10 The centroid of the ellipse is determined, and the number of pixels containing the major and minor axes of the ellipse is determined based on the centroid. The cosine value corresponding to the image acquisition angle is determined by the ratio of the number of pixels on the major axis to the standard laser point interval and the ratio of the number of pixels on the minor axis to the standard laser point interval. Then, the image acquisition angle is determined based on the inverse cosine function and the cosine value.

[0119] Step 804: Crop the defect image corresponding to the defect from the region image, and obtain the defect pixel coordinates of the defect image in the region image, so as to determine the size of the defect based on the defect pixel coordinates, the image acquisition angle, the distance and the focal length.

[0120] In this embodiment, a defect image containing only defects is cropped from the region image, and the pixel coordinates of each pixel in the defect image are obtained. Then, the pixel coordinates are corrected according to the acquisition angle to obtain the actual pixel coordinates. The correction process is as follows:

[0121]

[0122] Wherein, cosθ1 represents the ratio of the number of pixels along the major axis to the standard laser point interval; cosθ2 represents the ratio of the number of pixels along the minor axis to the standard laser point interval; where x0 and y0 are the centers of the laser point ellipse in the image pixel coordinates; x and y are the pixel coordinates of a certain point; and x' and y' are the corrected pixel coordinates.

[0123] The number of pixels in the defect image is calculated based on the corrected pixel coordinates. Then, the size of the defect is determined using the number of pixels, the distance, and the focal length. The defect size is then determined using a pre-calibrated pixel conversion function. The expression for the pixel conversion function is as follows:

[0124]

[0125] Wherein, the f0 represents the focal length of the laboratory calibration; the d0 represents the distance of the laboratory calibration; the m represents the proportional relationship between the calculated value and the actual value in the laboratory calibration process when testing different distances; the k represents the number of pixels corresponding to 1 millimeter under the focal length and distance of the laboratory calibration; the f represents the current focal length of the camera; the d represents the current distance of the camera; and the s represents the number of pixel points occupied by each unit length in the picture.

[0126] The method for calibrating the defect size of a large structure provided by the embodiment improves the defect positioning effect by using a rotatable rotating arm. The shooting angle of the image by the laser emitter on the image acquisition device is corrected to improve the accuracy of the size calibration.

[0127] The above embodiments further specifically describe the purposes, technical solutions and advantages of the present application. It should be understood that the above embodiments are only specific embodiments of the present application and are not intended to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for sizing defects in a large structure, comprising: The method is suitable for an image acquisition device comprising a camera and a plurality of laser emitters, and comprises the following steps: ​ positioning a surface area where a defect in a large structure to be measured is located by using the camera, and starting each laser emitter to form a plurality of laser points on the surface area to obtain a region image containing the laser points and the surface area; acquiring laser pixel coordinates of each laser point in the region image, a distance between the camera and the surface area, and a focal length of the camera to determine an image acquisition angle of the camera according to the distance, the focal length, and the laser pixel coordinates; cutting a defect image corresponding to the defect from the region image, and acquiring defect pixel coordinates of the defect image in the region image to determine a size of the defect according to the defect pixel coordinates, the image acquisition angle, the distance, and the focal length.

2. The method of claim 1, wherein The positioning of the surface area where the defect in the large structure to be measured is located by using the camera, and the starting of each laser emitter to form a plurality of laser points on the surface area comprises: controlling the camera to perform mobile scanning on the large structure to be measured to obtain a surface image corresponding to each surface area in the large structure to be measured; detecting defects in each surface image, and when detecting that the surface image contains a defect, controlling the camera to stop the mobile scanning and adjusting the focal length of the camera until an image containing the defect is obtained; wherein the image comprises a plurality of surface areas, and each surface area contains the defect; when the image is obtained, starting the laser emitters to form a plurality of laser points that are centrally symmetric on the surface area.

3. The method of claim 2, wherein The acquiring of the laser pixel coordinates of each laser point in the region image, the distance between the camera and the surface area, and the focal length of the camera to determine the image acquisition angle of the camera according to the distance, the focal length, and the laser pixel coordinates comprises: acquiring an interval pixel amount between two laser points that are centrally symmetric according to the laser pixel coordinates; finding a standard interval pixel amount corresponding to the two laser points that are centrally symmetric under the distance and the focal length from a pre-calibration database corresponding to the camera; acquiring a ratio of the standard interval pixel amount to the interval pixel amount to determine the image acquisition angle of the camera by using the ratio and an inverse cosine function.

4. The method of claim 1, wherein The cutting of the defect image corresponding to the defect from the region image comprises: detecting defects in the region image according to a preset defect detection algorithm to obtain a defect position in the region image; cutting the defect image corresponding to the defect from the region image according to the defect position.

5. The method of claim 4, wherein The determining of the size of the defect according to the defect pixel coordinates, the image acquisition angle, the distance, and the focal length comprises: correcting each defect pixel coordinate in the defect image according to the image acquisition angle to obtain a corrected pixel coordinate; acquiring a pixel quantity in the defect image according to the corrected pixel coordinate; and determining the size of the defect according to the pixel quantity, the distance, and the focal length. According to the pixel quantity, the distance and the focal length, a pixel point conversion function is determined through pre-calibration, so as to determine the defect size of the defect.

6. The method of claim 5, wherein The calculation expression of the pixel point conversion function is: Wherein, the f0 represents the focal length of the laboratory calibration; the d0 represents the distance of the laboratory calibration; the m represents the proportional relationship between the calculated value and the actual value in the laboratory calibration process when testing different distances; the k represents 1 millimeter corresponding to the pixel quantity under the focal length and the distance of the laboratory calibration; the f represents the current focal length of the camera; the d represents the current distance of the camera; and the s represents the pixel quantity of each unit length in the picture.

7. A system for sizing defects in large structures, comprising: The defect size calibration system is suitable for an image acquisition device comprising a camera and a plurality of laser emitters, and comprises a defect positioning module, an angle correction module and a size calibration module. The defect positioning module is used for positioning the surface area where the defect in the large-sized structural member to be tested is located through the camera, and starting each laser emitter to form a plurality of laser points on the surface area, so as to obtain a region image comprising the laser points and the surface area; The angle correction module 202 is used for obtaining the laser pixel coordinates of each laser point in the region image, the distance between the camera and the surface area and the focal length of the camera, so as to determine the image acquisition angle of the camera according to the distance, the focal length and the laser pixel coordinates; The size calibration module is used for cropping a defect image corresponding to the defect from the region image, and obtaining defect pixel coordinates of the defect image in the region image, so as to determine the size of the defect according to the defect pixel coordinates, the image acquisition angle, the distance and the focal length.

8. The system for sizing defects of a large structure according to claim 7, wherein The defect positioning module comprises a defect detection unit and a laser projection unit. The defect detection unit is used for controlling the camera to move and scan the large-sized structural member to be tested, so as to obtain a surface image corresponding to each surface area in the large-sized structural member to be tested; performing defect detection on each surface image; when detecting that the surface image has a defect, controlling the camera to stop the moving and scanning, and adjusting the focal length of the camera until an image comprising the defect is obtained; wherein, the image comprises a plurality of surface areas; and each surface area has the defect; The laser projection unit is used for starting the laser emitters when the image is obtained, so as to form a plurality of center-symmetrical laser points on the surface area.

9. A terminal device, comprising: A processor, a memory and a computer program stored in the memory and configured to be executed by the processor are included, and the processor executes the computer program to implement the defect size calibration method of the large-sized structural member according to any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer program is stored, and when the computer program is running, controls the device where the computer readable storage medium is located to execute the defect size calibration method of the large-sized structural member according to any one of claims 1-6. ​

Images