CN113252567A - Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate - Google Patents
Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate Download PDFInfo
- Publication number
- CN113252567A CN113252567A CN202110636997.XA CN202110636997A CN113252567A CN 113252567 A CN113252567 A CN 113252567A CN 202110636997 A CN202110636997 A CN 202110636997A CN 113252567 A CN113252567 A CN 113252567A
- Authority
- CN
- China
- Prior art keywords
- image
- valve plate
- camera
- aluminum valve
- light sources
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 229910052782 aluminium Inorganic materials 0.000 title claims abstract description 81
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 title claims abstract description 81
- 230000007547 defect Effects 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000005286 illumination Methods 0.000 claims abstract description 10
- 238000002310 reflectometry Methods 0.000 claims abstract description 10
- 230000000007 visual effect Effects 0.000 claims abstract description 10
- 238000006243 chemical reaction Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 7
- 230000010354 integration Effects 0.000 claims abstract description 7
- 238000001514 detection method Methods 0.000 claims description 42
- 238000004590 computer program Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000003384 imaging method Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 abstract description 5
- 238000013461 design Methods 0.000 abstract description 3
- 239000004411 aluminium Substances 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005498 polishing Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005375 photometry Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method, a system, a medium and a terminal for rapidly detecting multiple defects on the surface of an aluminum valve plate, and relates to the technical field of visual optical design. Aiming at a position to be detected on the surface of the aluminum valve plate, a camera and a light source are controlled to reach a specified position through a manipulator, the same position on the surface of the aluminum valve plate is sequentially irradiated by eight light sources at 4 angles of the same plane, and the camera sequentially takes pictures along with the irradiation of different light sources to obtain images of the light sources at corresponding angles; performing real-time integration processing on the image corresponding to each light source angle, namely calculating the image by using a photometric stereo theory, and acquiring an illumination reflectivity image corresponding to the image and a Gaussian convolution image of the image; and acquiring a preprocessing area of the image through the albedo image and the Gaussian convolution image, performing polar coordinate conversion on the preprocessing area, and performing filtering processing after the polar coordinate conversion. The problem of some qualified very slight mar also compare with unqualified mar unobviously on the image, can't discern unqualified product is solved.
Description
Technical Field
The invention relates to the technical field of visual optical design, in particular to a method, a system, a medium and a terminal for rapidly detecting multiple defects on the surface of an aluminum valve plate.
Background
The surface groove surface of the aluminum valve plate is uneven, and whether the valve plate is qualified or not needs to be detected in multiple aspects, such as scratches, peeling, collision, air holes and foreign matters. At present, the detection is generally carried out manually, the detection efficiency is low, the detection is not accurate enough, the total length of a metal block is about 220mm, the scanning length of a passing experiment table is 250mm, the scanning speed is 50mm/s, the time consumption is 5s, and most grooves can be measured in a 3D scanning picture, but the bottoms of some grooves cannot be completely scanned, and partial scanning blind areas exist, so that the groove depth cannot be detected.
In the prior art, manual or semi-automatic detection is not beneficial to improving the detection efficiency and ensuring the detection accuracy, and the existing optical scheme based on visual detection has some limitations, such as: use traditional machine vision detection technique, because the aluminium valve plate surface has the recess that the degree of depth differs, caused the unable complete defect image of shooting the aluminium valve plate of traditional mode of polishing, be difficult to satisfy quick on-line measuring's demand. The selection of current scheme can cause aluminium valve plate part region to produce the blind area, leads to shooting the aluminium valve plate incomplete. In addition, mechanical actions are more, the structural design is complex, the aluminum valve plate is larger, the required working distance is larger, and the fixed-point photographing can be more accurate and safer by carrying the camera and the light source through the mechanical arm.
Through the above analysis, the problems and defects of the prior art are as follows:
1. in long-term single repetitive work, workers are easy to fatigue, and unqualified products flow into the application market;
2. the problem of missing detection possibly occurring in manual detection by experience can be solved, and corresponding difference can be generated in the judgment of the qualification of the limit piece;
3. the surface of aluminium valve plate is uneven surface, and the surface recess is more, is difficult to satisfy the demand that online quick accurate detection exists many problems in machine visual detection.
The difficulty in solving the technical problems is as follows: the more and degree of depth of aluminium valve plate surface recess is different, and surface defect is also various, has defects such as mar, skinning, collide with, and the position has aluminium valve plate surface optional place, the state of defect, size all to be different. Because the depth of the groove cannot be comprehensively shot by a common polishing and photographing mode, the method for quickly detecting the defects on the surface of the aluminum valve plate is provided, and the method is suitable for the defects of different types, different forms and different positions.
The significance of solving the problems and the defects is as follows: in consideration of the traditional manual detection mode and the traditional visual detection mode, the detection method provided by the text can adapt to defects of different types, different forms and different positions, solves the problems of efficiency and precision of traditional manual detection, incomplete single-lens detection defect and low cost and efficiency of multi-view stereoscopic vision, and improves the efficiency and precision of detection because the characteristic imaging of the traditional visual detection is not ideal due to the influence of light rays in the common polishing mode.
Disclosure of Invention
In order to overcome the problems in the related art, the disclosed embodiment of the invention provides a method and a system for rapidly detecting multiple defects on the surface of an aluminum valve plate. The invention can effectively collect the picture information of each outer surface required by the quality detection of the aluminum valve plate, compared with other schemes, the invention adopts the photometric stereo method to shoot images from different angles, and completely collects the defects that the images cannot be collected in the groove, thereby reducing the labor intensity, the maintenance cost and the potential risk; the shooting precision and the detection speed are improved; the technical scheme is as follows:
the method for rapidly detecting various defects on the surface of the aluminum valve plate comprises the following steps:
the method comprises the following steps that firstly, aiming at a position to be detected on the surface of an aluminum valve plate, a camera and a light source are controlled to reach a specified position through a manipulator, the same position on the surface of the aluminum valve plate is sequentially irradiated through four angles of eight light sources on the same plane, the camera sequentially shoots along with the irradiation of different light sources, and images of the light sources at corresponding angles are obtained;
performing real-time integration processing on the image corresponding to each light source angle, calculating the image by using a photometric stereo theory, and acquiring an illumination reflectivity image corresponding to the image and a Gaussian convolution image of the image;
acquiring a preprocessing region of the image through the albedo image and the Gaussian convolution image, and performing polar coordinate conversion and filtering processing;
judging whether peeling exists or not by an experience threshold method, and acquiring position information of an area where peeling exists;
and fifthly, obtaining the position information of the corresponding image by adopting polar coordinate inverse transformation on the obtained position information, and marking the positions of all peeling positions on the obtained albedo image.
In one embodiment, in the step one, the shot position is divided according to the size of the detected position of the aluminum valve plate, the visual field range and the working distance to be achieved are determined according to the camera imaging principle, and the focal length of the industrial lens is calculated.
In one embodiment, in step one, in the 4-angle photographing mode, the following equation set is established:
the change to matrix form is:
in one embodiment, in the step one, the eight light sources are divided into five cameras according to the detected characteristics, wherein four cameras shoot the peeling defects of the aluminum valve plate, and the other camera shoots the surface defects of the aluminum valve plate; according to the lambertian surface reflection model in the principle of photometric stereo vision, for a light source with an illumination direction S, the unit normal vector of the surface is N, and the brightness I of the reflected light is:
I＝ξS·N
wherein: i is expressed as the brightness of the diffuse reflected light at the target object surface (x, y, z) projected onto the camera, i.e. the image gray value I (x, y); xi is the coefficient of reflectivity of the surface of the object; (S) ═ Sx,Sy,Sz)T；N＝(Nx,Ny,Nz)T。
In one embodiment, in five cameras, four light sources around the five cameras are lighted up when taking pictures, and the peeling of the angles around the aluminum valve plate is taken; the other camera takes eight pictures with eight light sources strobing at a time.
The invention also aims to provide a system for realizing the method for rapidly detecting the multiple defects on the surface of the aluminum valve plate, and the system for rapidly detecting the multiple defects on the surface of the aluminum valve plate comprises the following steps:
the image acquisition module comprises five cameras, wherein four cameras at the periphery are responsible for shooting peeling conditions, and one camera at the middle is responsible for shooting scratch defects on the front side;
the motion control module is connected with the image acquisition module and controls the motion state of each camera through the motion controller;
the upper computer is connected with each camera through the I/O equipment and controls the hardware I/O equipment under the motion control card through programming so as to control the shooting of the cameras and the starting of the light source;
and the storage module is used for transmitting the image shot by the camera to an industrial personal computer for storage after the image is processed in real time.
In one embodiment, the image acquisition module comprises five 1200 ten thousand pixel cameras and a 35mm lens in the middle, 25mm in the four surrounding cameras, the middle camera lens surface being spaced from the aluminum valve plate surface: 280mm, the distance between the surfaces of four camera lenses at the periphery and the surface of an aluminum valve plate: 140mm, the surface angles of the four surrounding cameras and the aluminum valve plate: 36 deg.
In one embodiment, the motion control module controls the motion control card, and the motion control card communicates with the computer in a PCIe communication mode; the motion control card controls a plurality of axes to execute the interpolated motion trail in a linkage manner, and controls the cylinder, the execution mechanism, the I/O input/output and the analog quantity measurement; the motion control card controls the triggering of the camera and the turning on and off of the light source in a mode of dragging the external multifunctional I/O module.
Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which when executed by a processor, causes the processor to execute the method for rapidly detecting multiple defects on the surface of an aluminum valve plate.
Another object of the present invention is to provide a computer data processing terminal comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
the method comprises the following steps that firstly, aiming at a position to be detected on the surface of an aluminum valve plate, a camera and a light source are controlled to reach a specified position through a manipulator, the same position on the surface of the aluminum valve plate is sequentially irradiated through four angles of eight light sources on the same plane, the camera sequentially shoots along with the irradiation of different light sources, and images of the light sources at corresponding angles are obtained;
performing real-time integration processing on the image corresponding to each light source angle, calculating the image by using a photometric stereo theory, and acquiring an illumination reflectivity image corresponding to the image and a Gaussian convolution image of the image;
acquiring a preprocessing region of the image through the albedo image and the Gaussian convolution image, and performing polar coordinate conversion and filtering processing;
judging whether peeling exists or not by an experience threshold method, and acquiring position information of an area where peeling exists;
and fifthly, obtaining the position information of the corresponding image by adopting polar coordinate inverse transformation on the obtained position information, and marking the positions of all peeling positions on the obtained albedo image.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
1. according to the camera imaging principle, the aluminum valve plate is divided into 13 shooting points, 9 shooting points on the front side and 4 shooting points on the back side. The problem of some qualified very slight mar also compare with unqualified mar unobviously on the image, can't discern unqualified product is solved.
2. The invention has 8 light sources, 5 cameras, the above-mentioned light source has solved the incomplete problem of traditional light source polishing, control camera and light source through the motion control card, use the multi-functional I/O module dragged to carry on the hard-wired connection, the module has 10 digital outputs and can meet the photometry and take a picture, the peripheral hardware dragged of the motion control card can expand and can expand more I/O and control more light sources in addition;
3. the acquired image is processed in real time and then stored on the industrial personal computer, the whole process does not need human participation, the problem of the defect of the traditional manual detection of the aluminum valve plate is solved, and the machine vision online detection is realized;
4. the invention solves the problem of incomplete defect detection caused by a common polishing mode in the traditional machine vision detection, and improves the detection accuracy;
5. the invention solves the problem of high cost and low efficiency of multi-view stereoscopic vision.
6. The detection items are increased, and the detection items such as scratches in the aluminum valve plate and the like cannot be accurately detected due to the limitation of a detection tool in the conventional manual detection, but the method can realize accurate detection, has the accuracy rate of 99.99 percent under the condition of no detection omission, has the false detection rate of less than 0.2 percent, avoids the detection omission condition caused by manual detection by experience, and greatly improves the yield.
7. The detection speed of the device is improved, 10000 products are detected by the device at the lowest time in one hour, about 1000 products are detected by one person in one hour, and the detection efficiency of the device is ten times that of the person; for a profiler, some high precision instruments such as three-coordinates detect more slowly.
8. When the detected data continuously generate NG, the device gives an alarm to prompt a worker to check whether the previous process has a problem or not, the problem is fed back in time, and the number of unqualified parts is reduced; in addition, the detection data can be traced, and when the detection data of a certain day or the data of a certain batch of products needs to be checked, the equipment can realize real-time inquiry and downloading.
9. The prior art is compared with the technology provided by the invention, and the following table shows that:
it is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a schematic view of a photometric stereo detection system according to an embodiment of the present invention.
FIG. 2 is a flowchart of a method for rapidly detecting multiple defects on the surface of an aluminum valve plate according to an embodiment of the present invention.
FIG. 3 is an apparatus diagram of a method for rapidly detecting multiple defects on the surface of an aluminum valve plate according to an embodiment of the present invention.
Fig. 4 is a composite view of the 13 shooting points involved in the invention provided in the embodiment of the present invention.
Fig. 5 is an image of a conventional visually photographed aluminum valve plate according to the invention provided in an embodiment of the present invention.
FIG. 6 is a 8 shot point segmentation image of the aluminum valve plate shot point segmentation problem involved in the invention provided in the embodiment of the present invention;
wherein a is a segmentation drawing from a 1 st station to a 4 th station; b is a division diagram from the 5 th station to the 8 th station.
Fig. 7 is a 13 shot point segmentation image of the problem of shot point segmentation of the aluminum valve plate involved in the invention provided in the embodiment of the present invention;
wherein a is a segmentation drawing from a 1 st station to a 9 th station; b is a division diagram from the 10 th station to the 13 th station.
Fig. 8 is a defect image of an aluminum valve plate involved in the invention provided in the example of the present invention.
Fig. 9 is a peeling image taken by photometry related to the invention provided in the embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, but rather should be construed as broadly as the present invention is capable of modification in various respects, all without departing from the spirit and scope of the present invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. As used herein, the terms "vertical," "horizontal," "left," "right," and the like are for purposes of illustration only and are not intended to represent the only embodiments.
Unless defined otherwise, 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 invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
As shown in FIG. 1, the disclosed embodiment of the present invention provides a method for rapidly detecting multiple defects on the surface of an aluminum valve plate, comprising the following steps:
the method comprises the steps that a camera and a light source are controlled to reach an appointed position through a mechanical arm aiming at a position to be detected on the surface of an aluminum valve plate, the same position on the surface of the aluminum valve plate is sequentially irradiated at 4 angles of the same plane through 8 light sources, the camera sequentially shoots along with the irradiation of different light sources, and images of the light sources at the corresponding angles are obtained.
And step two, performing real-time integration processing on the images corresponding to each light source angle, namely calculating the images by using a photometric stereo theory, and acquiring the corresponding illumination reflectivity images and the Gaussian convolution images of the images.
And thirdly, acquiring a preprocessing region of the image through the albedo image and the Gaussian convolution image, performing polar coordinate conversion on the preprocessing region, and performing filtering processing after the polar coordinate conversion.
And step four, judging whether peeling exists or not by an experience threshold method, and acquiring the position information of the approximate area where peeling exists.
And fifthly, obtaining corresponding image position information by adopting polar coordinate inverse transformation on the obtained position information, and marking the positions of all peeling positions on the albedo image obtained in the step two.
In the first step, the photographing position of the aluminum valve plate is divided; the shot position is divided according to the size of the detection position of the aluminum valve plate. The aluminum valve plate is divided into 13 shooting points, 9 shooting points on the front side and 4 shooting points on the back side according to the surface size of the tested aluminum valve plate, but the aluminum valve plate is not limited to the number. According to the camera imaging principle: determining a visual field range (FOV) and a Working Distance (WD) to be reached, and calculating a focal length (f) of the industrial lens according to the FOV and the Working Distance (WD), wherein the calculation formula is as follows:
focal length f ═ WD × target surface size h/FOV (H or V)
Field range HF ═ WD × target surface size (h)/focal length f
FOV (H or V) of field of view (H or V) is the target surface size (h)/optical magnification
Working distance WD ═ f (focal length) × target surface size (h)/FOV (H or V)
Optical magnification ═ target surface size (h)/fov (h or v).
As shown in fig. 1, the image acquisition module of the present invention includes 5 shooting points, two lights adjacent to the cameras are bright and the other lights are not bright when four cameras around the camera shoot, and one image and 8 images are shot when each single light of the middle camera is bright. 12 shooting positions are shot at each shooting position, and all shooting positions are shot in sequence according to the shooting position sequence. There are 8 light sources, and according to the detected characteristics, the total number is 5 cameras, wherein 4 cameras shoot the peeling defect of the aluminum valve plate, and the other camera shoots the surface defect of the aluminum valve plate. According to the lambertian surface reflection model in the principle of photometric stereo vision, for a light source with an illumination direction S, the unit normal vector of the surface is N, and the brightness I of the reflected light is:
I＝ξS·N
wherein: i is expressed as the brightness of the diffuse reflected light at the target object surface (x, y, z) projected onto the camera, i.e. the image gray value I (x, y); xi is the coefficient of reflectivity of the surface of the object; (S) ═ Sx,Sy,Sz)T；N＝(Nx,Ny,Nz)T。
The system has four photographing modes with different angles, and the following equation set can be established:
the change to matrix form is:
the method comprises the following specific steps:
when the camera 1 works, the light 1 and the light 8 are on;
when the camera 2 works, the light 2 and the light 3 are on;
when the camera 3 works, the light 4 and the light 5 are on;
when the camera 4 works, the light 6 and the light 7 are on;
when the camera 1 works, 8 lights are strobed in sequence, and the camera shoots an image every time the lights are strobed.
The camera 5 takes pictures with 8 light sources strobing once, for a total of 8 pictures.
Camera 1, camera 2, camera 3, camera 4, two light sources around when shooing are lighted, shoot the skinning of aluminium valve plate angle all around.
The visual field of shooting of 8 shooting points is larger, so that qualified slight scratches are also unobvious in comparison with unqualified scratches on the image, unqualified products cannot be identified, and the shooting is clearer by adopting a method of 13 shooting points.
As shown in the schematic diagrams of the shooting point division shown in fig. 6 and 7, according to the above calculation, the field of view for shooting at 8 shooting points is relatively large, so that qualified slight scratches are also inconspicuous in comparison with unqualified scratches on the image, and unqualified products cannot be identified, so that the shooting point division of 13 is adopted.
In the specific implementation of the present invention, the apparatus diagram is shown in fig. 3, and specifically includes:
five cameras: 1200 ten thousand pixel camera
Lens: the middle lens is 35 mm; the four lenses around the lens are 25mm
Detecting a target: aluminum valve plate
The surface of the intermediate camera lens is spaced from the surface of the aluminum valve plate: 280mm
The distances between the surfaces of the four surrounding camera lenses and the surface of the aluminum valve plate are as follows: 140mm
The surface angles of four surrounding cameras and the aluminum valve plate are as follows: at 36 °
The camera is controlled by the motion control card, the motion control card communicates with a computer in a PCIe communication mode, the communication has the characteristic of high real-time performance, and the motion control card can control a plurality of axes to execute complex motion track functions such as interpolation in a linkage mode, and can control cylinders, various execution mechanisms, I/O input/output, analog quantity measurement and the like, so that the motion control card is widely applied to an industrial personal computer integrated related automatic control system. The invention adopts a GSN series motion control card to control the triggering of a camera and the turning on and off of a light source in a mode of dragging an external multifunctional I/O module. The upper computer controls the hardware I/O equipment under the motion control card through programming so as to control the shooting of the camera and the starting of the light source.
When shooting different shooting positions, the positions of the camera and the light source are controlled by using the fixed point of the mechanical arm.
The collected aluminum valve plate image and the collected image transmission industrial personal computer are stored, and the method comprises the following steps:
step one, 8 images shot by a camera 5 are processed by an algorithm to be synthesized into a picture and stored on an industrial personal computer.
And step two, directly storing 4 images shot by the camera 1, the camera 2, the camera 3 and the camera 4 on an industrial personal computer.
Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which when executed by a processor, causes the processor to execute the method for rapidly detecting multiple defects on the surface of an aluminum valve plate.
Another object of the present invention is to provide a computer data processing terminal comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
the method comprises the following steps that firstly, aiming at a position to be detected on the surface of an aluminum valve plate, a camera and a light source are controlled to reach a specified position through a manipulator, the same position on the surface of the aluminum valve plate is sequentially irradiated through four angles of eight light sources on the same plane, the camera sequentially shoots along with the irradiation of different light sources, and images of the light sources at corresponding angles are obtained;
performing real-time integration processing on the image corresponding to each light source angle, calculating the image by using a photometric stereo theory, and acquiring an illumination reflectivity image corresponding to the image and a Gaussian convolution image of the image;
acquiring a preprocessing region of the image through the albedo image and the Gaussian convolution image, and performing polar coordinate conversion and filtering processing;
judging whether peeling exists or not by an experience threshold method, and acquiring position information of an area where peeling exists;
and fifthly, obtaining the position information of the corresponding image by adopting polar coordinate inverse transformation on the obtained position information, and marking the positions of all peeling positions on the obtained albedo image.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure should be limited only by the attached claims.
Claims (10)
1. A method for rapidly detecting multiple defects on the surface of an aluminum valve plate is characterized by comprising the following steps:
the method comprises the following steps that firstly, aiming at a position to be detected on the surface of an aluminum valve plate, a camera and a light source are controlled to reach a specified position through a manipulator, the same position on the surface of the aluminum valve plate is sequentially irradiated through four angles of eight light sources on the same plane, the camera sequentially shoots along with the irradiation of different light sources, and images of the light sources at corresponding angles are obtained;
performing real-time integration processing on the image corresponding to each light source angle, calculating the image by using a photometric stereo theory, and acquiring an illumination reflectivity image corresponding to the image and a Gaussian convolution image of the image;
acquiring a preprocessing region of the image through the albedo image and the Gaussian convolution image, and performing polar coordinate conversion and filtering processing;
judging whether peeling exists or not by an experience threshold method, and acquiring position information of an area where peeling exists;
and fifthly, obtaining the position information of the corresponding image by adopting polar coordinate inverse transformation on the obtained position information, and marking the positions of all peeling positions on the obtained albedo image.
2. The method for rapidly detecting the multiple defects on the surface of the aluminum valve plate as claimed in claim 1, wherein in the step one, the shot position is divided according to the size of the detected position of the aluminum valve plate, the visual field range and the working distance to be achieved are determined according to the camera imaging principle, and the focal length of the industrial lens is calculated.
3. The method for rapidly detecting the multiple defects on the surface of the aluminum valve plate as claimed in claim 1, wherein in the step one, in a 4-angle photographing mode, the following equation system is established:
the change to matrix form is:
4. the method for rapidly detecting the multiple defects on the surface of the aluminum valve plate as claimed in claim 1, wherein in the step one, eight light sources are divided into five cameras according to the detected characteristics, wherein four cameras shoot the peeling defects of the aluminum valve plate, and the other camera shoots the surface defects of the aluminum valve plate; according to the lambertian surface reflection model in the principle of photometric stereo vision, for a light source with an illumination direction S, the unit normal vector of the surface is N, and the brightness I of the reflected light is:
I＝ξS·N
wherein: i is expressed as the brightness of the diffuse reflected light at the target object surface (x, y, z) projected onto the camera, i.e. the image gray value I (x, y); xi is the coefficient of reflectivity of the surface of the object; (S) ═ Sx,Sy,Sz)T；N＝(Nx,Ny,Nz)T。
5. The method of claim 4, wherein in five cameras, four of the light sources are lit up around the four cameras to photograph the peeling of the angles around the aluminum valve plate; the other camera takes eight pictures with eight light sources strobing at a time.
6. A system for realizing the method for rapidly detecting the multiple defects on the surface of the aluminum valve plate as set forth in any one of claims 1 to 4, wherein the system for rapidly detecting the multiple defects on the surface of the aluminum valve plate comprises:
the image acquisition module comprises five cameras, wherein four cameras at the periphery are responsible for shooting peeling conditions, and one camera at the middle is responsible for shooting scratch defects on the front side;
the motion control module is connected with the image acquisition module and controls the motion state of each camera through the motion controller;
the upper computer is connected with each camera through the I/O equipment and controls the hardware I/O equipment under the motion control card through programming so as to control the shooting of the cameras and the starting of the light source;
and the storage module is used for transmitting the image shot by the camera to an industrial personal computer for storage after the image is processed in real time.
7. The system for rapidly detecting the multiple defects on the surface of the aluminum valve plate as claimed in claim 6, wherein the image acquisition module comprises five 1200 ten thousand pixel cameras and a middle camera which is a 35mm lens, four peripheral cameras which are 25mm lenses, and the surface of the middle camera lens is spaced from the surface of the aluminum valve plate: 280mm, the distance between the surfaces of four camera lenses at the periphery and the surface of an aluminum valve plate: 140mm, the surface angles of the four surrounding cameras and the aluminum valve plate: 36 deg.
8. The system for rapidly detecting the multiple defects on the surface of the aluminum valve plate according to claim 6, wherein the motion control module is controlled through a motion control card, and the motion control card is communicated with a computer in a PCIe communication mode; the motion control card controls a plurality of axes to execute the interpolated motion trail in a linkage manner, and controls the cylinder, the execution mechanism, the I/O input/output and the analog quantity measurement; the motion control card controls the triggering of the camera and the turning on and off of the light source in a mode of dragging the external multifunctional I/O module.
9. A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the method for rapid detection of multiple defects on the surface of an aluminum valve plate of any one of claims 1 to 5.
10. A computer data processing terminal, characterized in that the computer data processing terminal comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the steps of:
the method comprises the following steps that firstly, aiming at a position to be detected on the surface of an aluminum valve plate, a camera and a light source are controlled to reach a specified position through a manipulator, the same position on the surface of the aluminum valve plate is sequentially irradiated through four angles of eight light sources on the same plane, the camera sequentially shoots along with the irradiation of different light sources, and images of the light sources at corresponding angles are obtained;
performing real-time integration processing on the image corresponding to each light source angle, calculating the image by using a photometric stereo theory, and acquiring an illumination reflectivity image corresponding to the image and a Gaussian convolution image of the image;
acquiring a preprocessing region of the image through the albedo image and the Gaussian convolution image, and performing polar coordinate conversion and filtering processing;
judging whether peeling exists or not by an experience threshold method, and acquiring position information of an area where peeling exists;
and fifthly, obtaining the position information of the corresponding image by adopting polar coordinate inverse transformation on the obtained position information, and marking the positions of all peeling positions on the obtained albedo image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110636997.XA CN113252567A (en) | 2021-06-08 | 2021-06-08 | Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110636997.XA CN113252567A (en) | 2021-06-08 | 2021-06-08 | Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113252567A true CN113252567A (en) | 2021-08-13 |
Family
ID=77187017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110636997.XA Pending CN113252567A (en) | 2021-06-08 | 2021-06-08 | Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113252567A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113824827A (en) * | 2021-09-20 | 2021-12-21 | 苏州凯仕弘科技有限公司 | Visual detection system for mobile phone screen |
| CN114354607A (en) * | 2021-10-09 | 2022-04-15 | 七海测量技术（深圳）有限公司 | Luminosity three-dimensional flaw detection method based on spiral phase contrast filtering algorithm |
| CN114554088A (en) * | 2022-02-16 | 2022-05-27 | 广州市斯睿特智能科技有限公司 | High-speed beat detection system and detection method thereof |
| CN115334227A (en) * | 2022-10-18 | 2022-11-11 | 菲特（天津）检测技术有限公司 | Gear image acquisition device and method, gear image acquisition method and electronic equipment |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101710080A (en) * | 2009-12-01 | 2010-05-19 | 湖南大学 | Stacking glass bottle detection method based on machine vision and transporter |
| CN203385680U (en) * | 2013-06-30 | 2014-01-08 | 北京工业大学 | Inner wall surface defect image acquiring device |
| CN103743749A (en) * | 2014-01-03 | 2014-04-23 | 苏州吉视电子科技有限公司 | Device and method for detecting surface quality of flaky parts |
| CN103940822A (en) * | 2014-04-01 | 2014-07-23 | 华南理工大学 | Product outer surface defect image acquisition device based on machine vision |
| CN105158267A (en) * | 2015-09-22 | 2015-12-16 | 安徽省科亿信息科技有限公司 | Device and method for 360-degree bottle body production line backlight vision inspection |
| CN206684029U (en) * | 2017-03-17 | 2017-11-28 | 苏州富鑫林光电科技有限公司 | AOI vision-based detections annular light source matches somebody with somebody side light source and backlight testing agency |
| CN107607546A (en) * | 2017-09-19 | 2018-01-19 | 佛山缔乐视觉科技有限公司 | Leather defect inspection method, system and device based on photometric stereo vision |
| CN108490000A (en) * | 2018-03-13 | 2018-09-04 | 北京科技大学 | A kind of Bar Wire Product surface defect on-line measuring device and method |
| CN207908385U (en) * | 2017-12-13 | 2018-09-25 | 深圳市光速达机器人科技有限公司 | A kind of pcb board weld defect self-checking system that view-based access control model is differentiated |
| CN109712123A (en) * | 2018-12-14 | 2019-05-03 | 成都安锐格智能科技有限公司 | A kind of spot detection method |
| CN209198809U (en) * | 2018-12-13 | 2019-08-02 | 东莞三协精工科技有限公司 | A kind of backlight AOI detection image acquisition device |
| CN110487792A (en) * | 2019-08-28 | 2019-11-22 | 普洛赛斯（苏州）智能装备有限公司 | A kind of pcb board glue surface vision inspection apparatus and method |
| CN111122598A (en) * | 2019-12-16 | 2020-05-08 | 北京冶自欧博科技发展有限公司 | Three-dimensional detection system and method for surface defects of steel rail |
| CN111624206A (en) * | 2020-07-03 | 2020-09-04 | 东北大学 | Metal surface defect detection method based on linear array camera stereoscopic vision |
| CN111650212A (en) * | 2020-07-03 | 2020-09-11 | 东北大学 | Metal surface normal direction three-dimensional information acquisition method based on linear array camera three-dimensional vision |
| CN111842212A (en) * | 2020-07-21 | 2020-10-30 | 深圳市泰沃德自动化技术有限公司 | Automatic feeding structure, appearance detection device, mask appearance detection device and method |
| CN111896550A (en) * | 2020-03-31 | 2020-11-06 | 广西师范大学 | Surface defect detection device and method |
| CN112067625A (en) * | 2020-09-23 | 2020-12-11 | 湖北爱默思智能检测装备有限公司 | Device and method for detecting surface defects of rubber ring parting line |
| CN112345539A (en) * | 2020-11-05 | 2021-02-09 | 菲特（天津）检测技术有限公司 | Aluminum die casting surface defect detection method based on deep learning |
| CN112858332A (en) * | 2021-02-22 | 2021-05-28 | 菲特(珠海横琴)智能科技有限公司 | Synchronizer gear hub surface defect detection method, system and terminal based on machine vision |
-
2021
- 2021-06-08 CN CN202110636997.XA patent/CN113252567A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101710080A (en) * | 2009-12-01 | 2010-05-19 | 湖南大学 | Stacking glass bottle detection method based on machine vision and transporter |
| CN203385680U (en) * | 2013-06-30 | 2014-01-08 | 北京工业大学 | Inner wall surface defect image acquiring device |
| CN103743749A (en) * | 2014-01-03 | 2014-04-23 | 苏州吉视电子科技有限公司 | Device and method for detecting surface quality of flaky parts |
| CN103940822A (en) * | 2014-04-01 | 2014-07-23 | 华南理工大学 | Product outer surface defect image acquisition device based on machine vision |
| CN105158267A (en) * | 2015-09-22 | 2015-12-16 | 安徽省科亿信息科技有限公司 | Device and method for 360-degree bottle body production line backlight vision inspection |
| CN206684029U (en) * | 2017-03-17 | 2017-11-28 | 苏州富鑫林光电科技有限公司 | AOI vision-based detections annular light source matches somebody with somebody side light source and backlight testing agency |
| CN107607546A (en) * | 2017-09-19 | 2018-01-19 | 佛山缔乐视觉科技有限公司 | Leather defect inspection method, system and device based on photometric stereo vision |
| CN207908385U (en) * | 2017-12-13 | 2018-09-25 | 深圳市光速达机器人科技有限公司 | A kind of pcb board weld defect self-checking system that view-based access control model is differentiated |
| CN108490000A (en) * | 2018-03-13 | 2018-09-04 | 北京科技大学 | A kind of Bar Wire Product surface defect on-line measuring device and method |
| CN209198809U (en) * | 2018-12-13 | 2019-08-02 | 东莞三协精工科技有限公司 | A kind of backlight AOI detection image acquisition device |
| CN109712123A (en) * | 2018-12-14 | 2019-05-03 | 成都安锐格智能科技有限公司 | A kind of spot detection method |
| CN110487792A (en) * | 2019-08-28 | 2019-11-22 | 普洛赛斯（苏州）智能装备有限公司 | A kind of pcb board glue surface vision inspection apparatus and method |
| CN111122598A (en) * | 2019-12-16 | 2020-05-08 | 北京冶自欧博科技发展有限公司 | Three-dimensional detection system and method for surface defects of steel rail |
| CN111896550A (en) * | 2020-03-31 | 2020-11-06 | 广西师范大学 | Surface defect detection device and method |
| CN111624206A (en) * | 2020-07-03 | 2020-09-04 | 东北大学 | Metal surface defect detection method based on linear array camera stereoscopic vision |
| CN111650212A (en) * | 2020-07-03 | 2020-09-11 | 东北大学 | Metal surface normal direction three-dimensional information acquisition method based on linear array camera three-dimensional vision |
| CN111842212A (en) * | 2020-07-21 | 2020-10-30 | 深圳市泰沃德自动化技术有限公司 | Automatic feeding structure, appearance detection device, mask appearance detection device and method |
| CN112067625A (en) * | 2020-09-23 | 2020-12-11 | 湖北爱默思智能检测装备有限公司 | Device and method for detecting surface defects of rubber ring parting line |
| CN112345539A (en) * | 2020-11-05 | 2021-02-09 | 菲特（天津）检测技术有限公司 | Aluminum die casting surface defect detection method based on deep learning |
| CN112858332A (en) * | 2021-02-22 | 2021-05-28 | 菲特(珠海横琴)智能科技有限公司 | Synchronizer gear hub surface defect detection method, system and terminal based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 罗立浩等: "基于机器视觉的非平整物体表面凸起异物检测方法", 《计算机测量与控制》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113824827A (en) * | 2021-09-20 | 2021-12-21 | 苏州凯仕弘科技有限公司 | Visual detection system for mobile phone screen |
| CN114354607A (en) * | 2021-10-09 | 2022-04-15 | 七海测量技术（深圳）有限公司 | Luminosity three-dimensional flaw detection method based on spiral phase contrast filtering algorithm |
| CN114354607B (en) * | 2021-10-09 | 2023-10-31 | 七海测量技术（深圳）有限公司 | Luminosity three-dimensional flaw detection method based on spiral phase contrast filtering algorithm |
| CN114554088A (en) * | 2022-02-16 | 2022-05-27 | 广州市斯睿特智能科技有限公司 | High-speed beat detection system and detection method thereof |
| CN115334227A (en) * | 2022-10-18 | 2022-11-11 | 菲特（天津）检测技术有限公司 | Gear image acquisition device and method, gear image acquisition method and electronic equipment |
| CN115334227B (en) * | 2022-10-18 | 2024-01-19 | 菲特（天津）检测技术有限公司 | Gear image acquisition device and method, gear image acquisition method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113252567A (en) | Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate | |
| US7729530B2 (en) | Method and apparatus for 3-D data input to a personal computer with a multimedia oriented operating system | |
| CN110392252B (en) | Method for generating correction model of camera to correct aberration | |
| CN110702035A (en) | Household appliance spraying quality detection system and method based on surface structured light | |
| CN110455815B (en) | Method and system for detecting appearance defects of electronic components | |
| CN111612737B (en) | Artificial board surface flaw detection device and detection method | |
| CN109785319B (en) | System, device and method for detecting code-spraying character based on image processing | |
| CN113267452A (en) | Engine cylinder surface defect detection method and system based on machine vision | |
| CN103644852A (en) | Lens film thickness automatic detection system | |
| CN110261069B (en) | Detection method for optical lens | |
| CN110570412B (en) | Part error vision judgment system | |
| CN113375584A (en) | Monocular three-dimensional acquisition structure, monocular three-dimensional multi-gauge visual system and extensometer | |
| Wang et al. | Highly reflective surface measurement based on dual stereo monocular structured light system fusion | |
| CN109373904A (en) | 3D vision detection device and 3D vision detection method | |
| CN109406539A (en) | A kind of transparent medicine bottle bottom buildup defect detecting system and method | |
| KR102177726B1 (en) | Method and apparatus for inspecting workpiece | |
| CN114332231B (en) | Method, device and medium for positioning manipulator and camera in visual inspection equipment | |
| CN114926531A (en) | Binocular vision based method and system for autonomously positioning welding line of workpiece under large visual field | |
| CN114486939A (en) | Lens scratch detection system and method | |
| CN109900704B (en) | In-situ three-dimensional reconstruction method for microscopic morphology of worn surface of gear | |
| TWI742391B (en) | Three-dimensional image surface defect detection system | |
| CN114241059A (en) | Synchronous calibration method for camera and light source in photometric stereo vision system | |
| CN117078666B (en) | Two-dimensional and three-dimensional combined defect detection method, device, medium and equipment | |
| Kong et al. | Reconstruction of solder joint surface based on shape from shading | |
| CN114354607B (en) | Luminosity three-dimensional flaw detection method based on spiral phase contrast filtering algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210813 |
|
| RJ01 | Rejection of invention patent application after publication |