CN109682309B - Intelligent measuring device and method for black crystal panel parameters based on machine vision - Google Patents
Intelligent measuring device and method for black crystal panel parameters based on machine vision Download PDFInfo
- Publication number
- CN109682309B CN109682309B CN201811571439.4A CN201811571439A CN109682309B CN 109682309 B CN109682309 B CN 109682309B CN 201811571439 A CN201811571439 A CN 201811571439A CN 109682309 B CN109682309 B CN 109682309B
- Authority
- CN
- China
- Prior art keywords
- camera
- crystal panel
- black crystal
- black
- straight line
- 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.)
- Active
Links
- 239000011011 black crystal Substances 0.000 title claims abstract description 140
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000005259 measurement Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000000691 measurement method Methods 0.000 claims description 13
- 230000000007 visual effect Effects 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 6
- 239000004973 liquid crystal related substance Substances 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012937 correction Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000007688 edging Methods 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides an intelligent measuring device for parameters of a black crystal panel machine based on machine vision, which relates to the technical field of machine vision, and adopts four cameras, wherein a camera fixing device adopts a movable type, and the positions of a No. 1 camera and a No. 3 camera can be adjusted according to the type of a black crystal panel input by an interface so that one camera is directly above the upper left corner and the lower right corner of the black crystal panel, thereby eliminating errors caused by uneven chamfering and inconsistent thickness of the black crystal panel. The invention provides an intelligent measuring method for parameters of a black crystal panel on the basis of machine vision, which is used for drawing a straight line and a circle by using a least square method after Hough straight line detection in the process of processing pictures so as to solve the problem that the black crystal panel is placed incorrectly in a production line, and correct the black crystal panel, thereby obtaining accurate values and greatly reducing errors.
Description
Technical Field
The invention belongs to the technical field of machine vision, and is mainly used for industrial automatic detection, in particular relates to a machine vision intelligent measuring device and method for accurately measuring parameters (length, width, chamfer angle and diagonal line) of a black crystal panel.
Background
Today, the domestic manufacturing industry level is gradually improved and the market competition is continuously increased, enterprises and clients attach more and more importance to the quality of products, 100% detection of products can gradually replace sampling detection to meet the control of the quality of products, the Chinese living standard is increasingly increased, so that people can enjoy lives more, and the electromagnetic ovens, fireplaces, smoke ventilators and the like can bring more convenience to lives of people and do not harm to the environment, so that the electromagnetic ovens, the fireplaces, the smoke ventilators and the like are widely applied.
Black glass on the surface of induction cookers, range hoods, fireplaces, etc. is a so-called black crystal panel. The manufacturing of these home appliances is not limited to the manufacturing of black crystal panels, but is important in standardization and aesthetic properties while considering safety. The black crystal panels are of many kinds, and different customers have different requirements on the mechanical parameters of the black crystal panels. The existing detection method of the black crystal panel cannot detect all, only a sampling detection method can be adopted, manual measurement is used, and the measurement result is inaccurate and low in efficiency.
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides an intelligent measuring device and method for black crystal panel parameters based on machine vision; the non-contact accurate measurement of mechanical parameters of black crystal panels with various specifications can be realized, the measurement accuracy can reach 0.01mm, and the specifications of the measurement panels are 100 x 100 to 400 x 600 (unit: mm); by adopting a non-contact visual measurement technology, the mechanical parameters of the black crystal panel are dynamically measured on a production line, the accurate measurement of the black crystal panel can be realized when the speed of a conveyor belt reaches 1m/s, the measurement time is very short, only 2s or even shorter is needed for measuring one black crystal panel, and the labor is fully saved; 100% detection can be realized, and the method has the advantages of small error and short time consumption.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme:
the intelligent measuring device for the parameters of the black crystal panel board based on the machine vision comprises a camera fixing device, an image acquisition device, an image measuring device and a panel conveying platform; the image acquisition device is arranged above the panel conveying platform and is fixed through the camera fixing device; the image measuring device is connected with the image acquisition device and is used for receiving the image transmitted by the image acquisition device, processing the image on the industrial personal computer, finally transmitting a qualified signal to the alarm, and alarming if the qualified signal is unqualified.
Further, the panel conveying platform comprises a bottom frame, a conveying belt, a liquid crystal display, a display fixing frame, an electric box, a foot margin and a foot margin wheel; the conveyer belt is located the top of chassis 6, lower margin and lower margin wheel are supporting to exist, and six sets altogether are located the below of chassis and play the supporting role, the electric box is located the inside of chassis, the display mount is fixed on the section bar frame of conveyer belt top, fixes liquid crystal display.
Further, the camera fixing device comprises a section bar frame, an L-shaped bracket, a camera connecting piece, a sliding rail and a sliding block; the section bar frame is fixed on the left and right sides of the conveyor belt, the L-shaped support is fixed on the section bar frame, the slide rail and the slide block are one set, the section bar frame is fixed on two arms of the L-shaped support, the camera connecting piece is arranged above the slide block, and the industrial camera is fixed on the slide block through the camera connecting piece.
Further, the image acquisition device comprises three 890 ten thousand industrial cameras, one 230 ten thousand industrial cameras, 4 light sources and a light source fixing frame; four cameras, wherein the No. 1 890 ten thousand industrial cameras are fixed on one arm of an L-shaped bracket on the right side of the advancing direction of a conveyor belt, and the other three cameras are fixed on the other arm of the L-shaped bracket, wherein the No. 4 230 ten thousand industrial cameras are positioned between the No. 2 890 ten thousand industrial cameras and the No. 3 890 ten thousand industrial cameras and are used for identifying the arrival and departure of a board; the four light sources are fixed around the section bar frame through the light source fixing frame.
Further, the industrial camera comprises a camera power socket, a network cable socket, a camera body, lens exposure, a lens and a lens focal length; the camera power socket and the net wire socket are respectively arranged at the upper part of the camera body, and the lower part of the camera body is sequentially provided with a lens exposure, a lens and a lens focal length.
Further, the conveyor belt comprises a driving wheel, a belt and a driven wheel, wherein the driving wheel and the driven wheel are arranged at two ends of the conveyor belt, and the driving wheel and the driven wheel are connected through the belt.
The intelligent measurement method for the parameters of the black crystal panel based on the machine vision comprises the following steps:
s1, shooting a required picture;
the No. 1 and No. 3 cameras are adjusted to proper positions through mechanical parameters input by an operation interface, the cameras are guaranteed to vertically shoot four corners of the black crystal panel, the black crystal panel moves along the direction of the conveying belt, the No. 4 camera starts to trigger the No. 1,2 and No. 3 cameras to start shooting after recognizing that the upper bottom edge of the black crystal panel enters about 600 pixels of the visual field range, and shooting is triggered again when the lower bottom edge of the black crystal panel leaves the visual field until 600 pixels leave the visual field, and then the pictures are processed;
s2, processing the shot picture;
s2.1, gaussian filtering is carried out;
the two-dimensional gaussian function is:
the squares of x and y respectively represent the distances between other pixels in the neighborhood and the central pixel in the neighborhood, sigma represents the standard deviation, a 5*5 Gaussian filter template is generated, and the central position of the template is taken as the origin of coordinates for sampling; determining the coordinates of the template at each position, and taking the coordinates into a Gaussian function, wherein the obtained value is the coefficient of the template; for a window template size of (2k+1) × (2k+1), the calculation formula for each element value in the template is as follows:
the coefficients obtained by normalization are:i.e., the inverse of the template coefficient sum;
s2.2, binarizing the image, and then carrying out Hough straight line detection on the binarized image;
in the straight line detection task, namely, the straight line in the image space corresponds to the point in the polar coordinate space one by utilizing the duality of the point and the line, and the straight line in the polar coordinate space corresponds to the point in the image space one by one; each line in image space is represented in polar coordinate space corresponding to a single point; any part of line segments on the straight line in the image space correspond to the same point in the polar coordinate space, the straight line detection problem in the image space is converted into the point detection problem in the polar coordinate space, and the straight line detection task is completed by searching a peak value in the polar coordinate space;
s2.3, precisely fitting a straight line by using a least square method;
drawing a straight line detected by the Hough straight line on another graph, traversing the graph without considering the overlapped straight lines, and finally obtaining two straight lines, wherein the overlapped straight lines refer to that the difference of rho of the two straight lines in the same direction is smaller than 40 pixels or the difference of theta of the two straight lines is smaller than 0.5 degrees, namely, the two straight lines are considered to be overlapped;
s2.4, solving intersection points and included angles of the two straight lines, defining a fillet area and fitting a fillet by using a least square method;
calculating the intersection point and the included angle of two straight lines according to the two straight line equations obtained in the previous step, wherein the two straight line equations are y=k×x+b respectively 1 And y=l x+b 2 The intersection point coordinate of the two straight lines isThe included angle theta of the two straight lines is obtained to satisfy the following conditions: />Obtaining the coordinates of the intersection points and the size of the included angles, and obtaining the length, the width and the diagonal line of the black crystal panel; limiting the range of fitting the round angle according to the coordinates of the intersection point, fitting the round angle in the range within the intersection point, and discarding the exceeding edge points;
s3, calculating the size of the black crystal panel:
s3.1, calculating lengths of the upper bottom edge and the right side edge of the black crystal panel: when the camera performs first trigger photographing, the camera 1 photographs the upper left corner of the black crystal panel, the camera 2 photographs the upper right corner of the black crystal panel, the camera 3 photographs the lower right corner of the black crystal panel, the length of the upper bottom edge of the black crystal panel is calculated by the intersection point of two straight lines obtained by the images photographed by the camera 1 and the camera 2, and the calculation formula is omega 1 ＝(x 1 +x 2 )*ξ+L 12 The method comprises the steps of carrying out a first treatment on the surface of the Wherein omega 1 Is the length of the upper bottom edge, x 1 Is the abscissa, x of the intersection point coordinates of the fitting straight line of the image shot by the camera No. 1 2 Is the abscissa of the intersection point coordinates of the fitting straight line of the image shot by the No. 2 camera, and xi is the proportion, L 12 Calibrating cameras 1 and 2; the length of the right side edge of the black crystal panel is calculated by the intersection point of two straight lines obtained by the images shot by No. 2 and No. 3, and the calculation formula is l 1 ＝(y 2 +x 3 )*ξ+L 23 The method comprises the steps of carrying out a first treatment on the surface of the Wherein l 1 Is the length of the right side, y 2 Is the ordinate, x of the intersection point coordinates of the fitting straight line of the image shot by the No. 2 camera 3 Is the abscissa of the intersection point coordinates of the fitting straight line of the image shot by the No. 3 camera, and xi is the proportion, L 23 Calibrating cameras No. 2 and No. 3; when the camera performs triggering photographing for the second time, the camera 1 shoots the lower left corner of the black crystal panel, the camera 2 shoots the lower right corner of the black crystal panel, and the length of the lower bottom edge is calculated;
s3.2, calculating the length of the diagonal line of the black crystal panel: knowing that three sides of the black crystal panel and each angle fit straight angles, calculating the length of the diagonal line, and according to the angle alpha of the two straight lines fitted by the upper right corner of the black crystal panel when shooting for the first time, the hypotenuse of the triangle formed by the upper base and the right side is the diagonal line to satisfyWherein l 1 Is the length of the right side edge omega 1 Is the length of the upper bottom edge, D R Is the diagonal length; the other diagonal length is obtained from the right side and the lower bottom, and the calculation formula is +.>Wherein l 1 Is the length of the right side edge omega 2 Is the length of the lower bottom edge, D L The length of the diagonal line is beta, and the right lower corner of the black crystal panel is an included angle of a straight line;
s3.3, calculating the length of the left side edge of the black crystal panel: according to two known diagonal lines, the length of the left side edge of the black crystal panel is calculated twice, and then the length of the left side edge which is wanted by the user is calculated by averaging; the included angle is calculated according to the straight lines fitted by the four angles, the included angle of the straight lines fitted by the upper left corner of the known black crystal panel is gamma, the included angle of the straight lines fitted by the lower left corner of the black crystal panel is phi, and l can be derived according to a formula 2 And then averaging:
the method can obtain:
all mechanical parameters of the black crystal panel can be obtained.
Further, when the picture is taken in step S1, the cameras No. 1 and No. 3 are movable, when the picture is taken for the first time, the camera No. 1 takes the upper left corner of the black crystal panel, the camera No. 2 takes the upper right corner of the black crystal panel, the camera No. 3 takes the lower right corner of the black crystal panel, thereby obtaining the picture of three corners of the black crystal panel, when the picture is taken for the second time, the camera No. 1 takes the lower left corner, the camera No. 2 takes the lower right corner, and the camera No. 3 does not take the picture, thereby obtaining the picture of the fourth corner.
(III) beneficial effects
The invention has the beneficial effects that: the invention adopts four cameras, one of which is used for receiving signals to trigger the other three cameras, fully utilizes the function of a production line, completes shooting in the moving process of the black crystal panel, and saves one camera by using L-shaped placement, thereby saving the cost; according to the black crystal panel measuring device, the camera fixing device is movable, and the positions of the No. 1 camera and the No. 3 camera can be adjusted according to the type of the black crystal panel input by the interface so that one of the No. 1 camera and the No. 3 camera is directly above the upper left corner and the lower right corner of the black crystal panel, so that errors caused by uneven chamfering and inconsistent thickness of the black crystal panel are eliminated; in the process of processing the picture, the invention uses the Hough straight line detection and then carries out the least square method to draw the straight line and the circle, so as to solve the problem that the black crystal panel enters the assembly line to be placed incorrectly, correct the black crystal panel, thereby obtaining the accurate value and greatly reducing the error; the invention can realize non-contact accurate measurement of mechanical parameters of black crystal panels with various specifications, the measurement precision can reach 0.01mm, the specification of the measurement panel is 100 x 100 to 400 x 600 (unit: mm), the mechanical parameters of the black crystal panels can be dynamically measured on a production line, the accurate measurement of the black crystal panels can be realized when the speed of a conveyor belt reaches 1m/s, the measurement time is short, the manpower is fully saved, 100% detection can be realized, and the invention has the advantages of small error and short time consumption.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a measuring device according to the present invention;
FIG. 2 is a schematic diagram of an industrial camera structure;
FIG. 3 is a schematic view of a camera connection with an industrial camera;
FIG. 4 is a schematic diagram of a conveyor belt configuration;
FIG. 5 is a flow chart of the measurement method of the present invention;
FIG. 6 is a schematic diagram of a coordinate transformation;
fig. 7 is a schematic view of 8 polar axes.
Reference numerals illustrate:
1. a section bar frame; 2. a camera connection; 3. an industrial camera; 4. a light source; 5. a conveyor belt; 6. a chassis; 7. a foot margin; 8. floor casters; 9. an electric box; 10. a light source fixing frame; 11. A tripod; 12. an L-shaped bracket; 31. a camera power socket; 32. a network cable jack; 33. a camera body; 34. exposing a lens; 35. a lens; 36. a lens focal length; 51. a driving wheel; 52. A belt; 53. and (3) a driven wheel.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an intelligent measuring device for parameters of a black crystal panel based on machine vision comprises a camera fixing device, an image acquisition device, an image measuring device and a panel conveying platform; the image acquisition device is arranged above the panel conveying platform and is fixed through the camera fixing device; the image measuring device is connected with the image acquisition device and is used for receiving the image transmitted by the image acquisition device, processing the image on the industrial personal computer, finally transmitting a qualified signal to the alarm, and alarming if the qualified signal is unqualified.
The camera fixing device comprises a section bar frame 1, an L-shaped bracket 12, a camera connecting piece 2, a conveyor belt 5, a sliding rail and a sliding block; the profile frame 1 is fixed on the left and right sides of the conveyor belt 5, and the height is 70cm; the L-shaped bracket 12 is fixed on the section bar frame 1 and is 60cm away from the conveyor belt; the sliding rail and the sliding block are one set, are fixed on two arms of the L-shaped bracket 12, the camera connecting piece 2 is arranged above the sliding block, and the industrial camera 3 is fixed on the sliding block through the camera connecting piece 2 and can move along with the sliding rail.
The image acquisition device comprises three 890 ten thousand industrial cameras, one 230 ten thousand industrial cameras, 4 light sources 4 and a light source fixing frame 10; four cameras, wherein the No. 1 890 ten thousand industrial cameras are fixed on one arm of an L-shaped bracket on the right side of the advancing direction of the conveyor belt 5, and the other three cameras are fixed on the other arm of the L-shaped bracket, wherein the No. 4 230 ten thousand industrial cameras are positioned between the No. 2 890 ten thousand industrial cameras and the No. 3 890 ten thousand industrial cameras and are used for identifying the arrival and departure of a board; four light sources 4 are fixed on the periphery of the section bar frame through a light source fixing frame 10 and are positioned 5cm away from the conveyor belt.
The panel conveying platform comprises a chassis 6, a conveying belt 5, a liquid crystal display, a display fixing frame, an electric box 9, a foot 7 and ground casters 8; the conveyer belt 5 is located the top of chassis 6, the lower margin 7 and lower margin wheel 8 are supporting to exist, and six sets altogether are located the below of chassis 6 and play the supporting role, electrical box 9 is located the inside of chassis 6, can deposit public machine, power etc. the display mount is fixed on the section bar frame of conveyer belt top, fixes liquid crystal display. A tripod 11 is arranged between the section bar frame 1 and the panel conveying platform.
Referring to fig. 2 and 3, the industrial camera includes a camera power socket 31, a net wire socket 32, a camera body 33, a lens exposure 34, a lens 35, and a lens focal length 36; the camera power jack 31 and the net wire jack 32 are respectively provided on the upper part of the camera body 33, and the lens exposure 34, the lens 35 and the lens focal length 36 are sequentially installed on the lower part of the camera body 33.
Referring to fig. 4, the conveyor belt 5 includes a driving pulley 51, a belt 52, and a driven pulley 53, the driving pulley 51 and the driven pulley 53 are mounted at two ends of the conveyor belt, and the driving pulley 51 and the driven pulley 53 are connected by the belt 52.
During specific work, the model of the plate is input at the operation interface, the motor drives the sliding block to move, namely the movement of the control camera, the No. 2 camera is fixed in position, the No. 4 camera is adjacent to the No. 2 camera, and the positions of the No. 1 camera and the No. 3 camera are adjusted according to the size of the black crystal panel, so that the plate is vertically shot by the camera as much as possible, and the influence caused by inconsistent edging and thickness of the black crystal panel is eliminated.
The triggering mode adopted by the invention is external triggering, then four cameras trigger each other, namely the No. 4 camera is in a continuous mode, the No. 1, the No. 2 and the No. 3 cameras are in a triggering mode, the No. 2 camera is immediately triggered to take a picture when the No. 4 camera recognizes that a plate comes, the No. 2 camera is triggered to take a picture again, the No. 1 camera is triggered to take a picture again, and the No. 1 camera is triggered to take a picture again. The triggering mode can ensure simultaneous triggering, has better external triggering effect compared with a sensor, and avoids the defect of serious error in the process of sensor identification caused by edging of a black crystal panel.
Referring to fig. 5, the intelligent measurement method for the parameters of the black crystal panel based on machine vision comprises the following steps:
s1, shooting a required picture;
through the mechanical parameters input at the operation interface, the No. 1 and No. 3 cameras are adjusted to the proper positions, the cameras are guaranteed to shoot the four corners of the black crystal panel vertically, the black crystal panel moves along the direction of the conveying belt, the No. 4 camera starts to trigger the No. 1,2 and No. 3 cameras to shoot after recognizing that the upper bottom edge of the black crystal panel enters the visual field range by about 600 pixels, and shooting is triggered again when the lower bottom edge of the black crystal panel leaves the visual field and 600 pixels are left, and then the pictures are processed.
The No. 1 camera and the No. 3 camera are movable, the No. 1 camera shoots the upper left corner of the black crystal panel when shooting for the first time, the No. 2 camera shoots the upper right corner of the black crystal panel, the No. 3 camera shoots the lower right corner of the black crystal panel, so that pictures of three corners of the black crystal panel can be obtained, the No. 1 camera shoots the lower left corner when shooting for the second time, the No. 2 camera shoots the lower right corner, the No. 3 camera does not shoot, pictures of the fourth corner are obtained, and specific numerical values of the length, the width, the diagonal and the round angle of the black crystal panel can be obtained through processing calculation by obtaining information of the four corners.
S2, processing the shot picture; the method comprises the following steps:
s2.1, gaussian filtering is carried out;
the two-dimensional gaussian function is:
the squares of x and y respectively represent the distances between other pixels in the neighborhood and the central pixel in the neighborhood, sigma represents the standard deviation, a 5*5 Gaussian filter template is generated, and the central position of the template is taken as the origin of coordinates for sampling; the coordinates of the template at each location are shown below, with the i-axis (the same location as the x-axis) horizontally to the right and the j-axis (the opposite direction to the y-axis) vertically downward:
| (-2,2) | (-1,2) | (0,2) | (1,2) | (2,2) |
| (-2,1) | (-1,1) | (0,1) | (1,1) | (2,1) |
| (-2,0) | (-1,0) | (0,0) | (1,0) | (2,0) |
| (-2,-1) | (-1,-1) | (0,-1) | (1,-1) | (2,-1) |
| (-2,-2) | (-1,-2) | (0,-2) | (1,-2) | (2,-2) |
thus, the coordinates of each position are brought into a Gaussian function, and the obtained value is the coefficient of the template; for a window template size of (2k+1) × (2k+1), the calculation formula for each element value in the template is as follows:
the template used herein is integer, that is, normalized after calculation using the above formula, and the normalized coefficient is:i.e., the inverse of the template coefficient sum;
s2.2, binarizing the image, and then carrying out Hough straight line detection on the binarized image;
the basic principle of hough straight line detection is that the dual of points and lines is utilized, and in the straight line detection task, namely, the straight line in the image space corresponds to the points in the polar coordinate space one by one, and the straight line in the polar coordinate space corresponds to the points in the image space one by one. This means that two very useful conclusions can be drawn: each line in image space is represented in polar coordinate space corresponding to a single point; any part of line segments on the straight line in the image space correspond to the same point in the polar coordinate space, so that the Hough straight line detection algorithm converts the straight line detection problem in the image space into the point detection problem in the polar coordinate space, and the straight line detection task is completed by searching a peak value in the polar coordinate space.
Such as: for a straight line y=kx+b, it may be expressed as ρ=x×cos θ+y×sin θ in polar coordinates, that is, the straight line y=kx+b in rectangular coordinates may be expressed as (ρ, θ) in polar coordinates, that is, each point (ρ, θ) of the polar coordinates corresponds to a straight line of rectangular coordinates, or a point of rectangular coordinates corresponds to a curve in polar coordinates. If the pixels in the image form a straight line, the curves corresponding to the pixel coordinate values (x, y) in the polar coordinates are intersected at one point, so that the straight line can be determined by only converting all the pixel points (coordinate values) in the image into the curves in the polar coordinates and detecting the intersection points of the curves in the polar coordinates.
In practice, the number of lines (i.e. a limited number of directions) must be defined to be able to calculate. As shown in fig. 6, the direction θ of the straight line is discretized into a finite number of equally spaced discrete values, and the parameter ρ is correspondingly discretized into a finite number of values, so that the parameter space is not continuous any more, but is discretized into individual equal-size grid cells. Transforming the coordinate value of each pixel point in the image space (rectangular coordinate system) into the parameter space (polar coordinate system)The value will fall within a certain grid, incrementing the accumulation counter for that grid cell by 1. After all pixels in the image space are subjected to Hough transform, the grid cells are inspected, and the grid with the largest count value is accumulated, and the coordinate value (ρ 0 ,θ 0 ) Corresponds to the straight line found in the image space. That is, if the accumulated value is greater than the threshold value, a straight line is considered here.
S2.3, precisely fitting a straight line by using a least square method;
drawing a straight line detected by the Hough straight line on another graph, traversing the graph without considering the overlapped straight lines, and finally obtaining two straight lines, wherein the overlapped straight lines refer to that the difference of rho of the two straight lines in the same direction is smaller than 40 pixels or the difference of theta of the two straight lines is smaller than 0.5 degree, and the two straight lines are considered to be overlapped.
However, in practice, the straight line found by hough straight line detection is not accurate, taking a straight line obtained as an example: the obtained Hough straight line is rho=xcos theta+y sin theta, the drawn straight line is more accurate, a plurality of pixels are moved on two sides of the straight line, and then a straight line is drawn, the straight line can be expressed as rho+/-mu=xcos theta+y sin theta, wherein mu represents the plurality of moved pixels, then all points are traversed in the channel, fitting can be obtained through a least square method, and a more accurate fitting straight line can be obtainedAnd then x is used for representing y. However, the straight line found in this way is subject to the influence of the environment and is subject to errors, and the measurement is not accurate enough under the condition that the black crystal panel obliquely enters the conveyor belt, and the error is not within + -0.1 mm, so that calibration is set, taking the fitting of the upper bottom edge as an example (the inclination angle of the default panel does not need to be larger than 45 DEG when entering the conveyor belt), even if the upper bottom edge is inclined, the straight line is still considered to be the upper bottom edge, r and theta are returned during Hough straight line fitting in opencv,r will have a positive and negative value, polar angle +.>The time pole diameter r is positive, +.>The time pole diameter r is a negative value. As shown in fig. 7, the 8 wires are all polar axes, and can be divided into 4 cases:
a：at this time, the polar diameter r is negative (because θ is too large in inclination of the black crystal panel in the second quadrant, and the situation cannot occur, r is not positive), the left side and the right side of the black crystal panel are both inclined to the right when the contour line is perpendicular to the polar axis, and the fitted straight line needs to be calibrated to be inclined to the right at this time, so that the situation of inaccurate fitting when the black crystal panel is inclined to the right when entering is solved;
b：at this time, the polar diameter r is negative (because θ is too large in inclination of the black crystal panel in the second quadrant, and the situation cannot occur, r is not positive), the upper and lower edges of the black crystal panel are inclined upwards to the right when the contour line is perpendicular to the polar axis, and the fitted straight line needs to be calibrated to be inclined upwards to the right at this time, so that the problem of inaccurate fitting when the black crystal panel is inclined to the left when entering is solved;
c：at this time, the polar diameter r is positive and negative, and the contour line is certainly that the upper bottom edge or the lower bottom edge is inclined downwards to the right when being perpendicular to the polar axis; the fitted straight line needs to be calibrated so as to incline downwards to the right, so that the problem of inaccurate fitting when the black crystal panel inclines to the right when entering is solved;
d：at this time, the polar diameter r is divided into positive and negative, and the contour line is certainly left side or right side inclined to the left when being perpendicular to the polar axis; straight line fitted at this timeCalibration is needed to enable the black crystal panel to incline leftwards, so that the problem of inaccurate fitting when the black crystal panel is inclined leftwards when entering is solved;
in this case an ideal fitting line is obtained.
S2.4, solving intersection points and included angles of the two straight lines, defining a fillet area and fitting a fillet by using a least square method;
the intersection point and the included angle of two straight lines can be calculated according to the two straight line equations obtained in the previous step, wherein the two straight line equations are y=k, x+b respectively 1 And y=l x+b 2 The intersection point coordinate of the two straight lines isThe included angle theta of the two straight lines is obtained to satisfy the following conditions: />And obtaining the coordinates of the intersection points and the size of the included angles, and obtaining the length, the width and the diagonal line of the black crystal panel. The range of fitting the round corners can be limited according to the coordinates of the intersection points, namely, the range within the intersection points is fitted, and the exceeding edge points are discarded, so that the accuracy of fitting the round corners is improved.
S3, calculating the size of the black crystal panel:
s3.1, calculating lengths of the upper bottom edge and the right side edge of the black crystal panel: when the camera performs first trigger photographing, the camera 1 photographs the upper left corner of the black crystal panel, the camera 2 photographs the upper right corner of the black crystal panel, the camera 3 photographs the lower right corner of the black crystal panel, the length of the upper bottom edge of the black crystal panel can be calculated by the intersection point of two straight lines obtained by the images photographed by the camera 1 and the camera 2, and the calculation formula is omega 1 ＝(x 1 +x 2 )*ξ+L 12 The method comprises the steps of carrying out a first treatment on the surface of the Wherein omega 1 Is the length of the upper bottom edge, x 1 Is the abscissa, x of the intersection point coordinates of the fitting straight line of the image shot by the camera No. 1 2 Is the abscissa of the intersection point coordinates of the fitting straight line of the image shot by the No. 2 camera, and xi is the proportion, L 12 Is camera calibration number 1 and number 2. The length of the right side edge of the black crystal panel can be calculated by the intersection point of two straight lines obtained by the images shot by No. 2 and No. 3, and the calculation formula is l 1 ＝(y 2 +x 3 )*ξ+L 23 The method comprises the steps of carrying out a first treatment on the surface of the Wherein l 1 Is the length of the right side, y 2 Is the ordinate, x of the intersection point coordinates of the fitting straight line of the image shot by the No. 2 camera 3 Is the abscissa of the intersection point coordinates of the fitting straight line of the image shot by the No. 3 camera, and xi is the proportion, L 23 Is camera calibration No. 2 and No. 3. When the camera performs the second triggering photographing, the camera No. 1 photographs the lower left corner of the black crystal panel, the camera No. 2 photographs the lower right corner of the black crystal panel, and the length of the lower bottom edge can be calculated by the same method.
S3.2, calculating the length of the diagonal line of the black crystal panel: now, three sides of a black crystal panel are known to form included angles of straight lines by fitting each angle, the length of the diagonal line can be calculated, and according to the included angle alpha of two straight lines fitted by the upper right corner of the black crystal panel in the first shooting, the hypotenuse of a triangle formed by the upper base and the right side is the diagonal line to satisfyWherein l 1 Is the length of the right side edge omega 1 Is the length of the upper bottom edge, D R Is the diagonal length. The other diagonal length can be obtained from the right side and the lower side, and the calculation formula is +.>Wherein l 1 Is the length of the right side edge omega 2 Is the length of the lower bottom edge, D L Is the length of the diagonal line, and beta is the included angle of the straight line fitted by the right lower corner of the black crystal panel.
S3.3, calculating the length of the left side edge of the black crystal panel: according to two known diagonal lines, the length of the left side edge of the black crystal panel is obtained twice, and then the length of the left side edge which is wanted by the user is obtained by averaging. The included angle is calculated according to the straight lines fitted by the four angles, the included angle of the straight lines fitted by the upper left corner of the known black crystal panel is gamma, the included angle of the straight lines fitted by the lower left corner of the black crystal panel is phi, and l can be derived according to a formula 2 And then averaging:
the method can obtain:
all mechanical parameters of the black crystal panel can be obtained, the precision is within 0.1mm, and the influence of the inverted edge and the thickness of the black crystal panel on the measurement result is avoided.
In summary, according to the device and the method for intelligently measuring the parameters of the black crystal panel based on the machine vision, the four cameras are adopted, the camera fixing device is movable, and the positions of the No. 1 camera and the No. 3 camera can be adjusted according to the type of the black crystal panel input by the interface so that one camera is directly above the upper left corner and the lower right corner of the black crystal panel, and therefore errors caused by uneven chamfering and inconsistent thickness of the black crystal panel are eliminated. The invention provides an intelligent measuring method for parameters of a black crystal panel on the basis of machine vision, which is used for drawing a straight line and a circle by using a least square method after Hough straight line detection in the process of processing pictures so as to solve the problem that the black crystal panel is placed incorrectly in a production line, and correct the black crystal panel, thereby obtaining accurate values and greatly reducing errors.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. The measuring method of the intelligent measuring device for the parameters of the black crystal panel on the basis of machine vision is characterized by comprising an intelligent measuring device and an intelligent measuring method; the intelligent measuring device comprises a camera fixing device, an image acquisition device, an image measuring device and a panel conveying platform; the image acquisition device is arranged above the panel conveying platform and is fixed through the camera fixing device; the image measuring device is connected with the image acquisition device and is used for receiving the image transmitted by the image acquisition device, processing the image on the industrial personal computer, finally transmitting a qualified signal to the alarm, and alarming if the qualified signal is unqualified;
the intelligent measurement method comprises the following steps:
s1, shooting a required picture;
the No. 1 and No. 3 cameras are adjusted to proper positions through mechanical parameters input by an operation interface, the cameras are guaranteed to vertically shoot four corners of the black crystal panel, the black crystal panel moves along the direction of the conveying belt, the No. 4 camera starts to trigger the No. 1,2 and No. 3 cameras to start shooting after recognizing that the upper bottom edge of the black crystal panel enters about 600 pixels of the visual field range, and shooting is triggered again when the lower bottom edge of the black crystal panel leaves the visual field until 600 pixels leave the visual field, and then the pictures are processed;
s2, processing the shot picture;
s2.1, gaussian filtering is carried out;
the two-dimensional gaussian function is:
，
where the square of x and the square of y represent the distance of the other pixels in the neighborhood from the center pixel in the neighborhood,the representative is standard deviation, a 5*5 Gaussian filter template is generated, and sampling is carried out by taking the central position of the template as the origin of coordinates; determining the coordinates of the template at each position, and taking the coordinates into a Gaussian function, wherein the obtained value is the coefficient of the template; for window template size +.>The calculation formula of each element value in the template is as follows:
，
the coefficients obtained by normalization are:i.e., the inverse of the template coefficient sum;
s2.2, binarizing the image, and then carrying out Hough straight line detection on the binarized image;
in the straight line detection task, namely, the straight line in the image space corresponds to the point in the polar coordinate space one by utilizing the duality of the point and the line, and the straight line in the polar coordinate space corresponds to the point in the image space one by one; each line in image space is represented in polar coordinate space corresponding to a single point; any part of line segments on the straight line in the image space correspond to the same point in the polar coordinate space, the straight line detection problem in the image space is converted into the point detection problem in the polar coordinate space, and the straight line detection task is completed by searching a peak value in the polar coordinate space;
s2.3, precisely fitting a straight line by using a least square method;
drawing a straight line detected by the Hough straight line on another graph, traversing the graph without considering the overlapped straight lines to finally obtain two straight lines, wherein the overlapped straight lines refer to the two straight lines in the same directionThe difference is less than 40 pixels or +.>The difference is smaller than 0.5 degree, and as the Hough straight line detection result is not accurate enough, the correction in two aspects is carried out, firstly: expanding the range of the points on the two obtained straight lines to form a pipeline, performing least square fitting in the pipeline, and if the straight lines are horizontal, fitting according to +.>Fitting is performed according to +.>Fitting is carried out, the problem that the least square method cannot accurately represent a vertical line is counteracted, and then: aiming at the deflection problem possibly existing in the black crystal panel entering device, the black crystal panel entering device is calibrated in four different situations, so that an accurate fitting straight line is obtained;
s2.4, solving intersection points and included angles of the two straight lines, defining a fillet area and fitting a fillet by using a least square method;
calculating the intersection point and the included angle of two straight lines according to the two straight line equations obtained in the last step, wherein the two straight line equations are respectivelyAnd->The intersection point coordinate of the two straight lines is +.>Obtaining the included angle of two straight lines>The method meets the following conditions: />Obtaining the coordinates of the intersection points and the size of the included angles, and obtaining the length, the width and the diagonal line of the black crystal panel; limiting the range of fitting the round angle according to the coordinates of the intersection point, fitting the round angle in the range within the intersection point, and discarding the exceeding edge points;
s3, calculating the size of the black crystal panel:
s3.1, calculating lengths of the upper bottom edge and the right side edge of the black crystal panel: when the camera performs first trigger photographing, the camera 1 photographs the upper left corner of the black crystal panel, the camera 2 photographs the upper right corner of the black crystal panel, the camera 3 photographs the lower right corner of the black crystal panel, and the length of the upper bottom edge of the black crystal panel is calculated by the intersection point of two straight lines obtained by the images photographed by the camera 1 and the camera 2, wherein the calculation formula is thatThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Is the length of the upper bottom edge, < >>Is the abscissa of the intersection point coordinates of the fitting straight line of the image shot by the camera No. 1,/and>is the abscissa of the intersection point coordinates of the fitting straight line of the image shot by the No. 2 camera, +/->Is a proportion of->Calibrating cameras 1 and 2; the length of the right side edge of the black crystal panel is calculated by the intersection point of two straight lines obtained by the images shot by No. 2 and No. 3, and the calculation formula is +.>The method comprises the steps of carrying out a first treatment on the surface of the Wherein->Is the length of the right side, < >>Is the ordinate of the intersection point coordinate of the fitting straight line of the image shot by the No. 2 camera, +>Is the abscissa of the intersection point coordinates of the fitting straight line of the image shot by the No. 3 camera,/and>is a proportion of->Calibrating cameras No. 2 and No. 3; when the camera performs triggering photographing for the second time, the camera 1 shoots the lower left corner of the black crystal panel, the camera 2 shoots the lower right corner of the black crystal panel, and the length of the lower bottom edge is calculated;
s3.2, calculating the length of the diagonal line of the black crystal panel: three sides of the black crystal panel are known to be fitted with included angles of straight lines with each angle, the length of the diagonal line is calculated, and the included angles of the two straight lines fitted with the right upper corner of the black crystal panel at the time of first shooting are as followsThe hypotenuse of the triangle formed by the upper base and the right side is the diagonal line satisfying +.>Wherein->Is the length of the right side, < >>Is the length of the upper bottom edge, < >>Is the diagonal length; the other diagonal length is obtained from the right side and the lower bottom, and the calculation formula is +.>Wherein->Is the length of the right side, < >>Is the length of the lower bottom edge, < >>Is diagonal length, & gt>Fitting an included angle of a straight line from the right lower corner of the black crystal panel;
s3.3, calculating the length of the left side edge of the black crystal panel: according to two known diagonal lines, the length of the left side edge of the black crystal panel is calculated twice, and then the length of the left side edge which is wanted by the user is calculated by averaging; obtaining an included angle according to straight lines fitted by four angles, wherein the included angle of the straight lines fitted by the upper left corner of the known black crystal panel isThe included angle of straight line fitted by the lower left corner of the black crystal panel is +.>According to the formula +.>And then averaging:
，
the method can obtain:，
all mechanical parameters of the black crystal panel can be obtained.
2. The measurement method of the intelligent measurement device for the parameters of the black panel machine vision-based black panel machine vision according to claim 1, wherein the measurement method comprises the following steps: the panel conveying platform comprises a chassis, a conveying belt, a liquid crystal display, a display fixing frame, an electric box, a ground foot and a ground foot wheel; the conveyer belt is located the top of chassis, lower margin and lower margin wheel supporting exist, and six sets of below that are located the chassis play the supporting role altogether, the electric box is located the inside of chassis, the display mount is fixed on the section bar frame of conveyer belt top, fixed LCD.
3. The measurement method of the intelligent measurement device for the parameters of the black panel machine vision-based black panel machine according to claim 2, wherein the measurement method comprises the following steps: the camera fixing device comprises a section bar frame, an L-shaped bracket, a camera connecting piece, a sliding rail and a sliding block; the section bar frame is fixed on the left and right sides of the conveyor belt, the L-shaped support is fixed on the section bar frame, the slide rail and the slide block are one set, the section bar frame is fixed on two arms of the L-shaped support, the camera connecting piece is arranged above the slide block, and the industrial camera is fixed on the slide block through the camera connecting piece.
4. A method for measuring the intelligent measuring device for the parameters of the black panel board based on machine vision as set forth in claim 3, wherein: the image acquisition device comprises three 890 ten thousand industrial cameras, one 230 ten thousand industrial cameras, four light sources and a light source fixing frame; four cameras, wherein the No. 1 890 ten thousand industrial cameras are fixed on one arm of an L-shaped bracket on the right side of the advancing direction of a conveyor belt, and the other three cameras are fixed on the other arm of the L-shaped bracket, wherein the No. 4 230 ten thousand industrial cameras are positioned between the No. 2 890 ten thousand industrial cameras and the No. 3 890 ten thousand industrial cameras and are used for identifying the arrival and departure of a board; the four light sources are fixed around the section bar frame through the light source fixing frame.
5. The measurement method of the intelligent measurement device for the parameters of the black panel machine vision-based black panel machine vision according to claim 4 is characterized by comprising the following steps: the industrial camera comprises a camera power socket, a network cable socket, a camera body, lens exposure, a lens and a lens focal length; the camera power socket and the net wire socket are respectively arranged at the upper part of the camera body, and the lower part of the camera body is sequentially provided with a lens exposure, a lens and a lens focal length.
6. The measurement method of the intelligent measurement device for the parameters of the black panel machine vision-based black panel machine according to claim 2, wherein the measurement method comprises the following steps: the conveyor belt comprises a driving wheel, a belt and a driven wheel, wherein the driving wheel and the driven wheel are arranged at two ends of the conveyor belt, and the driving wheel and the driven wheel are connected through the belt.
7. The measurement method of the intelligent measurement device for the parameters of the black panel machine vision-based black panel machine vision according to claim 1, wherein the measurement method comprises the following steps: and when the picture is shot in the step S1, the No. 1 camera and the No. 3 camera are movable, when the picture is shot for the first time, the No. 1 camera shoots the upper left corner of the black crystal panel, the No. 2 camera shoots the upper right corner of the black crystal panel, the No. 3 camera shoots the lower right corner of the black crystal panel, so that the picture of three corners of the black crystal panel is obtained, when the picture is shot for the second time, the No. 1 camera shoots the lower left corner, the No. 2 camera shoots the lower right corner, and the No. 3 camera does not shoot, so that the picture of the fourth corner is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811571439.4A CN109682309B (en) | 2018-12-21 | 2018-12-21 | Intelligent measuring device and method for black crystal panel parameters based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811571439.4A CN109682309B (en) | 2018-12-21 | 2018-12-21 | Intelligent measuring device and method for black crystal panel parameters based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109682309A CN109682309A (en) | 2019-04-26 |
| CN109682309B true CN109682309B (en) | 2023-11-14 |
Family
ID=66188189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811571439.4A Active CN109682309B (en) | 2018-12-21 | 2018-12-21 | Intelligent measuring device and method for black crystal panel parameters based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109682309B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112468719A (en) * | 2020-11-16 | 2021-03-09 | 中国农业大学 | Processed product image acquisition device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0798214A (en) * | 1993-09-29 | 1995-04-11 | Nippondenso Co Ltd | Method and device for three dimensional position and attitude recognition method based on sense of sight |
| FR2921478A1 (en) * | 2007-09-24 | 2009-03-27 | 3D Ouest Sarl | SYSTEM AND METHOD FOR ACQUIRING THREE-DIMENSIONAL CHARACTERISTICS OF AN OBJECT FROM IMAGES TAKEN BY A PLURALITY OF MEASURING ORGANS |
| CN104458750A (en) * | 2013-09-25 | 2015-03-25 | 中国科学院沈阳自动化研究所 | Automatic aluminum profile surface defect detecting equipment based on machine vision |
| JP2017098859A (en) * | 2015-11-27 | 2017-06-01 | 株式会社明電舎 | Calibration device of image and calibration method |
| CN107665489A (en) * | 2017-09-18 | 2018-02-06 | 华中科技大学 | A kind of glass dihedral angle detection method based on computer vision |
| CN207573488U (en) * | 2017-12-26 | 2018-07-03 | 杭州友上智能技术有限公司 | A kind of industrial intelligent camera based on FPGA |
| CN108917594A (en) * | 2018-05-29 | 2018-11-30 | 广东理工学院 | A kind of machine vision device measuring household board size |
| CN209416276U (en) * | 2018-12-21 | 2019-09-20 | 北京安视中电科技有限公司 | Black crystal panel mechanical parameter intelligent device for measuring based on machine vision |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4690476B2 (en) * | 2009-03-31 | 2011-06-01 | アイシン精機株式会社 | Car camera calibration system |
-
2018
- 2018-12-21 CN CN201811571439.4A patent/CN109682309B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0798214A (en) * | 1993-09-29 | 1995-04-11 | Nippondenso Co Ltd | Method and device for three dimensional position and attitude recognition method based on sense of sight |
| FR2921478A1 (en) * | 2007-09-24 | 2009-03-27 | 3D Ouest Sarl | SYSTEM AND METHOD FOR ACQUIRING THREE-DIMENSIONAL CHARACTERISTICS OF AN OBJECT FROM IMAGES TAKEN BY A PLURALITY OF MEASURING ORGANS |
| CN104458750A (en) * | 2013-09-25 | 2015-03-25 | 中国科学院沈阳自动化研究所 | Automatic aluminum profile surface defect detecting equipment based on machine vision |
| JP2017098859A (en) * | 2015-11-27 | 2017-06-01 | 株式会社明電舎 | Calibration device of image and calibration method |
| CN107665489A (en) * | 2017-09-18 | 2018-02-06 | 华中科技大学 | A kind of glass dihedral angle detection method based on computer vision |
| CN207573488U (en) * | 2017-12-26 | 2018-07-03 | 杭州友上智能技术有限公司 | A kind of industrial intelligent camera based on FPGA |
| CN108917594A (en) * | 2018-05-29 | 2018-11-30 | 广东理工学院 | A kind of machine vision device measuring household board size |
| CN209416276U (en) * | 2018-12-21 | 2019-09-20 | 北京安视中电科技有限公司 | Black crystal panel mechanical parameter intelligent device for measuring based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109682309A (en) | 2019-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109003258B (en) | High-precision sub-pixel circular part measuring method | |
| CN110497187B (en) | Sun flower pattern assembly system based on visual guidance | |
| CN108918543B (en) | Dynamic detection device and method for mirror surface scratch | |
| CN114494045B (en) | Large spur gear geometric parameter measurement system and method based on machine vision | |
| CN108007364A (en) | A kind of tile detection device and detection method based on RGB-D cameras | |
| CN102589516B (en) | Dynamic distance measuring system based on binocular line scan cameras | |
| CN107816943B (en) | Logistics box volume and weight measurement system and implementation method thereof | |
| CN105783723A (en) | Machine vision-based precise die surface processing precision detection device and method | |
| CN204439022U (en) | A kind of capture mechanism and apply the automatic measuring equipment of this capture mechanism | |
| CN108088381B (en) | Non-contact type micro gap width measuring method based on image processing | |
| CN109406527B (en) | System and method for detecting fine appearance defects of micro camera module lens | |
| WO2022048617A1 (en) | Method, device, and system for recognizing projection position, and storage medium | |
| CN109682309B (en) | Intelligent measuring device and method for black crystal panel parameters based on machine vision | |
| WO2020119246A1 (en) | Highlight object surface defect detection system and method based on reflected light | |
| CN109191516B (en) | Rotation correction method and device of structured light module and readable storage medium | |
| CN115375636A (en) | Full-size detection method and equipment for power battery module | |
| CN113068019A (en) | Dual-optical camera calibration apparatus, method, electronic apparatus, and storage medium | |
| CN110470247B (en) | Device and method for detecting coaxiality of inner and outer circular surfaces of part | |
| CN109406539B (en) | Transparent medicine bottle bottom accumulated material defect detection system and method | |
| CN108759676B (en) | Checkerboard-based transmission case end face large-size form and position tolerance detection device and method | |
| CN108303427B (en) | Household damaged degree detection system based on image procossing | |
| CN114119483A (en) | Image processing technology-based quality detection method and device for light wallboard for building | |
| CN108459030B (en) | Online detection device and method applied to smooth surface flaws of non-planar plastic | |
| CN206281468U (en) | A kind of contactless detection device of columnar object perpendicularity | |
| CN209416276U (en) | Black crystal panel mechanical parameter intelligent device for measuring based on machine vision |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |