CN116297204A - System and method for detecting defects of automotive front cover paint - Google Patents

Abstract

The invention provides a system and a method for detecting defects of automotive front cover finish paint, wherein the system comprises the following steps: the detection support module comprises a frame main body part, wherein the frame main body part is provided with a vehicle cover placing part for supporting the front cover surface of the detected vehicle; the image acquisition module comprises a plurality of industrial cameras, an image acquisition fixing part and an image acquisition control module, wherein the image acquisition fixing part is positioned above the frame main body part and is used for acquiring images of the front cover surface of the detected automobile; the image processing analysis module is used for receiving the image transmitted by the image acquisition module and analyzing and obtaining the specific position of the front cover defect of the automobile; and the driving module is used for driving the movable light source supporting part provided with the movable light source module to move above the vehicle cover placing part. The invention provides a system and a method for detecting defects of a front cover paint of a vehicle body, which have the advantages of simple structure and higher detection precision.

Description

System and method for detecting defects of automotive front cover paint

Technical Field

The invention relates to the technical field of automotive finish defect detection, in particular to an automotive front cover finish defect detection system and method.

Background

As one of four processes for automobile production, automobile coating not only plays a role in decoration, but also can improve the anti-corrosion performance and the abrasion resistance of the automobile and prolong the service life of the automobile. After the spraying is finished, the spraying quality is usually required to be checked manually, and the defects are repaired. The automobile front cover is used as an important component of the automobile body, and has the defects of oil stains, scratches, particles and the like after spraying, and the defects of low efficiency, high cost, high omission ratio and the like in a manual defect detection mode, so that the automobile coating quality is reduced.

Machine vision is a comprehensive technology combining various disciplines such as image recognition, image processing, artificial intelligence and the like, and is widely applied to surface defect detection in the fields of automobiles, airplanes, ships and the like. Compared with the manual detection method, the defect detection technology based on machine vision has the advantages of high detection precision, high speed, good stability and the like. However, due to the difference of the detection device and the detection algorithm, the problems of high cost, low precision and the like exist among different defect detection devices based on machine vision.

For example, patent document 1 (chinese patent publication No. CN111638224 a) discloses a vehicle paint defect detection device based on intelligent sensing and machine vision, the whole device is composed of a square hollow base, a gantry-shaped fixing frame, a conveying mechanism, two sets of side detection mechanisms, a top detection mechanism, two sets of fixed illumination mechanisms and a control mechanism, and the detection work of the vehicle paint defect based on machine vision is completed by mutually matching the mechanisms.

However, in actual production, when the vehicle to be detected enters the detection area, the sled of the carrying vehicle may slip, so that the fixed illumination mechanism cannot work according to the designated steps, and the detection result is affected.

On the other hand, patent document 2 (chinese patent publication No. CN113324994 a) discloses a device and method for detecting a defect layering of a vehicle body and a finish paint, wherein an industrial personal computer, an industrial robot, a controller and a detection and marking device are used for detecting the defect of the vehicle body, and the detection comprises two steps of primary detection and secondary detection. However, the device has a complex structure, high precision requirement on the image acquisition device and high industrial cost.

Disclosure of Invention

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the disclosure.

Aiming at the problems, the invention provides a system and a method for detecting the paint defects of the front cover surface of the vehicle body, which have the advantages of simple structure and higher detection precision.

In order to solve the technical problems, the invention provides an automobile front cover paint defect detection system, which is characterized by comprising the following steps:

the detection support module comprises a frame main body part, wherein the frame main body part is provided with a vehicle cover placing part for supporting the front cover surface of the detected vehicle;

the image acquisition module comprises a plurality of industrial cameras, an image acquisition fixing part and an image acquisition control module, wherein the image acquisition fixing part is positioned above the frame main body part and is used for acquiring images of the front cover surface of the detected automobile;

the image processing analysis module is used for receiving the image transmitted by the image acquisition module and analyzing and obtaining the specific position of the front cover defect of the automobile;

and the driving module is used for driving the movable light source supporting part provided with the movable light source module to move above the vehicle cover placing part.

Preferably, the invention further provides a defect detection system for the automotive front cover finish paint, which is characterized in that,

the frame main body part comprises an upper rectangular supporting surface and a lower rectangular supporting surface which are formed by an upper pair of brackets and a lower pair of brackets which are parallel and intersected in the X-axis direction and the Y-axis direction;

the movable supporting part comprises a gantry frame, the gantry frame is fixed on the lower supporting surface of the frame main body part through a gantry frame connecting shaft below the gantry frame, at least two polished rods and a rotating shaft are arranged in the Y-axis direction in the frame main body part, the gantry frame connecting shaft is in transmission connection with the rotating shaft and supported by the two polished rods, a tank chain is arranged along a Y-axis support on one side of the lower supporting surface of the frame main body part, a first side of the gantry frame connecting shaft is in transmission connection with the tank chain, a second side of the gantry frame connecting shaft is connected with a Y-axis support on the other side of the lower supporting surface of the frame main body part, and the movable light source comprises a U-shaped strip-shaped light belt and is fixed on the gantry frame;

the driving module comprises a motor and a rotating shaft, the motor drives the rotating shaft to rotate, and the gantry frame is driven to move along the Y axial direction through a gantry frame connecting shaft which is in transmission with the motor.

Preferably, the invention further provides a defect detection system for the automotive front cover finish paint, which is characterized in that,

the movable supporting part further comprises a limiting module, the limiting module comprises a first sensor and a second sensor, the first sensor and the second sensor are respectively arranged at the end part of the tank chain, and the height of the limiting module is slightly lower than that of the gantry frame connecting shaft.

Preferably, the invention further provides a defect detection system for the automotive front cover finish paint, which is characterized in that,

the front part is placed to the bonnet and the bonnet is placed the rear part including the bonnet, the bonnet is placed the front portion and is constituteed the front holding surface including a plurality of crossbeams of at least a pair of parallel Z axle stand and tip, the bonnet is placed the rear part and is constituteed the back holding surface including a plurality of crossbeams of at least a pair of parallel Z axle stand and tip, the bonnet is placed the front portion two stand and is compared the bonnet is placed the rear portion two stand the interval is less, set up a plurality of locating pins on the back holding surface for fixed quilt bonnet.

Preferably, the invention further provides a defect detection system for the automotive front cover finish paint, which is characterized in that,

the detection support module is further provided with a stabilizing module, the stabilizing module comprises at least two connecting rods which are symmetrically fixed above the gantry-shaped frame, one end of each connecting rod is fixed on the frame main body part, the other end of each connecting rod is connected with the sliding module, and the sliding module moves along a Y-axis support of the upper support surface of the frame main body part in the detection process.

Preferably, the invention further provides a defect detection system for the automotive front cover finish paint, which is characterized in that,

the image acquisition module fixing part is arranged above the upper supporting surface of the frame main body part and comprises a plurality of parallel frames consisting of an X-axis cross beam and a Z-axis two-upright post, the cross beam is movably connected with the upright posts on two sides, and the upright posts are movably connected with a Y-axis bracket of the upper supporting surface of the frame main body part.

The invention also provides a method for detecting defects of the front cover paint of the automobile, which is characterized by further comprising the following steps of:

step one, initializing a system, namely setting a detected vehicle cover on the vehicle cover placing part;

step two, controlling the movable light source module to move at a constant speed along a Y axis, and starting the image acquisition module to acquire a plurality of sequence images of the vehicle cover;

thirdly, fusion processing is carried out on the sequence images, so that the transition of the image overlapping area is natural and smooth, the resolution ratio and the definition of the images are improved, and the fusion is as follows:

I _fusion ＝MAX(I ₁ ,I ₂ ,I ₃ …,I _n )

wherein I is _fusion Is a fused image, I _i The gray value of the acquired ith frame image is characterized in that the fused image represents the light band region closest to the mobile light source, so that the defect characteristic is enhanced, and the defect is more obvious;

extracting defect characteristics of the fused image based on a maximum gray threshold method, combining various basic characteristics of the image to form a comprehensive defect description characteristic vector, and detecting the defects of the front cover of the vehicle body, wherein the image processing method comprises the following steps:

I _fusion (x，y)≤Threshold(x，y)

wherein I is _fusion (x, y is the coordinate of the fused image, threshold (x, y), the Threshold value is set after the standard vehicle cover is calibrated, and when the coordinate Threshold value of the fused image is smaller than the set value, the fused image is considered to be a defect;

step five, after the defect characteristics are extracted, the specific positions of the defects on the vehicle cover are determined through characteristic points by combining the three-dimensional data of the front cover, and the defects are marked on the images by utilizing four-point perspective transformation, wherein a perspective transformation matrix is as follows:

wherein, (x, y) is original image coordinates, h11, h12, h21, h22, h31, h32 is rotation amount, h13, h23, h33 is translation amount, and the defect is positioned on the three-dimensional data diagram and finally displayed on the PC display.

Preferably, the invention also provides a method for detecting defects of the automotive front cover finish paint, which is characterized in that the system initialization comprises the following steps:

and calibrating each industrial camera in the image acquisition module, and adjusting exposure, focal length, acquisition frame number and delay parameters of the industrial camera.

Compared with the prior art, the invention has the following advantages:

firstly, the main body of the finish paint defect detection frame used by the invention has simple structure, can save industrial cost, and can detect finish paint defects of different types and sizes of automobile front covers by adjusting the spacing between different cross beams;

secondly, the invention uses a single movable light source to reduce the hardware cost of the light source, and meanwhile, the movable light source can effectively avoid the skidding risk of the automobile in the transportation process, and the detection stability is improved;

thirdly, the defects of the front cover paint of the automobile are detected based on computer vision, so that the problem of manual omission is effectively avoided, the detection precision is improved, meanwhile, the defect detection process is short, the detection time is effectively shortened, and the detection efficiency is improved;

fourth, the defect detection algorithm and the process used by the invention can be applied to the defect detection of the automobile front cover, are also applicable to the detection of other parts of the automobile and the whole automobile body, and have wide application range and strong applicability.

Drawings

Embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. Reference will now be made in detail to the preferred embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts. Furthermore, although terms used in the present disclosure are selected from publicly known and commonly used terms, some terms mentioned in the present disclosure may be selected by the applicant at his or her discretion, the detailed meanings of which are described in relevant parts of the description herein. Furthermore, it is required that the present disclosure is understood, not simply by the actual terms used but by the meaning of each term lying within.

The above and other objects, features and advantages of the present invention will become apparent to those skilled in the art from the following detailed description of the present invention with reference to the accompanying drawings.

FIG. 1 is a schematic diagram of an embodiment of a system and method for detecting defects in an automotive front cover paint;

FIG. 2 is a schematic diagram showing steps of an image analysis processing module in an automotive front cover paint defect detection system according to an embodiment;

FIG. 3 shows an image after image fusion processing in the image processing analysis processing module;

FIG. 4 is a diagram showing an image after defect detection processing in the image processing analysis processing module;

fig. 5 shows an image after defect localization processing in the image processing analysis processing module.

Reference numerals

1-rectangular hollow frame

2-front of roof

3-rear of roof positioning

4, 5-locating pin

6-8-camera placing cross beam

9-gantry frame

10-band of light

11-control screen

12――PLC

13-data acquisition instrument

14-mains switch

15-control box

16-gantry frame connecting shaft

17-tank chain

18 19-sensor

20-Motor

21-drive shaft

22 23-polished rod

24 25-connecting rod

26 27-pulleys

28-33-cameras

34――PC

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application may be applied to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

The relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present application unless it is specifically stated otherwise. Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description. Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but should be considered part of the specification where appropriate. In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

In the description of the present application, it should be understood that, where azimuth terms such as "front, rear, upper, lower, left, right", "transverse, vertical, horizontal", and "top, bottom", etc., indicate azimuth or positional relationships generally based on those shown in the drawings, only for convenience of description and simplification of the description, these azimuth terms do not indicate and imply that the apparatus or elements referred to must have a specific azimuth or be constructed and operated in a specific azimuth, and thus should not be construed as limiting the scope of protection of the present application; the orientation word "inner and outer" refers to inner and outer relative to the contour of the respective component itself.

Spatially relative terms, such as "above … …," "above … …," "upper surface at … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial location relative to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "above" or "over" other devices or structures would then be oriented "below" or "beneath" the other devices or structures. Thus, the exemplary term "above … …" may include both orientations of "above … …" and "below … …". The device may also be positioned in other different ways (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.

In addition, the terms "first", "second", etc. are used to define the components, and are merely for convenience of distinguishing the corresponding components, and unless otherwise stated, the terms have no special meaning, and thus should not be construed as limiting the scope of the present application. Furthermore, although terms used in the present application are selected from publicly known and commonly used terms, some terms mentioned in the specification of the present application may be selected by the applicant at his or her discretion, the detailed meanings of which are described in relevant parts of the description herein. Furthermore, it is required that the present application be understood, not simply by the actual terms used but by the meaning of each term lying within.

Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously. At the same time, other operations are added to or removed from these processes.

In order to make the technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

According to one or more embodiments, as shown in fig. 1, a machine vision-based automotive front cover paint defect detection system according to the present invention is shown, and a hardware part of the system includes a detection support module, a mobile light source module, an image acquisition module, and an image processing analysis module. Wherein the image acquisition module comprises an industrial camera.

The detection support module comprises a frame main body part, and in the illustrated preferred embodiment, the frame main body part is a hollow cuboid frame 1, the frame comprises an upper rectangular support surface and a lower rectangular support surface formed by two pairs of parallel crossed X-axis and Y-axis brackets, and only a lower pair of X-axis cross beams 101 and 102 are shown in fig. 1 to be provided with a front vehicle cover placement part 2 and a rear vehicle cover placement part 3 respectively. Specifically, the front hood-setting section 2 includes a pair of parallel Z-axis columns 201 to 202 and cross members 301 to 303 located above the columns 201 to 202 to form a front support surface, and the rear hood-setting section 3 is similarly structured to include a rear support surface, but has a wider pitch of the columns 203 to 204 than that of the columns 201 to 202.

In addition, two positioning pins 4 and 5 are arranged on the X-direction cross beam 304 of the rear supporting surface and used for fixing the detected vehicle cover, so that the detection stability is ensured.

The upper part of the cuboid frame 1 comprises an image acquisition module fixing part, and a plurality of upright posts and cross beams 6-8 are arranged on a pair of Y-axis cross beams 103 and 104 of the cuboid frame 1.

In the illustrated preferred embodiment, 6 upright posts and 3 pairs of cross beams form a camera placement area, and the height of the 3 cross beams for placing the camera is adjustable, namely, the two ends, connected with the upright posts, of the cross beams 6-8 for placing the camera can be adjusted up and down along the Z axis, so that the shooting range of the camera covers the whole front cover to be tested, and meanwhile, the detection precision is improved. In addition, the connection between the image acquisition module fixing portion and the rectangular parallelepiped frame 1 is also adjustable as required, that is, the entire fixing portion moves back and forth along the Y axis.

In the system, a tank chain 17 is horizontally arranged on the upper surface of a Y-axis one-side support at the bottom of a cuboid frame 1, one side of a gantry-shaped frame connecting shaft 16 is connected with the tank chain 17, the other side of the gantry-shaped frame connecting shaft is connected with another Y-axis support and is parallel to X-axis cross beams 101 and 102, and a gantry-shaped frame 9 is fixed on the bottom surface of the cuboid frame 1 through the connecting shaft 16 arranged below the gantry-shaped frame.

Two short upright posts (only two short upright posts 221 and 231 on the X axis at the front end are marked in the figure) are respectively arranged on two parallel X axis brackets below the hollow cuboid frame 1, one polish rod 22 and 23 is fixedly arranged on each pair of short upright posts, and the two polish rods 22 and 23 are contacted with the gantry frame connecting shaft 16 to play a supporting role.

The movable light source module comprises a light band 10 which is in a U-shaped strip shape and emits illumination light sources, and is fixedly arranged on a gantry-shaped frame 9. When the detection is carried out, the gantry-shaped frame 9 moves at a uniform speed along the Y axis through the driving mechanism, the light source moves to sweep the vehicle cover, the appearance of the whole vehicle cover is imaged, continuous illumination is ensured, and the camera is assisted to shoot.

The driving mechanism of the invention comprises a control screen 11, a PLC12, a motor 20 and a rotating shaft, wherein an operator controls the PLC12 through the control screen 11 and then controls the motor 20, the motor 20 is arranged between two short upright posts 221 and 231 above an X-axis rear side bracket below a cuboid hollow frame 1 of a bottom frame in a preferred embodiment, the motor 20 drives the rotating shaft 21 to move back and forth, and the motor rotating shaft 21 is contacted with a gantry frame connecting shaft 16 to drive the gantry frame 9 to move back and forth.

In addition, the gantry 9 is limited, and sensors 18 and 19 are also included. The sensors 18 and 19 are fixedly arranged at the inner side of the right Y-axis bracket below the rectangular hollow frame 1, the front and the rear of the Y-axis bracket are respectively provided with one sensor 18 and 19, the heights of the sensors 18 and 19 are slightly lower than the connecting shaft 16 below the gantry-shaped frame,

the gantry-shaped frame 9 moves at a constant speed along the Y-axis direction under the drive of the motor 20, so that the image acquisition is facilitated. The rotating speed of the motor 20 can be regulated by the control screen 11, and three gears of high speed, medium speed and low speed are shared, and the detecting efficiency and the detecting stability can be controlled by regulating the rotating speed of the motor. Since the height of the sensors 18, 19 is slightly lower than the connecting shaft 16 below the gantry, the movement is stopped immediately when the gantry 9 moves above the sensors 18, 19.

Meanwhile, in order to ensure the overall stability of the frame, the system is further provided with two connecting rods 24 and 25 symmetrically and fixedly arranged above the gantry-shaped frame 9, one ends of the connecting rods are fixed on the frame, the other sides of the connecting rods are connected with pulleys 26 and 27, and the pulleys 26 and 27 move along a Y-axis beam above the cuboid hollow frame 1 in the detection process so as to ensure the detection stability.

Wherein, control panel 11, PLC12, data acquisition instrument 13 are installed in control box 15, and control box 15 fixed mounting is in cuboid cavity frame 1 upper right side, still installs switch 14 in the box. The control screen 11 is electrically connected with the power switch 14, the sensors 18 and 19, the optical band 10 and the motor 20.

In the preferred embodiment of fig. 1, 6 industrial cameras 28-33 are illustrated. When the light source moves, the cameras synchronously and uninterruptedly shoot, the camera array is arranged, the lens faces downwards to the car cover, the shooting range of the cameras covers the whole car cover, meanwhile, the two cameras 30 and 31 in the middle are used for supplementing positions, the area shielded by the gantry frame is shot, the detection area covers the whole car cover, no blind area is left, and the shooting precision is improved. The data acquisition instrument 13 is used for acquiring and storing pictures shot by the camera and uploading the pictures to a database in the PC34, so that subsequent image processing and analysis are facilitated.

Smooth running of the light band is realized by two positioning wheels.

Referring to fig. 2, a flowchart of the method for detecting defects of automotive front cover paint according to the present invention is shown, and the following steps are described in detail in conjunction with the flowchart: s1, initializing a system;

the initialization process comprises the steps of opening a power switch in a control box, placing a vehicle cover in a detection area, fixing the vehicle cover through a locating pin, calibrating each camera for the first time, and adjusting the exposure and focal length of the camera to enable the photo shot by each camera to be clear and complete;

the data acquisition instrument is connected with the PC and is used for setting camera parameters including exposure time, acquisition frame number and delay;

step S2, clicking a control screen to enable the movable light source to move at a constant speed along the Y axis, and automatically stopping moving when the movable light source moves above the sensors 18 and 19;

when the mobile light source starts to move, the PC end image acquisition program runs, and each camera acquires 150 Zhang Zuoyou images in cooperation with the camera frame rate;

step S3, image fusion is carried out, namely, the shot sequence images are fused through a visual detection algorithm, so that the transition of the image overlapping area is natural and smooth, the resolution ratio and the definition of the images are improved, and the calculation method comprises the following steps:

I _fusion ＝MAX(I ₁ ,I ₂ ,I ₃ …,I _n ) (1)

wherein I is _fusion Is a fused image, I _i The gray value of the acquired ith frame image is shown in the fused image, and the light band area closest to the light source is shown in the fused image, so that the defect characteristics are enhanced, and the defects are more obvious.

It should be noted that, algorithms for detecting single defects are different, then 150 images are detected, and the detection of the fusion image may be repeated;

step S4, performing defect detection, namely extracting defect characteristics of the fused image based on a maximum gray threshold method through an image processing algorithm, combining various basic characteristics of the image to form comprehensive defect description characteristic vectors, and detecting defects of a front cover of the vehicle body, wherein the calculation method comprises the following steps:

I _fusion (x，y)≤Threshold(x，y) (2)

wherein I is _fusion (x, y) fusing image coordinates, threshold (x, y), calibrating a standard vehicle cover, and setting a Threshold value, wherein when the fused image coordinate Threshold value is smaller than a set value, the defect is considered;

and then detecting the image edge by using a Sobel operator: the Sobel operator acts as: the edge detection is mainly applied to the processing of some data information, extracts a wanted target, eliminates some irrelevant interference and useless information, and acquires more focused information through less data information.

Firstly, carrying out convolution processing on image pixels to respectively obtain horizontal and vertical brightness difference approximate values, wherein the formula is as follows:

wherein G is _x The gray value of the image detected by the transverse edge is Gy, the gray value of the image detected by the longitudinal edge is Gy, and A is the original image.

Calculating the gray value of a certain pixel point:

gradient direction:

the gradient G is compared with a set threshold value, and if it is greater than the threshold value, the point (x, y) is an edge point.

And by combining the contour detection result, the detection precision is improved, the contour detection can be performed based on the binarized image, and the principle of contour detection is to find only the outermost boundary.

Image stitching, namely stitching the detection result graphs of the single cameras, and extracting characteristic points among different images through a SURF algorithm; calculating homography moment H; carrying out overlapping region fusion through a homography matrix H; and performing special treatment on the overlapping boundary to realize image stitching.

Step S5, defect positioning is carried out, namely after the defect characteristics are extracted, the specific position of the defect on the vehicle cover is determined through characteristic points by combining with three-dimensional data of the front cover, and the defect is marked on an image by utilizing four-point perspective transformation, wherein a perspective transformation matrix is as follows:

wherein, (x, y) is original image coordinates, h11, h12, h21, h22, h31, h32 are rotation amounts, h13, h23 and h33 are translation amounts, and defects are positioned on the three-dimensional data diagram and finally displayed on a PC display.

It should be noted that, in this embodiment, the controller is a PLC controller of siemens, and the camera is a common industrial camera.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the above disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations of the present application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.

Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.

Some aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. The processor may be one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital signal processing devices (DAPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or a combination thereof. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media. For example, computer-readable media can include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, tape … …), optical disk (e.g., compact disk CD, digital versatile disk DVD … …), smart card, and flash memory devices (e.g., card, stick, key drive … …).

The computer readable medium may comprise a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer readable medium can be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer readable medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or the like, or a combination of any of the foregoing.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the above disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations of the present application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.

Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.

Likewise, it should be noted that in order to simplify the presentation disclosed herein and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the subject application. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

While the present application has been described with reference to the present specific embodiments, those of ordinary skill in the art will recognize that the above embodiments are for illustrative purposes only, and that various equivalent changes or substitutions can be made without departing from the spirit of the present application, and therefore, all changes and modifications to the embodiments described above are intended to be within the scope of the claims of the present application.

Claims (8)

1. An automotive front cover paint defect detection system, the system comprising:

the detection support module comprises a frame main body part, wherein the frame main body part is provided with a vehicle cover placing part for supporting the front cover surface of the detected vehicle;

the image acquisition module comprises a plurality of industrial cameras, an image acquisition fixing part and an image acquisition control module, wherein the image acquisition fixing part is positioned above the frame main body part and is used for acquiring images of the front cover surface of the detected automobile;

the image processing analysis module is used for receiving the image transmitted by the image acquisition module and analyzing and obtaining the specific position of the front cover defect of the automobile;

and the driving module is used for driving the movable light source supporting part provided with the movable light source module to move above the vehicle cover placing part.

2. The automotive front cover paint defect detection system of claim 1, wherein,

the frame main body part comprises an upper rectangular supporting surface and a lower rectangular supporting surface which are formed by an upper pair of brackets and a lower pair of brackets which are parallel and intersected in the X-axis direction and the Y-axis direction;

the movable supporting part comprises a gantry frame, the gantry frame is fixed on the lower supporting surface of the frame main body part through a gantry frame connecting shaft below the gantry frame, at least two polished rods and a rotating shaft are arranged in the Y-axis direction in the frame main body part, the gantry frame connecting shaft is in transmission connection with the rotating shaft and supported by the two polished rods, a tank chain is arranged along a Y-axis support on one side of the lower supporting surface of the frame main body part, a first side of the gantry frame connecting shaft is in transmission connection with the tank chain, a second side of the gantry frame connecting shaft is connected with a Y-axis support on the other side of the lower supporting surface of the frame main body part, and the movable light source comprises a U-shaped strip-shaped light belt and is fixed on the gantry frame;

the driving module comprises a motor and a rotating shaft, the motor drives the rotating shaft to rotate, and the gantry frame is driven to move along the Y axial direction through a gantry frame connecting shaft which is in transmission with the motor.

3. A vehicle front cover paint defect detection system according to claim 2, wherein,

the movable supporting part further comprises a limiting module, the limiting module comprises a first sensor and a second sensor, the first sensor and the second sensor are respectively arranged at the end part of the tank chain, and the height of the limiting module is slightly lower than that of the gantry frame connecting shaft.

4. A vehicle front cover paint defect detection system according to claim 3, wherein,

the front part is placed to the bonnet and the bonnet is placed the rear part including the bonnet, the bonnet is placed the front portion and is constituteed the front holding surface including a plurality of crossbeams of at least a pair of parallel Z axle stand and tip, the bonnet is placed the rear part and is constituteed the back holding surface including a plurality of crossbeams of at least a pair of parallel Z axle stand and tip, the bonnet is placed the front portion two stand and is compared the bonnet is placed the rear portion two stand the interval is less, set up a plurality of locating pins on the back holding surface for fixed quilt bonnet.

5. The automotive front cover paint defect detection system of claim 4, wherein,

the detection support module is further provided with a stabilizing module, the stabilizing module comprises at least two connecting rods which are symmetrically fixed above the gantry-shaped frame, one end of each connecting rod is fixed on the frame main body part, the other end of each connecting rod is connected with the sliding module, and the sliding module moves along a Y-axis support of the upper support surface of the frame main body part in the detection process.

6. The automotive front cover paint defect detection system of claim 5, wherein,

the image acquisition module fixing part is arranged above the upper supporting surface of the frame main body part and comprises a plurality of parallel frames consisting of an X-axis cross beam and a Z-axis two-upright post, the cross beam is movably connected with the upright posts on two sides, and the upright posts are movably connected with a Y-axis bracket of the upper supporting surface of the frame main body part.

7. A method for detecting defects in automotive front cover paint, applying the detection system according to any one of claims 1 to 6, characterized in that the detection method further comprises:

step one, initializing a system, namely setting a detected vehicle cover on the vehicle cover placing part;

step two, controlling the movable light source module to move at a constant speed along a Y axis, and starting the image acquisition module to acquire a plurality of sequence images of the vehicle cover;

thirdly, fusion processing is carried out on the sequence images, so that the transition of the image overlapping area is natural and smooth, the resolution ratio and the definition of the images are improved, and the fusion is as follows:

I _fusion ＝MAX(I ₁ ,I ₂ ,I ₃ …,I _n )

wherein I is _fusion Is a fused image, I _i The gray value of the acquired ith frame image is shown as the light band area closest to the moving light source after fusion, so that the defect characteristic is enhanced, and the defect is more obvious；

Extracting defect characteristics of the fused image based on a maximum gray threshold method, combining various basic characteristics of the image to form a comprehensive defect description characteristic vector, and detecting the defects of the front cover of the vehicle body, wherein the image processing method comprises the following steps:

I _fusion (x，y)≤Threshold(x，y)

wherein I is _fusion (x, y) is a fused image coordinate, threshold (x, y), a Threshold value is set after the standard vehicle cover is calibrated, and when the fused image coordinate Threshold value is smaller than a set value, the fused image coordinate is considered to be a defect;

step five, after the defect characteristics are extracted, the specific positions of the defects on the vehicle cover are determined through characteristic points by combining the three-dimensional data of the front cover, and the defects are marked on the images by utilizing four-point perspective transformation, wherein a perspective transformation matrix is as follows:

wherein, (x, y) is original image coordinates, h11, h12, h21, h22, h31, h32 is rotation amount, h13, h23, h33 is translation amount, and the defect is positioned on the three-dimensional data diagram and finally displayed on the PC display.

8. The method for detecting defects in an automotive front cover paint according to claim 7, wherein the system initialization includes:

and calibrating each industrial camera in the image acquisition module, and adjusting exposure, focal length, acquisition frame number and delay parameters of the industrial camera.

Images