CN115355850A - Detection apparatus for squareness based on intelligence vision - Google Patents
Detection apparatus for squareness based on intelligence vision Download PDFInfo
- Publication number
- CN115355850A CN115355850A CN202210959355.8A CN202210959355A CN115355850A CN 115355850 A CN115355850 A CN 115355850A CN 202210959355 A CN202210959355 A CN 202210959355A CN 115355850 A CN115355850 A CN 115355850A
- Authority
- CN
- China
- Prior art keywords
- industrial camera
- workpiece
- processor
- detecting
- lens
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/04—Sorting according to size
- B07C5/10—Sorting according to size measured by light-responsive means
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of intelligent visual detection, in particular to a device for detecting right angle based on intelligent vision. The detection device for the right angle based on the intelligent vision comprises an industrial camera and an industrial lens fixedly embedded at the bottom of the industrial camera, wherein the industrial lens is vertically downward and faces a conveying mechanism, and an annular light source is fixedly installed between the industrial lens and the conveying mechanism through a rack; an rejecting mechanism for rejecting unqualified workpieces on the conveying mechanism is installed on one side of the conveying mechanism; the industrial camera is electrically connected with the processor through a wire, and the processor is electrically connected with the display. The device for detecting the right angle based on the intelligent vision has the advantages that the machine vision is used for detecting workpieces, accurate measurement can be met, results can be obtained, long-time work can be achieved, and high-precision and high-efficiency detection can be achieved.
Description
Technical Field
The invention relates to the technical field of intelligent visual detection, in particular to a device for detecting right angle based on intelligent vision.
Background
The market demands right angles of components such as workpieces and the like more and more accurately, and the quality requirement is higher and higher. Meanwhile, the measurement of the right angle of the workpiece is complicated and time-consuming, so that a great deal of manpower and financial resources are forced to be invested in angle detection. During the production and application of the workpiece, the workpiece is worn, so that the right-angle accuracy of the workpiece is recognized and the quality of the workpiece is evaluated.
At present, the right angle of a workpiece is mainly detected manually, the manual detection method is convenient and visual, has high accuracy, but is greatly influenced by subjective factors, has high working strength of workers, easily causes visual fatigue after long-time working, has judgment errors and influences the quality detection of products; in addition, the right angle of the workpiece can be detected only by other observation tools; and when the required speed is too fast, the operator can not complete the detection basically.
Therefore, it is necessary to provide a new device for detecting right angle based on smart vision to solve the above technical problems.
Disclosure of Invention
In order to solve the technical problem, the invention provides a right-angle detection device based on intelligent vision.
The invention provides a device for detecting right angle based on intelligent vision, which comprises:
an industrial camera, and
the industrial lens is fixedly embedded at the bottom of the industrial camera, the industrial lens is vertically downward and faces the conveying mechanism, and an annular light source is fixedly arranged between the industrial lens and the conveying mechanism through a rack;
one side of the conveying mechanism is provided with a removing mechanism for removing unqualified workpieces on the conveying mechanism;
the industrial camera is electrically connected with the processor through a wire, and the processor is electrically connected with the display.
Preferably, it includes driving motor to reject the mechanism, the fixed gomphosis of driving motor is in one side of transport mechanism, just driving motor's output fixed mounting has the rolling disc, the skew centre of a circle department fixed mounting of rolling disc has the guide bar, just the guide bar passes the direction chamber that the arc pole was seted up, the one end of arc pole is passed through the dwang and is rotated and install on driving motor lateral wall fixed mounting's mounting bracket, just the other end fixed mounting of arc pole has the slurcam.
Preferably, the conveying mechanism is a conveying belt structure, the conveying belt is sleeved on the two groups of rotating rollers, any one of the rotating rollers is driven by a motor, and the conveying belt is made of a black light absorption material or a coating.
Preferably, the annular light source is positioned right above the workpiece on the conveyor belt, and the annular light source is a low-angle annular light source and irradiates the workpiece to make the surface of the workpiece and the background black.
Preferably, the industrial camera is a black and white industrial camera with 500 ten thousand pixels, and the accuracy formula of the industrial camera is as follows: the field of view (corresponding side)/resolution (opposite side) =25mm/1944pix ≈ 0.013mm/pix, and the lens magnification is calculated as: lens magnification = chip size/field of view = pixel size resolution/field of view.
Preferably, the lens multiplying power is 0.2, and the distortion-free telecentric lens with the compatible size of 2/3 is selected.
The detection device comprises the following operation steps:
the method comprises the following steps: the right-angle workpieces enter a detected conveying belt one by one;
step two: turning on the annular light source to illuminate the workpiece;
step three: the industrial camera positioned on the workpiece shoots an image and sends the image to the processor;
step four: the processor receives the image and performs algorithm analysis;
step five: and displaying the result obtained by the processor by using a line value display algorithm, and rejecting unqualified workpieces by using a rejecting mechanism.
The algorithm analysis steps adopted by the processor are as follows:
(1) Collecting images, and importing the polished images into software for analysis and processing;
(2) Matching and positioning the local frame of the workpiece by using a shape matching algorithm;
(3) Respectively detecting two straight lines of the step angle by using a straight line detection algorithm, and calculating by using a line-to-line algorithm to obtain an intersection point and an angle of the two lines;
(4) And displaying the processed result by using a numerical display algorithm, and transmitting the data to a utilization rejection mechanism.
Compared with the related art, the device for detecting the right angle based on the intelligent vision has the following beneficial effects that:
the invention provides a right-angle detection device based on intelligent vision, which uses machine vision to detect the excellence of a workpiece, can meet the requirements of accurate measurement and result obtaining, can work for a long time and can realize high-precision and high-efficiency detection.
Drawings
FIG. 1 is a schematic structural diagram of a preferred embodiment of a device for detecting squareness based on smart vision according to the present invention;
fig. 2 is a schematic structural view of the rejecting mechanism shown in fig. 1.
Reference numbers in the figures: 1. an industrial camera; 2. an industrial lens; 3. an annular light source; 4. a transport mechanism; 5. a rejection mechanism; 51. a drive motor; 52. rotating the disc; 53. a guide bar; 54. an arc-shaped rod; 55. a guide cavity; 56. rotating the rod; 57. a push plate; 6. a workpiece; 7. a processor; 8. a display.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Specific implementations of the present invention are described in detail below with reference to specific embodiments.
Referring to fig. 1 to fig. 2, an embodiment of the invention provides an apparatus for detecting a right angle based on smart vision, which includes: the industrial camera 1, the annular light source 3, the conveying mechanism 4, the rejecting mechanism 5 and the processor 7.
In an embodiment of the present invention, referring to fig. 1 and fig. 2, an industrial lens 2 is fixedly embedded at the bottom of the industrial camera 1, the industrial lens 2 faces downward and toward the transmission mechanism 4, an annular light source 3 is fixedly installed between the industrial lens 2 and the transmission mechanism 4 through a frame, the industrial camera 1 is electrically connected with a processor 7 through a wire, and the processor 7 is electrically connected with a display 8;
and a rejecting mechanism 5 for rejecting unqualified workpieces 6 on the conveying mechanism 4 is arranged on one side of the conveying mechanism 4.
It should be noted that: the annular light source 3 is positioned right above the workpiece and directly irradiates the surface of the workpiece 6, when the workpiece 6 is conveyed to the annular light source 3 by the driving belt, the industrial camera 1 sends a low-magnification image to the processor 7 in real time, the processor 7 judges whether the workpiece 6 can completely enter the visual field according to shape recognition, the processor 7 determines whether to trigger shooting of a high-definition image, the shot high-definition image is conveyed to the processor 7, the processor 7 performs right-angle detection to judge whether the image is qualified,
when all the workpieces enter the visual field, the industrial camera 1 sends the shot pictures to the processor 7, the processor analyzes the pictures through an algorithm, whether the right angles are qualified or not is displayed through the display 8, and the unqualified right angles of the workpieces are removed through the removing mechanism 5.
And the detection device comprises the following operation steps:
the method comprises the following steps: the right-angle workpieces 6 are fed onto a detected conveyor belt one by one;
step two: turning on the annular light source 3 to illuminate the workpiece 6;
step three: the industrial camera 1 positioned above the workpiece 6 captures an image and sends the image to the processor 7;
step four: the processor 7 receives the image and performs algorithm analysis;
step five: displaying the result obtained by the processor 6 by using a line value display algorithm, and rejecting unqualified workpieces 6 by using a rejection mechanism 5;
the algorithm analysis adopted by the processor 7 comprises the following steps:
(1) Collecting images, and importing the polished images into software for analysis and processing;
(2) Matching and positioning the local frame of the workpiece 6 by using a shape matching algorithm;
(3) Respectively detecting two straight lines of the step angle by using a straight line detection algorithm, and calculating by using a line-to-line algorithm to obtain an intersection point and an angle of the two lines;
(4) Displaying the processed result by using a numerical value display algorithm, and transmitting the data to a utilization rejection mechanism 5;
in the present embodiment, the steps of the algorithm analysis adopted by the image processor are as follows:
1. the step of matching and positioning the local frame of the workpiece by using the shape matching algorithm comprises the following steps:
A. calculating the context information of each point of the two-point set (when calculating SC for the image, the inner and outer outlines of the image need to be extracted first);
B. calculating a cost value, namely a cost value, between every two points in the two-point set;
C＝(1-β)C S +βC A
the cost value of every two points between two point sets can be calculated, k refers to the k-th grid, and g and h respectively represent a certain point in the two point sets.
C. And (3) counting the corresponding relation of a group of point sets with the lowest overall cost value by using a Hungarian algorithm:
the corresponding point relation is obtained, the process of model transformation is not described continuously, then the transformation from the point set to the point set is carried out through the transformation matrix, and after a plurality of times of iterative transformation, a shape distance is calculated;
2. respectively detecting two straight lines of the step angle by using a straight line detection algorithm, and calculating by using a line-to-line algorithm to obtain an intersection point and an angle of the two lines;
the angle of alpha can be calculated from this formula.
The annular light source 3 is positioned right above the workpiece 6 on the conveyor belt, the annular light source 3 adopts a low-angle annular light source and irradiates the workpiece 6 to enable the surface and the background of the workpiece 6 to be black, the edge chamfer of the workpiece 6 is bright, and the chamfer outline is highlighted;
the industrial camera 1 is a black and white industrial camera with 500 ten thousand pixels, and the accuracy of the industrial camera 1 is represented by the following formula: the field of view (corresponding side)/resolution (opposite side) =25mm/1944pix ≈ 0.013mm/pix, since the imaging shot by using the fixed-focus lens has certain distortion, the distortion can cause the influence of the measurement result, and the lens magnification is calculated as: the lens multiplying power = chip size/field of view = pixel size × resolution/field of view, therefore the lens multiplying power chooses for use 0.2, compatible size is 2/3 of distortionless telecentric lens, can reduce the distortion of the picture, improve the precision measured.
In an embodiment of the present invention, referring to fig. 1 and fig. 2, the conveying mechanism 4 is a conveying belt structure, the conveying belt is sleeved on two sets of rotating rollers, and any one of the rotating rollers is driven by a motor, the removing mechanism 5 includes a driving motor 51, the driving motor 51 is fixedly embedded on one side of the conveying mechanism 4, an output end of the driving motor 51 is fixedly provided with a rotating disc 52, a guide rod 53 is fixedly installed at a position of the rotating disc 52 deviating from a circle center, the guide rod 53 passes through a guide cavity 55 formed in an arc-shaped rod 54, one end of the arc-shaped rod 54 is rotatably installed on a mounting rack fixedly installed on a side wall of the driving motor 51 through a rotating rod 56, and the other end of the arc-shaped rod 54 is fixedly provided with a pushing plate 57.
It should be noted that: after the driving motor 51 receives the signal, the driving motor 51 is started to drive the rotating disc 52 to rotate, so that the guide rod 53 drives the guide rod 53 to rotate around the rotating rod 56 along the guide cavity 55 formed in the rotating rod 56, and the pushing plate 57 pushes and removes the unqualified workpieces 6 on the conveyor belt;
it should also be noted that: in the production process of the right angle of the workpiece 7, the produced machine can cause tiny looseness due to long-time stamping, however, the influence of the tiny looseness on the workpiece is very large, the straight line edge bending can be caused, the right angle is reduced or enlarged, the problem is difficult to judge accurately in time through human eyes in the past, because the details are difficult to find, tools used by the product are low in cost, the production efficiency is improved, the requirement of modern production is met, the superiority of the workpiece is detected by using machine vision, accurate measurement and result obtaining can be met, and the workpiece can work for a long time and can be detected with high accuracy and high efficiency.
The circuits and controls involved in the present invention are prior art and will not be described in detail herein.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. The utility model provides a detection apparatus for squareness based on intelligence vision, its characterized in that includes:
industrial camera (1), and
the industrial camera lens (2) is fixedly embedded at the bottom of the industrial camera (1), the industrial camera lens (2) vertically faces downwards and faces the conveying mechanism (4), and an annular light source (3) is fixedly installed between the industrial camera lens (2) and the conveying mechanism (4) through a rack;
a rejecting mechanism (5) for rejecting unqualified workpieces (6) on the conveying mechanism (4) is arranged on one side of the conveying mechanism (4);
the industrial camera (1) is electrically connected with the processor (7) through a conducting wire, and the processor (7) is electrically connected with the display (8).
2. The detection apparatus for right angle based on intelligent vision, according to claim 1, characterized in that, the rejection mechanism (5) includes a driving motor (51), the fixed gomphosis of driving motor (51) is in one side of transport mechanism (4), just the output fixed mounting of driving motor (51) has a rolling disc (52), the skew centre of a circle department fixed mounting of rolling disc (52) has guide bar (53), just guide bar (53) pass direction chamber (55) that arc pole (54) seted up, the one end of arc pole (54) is installed on driving motor (51) lateral wall fixed mounting's mounting bracket through dwang (56) rotation, just the other end fixed mounting of arc pole (54) has slurcam (57).
3. The device for detecting the squareness based on the intelligent vision according to claim 2, wherein the conveying mechanism (4) is a conveying belt structure, the conveying belt is sleeved on the two groups of rotating rollers, any one of the rotating rollers is driven by a motor, and the conveying belt is made of a black light absorption material or a coating.
4. The device for detecting the squareness based on the intelligent vision is characterized in that the annular light source (3) is positioned right above the workpiece (6) on the conveyor belt, and the annular light source (3) adopts a low-angle annular light source and irradiates the workpiece (6) to make the surface and the background of the workpiece (6) black.
5. The device for detecting the squareness based on the smart vision is characterized in that the industrial camera (1) adopts a black and white industrial camera with 500 ten thousand pixels, and the accuracy of the industrial camera (1) is represented by the following formula: the field of view (corresponding side)/resolution (opposite side) =25mm/1944pix ≈ 0.013mm/pix, and the lens magnification is calculated as: lens magnification = chip size/field of view = pixel size resolution/field of view.
6. The device for detecting the squareness based on the intelligent vision of claim 5, wherein the magnification of the lens is 0.2, and the device is compatible with a distortion-free telecentric lens with the size of 2/3.
7. The device for detecting squareness based on intelligent vision according to claim 1, characterized in that the device comprises the following operation steps:
the method comprises the following steps: the right-angle workpieces (6) are fed onto a detected conveyor belt one by one;
step two: turning on the annular light source (3) to illuminate the workpiece (6);
step three: the industrial camera (1) positioned above the workpiece (6) shoots an image and sends the image to the processor (7);
step four: the processor (7) receives the image and performs algorithm analysis;
step five: and displaying the result obtained by the processor (6) by using a line value display algorithm, and rejecting the unqualified workpiece (6) by using a rejecting mechanism (5).
8. An intelligent vision-based squareness detection apparatus according to claim 7, wherein said processor (7) employs an algorithmic analysis comprising the steps of:
(1) Collecting images, and importing the polished images into software for analysis and processing;
(2) Matching and positioning the local frame of the workpiece (6) by using a shape matching algorithm;
(3) Respectively detecting two straight lines of the step angle by using a straight line detection algorithm, and calculating by using a line-to-line algorithm to obtain an intersection point and an angle of the two lines;
(4) And displaying the processed result by using a numerical value display algorithm, and transmitting the data to a utilization rejection mechanism (5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210959355.8A CN115355850A (en) | 2022-08-11 | 2022-08-11 | Detection apparatus for squareness based on intelligence vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210959355.8A CN115355850A (en) | 2022-08-11 | 2022-08-11 | Detection apparatus for squareness based on intelligence vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115355850A true CN115355850A (en) | 2022-11-18 |
Family
ID=84001206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210959355.8A Pending CN115355850A (en) | 2022-08-11 | 2022-08-11 | Detection apparatus for squareness based on intelligence vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115355850A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117589091A (en) * | 2024-01-19 | 2024-02-23 | 钛玛科（北京）工业科技有限公司 | Angle detection system |
-
2022
- 2022-08-11 CN CN202210959355.8A patent/CN115355850A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117589091A (en) * | 2024-01-19 | 2024-02-23 | 钛玛科（北京）工业科技有限公司 | Angle detection system |
| CN117589091B (en) * | 2024-01-19 | 2024-03-26 | 钛玛科（北京）工业科技有限公司 | Angle detection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107941808B (en) | 3D printing forming quality detection system and method based on machine vision | |
| CN109772733B (en) | Defect bamboo block detecting and sorting device and method based on vision | |
| CN203124215U (en) | Frame sealant coating machine | |
| CN110567976B (en) | Mobile phone cover plate silk-screen defect detection device and detection method based on machine vision | |
| CN109978940B (en) | Visual measurement method for SAB safety airbag size | |
| CN111220544A (en) | Lens quality detection device and detection method | |
| CN103308524A (en) | PCB automatic optical inspection system | |
| CN114383505B (en) | Automatic detection device for short shaft part size | |
| CN214747807U (en) | Chip detection equipment | |
| CN113405530B (en) | Visual measurement system, method, equipment, production line and terminal for deviation of stamping process sheet material | |
| CN114705686A (en) | Method and system for detecting surface defects of cylindrical pot, controller and industrial personal computer | |
| CN115355850A (en) | Detection apparatus for squareness based on intelligence vision | |
| CN110940670A (en) | Flexible printing label printing head draft detection system based on machine vision and implementation method thereof | |
| CN106000903B (en) | A kind of non-contact detection system and method for being used to detect loom cloth gripper edge gap | |
| CN112200776A (en) | Chip packaging defect detection method and detection device | |
| CN109909175A (en) | A kind of volume key appearance AOI detection device and its detection method | |
| CN113418933A (en) | Flying shooting visual imaging detection system and method for detecting large-size object | |
| CN114252452A (en) | Online detection device and method for appearance defects and contour dimension of small-sized revolving body | |
| CN115436394A (en) | Appearance defect detection system and method | |
| CN111693535A (en) | Touch screen defect detection equipment and method based on machine vision analysis | |
| CN111521128A (en) | Shellfish external form automatic measurement method based on optical projection | |
| CN109557098A (en) | Metal surface detection system based on machine vision | |
| CN106767566B (en) | A kind of workpiece quality on-line monitoring appraisal procedure and monitoring system | |
| CN112378797A (en) | Full-automatic indentation measuring device and method | |
| CN108663376B (en) | Seamless steel tube quality detection device and detection method |
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 |