CN113096186A - Steel ladle position measuring method based on machine vision - Google Patents
Steel ladle position measuring method based on machine vision Download PDFInfo
- Publication number
- CN113096186A CN113096186A CN202110460459.XA CN202110460459A CN113096186A CN 113096186 A CN113096186 A CN 113096186A CN 202110460459 A CN202110460459 A CN 202110460459A CN 113096186 A CN113096186 A CN 113096186A
- Authority
- CN
- China
- Prior art keywords
- ladle
- image
- steel ladle
- current position
- measuring method
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 39
- 239000010959 steel Substances 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 238000000691 measurement method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 4
- 238000006243 chemical reaction Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 abstract 1
- 238000007670 refining Methods 0.000 description 13
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a ladle position measuring method based on machine vision, which comprises the following steps: s1, acquiring a current position image of a steel ladle in a preset detection area, wherein the actual position image comprises a lifting lug image and a laser line image of the steel ladle; and step S2, obtaining the current position information of the ladle based on the collected current position image. The method comprises the steps of realizing position positioning of a steel ladle based on a machine vision mode, adding a non-contact auxiliary feature into a machine vision system, carrying out image acquisition on the steel ladle and a laser line printed on the steel ladle, carrying out feature extraction to obtain a characteristic area of a lifting lug of the steel ladle, obtaining the position of the steel ladle after data conversion, and finishing the function of automatically aligning the steel ladle to a cover of a refined steel ladle; the method realizes the identification of the ladle characteristics and the acquisition of the position information of the ladle in a complex environment, is safe and effective, has high measurement precision, can fully improve the connectivity of the automatic positioning system of the ladle car, and is beneficial to the reconstruction of the original equipment.
Description
Technical Field
The invention belongs to the technical field of post-converter process molten iron refining in the steel industry, and particularly relates to a method for measuring a position of a steel ladle based on machine vision.
Background
In the post-furnace refining process, a ladle hung from a crown block is placed into a ladle car, and then the ladle car is driven to a position right below a refining furnace cover, and an electrode can be inserted. At present, it is accomplished by artifical observation to drive ladle car into mostly, artifical with eye observation and instruction ladle car stop, however, the eye observation time overlength can cause visual fatigue, cause the ladle position to berth very easily and have the error, and because the spark spatters all around during ladle refining, the surrounding environment is very abominable, also can produce the position deviation error for ladle car when the ladle is put into ladle car in addition, consequently, increased ladle car's the location degree of difficulty, the position location of the realization ladle that can't be accurate.
Disclosure of Invention
The invention aims to provide a ladle position measuring method based on machine vision aiming at the defects of the prior art, the ladle position is measured in a non-contact mode, and the ladle position measuring method is safe, effective and high in measuring precision.
In order to solve the technical problems, the invention adopts the following technical scheme:
a ladle position measuring method based on machine vision comprises the following steps:
s1, acquiring a current position image of a steel ladle in a preset detection area, wherein the actual position image comprises a lifting lug image and a laser line image of the steel ladle;
and step S2, obtaining the current position information of the ladle based on the collected current position image.
Further, the machine vision-based ladle position measuring method further comprises the following steps:
step S3, obtaining position adjustment quantity according to the current position information and the standard position image of the ladle;
and step S4, adjusting the ladle to move to a standard position according to the position adjustment amount.
Further, in step S1, a laser emitting device that emits a laser line toward the ladle is disposed in the preset detection area, and the laser emitting device is synchronously started during the current position image acquisition.
Further, the laser emission direction of the laser emission device is perpendicular to the moving direction of the ladle.
Further, the step S2 includes:
step S21, preprocessing the collected current position image;
and step S22, judging the image information obtained after the preprocessing according to the characteristic information generated between the laser line and the lifting lug to obtain the current position information of the steel ladle.
Further, the step S21 includes:
firstly, carrying out gray level processing on the acquired current position image, and carrying out weighted average on RGB three components according to the following formula to obtain a gray level image:
f(i，j)＝0.30R(i，j)+0.59G(i，j)+0.11B(i，j)
wherein R is an image red channel, G is an image green channel, B is an image blue channel, M < i, j < N, wherein M and N are image horizontal and vertical resolution;
secondly, filtering the image after the gray processing to reduce the interference of noise points;
and finally, carrying out threshold processing on the filtered image to obtain a corresponding binary gray level image.
Further, the threshold processing procedure is as follows: setting a global threshold value T, and dividing the data of the image into two parts by using T: pixel groups larger than T and pixel groups smaller than T; and setting the pixel value of the pixel group larger than T as white or black, and setting the pixel value of the pixel group smaller than T as black or white, thereby obtaining the corresponding binary gray level image.
Compared with the prior art, the invention has the beneficial effects that: the method is based on a machine vision mode to realize the position positioning of the steel ladle, namely, an industrial camera is installed to acquire the current position image of the steel ladle, a non-contact auxiliary feature is added into a machine vision system to acquire the images of the steel ladle and a laser line printed on the steel ladle and extract the feature to obtain a characteristic area of a lifting lug of the steel ladle, the position of the steel ladle is acquired after data conversion, and the function of automatically aligning the steel ladle to a refined steel ladle cover is completed; the invention realizes the identification of ladle characteristics and the acquisition of position information thereof in a complex environment, can fully improve the connectivity of the automatic positioning system of the ladle car, has no contact in the use process, improves the safety, is convenient for later equipment maintenance, is improved on the original basis, has no additional equipment change content, ensures that the robustness of the whole automatic positioning system of the ladle car is stronger, reduces errors caused by manual control, and improves the production benefits of enterprises.
Drawings
Fig. 1 is a flow chart of a ladle position measurement method based on machine vision in an embodiment of the present invention.
Fig. 2 is a top view of the structure of the ladle and the measuring device in the embodiment of the invention.
Fig. 3 is a side view of the structure of the ladle and the measuring device in the embodiment of the present invention.
Fig. 4 is a schematic diagram of a current position image of a ladle in an embodiment of the present invention.
Detailed Description
The invention will be further described with reference to examples of embodiments shown in the drawings.
As shown in fig. 1 to 4, the present embodiment discloses a method for measuring a position of a ladle based on machine vision, which is used for providing a method for accurately positioning the ladle without contact, and the measuring method comprises the following steps:
and step S1, acquiring a current position image of the ladle in the preset detection area.
And step S2, obtaining the current position information of the ladle based on the collected current position image.
In this embodiment, the current position image and the standard position image respectively include a lifting lug image of the ladle and a laser line image which is preset and acquired simultaneously. Specifically, as shown in fig. 2 and 3, a laser emitting device which emits a laser line towards the ladle is arranged in a preset detection area, and particularly, the laser line is emitted towards a lifting lug of the ladle, so that after the ladle car enters the preset detection area, the laser emitting device is synchronously started in the process of acquiring the current position image, and the acquired current position image not only contains the lifting lug image of the ladle, but also contains the laser line image. In this embodiment, the laser emission direction of the laser emission device is parallel to the moving direction of the ladle. Like this, through introducing the laser line, utilize the characteristic information that produces between its and the lug of ladle to realize the judgement and the acquisition to the lug position of ladle, specifically, as shown in fig. 4, when the laser line launches the lug on, the layering can take place for the laser line, and when the laser line did not launch the lug on, the laser line can not take place the layering and keep a continuous straight line, so, through looking for the pixel point that the laser line took place the layering then can further turn into the current position information of lug.
Based on the above concept, step S2 specifically includes:
and step S21, preprocessing the acquired current position image. The specific pretreatment process comprises the following steps:
firstly, carrying out gray level processing on an acquired current position image, and carrying out weighted average on RGB three components according to the following formula to obtain a gray level image:
f(i，j)＝0.30R(i，j)+0.59G(i，j)+0.11B(i，j)
wherein R is an image red channel, G is an image green channel, B is an image blue channel, M < i, j < N, and M and N are image horizontal and vertical resolution sizes.
And secondly, filtering the image after the gray processing to reduce the interference of noise points.
And finally, carrying out threshold processing on the filtered image to obtain a corresponding binary gray level image. The specific threshold processing process is as follows: setting a global threshold value T, and dividing the data of the image into two parts by using T: pixel groups larger than T and pixel groups smaller than T; and setting the pixel value of the pixel group larger than T as white or black, and setting the pixel value of the pixel group smaller than T as black or white, thereby obtaining the corresponding binary gray level image.
And step S22, judging the image information obtained after preprocessing according to the characteristic information generated between the laser line and the lifting lug to obtain the current position information of the ladle. The characteristic information is that the laser line is layered when being emitted to the lifting lug. That is to say, the characteristics of the ladle lifting lug are extracted under the assistance of the laser line, and the current position information of the ladle lifting lug is obtained.
And step S3, obtaining a position adjustment quantity according to the current position information and the standard position image of the ladle.
In this embodiment, the standard position image of the ladle refers to a position image acquired for the ladle when the ladle car moves to an accurate position corresponding to the ladle cover, and is used as a reference for the position of the ladle later, and alignment with the ladle cover can be achieved only when the ladle moves to the position.
As a specific implementation structure of the measuring method of this embodiment, an industrial camera and a linear laser emitter are installed below the steel refining position and at a position perpendicular to the running direction of the ladle car, and the industrial camera and the laser emitter are in the same vertical direction, and the industrial camera acquires an image of the ladle in the visual field range. After the installation is finished, calibrating image information acquired by the industrial camera, determining a refining position, converting the refining position into a pixel position in the image, and determining a standard position image of the ladle. The specific image calibration is realized as follows: after the industrial camera is installed, the ladle car is manually driven to a ladle refining position, a laser transmitter is started, at the moment, ladle car image information is collected, when the ladle is determined to be in the refining position according to the image information, a ladle lifting lug is converted into a pixel position on the image and an actual length distance value represented by each pixel, the pixel position is set as a standard position for reference, and the difference value of the length distance between the ladle and the refining position is measured by taking the position as the standard position.
After the current position information (namely the actual position information) of the ladle lifting lug is obtained, the distance between the current position information of the ladle lifting lug and a refining bit pixel point in a standard position image is further calculated and obtained, and the distance is converted into an actual distance value, namely the position adjustment quantity of the ladle.
And step S4, adjusting the ladle to move to a standard position, namely a refining position according to the position adjustment quantity, so that the ladle is accurately aligned with the ladle cover of the refining position.
According to the measuring method of the embodiment, the position of the steel ladle is positioned based on a machine vision mode, namely, an industrial camera is installed to acquire the current position image of the steel ladle, a non-contact auxiliary feature is added into a machine vision system, the steel ladle and a laser line printed on the steel ladle are subjected to image acquisition and feature extraction to obtain a characteristic area of a lifting lug of the steel ladle, the position of the steel ladle is acquired after data conversion, and the function of automatically aligning the steel ladle to a cover of a refined steel ladle is completed.
The main problem of positioning treatment by adopting a visual mode is the extraction of the edge characteristics of the steel ladle. However, because of the harsh field environment, the dust is large, and the number of the ladles is large, the manual auxiliary characteristic (such as painting color paint and the like) is difficult to realize in the steel field according to the prior art. And to this technological problem, the measurement method of this embodiment develops a new way, proposes to increase ladle auxiliary feature with contactless mode, just beat a word red laser line at the ladle lug height, for complicated background like this, just can carry out feature recognition to the ladle lug, and then extract the positional information of ladle lug to confirm the position of ladle, its core just lies in and carries out the feature extraction most in a word laser line image on the ladle, analyzes out ladle lug position, then turns into the positional data of ladle.
Based on this, the measuring method of this embodiment has realized ladle characteristic identification and its positional information of acquireing under the complex environment, can fully improve buggy ladle automatic positioning system's connectivity to contactless in the use improves the security, and later stage equipment maintenance is convenient, reforms transform on original basis, does not have extra equipment to change content, makes whole buggy ladle automatic positioning system robustness stronger, reduces the error that manual control brought, improves enterprise productivity effect.
The protective scope of the present invention is not limited to the above-described embodiments, and it is apparent that various modifications and variations can be made to the present invention by those skilled in the art without departing from the scope and spirit of the present invention. It is intended that the present invention cover the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents.
Claims (7)
1. A ladle position measuring method based on machine vision is characterized by comprising the following steps:
s1, acquiring a current position image of a steel ladle in a preset detection area, wherein the actual position image comprises a lifting lug image and a laser line image of the steel ladle;
and step S2, obtaining the current position information of the ladle based on the collected current position image.
2. The machine-vision-based ladle position measurement method according to claim 1, further comprising:
step S3, obtaining position adjustment quantity according to the current position information and the standard position image of the ladle;
and step S4, adjusting the ladle to move to a standard position according to the position adjustment amount.
3. The machine-vision-based ladle position measuring method according to claim 1 or 2, wherein:
in step S1, a laser emitting device that emits a laser line toward the ladle is disposed in the preset detection area, and the laser emitting device is synchronously started during the current position image acquisition.
4. The machine-vision-based ladle position measuring method according to claim 3, wherein:
and the laser emission direction of the laser emission device is parallel to the moving direction of the steel ladle.
5. The machine-vision-based ladle position measuring method according to claim 4, wherein:
the step S2 includes:
step S21, preprocessing the collected current position image;
and step S22, judging the image information obtained after preprocessing according to the characteristic information generated between the laser line and the lifting lug to obtain the current position information of the steel ladle.
6. The machine-vision-based ladle position measuring method according to claim 5, wherein:
the step S21 includes:
firstly, carrying out gray level processing on the acquired current position image, and carrying out weighted average on RGB three components according to the following formula to obtain a gray level image:
f(i，j)＝0.30R(i，j)+0.59G(i，j)+0.11B(i，j)
in the formula, R-image red channel, G-image green channel, B-image blue channel, M is more than i, j is more than N, wherein M and N are the size of the horizontal resolution and the vertical resolution of the image;
secondly, filtering the image after the gray processing to reduce the interference of noise points;
and finally, carrying out threshold processing on the filtered image to obtain a corresponding binary gray level image.
7. The machine-vision-based ladle position measuring method according to claim 6, wherein:
the threshold processing process comprises the following steps: setting a global threshold value T, and dividing the data of the image into two parts by using T: pixel groups larger than T and pixel groups smaller than T; and setting the pixel value of the pixel group larger than T as white or black, and setting the pixel value of the pixel group smaller than T as black or white, thereby obtaining the corresponding binary gray level image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460459.XA CN113096186A (en) | 2021-04-27 | 2021-04-27 | Steel ladle position measuring method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460459.XA CN113096186A (en) | 2021-04-27 | 2021-04-27 | Steel ladle position measuring method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113096186A true CN113096186A (en) | 2021-07-09 |
Family
ID=76680320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110460459.XA Pending CN113096186A (en) | 2021-04-27 | 2021-04-27 | Steel ladle position measuring method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113096186A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114606365A (en) * | 2022-03-18 | 2022-06-10 | 西安宝科流体技术有限公司 | Coordinated control system and method for ladle bottom blowing |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011104617A (en) * | 2009-11-17 | 2011-06-02 | Nippon Steel Corp | Method and device for detecting butt-groove position of steel plate |
| CN102448679A (en) * | 2009-05-27 | 2012-05-09 | 莱卡地球***公开股份有限公司 | Method and system for extremely precise positioning of at least one object in the end position in space |
| CN104573674A (en) * | 2015-01-29 | 2015-04-29 | 杨克己 | 1D (one-dimensional) barcode recognition for real-time embedded system |
| CN207209795U (en) * | 2017-08-16 | 2018-04-10 | 唐山钢铁国际工程技术股份有限公司 | Ladle lifting control device based on machine vision |
| CN110033436A (en) * | 2019-03-08 | 2019-07-19 | 安徽理工大学 | It is a kind of that diagnosis and its positioning system are deformed based on the mine rigid cage guide of machine vision and laser fusion |
| CN110296606A (en) * | 2019-07-22 | 2019-10-01 | 上海联达节能科技股份有限公司 | A kind of steel billet based on image procossing enters stokehold positioning control system and method |
| CN209778095U (en) * | 2019-03-25 | 2019-12-13 | 北京科技大学 | Overhead traveling crane hook safety detection system under complicated industrial environment based on image |
| CN110781779A (en) * | 2019-10-11 | 2020-02-11 | 北京地平线机器人技术研发有限公司 | Object position detection method and device, readable storage medium and electronic equipment |
-
2021
- 2021-04-27 CN CN202110460459.XA patent/CN113096186A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102448679A (en) * | 2009-05-27 | 2012-05-09 | 莱卡地球***公开股份有限公司 | Method and system for extremely precise positioning of at least one object in the end position in space |
| JP2011104617A (en) * | 2009-11-17 | 2011-06-02 | Nippon Steel Corp | Method and device for detecting butt-groove position of steel plate |
| CN104573674A (en) * | 2015-01-29 | 2015-04-29 | 杨克己 | 1D (one-dimensional) barcode recognition for real-time embedded system |
| CN207209795U (en) * | 2017-08-16 | 2018-04-10 | 唐山钢铁国际工程技术股份有限公司 | Ladle lifting control device based on machine vision |
| CN110033436A (en) * | 2019-03-08 | 2019-07-19 | 安徽理工大学 | It is a kind of that diagnosis and its positioning system are deformed based on the mine rigid cage guide of machine vision and laser fusion |
| CN209778095U (en) * | 2019-03-25 | 2019-12-13 | 北京科技大学 | Overhead traveling crane hook safety detection system under complicated industrial environment based on image |
| CN110296606A (en) * | 2019-07-22 | 2019-10-01 | 上海联达节能科技股份有限公司 | A kind of steel billet based on image procossing enters stokehold positioning control system and method |
| CN110781779A (en) * | 2019-10-11 | 2020-02-11 | 北京地平线机器人技术研发有限公司 | Object position detection method and device, readable storage medium and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 张传雷 等: "《基于图像分析的植物及其病虫害识别方法研究》", 31 October 2018, 中国经济出版社 * |
| 高宏伟: "《电子封装工艺与装备技术基础教程》", 31 July 2017, 西安电子科技大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114606365A (en) * | 2022-03-18 | 2022-06-10 | 西安宝科流体技术有限公司 | Coordinated control system and method for ladle bottom blowing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109443480B (en) | Water level scale positioning and water level measuring method based on image processing | |
| CN111421425B (en) | Metal surface grinding system based on industrial vision | |
| CN101358836B (en) | Method for recognizing weld spot central position based on computer vision | |
| CN107014291B (en) | A kind of vision positioning method of material precision transfer platform | |
| CN112304954B (en) | Part surface defect detection method based on line laser scanning and machine vision | |
| US10311322B2 (en) | Character information recognition method based on image processing | |
| CN110108711A (en) | The vision detection system of annulus side wall defect | |
| CN108960237B (en) | Reading identification method for pointer type oil level indicator | |
| CN110378957B (en) | Torpedo tank car visual identification and positioning method and system for metallurgical operation | |
| CN113465541B (en) | Contact line abrasion measuring method and system | |
| CN109520706A (en) | Automobile fuse box assembly detection system, image-recognizing method and screw hole positioning mode | |
| CN108190774B (en) | A kind of row's rope fault detection method and its device based on projection | |
| CN112634269B (en) | Railway vehicle body detection method | |
| CN113096186A (en) | Steel ladle position measuring method based on machine vision | |
| CN111445444A (en) | Molten iron flow velocity detection method based on polarization characteristics | |
| CN110202576A (en) | A kind of workpiece two-dimensional visual guidance crawl detection system and method | |
| CN112067618A (en) | Product quality defect acquisition and analysis system based on imaging | |
| CN111784627A (en) | Container alignment method for vehicle | |
| CN110751669A (en) | Novel CBOCP online infrared converter tapping steel flow automatic detection and tracking method and system | |
| CN110514664B (en) | Cheese yarn rod positioning and detecting robot and method | |
| CN105760869A (en) | Examination paper marking method based on image gray level recognition and processing | |
| CN109631763A (en) | Irregular part detects localization method | |
| CN116402784A (en) | Auxiliary centering method, system, equipment and storage medium based on machine vision | |
| CN115731380A (en) | Computer vision-based positioning method, control method and device for four coke oven trucks | |
| CN109631803A (en) | Part angle detects adjusting 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 |