CN115183687A - Method, device and system for identifying thickness of single plates of stacked plates - Google Patents
Method, device and system for identifying thickness of single plates of stacked plates Download PDFInfo
- Publication number
- CN115183687A CN115183687A CN202210621847.6A CN202210621847A CN115183687A CN 115183687 A CN115183687 A CN 115183687A CN 202210621847 A CN202210621847 A CN 202210621847A CN 115183687 A CN115183687 A CN 115183687A
- Authority
- CN
- China
- Prior art keywords
- plate
- thickness
- measurement image
- distance sensor
- camera
- 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
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
Abstract
The invention discloses a method, a device and a system for identifying the thickness of a stacked plate veneer, which comprise a material preparation platform for placing a plate stacking block and a thickness detection assembly, wherein the thickness detection assembly comprises a distance sensor group and a camera assembly, the distance sensor group is arranged above the material preparation platform and is used for measuring the height of the plate stacking block, and the camera is used for acquiring a measurement image of the side surface of the plate stacking block; the device comprises a distance sensor group and a camera assembly, and is characterized by further comprising a controller, wherein the controller is respectively connected with the distance sensor group and the camera assembly so as to read height data of the plate stacking blocks collected by the distance sensor group and measurement images collected by the camera assembly and calculate the thickness of the plate stacking blocks. According to the invention, the thickness of the single plate of the plate stacking block is automatically determined, so that the complex manual operation is reduced, the manpower and material resources are saved, the error of the manual operation is avoided, the manual error rate is reduced, and the automatic purification efficiency is improved.
Description
Technical Field
The invention relates to the technical field of plate processing, in particular to a stacked plate single plate thickness identification method, a device and a system thereof.
Background
In the automatic purification process of panel, need remove the aldehyde storehouse to high temperature to panel transportation in proper order, the humidification storehouse, spout and handle like the medicament storehouse, the formaldehyde release is with higher speed heated to panel in the aldehyde storehouse is removed to high temperature, the humidification storehouse is used for the humidity control after the panel high temperature, spraying medicament storehouse is used for having the medicament that removes aldehyde or function such as smell to panel surface coating, to needing the automatic purification process of panel, need acquire the initial state data of waiting to purify panel, mainly include: the material, density, thickness, length and width, water content and initial environmental protection level (initial formaldehyde emission) are determined according to the obtained initial state data, and an initial purification mode related to parameters such as temperature parameters, humidification parameters and the like is determined, so that the full-automatic purification of the plate is realized. Then before the automatic purification process of the plate, a camera arranged above the top surface of the stacked plate block usually shoots a measurement image containing a two-side view or a three-side view of the stacked plate block, wherein the two-side view or the three-side view comprises the side surface of the stacked plate block and one or two side surfaces adjacent to the side surface, so that the shot measurement image of the inclination or deformation of the stacked plate block caused by the shooting angle in the shooting process can greatly reduce the accuracy of the identification of the thickness of the single plate.
Disclosure of Invention
The invention aims to provide a method, a device and a system for identifying the thickness of a single plate of a stacked plate.
A stacked plate veneer thickness identification system is used for a material preparation platform for placing a stacked plate and a thickness detection assembly, wherein the thickness detection assembly comprises a distance sensor group and a camera assembly which are arranged above the material preparation platform, the distance sensor group is used for measuring the height of the stacked plate, and the camera is used for acquiring a measurement image of the side face of the stacked plate;
the device comprises a distance sensor group and a camera assembly, and is characterized by further comprising a controller, wherein the controller is respectively connected with the distance sensor group and the camera assembly so as to read height data of the plate stacking blocks collected by the distance sensor group and measurement images collected by the camera assembly and calculate the thickness of the plate stacking blocks.
Further, the distance sensor group comprises at least one distance sensor, and the sensing direction of the distance sensor is opposite to the top surface of the plate stacking block and used for detecting the distance between the distance sensor and the plate stacking block in the height direction.
Furthermore, the camera assembly is arranged above the plate stacking block in an inclined mode and comprises a holder and a camera installed on the holder, and the controller is connected with the holder and the camera respectively.
A method for identifying the thickness of single plates of a stacked plate specifically comprises the following steps:
s1, acquiring a first distance D0 between a distance sensor in a distance sensor group and the top surface of a plate stacking block;
s2, calculating the height H = DX0-D0 of the plate stacking block according to a first preset distance DX0 and a first distance D0 measured by a distance sensor of the distance sensor group and between the plate stacking block and a material preparation platform;
s3, obtaining a measurement image shot by a camera, and judging whether the measurement image contains the side surfaces of all single plates or not;
when the measured image contains the side faces of all the single plates, acquiring the number K of boundary lines in the measured image by using a pre-established recognition model;
calculating the number N of single plates of the plate stacking block according to the number K of the dividing lines;
and S4, calculating the thickness H of the single plate corresponding to the plate stacking block according to the obtained height H of the plate stacking block and the number N of the single plates, wherein H = H/N.
Further, before acquiring the boundary number K in the measurement image by using a pre-established recognition model, the method further comprises a correction step of:
determining the original four corner point coordinates of the side face of the plate stacking block in the measurement image;
determining four corner point coordinates of the sides of the plate stacking block after expected perspective transformation;
calculating parameters of a perspective transformation matrix according to the original four corner coordinates and the corrected four corner coordinates;
and carrying out perspective transformation on the side surface of the plate stacking block in the measurement image according to the perspective transformation matrix parameters to obtain a corrected measurement image.
Further, the original four corner coordinates are obtained by the following steps:
performing straight line detection in the measurement image to obtain two end points of line segments corresponding to four edges in the measurement image;
generating a linear equation corresponding to each edge according to the two end points of the line segment corresponding to each edge;
and obtaining four intersection point coordinates according to a linear equation corresponding to four edges in the measured image, and determining the four intersection point coordinates as the original four corner point coordinates.
Further, the measurement image is a measurement image which is obtained under the guidance of the placement area frame and contains the side face of the plate stacking block; the placing area frame is used for guiding and adjusting the shooting angle of the camera so as to enable the side area of the plate stacking block to be positioned in the placing area frame for shooting;
the performing of the line detection in the measurement image includes: and performing straight line detection in the measurement image within a predetermined range corresponding to each side of the placement area frame.
Further, the measurement image including the side surface of the plate material stacking block acquired under the guidance of the placement area frame specifically includes the following steps:
acquiring a currently shot measurement image;
and judging whether the IOU of the plate stacking block side area and the placing area frame in the currently shot measurement image is larger than a preset intersection threshold value or not, if so, adjusting the shooting angle of the camera until the plate stacking block side area is positioned in the placing area frame.
Further, the adjusting process of the shooting angle of the camera specifically includes the following steps:
determining a deviation angle of the camera according to the placement area frame and the first position, wherein the deviation direction of the deviation angle comprises four directions, namely an upper direction, a lower direction, a left direction and a right direction;
and generating a control instruction according to the offset angle, wherein the control instruction is used for controlling the holder to enable the camera to move at the offset angle.
A control device for identifying the thickness of single plates of a stacked plate comprises:
one or more processors;
a storage unit, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, enable the one or more processors to implement the method for identifying a thickness of a stacked board veneer.
The invention has the following beneficial effects:
1. the method comprises the steps of obtaining a two-side view or three-side view measurement image of a plate stacking block through a camera assembly, carrying out image cutting and correction preprocessing (perspective transformation method) on the two-side view or three-side view measurement image to obtain a side view of a plate to be identified, further identifying the thickness of the single plate according to a convolutional neural network, and improving the accuracy of single plate thickness identification in the full-automatic purification process of the existing plate.
2. By efficiently tracking the plate stacking blocks, the adjusting efficiency is higher, so that the side surfaces of the plate stacking blocks in each measuring process are always positioned in the placing area frame without being manually adjusted by a user, the operation difficulty of the user is reduced, the adjusting accuracy of the shooting angle is improved, and the calculating speed of the original four angular point coordinates is further improved;
3. the method comprises the steps of obtaining a measurement picture through a camera assembly arranged above a plate stacking block in an inclined mode, wherein the measurement picture is obtained before a tag image is uploaded to a cloud end for identification, the collected measurement image is not a front identification image of the side face of the plate stacking block, and an error exists when a boundary is obtained, so that a standard measurement image is obtained through correction processing of the measurement image, the error of an image identification process is reduced, the processing efficiency is high, the thickness of a single plate of the plate stacking block is automatically determined, tedious manual operation is reduced, manpower and material resources are saved, errors of manual operation are avoided, the artificial error rate is reduced, and the automatic purification efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of a veneer thickness recognition method according to the present invention;
FIG. 2 is a schematic illustration of a stock preparation platform of the present invention;
FIG. 3 is a schematic view of a system for identifying a thickness of stacked sheets of material;
FIG. 4 is a schematic diagram of the first distance D0 according to the present invention;
FIG. 5 is a schematic view of a first predetermined distance DX0 according to the present invention;
FIG. 6 is a measurement image of a three-sided view of a sheet stacking block of the present invention;
FIG. 7 is a corrected measurement image of a sheet stacking block of the present invention;
reference numerals are as follows: 1-material preparation platform, 2-feeding platform, 3-linear driving mechanism, 4-sleeper, 5-clamping groove, 6-blocking block, 11-mounting rack, 12-plate stacking block, and 13-distance sensor group C, 14-camera assembly.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
In addition, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness. Those of ordinary skill in the art will recognize that various changes and modifications of the examples described herein can be made without departing from the spirit and scope of the disclosure.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
Example 1
A stacked plate veneer thickness identification system is used for a material preparation platform for placing a stacked plate and a thickness detection assembly, wherein the thickness detection assembly comprises a distance sensor group and a camera assembly which are arranged above the material preparation platform, the distance sensor group is used for measuring the height of the stacked plate, and the camera is used for acquiring a measurement image of the side face of the stacked plate;
the device comprises a distance sensor group and a camera assembly, and is characterized by further comprising a controller, wherein the controller is respectively connected with the distance sensor group and the camera assembly so as to read height data of the plate stacking blocks collected by the distance sensor group and measurement images collected by the camera assembly and calculate the thickness of the plate stacking blocks.
In one embodiment, the distance sensor group comprises at least one distance sensor, and the sensing direction of the distance sensor is opposite to the top surface of the plate stacking block and is used for detecting the distance between the distance sensor and the plate stacking block in the height direction.
In one embodiment, the camera assembly is deployed obliquely above the plate stacking block and comprises a holder and a camera mounted on the holder, and the controller is connected with the holder and the camera respectively.
The camera can be connected with the controller, a measurement image of a preset area is obtained according to an instruction of the controller, and the controller is started after receiving an image sent by the camera assembly to perform image recognition of the panel stacking block in the image.
Specifically, camera and distance sensor install on the mounting bracket, the mounting bracket sets up on the diagonal extension line apart from the stacked piece of panel.
The controller is connected with the cradle head and used for controlling the cradle head, the camera is installed on the cradle head and used for controlling the rotation of the camera, the MCU control circuit board is connected with the PC through a USB-HUB, the PC end mainly comprises an interface layer and an application layer, the application layer is used for displaying a user UI interface, the interface layer is used for realizing image recognition and detection algorithms, and meanwhile, the interface layer drives the control module through driving software.
Specifically, the camera assembly may be in an on state for a long time, and obtain a measurement image of the predetermined area at a preset time interval, for example, obtain an image of the predetermined area at preset time intervals for identification. The camera assembly can be in a closed state, can be started after receiving a driving command of the controller, and obtains a measurement image of a preset area. Before the automatic purification of panel, the controller drive distance sensor group measures its and prepare material the first preset distance DX0 between the platform.
When plates need to be automatically purified, an operator transports plate stacking blocks which are orderly stacked to an appointed material preparation platform through a forklift, sends a detection instruction to a distance sensor group through a controller and sends a shooting instruction to a camera assembly so as to obtain a first distance D0 measured by the distance sensor and obtain a measurement image of a plurality of plate stacking blocks shot by the camera assembly.
In one embodiment of the application, the stock preparation platform comprises at least two sleepers arranged on top of the stock preparation platform, and the sleepers are adjustable in position on the stock preparation platform perpendicular to the direction of the feed side. The number of crossties is freely chosen according to the size of the board. When the height H of the plate stacking block is calculated, the thickness of the sleepers and the height of gaps between the sleepers and the material preparation platform need to be considered, the thickness of the sleepers and the height of the gaps between the sleepers and the material preparation platform can be obtained through actual measurement, and the thickness of the sleepers and the height of the gaps between the sleepers and the material preparation platform are set to be delta H, so that the height H = DX 0-D0-delta H.
Example 2
A method for identifying the thickness of single plates of a stacked plate specifically comprises the following steps:
s1, acquiring a first distance D0 between the distance sensor of the distance sensor group and the top surface of the plate stacking block;
s2, calculating the height H = DX0-D0 of the plate stacking block according to a first preset distance DX0 and a first distance D0 measured by a distance sensor of the distance sensor group and between the plate stacking block and a material preparation platform;
s3, obtaining a measurement image shot by a camera, and judging whether the measurement image contains the side surfaces of all single plates or not;
when the measured image contains the side faces of all the single plates, acquiring the number K of boundary lines in the measured image by using a pre-established recognition model;
calculating the number N of the single plates of the plate stacking block according to the number K of the dividing lines;
and when the measured image does not contain the side surfaces of all the single plates, sending an instruction for adjusting the shooting direction of the camera.
Specifically, the number K of the dividing lines is a dividing line between two single plates, and the number N = K +1 of the single plates of the plate stacking block.
And S4, calculating the thickness H of the single plate corresponding to the plate stacking block according to the obtained height H of the plate stacking block and the number N of the single plates, wherein H = H/N.
Specifically, the original four corner coordinates are obtained by the following steps:
performing straight line detection in the measurement image to obtain two end points of line segments corresponding to four edges in the measurement image;
generating a linear equation corresponding to each edge according to the two end points of the line segment corresponding to each edge;
and obtaining four intersection point coordinates according to a linear equation corresponding to four edges in the measured image, and determining the four intersection point coordinates as the original four corner point coordinates.
Specifically, the measurement image is a measurement image including a side surface of the plate material stacking block, which is acquired under the guidance of the placement area frame; the placing area frame is used for guiding and adjusting the shooting angle of a camera so as to enable the side area of the plate stacking block to be positioned in the placing area frame for shooting;
the performing of the line detection in the measurement image includes: and performing straight line detection in the measurement image within a predetermined range corresponding to each side of the placement area frame.
Specifically, the measurement image including the side surface of the plate material stacking block acquired under the guidance of the placement area frame specifically includes the following steps:
acquiring a currently shot measurement image;
and judging whether the IOU of the plate stacking block side area and the placing area frame in the currently shot measurement image is larger than a preset intersection threshold value or not, if so, adjusting the shooting angle of the camera until the plate stacking block side area is positioned in the placing area frame.
Specifically, the device realizes 360-degree continuous rotation of the camera through the rotating cradle head. The method comprises the following steps:
acquiring an acquired measurement image, and determining a first position of the side face of the plate stacking block in the measurement image when the plate stacking block side face is detected to be included in the measurement image;
determining whether the first position meets an adjustment condition, if so, determining a deviation angle of the camera according to a placement area frame and the first position, wherein the placement area frame comprises the central position of the measurement image, and the deviation direction of the deviation angle comprises four directions, namely an upper direction, a lower direction, a left direction and a right direction;
generating a control instruction according to the offset angle, wherein the control instruction is used for controlling a holder to enable the camera to move by the offset angle;
the adjustment condition is specifically a placing area frame comparison method: and judging whether the IOU of the plate stacking block side area and the placing area frame in the currently shot measurement image is larger than a preset intersection threshold value or not, if so, adjusting the shooting angle of the camera until the plate stacking block side area is positioned in the placing area frame.
The offset angle is the rotation angle of the camera, and the rotation direction can be four directions, namely the camera can rotate in four directions. When the camera shifts, the range of the corresponding acquisition picture changes, and the position of the side face of the plate stacking block contained in the measurement image picture in the image picture changes correspondingly. In one embodiment, the database stores the variation distances of the offset angles in different directions corresponding to the first positions, and illustratively, the first positions of the sides of the sheet stack block in the image frame are shifted by 2cm in response to a 5 ° rotation of the camera in one direction (e.g., the lateral direction). Specifically, a distance value a of the first position and the placement area frame is calculated, component distance values ax and ay of the distance value in an x axis and a y axis are calculated, a bx offset angle corresponding to the ax distance value and a by offset angle corresponding to the ay distance value are obtained according to a relation between the distance value and the offset angle stored in a database, wherein the bx offset angle is an angle of rotation offset along the x axis, the by offset angle is an angle of rotation offset along the y axis, and bx and by are determined as offset angles which the current camera head needs to rotate.
Illustratively, the control command is generated by the controller, and if the determined offset angle bx along the x-axis is 5 ° and the determined offset angle by along the y-axis is 10 °, the control command is generated to control the pan/tilt head, wherein the camera on the pan/tilt head performs angular deflection, that is, the camera is rotated by 5 ° and 10 ° along the x-axis and the y-axis, respectively, by issuing the control command. In another embodiment, the pan-tilt is a three-axis pan-tilt, and the direction of the comprehensive rotation of the camera can be calculated, for example, the camera rotates along the x-axis and y-axis directions with an included angle of 30 degrees, that is, the camera does not rotate in a pure horizontal or pure vertical manner, but rotates in a direction with a certain inclination angle.
Wherein, before acquiring the acquired measurement image, the method further comprises:
when the trigger of a side face identification event of the plate stacking block is detected, controlling a camera to shoot pictures;
if the side face of the plate stacking block is detected not to be contained in the measurement image, carrying out position recognition on the measurement image;
determining a first offset angle according to a part identification result, and generating a first control instruction according to the first offset angle, wherein the first control instruction is used for controlling a holder to enable the camera to move by the first offset angle;
determining a first offset angle according to a part recognition result, and generating a control instruction according to the first offset angle, wherein the control instruction is used for controlling a holder to enable the camera to move at the first offset angle, and the control instruction comprises:
searching an offset angle interval associated with the corresponding part in a preset table according to the part identification result;
generating a control instruction group according to the offset angle interval, wherein each control instruction in the control instruction group corresponds to one offset angle in the offset angle interval;
and the control instruction group is used for controlling the holder to enable the camera to move or rotate in the offset angle interval.
The part is identified as the part of the plate stacking block placing area, a plurality of identification parts can be placed on the periphery of a material preparation platform in an automatic plate stacking workshop, and different first offset angles are determined according to different identification parts.
In an embodiment of the present invention, when a predetermined area of a sheet stack block is identified by an image model, the controller inputs the predetermined area of the sheet stack block into a pre-established identification model to obtain the number of boundaries of the predetermined area of the sheet stack block in the image. The recognition model is stored in the controller and is activated after the input of the measurement image. The recognition model may be a deep learning model or the like, and includes a deep learning unit and an output terminal, and the recognition model receives the measurement image for analysis by the deep learning unit and outputs an analysis result from the output terminal. The deep learning unit can be RNN learning unit, CNN learning unit, LSTM learning unit, etc.
In an embodiment of the invention, the sheet stacking block is fixedly disposed within a predetermined area. For example, in performing automated cleaning of sheet material, a stack of sheet material is placed on a stock preparation platform by a forklift.
As can be understood by those skilled in the art, the number of boundaries of the sheet material stacking block in the measurement image is obtained by identifying the model, the initial marking is performed on the training measurement picture of the sheet material stacking block, the number of boundaries in each measurement picture is marked, and the marked image sample data comprises one measurement picture and a label of the number of the boundaries;
in one embodiment, a neural network is trained based on initially labeled image sample data;
determining the confidence coefficient of the sheet material stacking blocks to be marked on each boundary line by using the trained neural network; wherein, the output of the neural network is the final confidence estimation value of each boundary number; based on these estimates, the number of boundaries with the highest confidence is selected as the final output.
In one embodiment, the recognition model comprises a side recognition model and a recognition boundary line model.
Inputting the measurement image into a side recognition model, wherein the side recognition model is trained by using a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: an image of a sheet stacking block and identification information for identifying whether a side of the sheet stacking block is complete;
obtaining output information of the model, wherein the output information comprises an identifier of whether the measurement image is complete or not.
Inputting the measurement image into the sheet stacking block model;
acquiring information whether the measurement image contains all single-plate side faces from the plate stacking block model, wherein the side face identification model is obtained by using multiple groups of data through machine learning training, the multiple groups of data comprise first-class data and second-class data, and each group of data in the first-class data comprises: the image containing the information of all the single board sides and the label for marking that the photo contains the information of all the single board sides; each group of the second type data comprises: a photograph that does not contain information on all the sides of the single board and a label that identifies that the photograph does not contain information on all the sides of the single board.
When the measurement image does not contain the sheet material stacking block, sending a command for readjusting the shooting angle to the camera assembly.
Example 3
A control device for identifying the thickness of single plates of a stacked plate comprises:
one or more processors;
a storage unit, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, enable the one or more processors to implement the stacked plate single plate thickness identification method.
The foregoing is only a preferred embodiment of the present invention, and the present invention is not limited thereto in any way, and any simple modification, equivalent replacement and improvement made to the above embodiment within the spirit and principle of the present invention still fall within the protection scope of the present invention.
Claims (10)
1. The system for identifying the thickness of the single plates of the stacked plates is characterized by comprising a material preparation platform for placing the stacked plates and a thickness detection assembly, wherein the thickness detection assembly comprises a distance sensor group and a camera assembly, the distance sensor group and the camera assembly are arranged above the material preparation platform, the distance sensor group is used for measuring the height of the stacked plates, and the camera is used for acquiring a measurement image of the side face of the stacked plates;
the controller is respectively connected with the distance sensor group and the camera assembly so as to read the height data of the plate stacking blocks collected by the distance sensor group and the measurement images collected by the camera assembly and calculate the thickness.
2. The system for identifying the thickness of single plates of stacked plates according to claim 1, wherein the distance sensor set comprises at least one distance sensor, and the sensing direction of the distance sensor is opposite to the top surface of the stacked plate blocks for detecting the distance between the distance sensor and the stacked plate blocks in the height direction.
3. The system for identifying the thickness of the stacked single plates according to claim 1, wherein the camera assembly is disposed obliquely above the plate stacking block and comprises a pan-tilt and a camera mounted on the pan-tilt, and the controller is connected to the pan-tilt and the camera respectively.
4. A method for identifying the thickness of single plates of a stacked plate is characterized by comprising the following steps:
s1, acquiring a first distance D0 between a distance sensor in a distance sensor group and the top surface of a plate stacking block;
s2, calculating the height H = DX0-D0 of the plate stacking block according to a first preset distance DX0 and a first distance D0 measured by a distance sensor of the distance sensor group and between the plate stacking block and a material preparation platform;
s3, obtaining a measurement image shot by a camera, and judging whether the measurement image contains the side surfaces of all single plates or not;
when the measured image contains the side faces of all the single plates, acquiring the number K of boundary lines in the measured image by using a pre-established recognition model;
calculating the number N of the single plates in the plate stacking block according to the number K of the dividing lines;
and S4, calculating the thickness H of the single plate corresponding to the plate stacking block according to the obtained height H of the plate stacking block and the number N of the single plates, wherein H = H/N.
5. The method for identifying the thickness of the single plates of the stacked plates according to claim 4, wherein before the number K of boundaries in the measurement image is obtained by using the pre-established identification model, the method further comprises the following correction steps:
determining the original four corner point coordinates of the side face of the plate stacking block in the measurement image;
determining the coordinates of four corrected corner points of the side face of the plate stacking block after prospective perspective transformation;
calculating perspective transformation matrix parameters according to the original four corner coordinates and the corrected four corner coordinates;
and carrying out perspective transformation on the side surface of the plate stacking block in the measurement image according to the perspective transformation matrix parameters to obtain a corrected measurement image.
6. The method for identifying the thickness of the single plates of the stacked plates according to claim 5, wherein the original four corner point coordinates are obtained by the following steps:
performing straight line detection in the measurement image to obtain two end points of line segments corresponding to four edges in the measurement image;
generating a linear equation corresponding to each edge according to the two end points of the line segment corresponding to each edge;
and obtaining four intersection point coordinates according to a linear equation corresponding to four edges in the measured image, and determining the four intersection point coordinates as the original four corner point coordinates.
7. The method according to claim 6, wherein the measurement image is a measurement image obtained under the guidance of a placement area frame and including the side surface of the stacked plate material blocks; the placing area frame is used for guiding and adjusting the shooting angle of a camera so as to enable the side area of the plate stacking block to be positioned in the placing area frame for shooting;
the performing of the line detection in the measurement image includes: and performing straight line detection in the measurement image within a predetermined range corresponding to each side of the placement area frame.
8. The method for identifying the thickness of the stacked plate veneers according to claim 7, wherein the measurement image containing the side surface of the plate stacking block obtained under the guidance of the placement area frame specifically comprises the following steps:
acquiring a currently shot measurement image;
and judging whether the IOU of the plate stacking block side area and the placing area frame in the currently shot measurement image is larger than a preset intersection threshold value or not, if so, adjusting the shooting angle of the camera until the plate stacking block side area is positioned in the placing area frame.
9. The method for identifying the thickness of the stacked plate veneers according to claim 8, wherein the adjusting process of the shooting angle of the camera specifically comprises the following steps:
determining the offset angle of the camera according to the placement area frame and the first position, wherein the offset direction of the offset angle comprises four directions, namely an upper direction, a lower direction, a left direction and a right direction;
and generating a control instruction according to the offset angle, wherein the control instruction is used for controlling the holder to enable the camera to move at the offset angle.
10. A control device for identifying the thickness of single plates of a stacked plate is characterized by comprising:
one or more processors;
a storage unit, configured to store one or more programs, which when executed by the one or more processors, enable the one or more processors to implement a stacked plate veneer thickness identification method according to any one of claims 4 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210621847.6A CN115183687A (en) | 2022-06-02 | 2022-06-02 | Method, device and system for identifying thickness of single plates of stacked plates |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210621847.6A CN115183687A (en) | 2022-06-02 | 2022-06-02 | Method, device and system for identifying thickness of single plates of stacked plates |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115183687A true CN115183687A (en) | 2022-10-14 |
Family
ID=83513836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210621847.6A Pending CN115183687A (en) | 2022-06-02 | 2022-06-02 | Method, device and system for identifying thickness of single plates of stacked plates |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115183687A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116809756A (en) * | 2023-07-19 | 2023-09-29 | 重庆望变电气（集团）股份有限公司 | Silicon steel sheet transverse cutting device and control method thereof |
-
2022
- 2022-06-02 CN CN202210621847.6A patent/CN115183687A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116809756A (en) * | 2023-07-19 | 2023-09-29 | 重庆望变电气（集团）股份有限公司 | Silicon steel sheet transverse cutting device and control method thereof |
| CN116809756B (en) * | 2023-07-19 | 2024-03-22 | 重庆望变电气（集团）股份有限公司 | Silicon steel sheet transverse cutting device and control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10265911B1 (en) | Image-based monitoring and feedback system for three-dimensional printing | |
| CN115183687A (en) | Method, device and system for identifying thickness of single plates of stacked plates | |
| US6856843B1 (en) | Method and apparatus for displaying an image of a sheet material and cutting parts from the sheet material | |
| CN106379684A (en) | Submersible AGV abut-joint method and system and submersible AGV | |
| EP2774079B1 (en) | Image acquisition method | |
| CN109076728B (en) | Substrate working machine | |
| CN101105715A (en) | Simulation device of robot system | |
| US20130176422A1 (en) | Systems, methods and computer program products for processing of coverings such as leather hides and fabrics for furniture and other products | |
| US20200242793A1 (en) | Object dimensioning system and method | |
| CN101149249A (en) | Measuring method of image measuring instrument | |
| CN103917376A (en) | A printer and a method of printing | |
| CN104129174A (en) | Intelligent printing method and intelligent printer/printing system | |
| WO2020144784A1 (en) | Image processing device, work robot, substrate inspection device, and specimen inspection device | |
| CN110942120A (en) | System and method for automatic product registration | |
| CN104658015B (en) | Visual locating method for automatic laser slicing in corn breeding | |
| CN115015031A (en) | Stacked plate density identification method, device and system | |
| US20150172630A1 (en) | Scanner | |
| CN108501575B (en) | Writing device and control system | |
| JP2005274600A (en) | Method for regulating image-recording device | |
| CN109631764A (en) | Size Measuring System and method based on RealSense camera | |
| CN205496098U (en) | Full -automatic ABS ring gear defect visual inspection device | |
| CN117274257B (en) | Automatic classification system for book looks based on machine vision | |
| CN115187806A (en) | Method, device and system for identifying plate types | |
| CN113569841A (en) | Data acquisition and marking device for linear array camera and marking method thereof | |
| CN103673994A (en) | Dynamic image capturing system |
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 |