CN116105606A - Visual measurement system and method for length of steel wide and thick plate - Google Patents
Visual measurement system and method for length of steel wide and thick plate Download PDFInfo
- Publication number
- CN116105606A CN116105606A CN202211725731.3A CN202211725731A CN116105606A CN 116105606 A CN116105606 A CN 116105606A CN 202211725731 A CN202211725731 A CN 202211725731A CN 116105606 A CN116105606 A CN 116105606A
- Authority
- CN
- China
- Prior art keywords
- image
- steel
- length
- module
- measurement
- 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
- G01B11/028—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring lateral position of a boundary of the object
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The embodiment of the invention discloses a visual measurement system and a visual measurement method for the length of a steel wide and thick plate, wherein an image acquisition module is used for acquiring an original image of a production site, an image processing module is used for converting the original image into an image on a measurement plane, a steel plate measurement module is used for detecting, identifying edges and calculating the length of a steel plate on the measurement plane, a UI (user interface) module is used for displaying the image processed at each stage and the measurement data of the steel plate, and a communication module is used for image and data communication among the image acquisition module, the image processing module, the steel plate measurement module and the UI module. The embodiment of the invention measures the wide and thick plates through vision, solves the problems of difficult measurement of the thick and heavy plates, and improves the accuracy of measurement.
Description
Technical Field
The invention relates to the technical field of wide and thick plate size measurement in the steel industry, in particular to a visual measurement system and method for the length of a wide and thick plate of steel.
Background
The whole steel production process is finished by a plurality of continuous processes, accurate material data are required in a plurality of links, and the dimensional data of the steel are required to be accurately obtained whether the steel billet is fixed in length in the continuous casting process, the steel is fixed in length in the steel rolling process or the final product protection inspection of the finished steel.
At present, the conventional length measurement in the steel industry mainly comprises two types, namely, the length is fixed by an encoder, but the length of a thick plate is easy to have measurement errors due to the fact that the thick plate has a large weight and has a slipping problem; the other mode is laser ranging, and the method has the unstable condition in the measuring process and is easy to cause the problems of collision, data fluctuation and the like.
Because the wide and thick plate has the problems of large length (the length range is 8000mm-20000 mm), thick plate and heavy weight, the conventional measuring method has certain errors, has certain limitations in the production field and the production process, and has the problems of low efficiency or easy damage of equipment.
Disclosure of Invention
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, an embodiment of the present invention provides a visual measurement system for lengths of steel wide and thick plates, including an image acquisition module, an image processing module, a steel plate measurement module, a UI module and a communication module, where the image acquisition module is used to acquire an original image of a production site, the image processing module is used to transform the original image into an image on a measurement plane, the steel plate measurement module is used to detect, identify edges and calculate lengths of steel plates on the measurement plane, the UI module is used to display images processed in each stage and measurement data of the steel plates, and the communication module is used to communicate images and data between the image acquisition module, the image processing module, the steel plate measurement module and the UI module.
Further, the image processing module comprises an image distortion correction unit, an image clipping unit and a perspective transformation unit, wherein the image distortion correction unit is used for performing distortion correction processing on an original image of a production site, the image clipping unit is used for clipping the image subjected to the distortion correction processing, and the perspective transformation unit is used for perspective-transforming the clipped image to a measurement plane.
Further, the steel plate measuring module comprises an AI visual detection unit, an ROI processing unit and a data conversion unit, wherein the AI visual detection unit is used for automatically detecting the steel plate on the measuring plane, the ROI processing unit is used for carrying out edge recognition on the steel plate on the measuring plane, and the data conversion unit is used for calculating the length data of the steel plate.
Further, the AI visual detection unit automatically detects other objects on the measurement plane in addition to the steel plate on the measurement plane; and the AI visual detection unit randomly selects the objects on the measurement plane for marking, generates a data set and trains an AI model by using the data set.
Further, the process of the ROI processing unit for carrying out edge recognition on the steel plate on the measuring plane is as follows: and carrying out convolution operation on the transverse pixels of the steel plate by using a transverse Sobel operator, carrying out convolution operation on the longitudinal pixels of the steel plate by using a longitudinal Sobel operator, and determining the edge position of the steel plate according to the convolution result.
Further, the convolution operation formula is:
G x (x,y)＝A*f(x,y)
＝-1*f(x-1,y-1)+0*f(x,y-1)+1*f(x+1,y-1)+(-2)*f(x-1,y)+0*f(x,y)+2*f(x+1,y)+(-1)*f(x-1,y+1)+0*f(x,y+1)+1*f(x+1,y+1)
G y (x,y)＝B*f(x,y)
＝1*f(x-1,y-1)+2*f(x,y-1)+1*f(x+1,y-1)+0*f(x-1,y)+0*f(x,y)+0*f(x+1,y)+(-1)*f(x-1,y+1)+(-2)*f(x,y+1)+(-1)*f(x+1,y+1)
wherein x, y represent the lateral and longitudinal coordinates of the pixel, respectively, f (x, y) represents the pixel value at that point, A is the lateral Sobel operator, B is the longitudinal Sobel operator, G x (x, y) is the result of the lateral convolution of the pixel, G y (x, y) is an imageThe result of the longitudinal convolution of the elements,
the transverse Sobel operator is
The longitudinal Sobel operator is +.>
Further, the process of calculating the steel plate length data by the data conversion unit is as follows:
dividing the image pixel equal ratio into preset parts by taking the middle pixel point and the field pixel point as standard proportion relation, and sequentially decreasing the preset proportion from the middle to the two sides;
and calculating the steel plate length data according to the image pixel duty ratio after the preset proportion is decreased.
In a second aspect, an embodiment of the present invention provides a method for visually measuring a length of a steel wide and thick plate, including:
collecting an original image of a production site;
transforming the original image into an image on a measurement plane;
detecting, identifying edges and calculating the length of the steel plate on the measuring plane;
the images processed at each stage and the measured data of the steel sheet are displayed.
Further, detecting, edge recognition and length calculation of the steel plate on the measuring plane includes:
the AI visual detection unit automatically detects the steel plate on the measurement plane;
the ROI processing unit performs edge recognition on the steel plate on the measuring plane;
the data conversion unit calculates length data of the steel sheet.
Further, the AI visual detection unit automatically detects other articles on the measurement plane in addition to the steel plate on the measurement plane; and the AI visual detection unit randomly selects the objects on the measurement plane for marking, generates a data set and trains an AI model by using the data set.
The beneficial effects are that:
(1) According to the visual measurement system and method for the length of the steel wide and thick plate, provided by the embodiment of the invention, after the original image of a production site is acquired and transmitted to the image processing module, the original image is subjected to distortion correction, cutting and perspective transformation to generate a measurement plane image, and then the steel plate on the measurement plane is subjected to detection, edge identification and length calculation. The embodiment of the invention measures the wide and thick plates through vision, solves the problems of difficult measurement of the thick and heavy plates, and improves the accuracy of measurement.
(2) According to the visual measurement system and method for the length of the steel wide and thick plate, provided by the embodiment of the invention, the AI visual detection unit randomly selects the graph and randomly maps, so that a data set has richer contents, the generation of the overfitting condition in the training process is greatly reduced, and the accuracy of a model is improved.
(3) The visual measurement system and the visual measurement method for the length of the steel wide and thick plate are suitable for all occasions of accurate measurement of large materials, acquire images through an industrial camera, train related AI models, quickly acquire the length of the materials in real time, transmit the materials to a field control part, improve the production efficiency, ensure the accuracy of products produced, ensure the safety of manual production without carrying out field measurement, and have great popularization and application values.
Drawings
FIG. 1 is a block diagram of a system architecture according to an embodiment of the present invention;
fig. 2 is a diagram showing an effect of correcting distortion of an image distortion correcting unit according to an embodiment of the present invention;
FIG. 3 is a view showing an image clipping effect of an image clipping unit according to an embodiment of the present invention;
FIG. 4 is a perspective transformation effect diagram of a perspective transformation unit according to an embodiment of the present invention;
FIG. 5 is an enhanced graph of random mapping data set of the AI visual detection unit provided by an embodiment of the invention;
fig. 6 is an AI visual detection unit AI identification effect diagram provided by an embodiment of the present invention;
FIG. 7 is a UI module interface diagram provided by an embodiment of the invention;
FIG. 8 is a system software architecture diagram provided in an embodiment of the present invention;
fig. 9 is a flowchart of a method according to an embodiment of the present invention.
Detailed Description
The present invention is described below with reference to the drawings and the detailed description.
The embodiment of the invention provides a visual measurement system and a visual measurement method for the length of a steel wide and thick plate, relates to the application of machine vision and deep learning technology, and solves the problem of length measurement in the production process of the wide and thick plate.
Fig. 1 is a block diagram of a system structure provided by an embodiment of the present invention, where the system includes an image acquisition module, an image processing module, a steel plate measurement module, a UI module and a communication module, where the image acquisition module is used to acquire an original image of a production site, the image processing module is used to transform the original image into an image on a measurement plane, the steel plate measurement module is used to detect, identify edges and calculate lengths of steel plates on the measurement plane, the UI module is used to display images processed in each stage and measurement data of the steel plates, and the communication module is used to communicate images and data between the image acquisition module, the image processing module, the steel plate measurement module and the UI module.
The image acquisition module comprises an industrial camera and an industrial computer, and the camera is mainly characterized by being capable of acquiring and transmitting field pictures at high speed and large in field angle. The on-site wide thick plate has the length range of 8 meters to 20 meters, the measurement accuracy is required to be within 30mm, and the difficult points of large measurement range and high measurement accuracy exist, so in the image acquisition module, the installation position of the industrial camera is positioned on a lateral factory building beam at the center position of the thick plate, the distance from the measured thick plate is about 14 meters, the angle of view is 95 degrees, and the visual field is approximately 21 meters long and 10 meters wide. The method comprises the steps of collecting an original image of a production site through an industrial camera, transmitting the original image to an image processing module for image processing, and storing the image in an industrial computer.
The image processing module comprises an image distortion correction unit, an image clipping unit and a perspective transformation unit, wherein the image distortion correction unit is used for carrying out distortion correction processing on an original image of a production site, the image clipping unit is used for clipping the image subjected to the distortion correction processing, and the perspective transformation unit is used for perspective-transforming the clipped image onto a measurement plane.
The original image photographed by the industrial camera has distortion (the optical lens imaging principle determines that the distortion is necessarily present and cannot be eliminated), so that the collected image may be distorted, that is, a straight line in the real world may be a bar curve in the image. The image distortion correcting unit is used for performing distortion correction processing on an original image of a production site, and fig. 2 is a diagram of distortion correction effects of the image distortion correcting unit according to an embodiment of the present invention.
In order to eliminate unnecessary interference caused by the field environment, the image clipping unit clips the acquired image, only the region needing to be focused is clipped, and fig. 3 is an image clipping effect diagram of the image clipping unit provided by the embodiment of the invention.
The camera optical imaging principle and the installation angle of the field camera determine that the original image acquired by the camera cannot represent the real size proportion of the object. The perspective transformation unit projects a plane to a new plane through a certain mathematical relationship, and restores the real size proportion of the target, and fig. 4 is a perspective transformation effect diagram of the perspective transformation unit provided by the embodiment of the invention.
The steel plate measuring module comprises an AI visual detection unit, an ROI processing unit and a data conversion unit, wherein the AI visual detection unit is used for automatically detecting the steel plate on the measuring plane, the ROI processing unit is used for carrying out edge recognition on the steel plate on the measuring plane, and the data conversion unit is used for calculating the length data of the steel plate.
The AI visual detection unit adopts artificial intelligent visual detection technique to automatically detect target (such as steel plate).
FIG. 5 is a random mapping data set enhancement chart of an AI visual detection unit provided by an embodiment of the invention, wherein the AI visual detection unit automatically detects other objects on a measurement plane in addition to a steel plate on the measurement plane; the AI visual detection unit randomly picks the objects on the measurement plane for labeling, generates a data set, and trains an AI model by using the data set.
The AI vision detection unit automatically detects the target by:
acquiring an image in a perspective transformation unit;
randomly selecting and labeling the objects on the measuring plane to generate a data set;
and training the AI model using the data set.
Fig. 6 is an AI visual detection unit AI-recognition effect diagram provided in an embodiment of the present invention.
The AI visual detection unit randomly selects the graph and maps the graph, so that the data set has richer content, the generation of the over-fitting condition in the training process is greatly reduced, and the accuracy of the model is improved.
ROI (region of interest), in the machine vision and image processing, the region to be processed is outlined from the processed image in the form of a square, a circle, an ellipse, an irregular polygon, etc., which is called the region of interest. Various operators and functions are commonly used in machine vision software such as Halcon, openCV, matlab to calculate the ROI and process the image in the next step.
The identification frame given by the AI visual detection unit is determined as the ROI of a new processing algorithm, the ROI comprises a set of all pixel points of a steel plate, edge detection is carried out on the ROI area, finer steel plate pixel edges are found, the edge detection algorithm carries out convolution operation on each pixel in the set, and due to the special design of convolution kernels, edge positions can be accurately judged in the graph after corresponding convolution operation is carried out.
The Sobel operator is a first-order differential operator, and utilizes the gray level difference of the adjacent points of the pixel point up and down and left and right to reach the extremum at the edge to detect the edge, thereby having a smoothing effect on noise. The principle of the edge detection algorithm is to perform neighborhood convolution on an image by using a transverse template and a longitudinal template in an image space.
The transverse Sobel operator is
The longitudinal Sobel operator is +.>
The horizontal Sobel operator detects a horizontal edge and the longitudinal Sobel operator detects a vertical edge. The distortion correction and perspective transformation are carried out in the front, so that the transverse direction and the longitudinal direction of the steel plate are completely parallel to the pixel direction, and therefore, when edge searching is carried out, transverse Sobel operators and longitudinal Sobel operators are respectively used for the transverse direction and the longitudinal direction of the steel plate, and the extremely accurate and rapid edge searching can be realized.
The process of the ROI processing unit for carrying out edge recognition on the steel plate on the measuring plane comprises the following steps: and carrying out convolution operation on the transverse pixels of the steel plate by using a transverse Sobel operator, carrying out convolution operation on the longitudinal pixels of the steel plate by using a longitudinal Sobel operator, and determining the edge position of the steel plate according to the convolution result.
The convolution operation formula is:
G x (x,y)＝A*f(x,y)
＝-1*f(x-1,y-1)+0*f(x,y-1)+1*f(x+1,y-1)+(-2)*f(x-1,y)+0*f(x,y)+2*f(x+1,y)+(-1)*f(x-1,y+1)+0*f(x,y+1)+1*f(x+1,y+1)
G y (x,y)＝B*f(x,y)
＝1*f(x-1,y-1)+2*f(x,y-1)+1*f(x+1,y-1)+0*f(x-1,y)+0*f(x,y)+0*f(x+1,y)+(-1)*f(x-1,y+1)+(-2)*f(x,y+1)+(-1)*f(x+1,y+1)
wherein x, y represent the lateral and longitudinal coordinates of the pixel, respectively, f (x, y) represents the pixel value at that point, A is the lateral Sobel operator, B is the longitudinal Sobel operator, G x (x, y) is the result of the lateral convolution of the pixel, G y (x, y) is the longitudinal convolution result of the pixel.
Although distortion correction of the camera has been performed, since the actual measurement distance in the field is large, there is a problem that a few pixels represent a large actual distance in both side edge portions of the image in the image, and thus the image pixels are scaled by the data conversion unit.
The process of calculating the steel plate length data by the data conversion unit is as follows:
dividing the image pixel equal ratio into preset parts by taking the middle pixel point and the field pixel point as standard proportion relation, and sequentially decreasing the preset proportion from the middle to the two sides;
and calculating the steel plate length data according to the image pixel duty ratio after the preset proportion is decreased.
In the embodiment of the invention, the preset number of parts is set to 9, and the preset proportion is set to 0.05, so that the pixels from the middle to the two sides have the following parts by weight:
| intermediate part | First portion | Second part | Third portion | Fourth part |
| 1 | 0.95 | 0.9 | 0.85 | 0.8 |
Other preset parts and preset proportions according with actual needs can be used, and the embodiment of the invention is not repeated.
The accuracy of measurement can be greatly improved through the mutual comparison relation between the image pixels and the actual distance formed by the image pixel proportion conversion.
Fig. 7 is a UI module interface diagram provided by the embodiment of the present invention, where the UI module displays images processed at each stage and measurement data of a steel plate, and the embodiment of the present invention mainly shows an original image and an AI visual inspection image of a production site.
The communication module is used for image and data communication among the image acquisition module, the image processing module, the steel plate measuring module and the UI module. If the device is communicated with an on-site industrial camera, the device participates in on-site roller way locking control.
The system of the embodiment of the invention further comprises a storage module which is used for recording each measurement result and storing the measurement result into a corresponding catalogue.
Fig. 8 is a schematic diagram of a system software provided in an embodiment of the present invention, where after an original image is processed by an image acquisition module, a communication module, a belt image processing module, and a steel plate measurement module, measurement data and an image are displayed in a UI module, and the measurement data and the image are stored in a storage module.
Fig. 9 is a flowchart of a method provided in an embodiment of the present invention, including:
collecting an original image of a production site;
transforming the original image into an image on a measurement plane;
detecting, identifying edges and calculating the length of the steel plate on the measuring plane;
the images processed at each stage and the measured data of the steel sheet are displayed.
The detection, edge recognition and length calculation of the steel plate on the measuring plane comprise the following steps:
the AI visual detection unit automatically detects the steel plate on the measurement plane;
the ROI processing unit performs edge recognition on the steel plate on the measuring plane;
the data conversion unit calculates length data of the steel sheet.
The AI visual detection unit is used for automatically detecting other objects on the measuring plane besides the steel plate on the measuring plane; the AI visual detection unit randomly picks the objects on the measurement plane for labeling, generates a data set, and trains an AI model by using the data set.
In the method of the embodiment of the invention, after original images of a production site are acquired and transmitted to an image processing module, distortion correction is carried out on the original images to obtain corrected images, images of a region of interest are cut to obtain cut images, perspective transformation is carried out on the images to obtain transformed images, the images are transmitted to an AI visual detection unit, the AI visual detection unit firstly identifies partial pixels of a tapping plate, then edge identification and pixel proportion conversion are carried out on the pixels to obtain a final measurement result, the data are transmitted to field equipment, related data are recorded in a local database, and the final result is displayed on a UI interface.
The visual measurement system and the visual measurement method for the length of the steel wide and thick plate are suitable for all occasions of accurate measurement of large materials, acquire images through an industrial camera, train related AI models, quickly acquire the length of the materials in real time, transmit the materials to a field control part, improve the production efficiency, ensure the accuracy of products produced, ensure the safety of manual production without carrying out field measurement, and have great popularization and application values.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. The utility model provides a steel wide and thick plate length vision measurement system, its characterized in that includes image acquisition module, image processing module, steel sheet measurement module, UI module and communication module, image acquisition module is used for gathering the original image of production scene, image processing module is used for changing original image into the image on the measurement plane, steel sheet measurement module is used for detecting, edge recognition and length calculation to the steel sheet on the measurement plane, UI module is used for showing the measured data of each stage processing's image and steel sheet, communication module is used for image acquisition module, image processing module, steel sheet measurement module, image and data communication between the UI module.
2. The visual measuring system for the length of the steel wide and thick plate according to claim 1, wherein the image processing module comprises an image distortion correcting unit, an image clipping unit and a perspective transformation unit, the image distortion correcting unit is used for performing distortion correction processing on an original image of a production site, the image clipping unit is used for clipping the image subjected to the distortion correction processing, and the perspective transformation unit is used for perspective-viewing the clipped image on a measuring plane.
3. The visual measuring system for the length of the steel wide and thick plate according to claim 2, wherein the steel plate measuring module comprises an AI visual detecting unit, an ROI processing unit and a data converting unit, the AI visual detecting unit is used for automatically detecting the steel plate on a measuring plane, the ROI processing unit is used for carrying out edge recognition on the steel plate on the measuring plane, and the data converting unit is used for calculating the length data of the steel plate.
4. The visual measuring system for the length of a steel wide and thick plate according to claim 3, wherein the AI visual detecting unit automatically detects other objects on the measuring plane in addition to the steel plate on the measuring plane; and the AI visual detection unit randomly selects the objects on the measurement plane for marking, generates a data set and trains an AI model by using the data set.
5. The visual measuring system for the length of the steel wide and thick plate according to claim 4, wherein the process of identifying the edges of the steel plate on the measuring plane by the ROI processing unit is as follows: and carrying out convolution operation on the transverse pixels of the steel plate by using a transverse Sobel operator, carrying out convolution operation on the longitudinal pixels of the steel plate by using a longitudinal Sobel operator, and determining the edge position of the steel plate according to the convolution result.
6. The visual measurement system of the length of the steel wide and thick plate according to claim 5, wherein the convolution operation formula is:
G x (x,y)＝A*f(x,y)
＝-1*f(x-1,y-1)+0*f(x,y-1)+1*f(x+1,y-1)+(-2)*f(x-1,y)+0*f(x,y)+2*f(x+1,y)+(-1)*f(x-1,y+1)+0*f(x,y+1)+1*f(x+1,y+1)
G y (x,y)＝B*f(x,y)
＝1*f(x-1,y-1)+2*f(x,y-1)+1*f(x+1,y-1)+0*f(x-1,y)+0*f(x,y)+0*f(x+1,y)+(-1)*f(x-1,y+1)+(-2)*f(x,y+1)+(-1)*f(x+1,y+1)
wherein x, y represent the lateral and longitudinal coordinates of the pixel, respectively, f (x, y) represents the pixel value at that point, A is the lateral Sobel operator, B is the longitudinal Sobel operator, G x (x, y) is the result of the lateral convolution of the pixel, G y (x, y) is the longitudinal convolution result of the pixel,
the transverse Sobel operator is
The longitudinal Sobel operator is +.>
7. The visual measuring system for the length of steel slabs according to claim 6, wherein the process of calculating the steel slab length data by the data conversion unit is as follows:
dividing the image pixel equal ratio into preset parts by taking the middle pixel point and the field pixel point as standard proportion relation, and sequentially decreasing the preset proportion from the middle to the two sides;
and calculating the steel plate length data according to the image pixel duty ratio after the preset proportion is decreased.
8. A method for visually measuring the length of a steel wide and thick plate, which is realized based on the system as claimed in any one of claims 1 to 7, and comprises the following steps:
collecting an original image of a production site;
transforming the original image into an image on a measurement plane;
detecting, identifying edges and calculating the length of the steel plate on the measuring plane;
the images processed at each stage and the measured data of the steel sheet are displayed.
9. The visual measuring method for the length of the steel wide and thick plate according to claim 8, wherein the detecting, the edge identifying and the length calculating of the steel plate on the measuring plane comprise the following steps:
the AI visual detection unit automatically detects the steel plate on the measurement plane;
the ROI processing unit performs edge recognition on the steel plate on the measuring plane;
the data conversion unit calculates length data of the steel sheet.
10. The visual measuring method for the length of a steel wide and thick plate according to claim 9, wherein the AI visual detecting unit automatically detects other objects on the measuring plane in addition to the steel plate on the measuring plane; and the AI visual detection unit randomly selects the objects on the measurement plane for marking, generates a data set and trains an AI model by using the data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211725731.3A CN116105606A (en) | 2022-12-30 | 2022-12-30 | Visual measurement system and method for length of steel wide and thick plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211725731.3A CN116105606A (en) | 2022-12-30 | 2022-12-30 | Visual measurement system and method for length of steel wide and thick plate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116105606A true CN116105606A (en) | 2023-05-12 |
Family
ID=86266763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211725731.3A Pending CN116105606A (en) | 2022-12-30 | 2022-12-30 | Visual measurement system and method for length of steel wide and thick plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116105606A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117848221A (en) * | 2024-03-04 | 2024-04-09 | 南通进宝机械制造有限公司 | Steel part length measurement system |
-
2022
- 2022-12-30 CN CN202211725731.3A patent/CN116105606A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117848221A (en) * | 2024-03-04 | 2024-04-09 | 南通进宝机械制造有限公司 | Steel part length measurement system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11551341B2 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
| CN104408460B (en) | A kind of lane detection and tracking detection method | |
| CN101408985A (en) | Method and apparatus for extracting circular luminous spot second-pixel center | |
| CN114820773B (en) | Silo transport vehicle carriage position detection method based on computer vision | |
| CN110647850A (en) | Automatic lane deviation measuring method based on inverse perspective principle | |
| CN111539938B (en) | Method, system, medium and electronic terminal for detecting curvature of rolled strip steel strip head | |
| CN114972356B (en) | Plastic product surface defect detection and identification method and system | |
| CN110031829A (en) | A kind of targeting accuracy distance measuring method based on monocular vision | |
| CN101365144A (en) | Regulating and calibrating method for linear array CCD scanning detection system | |
| CN109816645B (en) | Automatic detection method for steel coil loosening | |
| CN116309565B (en) | High-strength conveyor belt deviation detection method based on computer vision | |
| CN111694011A (en) | Road edge detection method based on data fusion of camera and three-dimensional laser radar | |
| CN111178193A (en) | Lane line detection method, lane line detection device and computer-readable storage medium | |
| CN116105606A (en) | Visual measurement system and method for length of steel wide and thick plate | |
| CN107292879A (en) | A kind of sheet metal surface method for detecting abnormality based on graphical analysis | |
| CN112598066A (en) | Lightweight road pavement detection method and system based on machine vision | |
| CN113781537A (en) | Track elastic strip fastener defect identification method and device and computer equipment | |
| CN112198170A (en) | Detection method for identifying water drops in three-dimensional detection of outer surface of seamless steel pipe | |
| CN113838043A (en) | Machine vision-based quality analysis method in metal foil manufacturing | |
| CN113313047A (en) | Lane line detection method and system based on lane structure prior | |
| CN116485764A (en) | Structural surface defect identification method, system, terminal and medium | |
| CN116883439A (en) | Method and device for detecting slab contour with water stain on surface | |
| CN117670886B (en) | Display screen defect detection method, device, equipment and storage medium | |
| CN115656182A (en) | Sheet material point cloud defect detection method based on tensor voting principal component analysis | |
| CN114529555A (en) | Image recognition-based efficient cigarette box in-and-out 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 |