CN1904090A - Method of automatically distinguishing band steel running aside in continuous annealing furnace - Google Patents
Method of automatically distinguishing band steel running aside in continuous annealing furnace Download PDFInfo
- Publication number
- CN1904090A CN1904090A CN 200510028320 CN200510028320A CN1904090A CN 1904090 A CN1904090 A CN 1904090A CN 200510028320 CN200510028320 CN 200510028320 CN 200510028320 A CN200510028320 A CN 200510028320A CN 1904090 A CN1904090 A CN 1904090A
- Authority
- CN
- China
- Prior art keywords
- image
- gravity
- grey scale
- area
- reference area
- 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.)
- Granted
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 25
- 239000010959 steel Substances 0.000 title claims abstract description 25
- 238000000137 annealing Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 title claims abstract description 10
- 230000005484 gravity Effects 0.000 claims description 37
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000005070 sampling Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 206010000372 Accident at work Diseases 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The present invention belongs to the field of image identification technology, in particular it relates to an image identification method for identifying running-off strip steel in continuous annealing furnace. Said method includes the following steps: converting the image shot by industrial TV set mounted in the continuous annealing furnace into digital signal, then calculating and sampling the transverse displacement change of image gray median point, utilizing the image median point displacement extent to automatically judge that the strip steel in the continuous annealing furnace is run off or not.
Description
(1) technical field
The present invention relates to image recognition technology, relate in particular to the image-recognizing method of band steel running aside in continuous annealing furnace.
(2) background technology
The band steel runs at high speed in the continuous annealing furnace, usually causes strip running deviation for a certain reason and influences the stability of logical plate, clips furnace wall behind the strip running deviation and rupture under extreme case, causes industrial accident.Analysis for cause of accident, the strongest evidence is the surveillance video before and after accident takes place, but connect the industrial shooting and monitoring system that moves back in the stove at present and only have real-time photography function Industrial processes, image analysis is judged and the function of storage and do not possess, need operator to watch monitoring image at any time, cause great industrial accident so usually observe untimely owing to operator or have little time to judge, the video recording before and after accident takes place is not storage also, for accident analysis is made troubles.U.S. Pat 4476430 discloses a kind of contactless strip profile and flatness proofing unit, this device is that one flat plate is installed near belt steel surface, continuous detecting band steel and should flat board between electric capacity, when strip running deviation, band steel peace distance between plates from variation will cause changes in capacitance, can reflect the size of running deviation value thus.
(3) summary of the invention
The object of the present invention is to provide a kind of method of automatic identification band steel running aside in continuous annealing furnace, this recognition methods is promoted existing supervision to production process by artificial judgment be that computer is judged automatically, improve the level of automation of system of supervision on the one hand, the liberation productivity; Improve failure judgment speed on the other hand greatly, provide the time, prevent the generation of big fault in time taking counter-measure.
The present invention is achieved in that a kind of method of automatic identification band steel running aside in continuous annealing furnace, the image light signals that it is characterized in that will the company of being installed in moving back the industrial camera picked-up in the stove is delivered to the watch-keeping cubicle by signal cable, and the frequency divider by a band signal enlarging function carries out being sent to watch-dog, first industrial computer and second industrial computer respectively after signal amplifies again; In first industrial computer image pick-up card is housed, the analog signal conversion that is used for industrial camera is the numerary signal that computer can be discerned, then digital picture is carried out analytical calculation, second industrial computer is carried out the accident video recording when receiving the guard signal of first industrial computer; Its step to picture processing is:
The first step is chosen reference area and sample area on the image of industrial camera picked-up, choose a motionless substantially object of reference on image, makes a reference area, chooses a sample area in band steel zone;
In second step, when supervisory system just starts, calculate the grey scale centre of gravity X of start image reference area
QzGrey scale centre of gravity X with the start image sample area
Qy
The 3rd step, the grey scale centre of gravity X of each computation of Period present image reference area
DzGrey scale centre of gravity X with the present image sample area
Dy, by the grey scale centre of gravity X of present image reference area
DzWith start image reference area grey scale centre of gravity X
QzComparison, calculate the translational movement of the reference area of present image;
In the 4th step, utilization coordinate transform computing calculates the grey scale centre of gravity X of present image sample area with respect to the start image reference area
Dyqz, with X
DyqzAnd X
QyCompare, calculate the absolute translational movement c of the sample area of present image, and be worth eigenwert as sideslip with this; The 5th step, as the centre-of gravity shift eigenwert c of sample area during, think that promptly deviation phenomenon has taken place the band steel in the stove greater than a certain threshold value, system's warnings of sounding notified second industrial computer to carry out accident by local area network simultaneously and recorded a video.
The present invention utilizes the company of being contained in to move back the image of the industrial television picked-up in the stove, after being converted into numerary signal, the transversal displacement of calculating sampling gradation of image center of gravity changes, and is with steel whether to produce sideslip in the continuous annealing furnace according to how much judging automatically of image centre-of gravity shift.When ordinary production, the grey scale centre of gravity of industrial television image is constant substantially or fluctuate in very little scope, when being with steel generation sideslip in the stove, bigger skew will take place in the grey scale centre of gravity of industrial television image, therefore can be with steel whether to produce sideslip in the continuous annealing furnace according to how much judging automatically of image centre-of gravity shift.System can report to the police and the video recording of storage accident automatically when sideslip takes place being judged as, and in time takes measures and accident analysis provides foundation for operating.The present invention is on existing system of supervision basis, make operator not need to watch monitoring image at any time and can obtain than naked eyes monitor more in time, the alarm message that takes place of sideslip accurately, thereby in time take corresponding counter-measure, the accident of preventing further develops, simultaneously, for the accident video recording provides foundation, reduce meaningless video recording room and time.This patent facility investment is few, and body of heater and production run are not exerted an influence.
The present invention is that existing supervision to production process is promoted by artificial judgment is that computer is judged automatically, improves the level of automation of system of supervision on the one hand, the liberation productivity; Improve failure judgment speed on the other hand greatly, provide the time, prevent the generation of big fault in time taking counter-measure.
(4) description of drawings
The invention will be further described below in conjunction with the drawings and specific embodiments.
Fig. 1 is the supervisory system configuration schematic diagram;
Fig. 2 is the image sampling schematic diagram;
Fig. 3 is a sample area centre-of gravity shift schematic diagram calculation;
Fig. 4 is an area grayscale center of gravity calculation schematic diagram.
Among the figure: 1 industrial camera, 2 watch-dogs, 3 frequency dividers, 4 first industrial computer, 5 second industrial computer, 6 pickup images, 7 band steel, 8 furnace rollers, 9 reference areas, 10 sample area.
(5) embodiment
Referring to Fig. 1, the system that discerns band steel running aside in continuous annealing furnace automatically is made up of industrial camera 1, watch-dog 2, frequency divider 3, first industrial computer 4, second industrial computer 5.Industrial camera 1 company of being installed in moves back in the stove, is used to shoot with video-corder the running condition of band steel in the stove.Watch-dog 2, frequency divider 3, first industrial computer 4, second industrial computer 5 all are installed in the watch-keeping cubicle.The image light signals of industrial camera picked-up is delivered to the watch-keeping cubicle by signal cable, and the frequency divider 3 by a band signal enlarging function carries out being sent to watch-dog 2, first industrial computer 4 and second industrial computer 5 respectively after signal amplifies again.In first industrial computer 4 image pick-up card is housed, the analog signal conversion that is used for industrial camera is the numerary signal that computer can be discerned, and then digital picture is carried out analytical calculation.Second industrial computer 5 is carried out the accident video recording when receiving the guard signal of first industrial computer 4.
Referring to Fig. 2, be to the step of picture processing:
The first step is chosen reference area and sample area on the image of industrial camera picked-up.In the image 6 of industrial camera picked-up, can clearly see the image of band steel 7 high-speed cruising on furnace roller 8.In pickup image 6, choose a motionless substantially object of reference, as lamp or fire door, and make a reference area 9, choose a sample area 10 in band steel zone.
Sample area centre-of gravity shift schematic diagram calculation referring to Fig. 3.In second step, when supervisory system just starts, calculate the grey scale centre of gravity X of start image reference area
QzGrey scale centre of gravity X with the start image sample area
Qy
The 3rd step, the grey scale centre of gravity X of each computation of Period present image reference area
DzGrey scale centre of gravity X with the present image sample area
Dy, by the grey scale centre of gravity X of present image reference area
DzWith start image reference area grey scale centre of gravity X
QzComparison, calculate the translational movement of the reference area of present image;
In the 4th step, utilization coordinate transform computing calculates the grey scale centre of gravity X of present image sample area with respect to the start image reference area
Dyqz, with X
DyqzAnd X
QyCompare, calculate the absolute translational movement c of the sample area of present image, and be worth eigenwert as sideslip with this;
The 5th step, as the centre-of gravity shift eigenwert c of sample area during, think that promptly deviation phenomenon has taken place the band steel in the stove greater than a certain threshold value, system's warnings of sounding notified second industrial computer to carry out accident by local area network simultaneously and recorded a video.The empirical value of characteristic threshold value for drawing through bulk trial.
The reason of considering present image and start image coordinate transform in the aforementioned calculation mainly is because signal interference, camera lens adjustment etc. are former thereby the changes in coordinates of the grey scale centre of gravity of the reference area that may cause.If the grey scale centre of gravity X of present image reference area
DzGrey scale centre of gravity X with the start image reference area
QzOverlap, illustrate that lens location does not change; If do not overlap, illustrate that camera lens has skew or has interference, its changing value to be translational movement new, old coordinate.
The principle of present image coordinate transform is as follows: suppose the center of gravity of the image of reference area, its coordinate figure in start image is (0,0), coordinate figure in present image be (a, b), then present image is compared with start image, the along continuous straight runs translation a, translation vertically b.Suppose to have in the sample area 1 K, its reference coordinate value in start image be (x, y); Reference coordinate value in present image is (x ', y '); Then have:
x＝x’+a
y＝y’+b
Therefore, after being added the respective offsets amount, the barycentric coordinates of the sample area of present image can be transformed to the barycentric coordinates of present image sample area with respect to the start image reference area.
Area grayscale center of gravity calculation schematic diagram referring to Fig. 4.Capable N is listed as if sample area is M, and any some gray-scale values are u on it
Ij, X-coordinate is x
Ij, regional barycenter then
The present invention adopts mathematical method that pickup image is analyzed, and draws the whether judgement of sideslip of monitored object.This method is applicable to the supervision of any motion object, has a extensive future.
Claims (1)
1. automatic method of identification band steel running aside in continuous annealing furnace, the image light signals that it is characterized in that will the company of being installed in moving back the industrial camera picked-up in the stove is delivered to the watch-keeping cubicle by signal cable, and the frequency divider by a band signal enlarging function carries out being sent to watch-dog, first industrial computer and second industrial computer respectively after signal amplifies again; In first industrial computer image pick-up card is housed, the analog signal conversion that is used for industrial camera is the numerary signal that computer can be discerned, then digital picture is carried out analytical calculation, second industrial computer is carried out the accident video recording when receiving the guard signal of first industrial computer; Its step to picture processing is:
The first step is chosen reference area and sample area on the image of industrial camera picked-up, choose a motionless substantially object of reference on image, makes a reference area, chooses a sample area in band steel zone;
In second step, when supervisory system just starts, calculate the grey scale centre of gravity X of start image reference area
QzGrey scale centre of gravity X with the start image sample area
Qy
The 3rd step, the grey scale centre of gravity X of each computation of Period present image reference area
DzGrey scale centre of gravity X with the present image sample area
Dy, by the grey scale centre of gravity X of present image reference area
DzWith start image reference area grey scale centre of gravity X
QzComparison, calculate the translational movement of the reference area of present image;
In the 4th step, utilization coordinate transform computing calculates the grey scale centre of gravity X of present image sample area with respect to the start image reference area
Dyqz, with X
DyqzAnd X
QyCompare, calculate the absolute translational movement c of the sample area of present image, and be worth eigenwert as sideslip with this;
The 5th step, as the centre-of gravity shift eigenwert c of sample area during, think that promptly deviation phenomenon has taken place the band steel in the stove greater than a certain threshold value, system's warnings of sounding notified second industrial computer to carry out accident by local area network simultaneously and recorded a video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100283209A CN100398675C (en) | 2005-07-29 | 2005-07-29 | Method of automatically distinguishing band steel running aside in continuous annealing furnace |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100283209A CN100398675C (en) | 2005-07-29 | 2005-07-29 | Method of automatically distinguishing band steel running aside in continuous annealing furnace |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1904090A true CN1904090A (en) | 2007-01-31 |
| CN100398675C CN100398675C (en) | 2008-07-02 |
Family
ID=37673454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2005100283209A Active CN100398675C (en) | 2005-07-29 | 2005-07-29 | Method of automatically distinguishing band steel running aside in continuous annealing furnace |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100398675C (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102773265A (en) * | 2012-07-10 | 2012-11-14 | 首钢总公司 | System for controlling deviation of strip steel |
| CN107101568A (en) * | 2017-04-27 | 2017-08-29 | 山东钢铁集团日照有限公司 | A kind of cold rolled continuous annealing stove and steel edge portion detection method |
| CN107944342A (en) * | 2017-10-27 | 2018-04-20 | 天津美腾科技有限公司 | A kind of scrapper conveyor abnormal state detection system based on machine vision |
| CN110207583A (en) * | 2019-07-02 | 2019-09-06 | 唐山迪安自动化设备有限公司 | Steel band position measurement sensor in acid tank |
| CN111717616A (en) * | 2020-07-02 | 2020-09-29 | 徐州宏远通信科技有限公司 | Scraper conveyor inclined chain detection method based on image recognition and control system |
| CN113538320A (en) * | 2020-03-31 | 2021-10-22 | 宝山钢铁股份有限公司 | Gray scale self-adaption method for hot-rolled strip steel deviation detection |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102230067B (en) * | 2011-03-30 | 2012-11-14 | 北京首钢自动化信息技术有限公司 | Method for realizing accurate positioning of steel billet delivered into a heating furnace |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4476430A (en) * | 1982-04-05 | 1984-10-09 | Wright Wade S | Non-contact sensor for determining moving flat steel strip shape profile |
| JP4022090B2 (en) * | 2002-03-27 | 2007-12-12 | 富士通株式会社 | Finger movement detection method and detection apparatus |
-
2005
- 2005-07-29 CN CNB2005100283209A patent/CN100398675C/en active Active
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102773265A (en) * | 2012-07-10 | 2012-11-14 | 首钢总公司 | System for controlling deviation of strip steel |
| CN102773265B (en) * | 2012-07-10 | 2015-02-25 | 首钢总公司 | System for controlling deviation of strip steel |
| CN107101568A (en) * | 2017-04-27 | 2017-08-29 | 山东钢铁集团日照有限公司 | A kind of cold rolled continuous annealing stove and steel edge portion detection method |
| CN107944342A (en) * | 2017-10-27 | 2018-04-20 | 天津美腾科技有限公司 | A kind of scrapper conveyor abnormal state detection system based on machine vision |
| CN110207583A (en) * | 2019-07-02 | 2019-09-06 | 唐山迪安自动化设备有限公司 | Steel band position measurement sensor in acid tank |
| CN113538320A (en) * | 2020-03-31 | 2021-10-22 | 宝山钢铁股份有限公司 | Gray scale self-adaption method for hot-rolled strip steel deviation detection |
| CN111717616A (en) * | 2020-07-02 | 2020-09-29 | 徐州宏远通信科技有限公司 | Scraper conveyor inclined chain detection method based on image recognition and control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100398675C (en) | 2008-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101299275B (en) | Method and device for detecting target as well as monitoring system | |
| CN101916447B (en) | Robust motion target detecting and tracking image processing system | |
| CN101576952B (en) | Method and device for detecting static targets | |
| CA2795896A1 (en) | Method and system for security system tampering detection | |
| CN103929592A (en) | All-dimensional intelligent monitoring equipment and method | |
| CN101079171A (en) | Intelligent video monitoring system of bank self-aid apparatus | |
| CN112257632A (en) | Transformer substation monitoring system based on edge calculation | |
| CN101571982A (en) | Method for judging stolen articles in video monitoring range | |
| CN100398675C (en) | Method of automatically distinguishing band steel running aside in continuous annealing furnace | |
| CN112367475B (en) | Traffic incident detection method and system and electronic equipment | |
| CN103152558B (en) | Based on the intrusion detection method of scene Recognition | |
| CN1406366A (en) | Video smoke detection system | |
| CN115527158A (en) | Method and device for detecting abnormal behaviors of personnel based on video monitoring | |
| CN117834821A (en) | Intelligent interaction type security monitoring system | |
| KR101830331B1 (en) | Apparatus for detecting abnormal operation of machinery and method using the same | |
| CN116051522A (en) | Working face transfer position congestion processing method and device and electronic equipment | |
| JPH08228338A (en) | Device and method for state monitoring | |
| CN116342481A (en) | Converter flue slagging monitoring system and method based on machine vision | |
| CN112291282B (en) | Dynamic inspection alarm method and device | |
| CN101469987B (en) | Movable object detecting apparatus and method | |
| CN114549406A (en) | Hot rolling line management method, device and system, computing equipment and storage medium | |
| KR20220067271A (en) | Image acquisition apparatus and image acquisition method | |
| CN118429947B (en) | Intelligent early warning method and system for preventing misoperation of monorail crane | |
| CN111551196B (en) | Detection method for detecting whether vehicle exists on overhaul station | |
| CN118823687B (en) | Intelligent mine underground monitoring system based on video analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |