CN109654997B - Precise positioning device and method for plug hole based on machine vision - Google Patents
Precise positioning device and method for plug hole based on machine vision Download PDFInfo
- Publication number
- CN109654997B CN109654997B CN201910102870.2A CN201910102870A CN109654997B CN 109654997 B CN109654997 B CN 109654997B CN 201910102870 A CN201910102870 A CN 201910102870A CN 109654997 B CN109654997 B CN 109654997B
- Authority
- CN
- China
- Prior art keywords
- plug
- tray
- hole
- image
- image acquisition
- 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
- 238000000034 method Methods 0.000 title claims description 29
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000001467 acupuncture Methods 0.000 claims abstract description 4
- 238000005286 illumination Methods 0.000 claims description 24
- 238000012937 correction Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 description 11
- 230000011218 segmentation Effects 0.000 description 5
- 238000009434 installation Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000010899 nucleation Methods 0.000 description 2
- 239000004033 plastic Substances 0.000 description 2
- 229920003023 plastic Polymers 0.000 description 2
- 240000007651 Rubus glaucus Species 0.000 description 1
- 235000011034 Rubus glaucus Nutrition 0.000 description 1
- 235000009122 Rubus idaeus Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
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
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G06T5/80—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
Abstract
A precise positioning device for a plug hole based on machine vision comprises a rack, an image acquisition device, a conveying device, a positioning device and a control system, wherein the conveying device is installed on the rack, and the image acquisition device is used for acquiring images of a plug; the positioning device comprises a fixed baffle, a self-adaptive baffle, a pressing plate and a photoelectric sensor for detecting the position of the plug; the plug tray, the conveying device and the positioning device are different in color; the control system is arranged on the rack, receives signals sent by the photoelectric sensor and controls the work of the image acquisition device, and the acquired images are processed by an image processing module in the control system to realize the positioning of the hole of the acupuncture plate. The invention can solve the problems of poor positioning adaptability of the hole tray holes, low operation efficiency, low positioning precision and the like in the current industrialized seedling culture.
Description
Technical Field
The invention belongs to the field of intelligent agricultural equipment, and relates to a precise positioning device and method for a plug hole based on machine vision.
Background
In recent years, with the development of transplanting technology, large-scale industrial seedling raising is a trend. In the industrialized seedling raising, the accurate positioning of the hole plate holes directly influences the efficiency of automatic seeding, selective transplanting and subsequent thinning operation, the existing hole plate hole positioning is realized by combining manual judgment with a pure mechanical structure, and a series of problems of poor adaptability, low operation efficiency, low positioning precision and the like exist. In order to realize high-precision and strong-adaptability plug hole positioning and improve the efficiency of industrial seedling raising operation, a brand-new plug hole positioning device and method are urgently needed, and accurate positioning of plug holes of seedling trays of different specifications can be realized. Therefore, a precise positioning device and method for a plug hole based on machine vision are provided.
Disclosure of Invention
The invention aims to provide a precise positioning device and method for a plug hole based on machine vision, and solves the problems of poor plug hole positioning adaptability, low operation efficiency, low positioning precision and the like in the conventional industrial seedling culture.
In order to achieve the above object, the present invention adopts the following technical solutions to solve the above technical problems:
a precise positioning device for a plug hole based on machine vision comprises a rack, an image acquisition device, a conveying device, a positioning device and a control system, wherein the conveying device is installed on the rack, the image acquisition device comprises an illumination box, a light source and a camera, the illumination box is arranged on the conveying device in a spanning mode and is provided with a channel for enabling a plug on the conveying device to enter and exit the illumination box, and the camera in the illumination box acquires an image of the plug entering the illumination box; the positioning device comprises a fixed baffle, a self-adaptive baffle, a pressing plate and a photoelectric sensor for detecting the position of the plug tray, the fixed baffle and the self-adaptive baffle are respectively arranged on two sides of the rack, the self-adaptive baffle is rotationally connected with the rack, when the plug tray passes through the positioning device, the self-adaptive baffle can swing according to the specification of the plug tray and is matched with the fixed baffle on the opposite side to be clamped on two sides of the plug tray, and the pressing plate is arranged on two sides of the rack to limit the vertical jumping of the plug tray on the conveying device; the plug tray, the conveying device and the positioning device are different in color; the control system is installed on the frame, receives signals sent by the photoelectric sensor and starts the light source and the industrial camera.
One end of the self-adaptive baffle is rotatably connected to the rack through a rotating shaft, a torsion spring is arranged on the rotating shaft, and the hole disc presses the self-adaptive baffle to swing around the rotating shaft when passing through a channel between the fixed baffle and the self-adaptive baffle.
And a plurality of rollers in contact with the edge of the plug tray are arranged on the fixed baffle and the self-adaptive baffle.
The roller is a one-way bearing or a one-way roller.
The conveying device comprises a servo motor and a conveying belt, and the servo motor is connected with the control system.
The conveying belt is provided with a plurality of fixing strips, the fixing strips are arranged at intervals vertical to the conveying direction, and the relative movement between the hole tray and the conveying belt is prevented in the conveying direction.
The control system comprises a controller, an image acquisition card, an image processing module and a driving module, wherein the photoelectric sensor is connected with the controller, the controller is connected with the image acquisition device, an image acquired by the image acquisition device is transmitted to the image processing module through the image acquisition card for analysis and processing, and the controller drives the conveying device to operate through the driving module.
A precise positioning method for a plug hole based on machine vision is carried out by utilizing the precise positioning device for the plug hole, and comprises the following steps:
step one, collecting a plug tray image: when the device is operated, the plug moves on the conveying device, when the photoelectric sensor detects that the plug reaches a specified position, a signal is sent to the controller, the controller instructs the image acquisition device to acquire the plug image, and the acquired plug image is sent to the image processing module through the image acquisition card;
step two, plug matching identification: after an upper computer algorithm processor in the image processing module receives the plug image, distortion correction is carried out on the image, and the plug boundary is restored; then, dividing the plug tray by adopting contour matching; calculating the length and width of the boundary of the divided plug, and matching the length and width with a plug specification library in an upper computer algorithm processor to obtain plug specification parameters; dividing grids of the plug according to plug specification parameters, extracting four coordinates of each grid, calculating grid center coordinates, and representing plug hole positions by matching with grid numbers;
step three, positioning the plug hole: and the controller calculates the advancing real-time distance of the plug according to the received pulse number fed back by the servo motor, and finally obtains the real-time coordinates of the centers of the plug holes to realize plug hole positioning.
The plug matching identification method comprises the following steps:
(1) traversing each pixel point of the plug image, calculating the average of pixel value differences between 8 adjacent pixel points and the point, comparing the average with a set threshold value, setting the pixel value of the point to be 0 if the calculated average is greater than or equal to the threshold value, displaying the point as black, obtaining the black boundary of the plug, and displaying the black boundary, otherwise, setting the pixel value of the point to be 1, and displaying the black boundary of the plug as white;
(2) counting the number of pixel points of each boundary of the plug, calculating the length and width of the plug boundary as a and b, and respectively matching with a plug specification library in an upper computer algorithm processor to obtain the specification parameters of the plug; comparing the length a and the width b with the length l and the width w of the cavity tray in the cavity tray specification library, if the error is within 30mm, the matching of the cavity tray specification is successful, and the parameters of the cavity tray specification are recorded as
；
(3) According to the specification parameters of the plug tray
Dividing the area surrounded by the boundary of the cave disk into grids, establishing a rectangular coordinate system by taking one corner of the cave disk as an original point, extracting coordinate points of four corners of each grid and recording the coordinate points as
Wherein i, j represents the number of holes on the upper row and the row of the plug, and the grids are numbered 1,2,3 ∙ ∙ ∙ ∙ h; then, the central coordinates of the hole of the acupuncture point disk are obtained according to 4 coordinate points of the four corners of the grid, and are matched with the grid number to be recorded as
And represents the location of the disc hole.
Compared with the prior art, the invention has the beneficial effects that:
firstly, the invention realizes mechanization and continuity of hole tray hole positioning by combining the image acquisition device and the conveying device, meets the requirement of industrialized seedling culture, improves the precision of hole tray hole positioning by combining the image processing technology, and lays a good foundation for subsequent operations of seeding, transplanting, thinning and the like.
Secondly, the positioning device for the hole tray not only can realize the positioning of the hole tray on the conveying belt, but also can avoid the jumping of the hole tray in the conveying process, and the self-adaptive baffle is rotationally connected with the rack, so that when the size of the hole tray is increased, the self-adaptive baffle can rotate towards one side of the rack, the hole tray is ensured to pass through the fixed baffle and the self-adaptive baffle, the device can be suitable for the hole trays with different sizes, the application range is wider, meanwhile, the hole tray can be clamped by the self-adaptive baffle and the fixed baffle, the deviation of the hole tray is avoided, the subsequent image acquisition is ensured to be carried out smoothly, and in addition, rollers are also arranged on the fixed baffle and the self-adaptive baffle, so that the friction resistance with the hole tray can be reduced when the hole tray passes through, and the conveying track of the hole tray is corrected.
Thirdly, the conveyor belt of the invention is also provided with a fixing strip, so that the hole tray can be positioned in the conveying direction to prevent the relative movement between the hole tray and the conveyor belt.
Fourthly, as the hole discs are mostly made of black or dark plastics, the color distinction between the hole disc holes and the edge of the hole disc is not obvious, the edge of the hole disc can be shielded in the pot seedling growing process, and the recognition and segmentation effects of the hole disc holes are poor due to the traditional image segmentation method, the recognition and segmentation of the hole disc holes are realized by combining the contour matching with the grid segmentation method, and the positions of the hole disc holes can be accurately obtained.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic view of the positioning device of the present invention;
FIG. 3 is a control flow diagram of the present invention;
FIG. 4 is a rectangular coordinate system established with an angle of the plug as the origin in the image processing process of the present invention;
the labels in the figure are: 1. servo motor, 2, conveyer belt, 3, fixed strip, 4, illumination case, 5, light source, 6, industrial camera, 7, cave dish, 8, frame, 201, fixed baffle, 202, self-adaptation baffle, 203, clamp plate, 204, photoelectric sensor, 205, gyro wheel, 901, cave dish perception module, 902, controller, 903, image acquisition module, 904, image processing module, 905 drive module.
Detailed Description
The technical solution of the present invention will be further explained by the following detailed description with reference to the accompanying drawings.
As shown in fig. 1, a precise positioning device for a plug hole based on machine vision comprises a frame 8, an image acquisition device, a conveying device and a positioning device; the image acquisition device and the positioning device are arranged on the rack 8, wherein the image acquisition device is arranged in the middle of the rack 8, and the positioning device is arranged right below the image acquisition device; the conveying device comprises a servo motor 1 and a conveyor belt 2, in order to ensure that the position of the plug tray 7 in the advancing direction is unchanged, the conveyor belt 2 is provided with fixed strips 3, the fixed strips 3 are 200mm in length, 20mm in width and 600mm in distance and are uniformly distributed on the conveyor belt 2; in order to facilitate the subsequent extraction of the contour of the plug tray 7, the color of the conveyor belt is selected to be red, and is distinguished from the black color of the plug tray 7; the image acquisition device comprises an illumination box 4, a light source 5 and an industrial camera 6; the illumination box 4 is a semi-closed space formed by mounting plates, the bottom of the illumination box is arranged on the frame 8 at two sides of the conveyor belt 2 in a spanning mode, gaps are reserved at the lower portions of the mounting plates at the front end and the rear end of the forward direction of the plug tray 7, the plug tray 7 is guaranteed to normally enter and exit the illumination box 4, the length of the illumination box 4 is required to be capable of accommodating one plug tray 7, only the plug trays 7 entering the illumination box 4 are photographed one by one during image acquisition, and an illumination box door is further arranged on the side face of the illumination box 4 to facilitate installation and debugging of devices in the illumination box 4; in order to ensure the illumination environment of image acquisition, the light sources 5 are soft light sources, the number of the soft light sources is 2, and the soft light sources are arranged on two sides of the industrial camera 6 at the top of the illumination box 4; the industrial camera 6 is arranged in the middle of the top of the illumination box 4.
As shown in fig. 2, the positioning device includes a fixed baffle 201, an adaptive baffle 202, a pressing plate 203, and a photoelectric sensor 204, where 1 of the fixed baffle 201 and the adaptive baffle 202 are respectively installed inside the rack 8 at both sides of the conveyor belt 2, and the fixed baffle 201 and the adaptive baffle 202 are arranged oppositely, and the fixed baffle 201 and the adaptive baffle 202 are matched and clamped at both sides of the passing plug 7, so as to prevent the plug 7 from moving longitudinally (perpendicular to the advancing direction) to affect the positioning accuracy, and one side of the fixed baffle 201 and one side of the adaptive baffle 202 close to the plug 7 both adopt a one-way bearing as a roller 205 to prevent the plug 7 from moving backwards; as shown in fig. 2, the fixed baffle 201 is installed on the rack 8 at the left side of the conveyor belt 2, and the adaptive baffle 202 is installed on the rack 8 at the right side of the conveyor belt 2; one end of the self-adaptive baffle 202 is rotatably connected with the frame 8 through a rotating shaft, and the rotating shaft is provided with a torsion spring, so that when the plug trays 7 of different batches and specifications pass through in front and back, the distance between the two baffles does not need to be adjusted in advance, but the plug trays 7 push the self-adaptive baffle 202 to swing freely when passing through, and the distance between the two baffles is changed, so that the application range of the device can be improved, and the operation of the device is simplified; during installation, the length direction of the fixed baffle 201 is parallel to the advancing direction of the plug tray 7, the length direction of the adaptive baffle 202 and the advancing direction of the plug tray 7 form a certain angle, and one end of the adaptive baffle 202, which is far away from the rotating connection point, inclines to one side of the fixed baffle 201, so that the connecting line of the fixed baffle 201, the adaptive baffle 202 and the end parts of the fixed baffle 201 and the adaptive baffle 202 is in a right-angled ladder shape, and the plug trays 7 with different sizes can smoothly pass through; the number of the pressing plates 203 is 2, the pressing plates 203 are respectively arranged on two sides of the conveyor belt 2 and are positioned above the fixed baffle 201 and the self-adaptive baffle 202, and the distance between the pressing plates 203 and the conveyor belt 2 is greater than the height of the plug tray 7, so that the plug tray 7 can not be blocked by the pressing plates 203 to pass through the lower part of the pressing plates 203; the number of the photoelectric sensors 204 is 2, and the photoelectric sensors are installed on the machine frame 8 on two sides of the conveyor belt 2 according to the mode shown in fig. 2, and are used for detecting whether the plug tray 7 reaches an image acquisition area. The installation mode and the position of the parts can be adjusted according to the actual operation condition.
In order to facilitate the processing after image acquisition, the fixed baffle 201, the adaptive baffle 202 and the pressing plate 203 are made of colors with high contrast with the plug 7.
As shown in fig. 3, the precise positioning device for a plug hole based on machine vision further includes a control system closely matched with the device, and the photoelectric sensor 204 adopts an ohilong EE-SV3 photoelectric sensor as a plug sensing module 301 of the control system; the light source 5 adopts a Weidel LED light source, the industrial camera 6 adopts a Beijing navigation 300F industrial camera, and the light source 5, the industrial camera 6 and an image acquisition card form an image acquisition module 303 of the control system, wherein the image acquisition card adopts an acute-viewing RS400 image acquisition card; the servo motor 1 and the servo driver form a driving module 305 in the control system; the control system also comprises a controller 302 and an image processing module 304, wherein the controller 302 can adopt a PLC, a singlechip and a raspberry dispatching system, and the image processing module 304 comprises an upper computer algorithm processor and an RS485 communication serial port protocol;
the photoelectric sensor 204 is connected with the controller 302, the controller 302 is connected with the image acquisition module 303, an image acquired by the image acquisition module is transmitted to the image processing module 304 through the image acquisition card for analysis and processing, the controller 302 drives the servo motor 1 to operate through the servo driver, and the aperture disk 7 is transmitted for image acquisition.
The method for positioning the plug hole by using the plug hole accurate positioning device based on the machine vision comprises the following steps:
the method comprises the following steps: acquisition of plug images: when the device is operated, the servo motor 1 is operated, the conveyor belt 2 drives the plug tray 7 to move forward, the plug tray 7 enters the illumination box 4, when the photoelectric sensor 204 detects the plug tray 7, the plug tray 7 reaches the designated position of an image acquisition area, the photoelectric sensor 204 sends a signal to the controller 302, the controller 302 instructs the light source 5 to be turned on, the industrial camera 6 acquires a plug tray image, and the acquired plug tray image is transmitted to the image processing module 304 through the image acquisition card.
Step two: and (3) plug matching identification: after the upper computer algorithm processor in the image processing module 304 receives the plug picture, the plug holes are identified and positioned through the following 3 links.
(1) Image distortion correction
In order to compensate for the recognition error and error of the aperture disk 7 caused by the distortion of the camera, the distortion correction is firstly performed on the received picture, and the principle is as follows:
in the formula (I), the compound is shown in the specification,
in order to correct the coordinates of the pixel points,
in order to correct the coordinates of the pixel points before correction,
in order to be a distortion coefficient of the image,
。
(2) identification of acupoint plate matching
As the plug 7 is mostly made of black or dark plastics, the color distinction between the plug holes and the edge of the plug 7 is not obvious, and the edge of the plug can be shielded in the pot seedling growing process, the plug hole identification and segmentation effect is poor due to the traditional image segmentation method. The invention adopts contour matching and grid selection division to realize the matching, identification and segmentation of the plug 7. In the invention, as the color of the plug tray 7 is greatly different from the colors of the conveyor belt 2, the fixed baffle 201, the self-adaptive baffle 202 and the pressing plate 203, the plug tray boundary is extracted by adopting an average threshold difference method, which specifically comprises the following steps: traversing each pixel point of the image, calculating the average of pixel value differences of 8 adjacent pixel points and the pixel point, and comparing the average with a set threshold value; if the average difference value is greater than or equal to the threshold value, setting the pixel value of the point to be 0, displaying the pixel value as black, and obtaining and displaying the black boundary of the plug 7; otherwise, the pixel value of the point is set to 1, and the display is white.
The principle of extracting the boundary of the plug by the average threshold difference method is as follows:
in the formula (I), the compound is shown in the specification,
in order to output the image(s),
in order to input an image, the image is,
and T is the average pixel difference of any pixel point of the input image, and is the set threshold value.
Counting the number of pixel points on each boundary of the plug 7, calculating the length and width of the plug boundary as a and b, and respectively matching with a plug specification library in an upper computer algorithm processor to obtain specification parameters of the plug 7; comparing the length a and the width b with the length l and the width w of the plug 7 in the plug specification library, if the error is within 30mm, the matching plug specification is successful, and the plug specification parameters are recorded as
。
Finally, according to the specification parameters of the plug tray
Dividing the area surrounded by the boundary of the plug into grids, as shown in fig. 4, establishing a rectangular coordinate system with one corner of the plug 7 as the origin, extracting four coordinate points of each grid and recording the four coordinate points as
Wherein i, j represents the number of rows and columns of the tray holes on the tray 7, and the grids are numbered 1,2,3 ∙ ∙ ∙ ∙ h; then, the central coordinates of the hole of the acupuncture point disk are obtained according to the 4 coordinate points of the grid, and are matched with the grid number to be recorded as
Is represented byThe location of the disc hole.
(3) Positioning of the disc holes
The industrial camera 6 finishes the acquisition of the aperture disk image, after the signal is sent to the controller 302, the controller 302 starts to receive and record the pulse number n fed back by the servo motor 1, the pulse number is fed back to the upper computer algorithm processor through an RS485 communication serial port protocol to calculate the advancing distance d of the aperture disk 7 in real time, and finally the real-time coordinate of the center of each aperture disk hole is obtained
And the positioning of the plug hole is realized.
Claims (7)
1. A precise positioning method for a plug hole based on machine vision adopts a precise positioning device for the plug hole based on machine vision, the precise positioning device for the plug hole comprises a rack (8), an image acquisition device, a conveying device, a positioning device and a control system, the conveying device is installed on the rack (8), the image acquisition device comprises an illumination box (4), a light source (5) and an industrial camera (6), the illumination box (4) is arranged on the conveying device in a spanning mode and is provided with a channel for the plug (7) on the conveying device to enter and exit the illumination box (4), and the industrial camera (6) in the illumination box (4) acquires an image of the plug (7) entering the illumination box (4); the positioning device comprises a fixed baffle (201), a self-adaptive baffle (202), a pressing plate (203) and a photoelectric sensor (204) for detecting the position of the plug tray (7), wherein the fixed baffle (201) and the self-adaptive baffle (202) are respectively arranged on two sides of the rack (8), the self-adaptive baffle (202) is rotatably connected with the rack (8), when the plug tray (7) passes through, the self-adaptive baffle (202) can swing according to the specification of the plug tray (7) and is matched with the fixed baffle (201) on the opposite side to be clamped on two sides of the plug tray (7), and the pressing plate (203) is arranged on two sides of the rack (8) to limit the vertical jumping of the plug tray (7) on the conveying device; the plug tray (7), the conveying device and the positioning device are different in color; the control system is arranged on a frame (8), receives a signal sent by the photoelectric sensor (204), and starts the light source (5) and the industrial camera (6); the control system comprises a controller (902), an image acquisition card, an image processing module (904) and a driving module (905), wherein the photoelectric sensor (204) is connected with the controller (902), the controller (902) is connected with the image acquisition device, an image acquired by the image acquisition device is transmitted to the image processing module (904) through the image acquisition card for analysis and processing, and the controller (902) drives the conveying device to operate through the driving module (905); the method is characterized in that: the precise positioning method of the hole plate hole comprises the following steps:
step one, collecting a plug tray image: when the accurate positioning device for the plug hole runs, the plug (7) moves on the conveying device, when the photoelectric sensor (204) detects that the plug (7) reaches a specified position, a signal is sent to the controller (902), the controller (902) instructs the image acquisition device to acquire plug images, and the acquired plug images are sent to the image processing module (904) through the image acquisition card;
step two, plug matching identification: after an upper computer algorithm processor in the image processing module (904) receives the plug image, distortion correction is carried out on the image, and the plug boundary is restored; then, the plug (7) is divided by adopting contour matching; calculating the length and width of the boundary of the divided plug, and matching the length and width with a plug specification library in an upper computer algorithm processor to obtain plug specification parameters; dividing grids of the plug (7) according to plug specification parameters, extracting four coordinates of each grid, calculating grid center coordinates, and representing plug hole positions by matching with grid numbers;
step three, positioning the plug hole: the controller (902) calculates the real-time distance of the forward motion of the plug (7) according to the received pulse number fed back by the servo motor (1), and finally obtains the real-time coordinates of the centers of the plug holes to realize plug hole positioning.
2. The precise positioning method for the plug hole based on the machine vision as claimed in claim 1, wherein: one end of the self-adaptive baffle (202) is rotatably connected to the rack (8) through a rotating shaft, a torsion spring is arranged on the rotating shaft, and the hole disc (7) presses the self-adaptive baffle (202) to swing around the rotating shaft when passing through a channel between the fixed baffle (201) and the self-adaptive baffle (202).
3. The precise positioning method for the plug hole based on the machine vision as claimed in claim 1 or 2, wherein: and a plurality of rollers (205) contacted with the edge part of the plug tray (7) are arranged on the fixed baffle (201) and the self-adaptive baffle (202).
4. The precise positioning method for the plug hole based on the machine vision as claimed in claim 3, characterized in that: the roller (205) is a one-way bearing or a one-way roller.
5. The precise positioning method for the plug hole based on the machine vision as claimed in claim 1, wherein: the conveying device comprises a servo motor (1) and a conveying belt (2), and the servo motor (1) is connected with the control system.
6. The precise positioning method for the plug hole based on the machine vision as claimed in claim 5, wherein: the conveying belt (2) is provided with a plurality of fixing strips (3), the fixing strips (3) are arranged at intervals in a direction perpendicular to the conveying direction, and relative movement between the plug tray (7) and the conveying belt (2) is prevented in the conveying direction.
7. The precise positioning method for the plug hole based on the machine vision as claimed in claim 1, wherein the plug matching identification method is:
(1) traversing each pixel point of the plug image, calculating the average of pixel value differences between 8 adjacent pixel points and the point, comparing the average with a set threshold value, setting the pixel value of the point to be 0 if the calculated average is greater than or equal to the threshold value, displaying the point as black, obtaining the black boundary of the plug, and displaying the black boundary, otherwise, setting the pixel value of the point to be 1, and displaying the black boundary of the plug as white;
(2) counting the number of pixel points of each boundary of the plug, calculating the length and width of the plug boundary as a and b, and respectively matching with a plug specification library in an upper computer algorithm processor to obtain the specification parameters of the plug; comparing the length a and the width b with the length l and the width w of the cavity tray in the cavity tray specification library, if the error is within 30mm, the matching of the cavity tray specification is successful, and the parameters of the cavity tray specification are recorded as
；
(3) According to the specification parameters of the plug tray
Dividing the area surrounded by the boundary of the cave disk into grids, establishing a rectangular coordinate system by taking one corner of the cave disk as an original point, extracting coordinate points of four corners of each grid and recording the coordinate points as
Wherein i, j represents the number of holes on the upper row and the row of the plug, and the grids are numbered 1,2,3 ∙ ∙ ∙ ∙ h; then, the central coordinates of the hole of the acupuncture point disk are obtained according to 4 coordinate points of the four corners of the grid, and are matched with the grid number to be recorded as
And represents the location of the disc hole.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910102870.2A CN109654997B (en) | 2019-02-01 | 2019-02-01 | Precise positioning device and method for plug hole based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910102870.2A CN109654997B (en) | 2019-02-01 | 2019-02-01 | Precise positioning device and method for plug hole based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109654997A CN109654997A (en) | 2019-04-19 |
| CN109654997B true CN109654997B (en) | 2020-10-30 |
Family
ID=66122601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910102870.2A Active CN109654997B (en) | 2019-02-01 | 2019-02-01 | Precise positioning device and method for plug hole based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109654997B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113724254A (en) * | 2021-10-13 | 2021-11-30 | 石河子大学 | Full-automatic plug seedling recognition device |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6208769B1 (en) * | 1998-05-28 | 2001-03-27 | Acuity Imaging, Llc | Method of accurately locating the fractional position of a template match point |
| CN201872029U (en) * | 2010-09-14 | 2011-06-22 | 乳山市双兴机床制造有限公司 | Novel full automatic double-end surface grinding machine |
| CN102135429B (en) * | 2010-12-29 | 2012-06-13 | 东南大学 | Robot indoor positioning and navigating method based on vision |
| KR101822655B1 (en) * | 2011-06-21 | 2018-01-29 | 삼성전자주식회사 | Object recognition method using camera and camera system for the same |
| CN102890840B (en) * | 2012-08-22 | 2016-03-23 | 山东新北洋信息技术股份有限公司 | Banknote discriminating method and device |
| CN203612567U (en) * | 2013-12-09 | 2014-05-28 | 云南省师宗金曲陶瓷有限公司 | Tile conveying process automatic deviation rectifying device |
| CN203946568U (en) * | 2014-06-16 | 2014-11-19 | 徐工集团工程机械股份有限公司 | Material receiving device and belt conveyer |
| CN105118028B (en) * | 2015-07-30 | 2018-07-06 | 沈阳农业大学 | A kind of grafting seam identification device of full-automatic grafting machine and seam recognition methods |
| CN107609270A (en) * | 2017-09-12 | 2018-01-19 | 武汉大学 | A kind of ellipsoid building damnification recognition method based on digitlization modal coordinate |
| CN107909083B (en) * | 2017-11-10 | 2019-03-15 | 中国科学院地理科学与资源研究所 | A kind of hough transform extracting method based on outline optimization |
| CN107690906B (en) * | 2017-11-22 | 2023-10-20 | 河南科技大学 | Pot seedling tray seedling leakage detection and positioning seedling searching and changing device and method |
| CN109220110B (en) * | 2018-09-27 | 2024-02-06 | 湖南农业大学 | Seedling tray positioning device |
-
2019
- 2019-02-01 CN CN201910102870.2A patent/CN109654997B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109654997A (en) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN206132660U (en) | Small dimension ceramic tile vision sorting device | |
| CN107860366B (en) | Mobile greenhouse crop information measurement and diagnosis system | |
| CN113313711B (en) | Camera, system and detection method for detecting width of lithium battery pole piece | |
| CN108225798B (en) | Tire slippage testing system and method based on edge enhancement identification | |
| CN109380146B (en) | Automatic measurement device and method for live pigs | |
| CN109654997B (en) | Precise positioning device and method for plug hole based on machine vision | |
| CN102673106A (en) | Silk screen print positioning equipment and method for photovoltaic solar silicon chip | |
| CN109144043A (en) | The method for tracking object | |
| CN216622191U (en) | Lithium battery appearance defect detection system based on machine vision | |
| CN207530941U (en) | Image tracing device | |
| CN113277314B (en) | Panel offset adjusting device and method based on FPGA image detection control | |
| CN105549486A (en) | Tobacco topping sprouting inhibition detection control system based on machine vision | |
| CN203633110U (en) | Device for automatically identifying seedling tray and pot seedlings as well as picking seedlings | |
| CN109590231A (en) | A kind of non-regular shape material image measurement measuring and controlling device and method | |
| CN102645160B (en) | Image measuring apparatus | |
| CN114136217B (en) | Steel plate flexibility detection system and method | |
| CN108257188A (en) | A kind of moving target detecting method | |
| EP3961568A1 (en) | Crop growth measurement system based on crop images, and method thereof | |
| CN106815556A (en) | A kind of plane crowd hazards data collecting system of many data types | |
| CN109884054A (en) | A kind of high-precision health pot seedling intelligent recognition and positioning device based on machine vision | |
| CN110741790B (en) | Multi-claw transplanting-sorting processing method for plug seedlings based on depth camera | |
| CN204479092U (en) | Based on the vision inspection apparatus of planar imaging techniques | |
| CN108180825A (en) | A kind of identification of cuboid object dimensional and localization method based on line-structured light | |
| CN108594323B (en) | Robust seedling recognition device based on machine vision and use method thereof | |
| CN108226185A (en) | The accurate acquisition device of bottle cap image and method based on iteration control |
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 |