CN115272269A - Raw material blank furnace-entering positioning detection method, device and system - Google Patents
Raw material blank furnace-entering positioning detection method, device and system Download PDFInfo
- Publication number
- CN115272269A CN115272269A CN202210944782.9A CN202210944782A CN115272269A CN 115272269 A CN115272269 A CN 115272269A CN 202210944782 A CN202210944782 A CN 202210944782A CN 115272269 A CN115272269 A CN 115272269A
- Authority
- CN
- China
- Prior art keywords
- image
- raw material
- material blank
- edge
- gray
- 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
- 239000002994 raw material Substances 0.000 title claims abstract description 136
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 91
- 238000000034 method Methods 0.000 claims abstract description 38
- 230000033001 locomotion Effects 0.000 claims abstract description 25
- 229910000831 Steel Inorganic materials 0.000 claims description 44
- 239000010959 steel Substances 0.000 claims description 44
- 238000003708 edge detection Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000010438 heat treatment Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 235000020061 kirsch Nutrition 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G06T5/90—
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
Abstract
The invention provides a raw material blank charging positioning detection method, a device and a system, wherein the method comprises the following steps: based on the image acquired by the image acquisition device, calibrating an image processing fixed area for extracting the appearance position of the raw material blank on the image; identifying the type of the current raw material blank within the image processing fixed area range, and matching corresponding identification modes aiming at different types of raw material blanks to identify the movement position of the raw material blank; and calibrating a judgment reference in the image processing fixed area, comparing the identified movement position of the raw material blank with the judgment reference, and judging whether the raw material blank moves in place. The invention is used for improving the accuracy and efficiency of detection and realizing unmanned automatic production.
Description
Technical Field
The invention relates to the technical field of bars, in particular to a raw material blank charging positioning detection method, a raw material blank charging positioning detection device and a raw material blank charging positioning detection system.
Background
The raw material billet of the rod wire is usually a square billet, the side length of the cross section is about 200mm, and the length is about 10 meters. In the production process, the raw material blank needs to enter a heating furnace through a section of conveying roller way for heating. After the raw material blank enters the furnace, whether the raw material blank runs in place or not is difficult to judge due to the lack of a corresponding detection means. Once the subsequent actions are performed under the condition that the operation is not in place, abnormal production can be caused, and even equipment can be damaged when the operation is serious.
At present, most of rod and wire production lines are manually checked by operators through monitoring videos to judge whether raw material blanks run in place or not. However, the mode of manually and visually judging whether the raw material blank runs in place has more defects, and firstly, the working strength of an operator is very high; secondly, the precision of visual inspection is limited, and the accuracy rate is low; automatic closed-loop control cannot be realized, and the production efficiency is reduced; not in line with the intended goal of reducing human efficiency.
Disclosure of Invention
In order to overcome the defects in the prior art, the technical problem to be solved by the embodiment of the invention is to provide a raw material blank furnace-entering positioning detection method, device and system, which are used for improving the accuracy and efficiency of detection and realizing unmanned automatic production.
The above object of the present invention can be achieved by the following technical solutions, and the present invention provides a raw material blank charging positioning detection method, including:
based on the image acquired by the image acquisition device, calibrating an image processing fixed area for extracting the appearance position of the raw material blank on the image;
identifying the type of the current raw material blank within the image processing fixed area range, and matching corresponding identification modes aiming at different types of raw material blanks to identify the movement position of the raw material blank;
and calibrating a judgment reference in the image processing fixed area, comparing the identified movement position of the raw material blank with the judgment reference, and judging whether the raw material blank moves in place.
In a preferred embodiment of the present invention, the raw material slab includes a steel slab, and the steel slab includes: hot-feeding steel billets with red bodies and cold-feeding steel billets with gray bodies.
In a preferred embodiment of the present invention, when the type of the billet is a hot-fed billet, the identification method corresponding to the hot-fed billet includes:
acquiring a gray value of an image red channel in an image processing fixed area, and generating a corresponding gray image;
performing contrast enhancement processing on the generated gray level image to obtain an enhanced image;
carrying out binarization processing on the enhanced image to obtain an image after binarization processing;
traversing all the regions in the image after the binarization processing, and calculating the area of each region;
when the sum of the calculated areas is larger than a first threshold value, determining that the current hot-delivery steel billet has reached a specified position;
traversing all points of the hot steel conveying billet, and taking the minimum value in the moving direction of the hot steel conveying billet as the current moving position of the hot steel conveying billet.
In a preferred embodiment of the present invention, the performing contrast enhancement processing on the generated grayscale image includes:
substituting the original gray scale of the gray scale image into a first calculation formula, wherein the first calculation formula is as follows:
G new ＝G old *a+N
wherein G is old Is the original gray scale of the image, G new Is the gray scale after image enhancement, a and N are preset parameters;
when G is new <0, then G new ＝0；
When G is new >255, then G new ＝255；
When G is new Between 0 and 255, take G new The actual value.
In a preferred embodiment of the present invention, the binarizing process on the enhanced image is specifically a binarizing process on the enhanced image by a threshold segmentation algorithm, wherein G new Is the gray scale after the image enhancement and,
when G is new <=125, gray =0 is set;
when G is new >125, gray =255 is set.
In a preferred embodiment of the present invention, when the type of the billet is a cold-fed billet, the identification method corresponding to the cold-fed billet includes:
acquiring a gray value of an image blue channel in an image processing fixed area, and generating a corresponding gray image;
performing edge detection on the generated gray level image to obtain an edge image after edge detection;
performing binarization processing on the edge image after edge detection to obtain an edge image after binarization processing;
traversing all the areas in the edge image after the binarization processing, and calculating all pixel values on the edge image;
and traversing all the points with the pixel value of 1 in the edge image to obtain the contour line of the cold-fed steel billet, and taking the minimum value in the moving direction of the cold-fed steel billet as the current moving position of the cold-fed steel billet.
In a preferred embodiment of the present invention, the binarizing process performed on the edge image after the edge detection is specifically a binarizing process performed on the edge image by a threshold segmentation algorithm, wherein,
if the gray scale of the edge image is less than or equal to the preset gray scale, setting the gray scale of the current position of the edge image as 0;
and if the gray scale of the edge image is greater than the preset gray scale, setting the gray scale of the current position of the edge image to be 255.
In a preferred embodiment of the present invention, when the gray levels of all the positions on the edge image are zero, all the pixel values on the corresponding edge image are zero; indicating that no material blank was present in the image at this time.
In a preferred embodiment of the present invention, the determination reference is a reference line y = d marked on the image along the billet conveying direction,
when the position P of the raw material blank slab When d is more than or equal to d, indicating that the raw material base moves in place;
when the position P of the raw material blank slab <d, indicating that the raw material blank is not moved in place.
A raw material blank furnace-entering positioning detection device comprises:
the image processing fixed area creating module is used for calibrating an image processing fixed area used for extracting the appearance position of the raw material blank on the image based on the image acquired by the image receiving and acquiring device;
the raw material blank motion position identification module is used for identifying the type of the current raw material blank within the image processing fixed region range, matching corresponding identification modes aiming at different types of raw material blanks and identifying the motion position of the raw material blank;
and the raw material blank in-place movement judging module is used for calibrating a judgment reference in the image processing fixed area, comparing the identified movement position of the raw material blank with the judgment reference and judging whether the raw material blank moves in place.
An image processing server comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing any of the methods described above when executing the computer program.
A raw material blank furnace-entering positioning detection system comprises: the image processing server, the controller and the image acquisition device can be communicated with the image processing server.
The technical scheme of the invention has the following remarkable beneficial effects:
on the whole, the raw material blank furnace-entering positioning detection method provided by the application can replace manual detection and can be combined with an automatic control system to realize unmanned production; the detection precision and the detection efficiency are higher; can achieve the effect of reducing personnel and improving efficiency.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way. In addition, the shapes, the proportional sizes, and the like of the respective members in the drawings are merely schematic for facilitating the understanding of the present invention, and do not specifically limit the shapes, the proportional sizes, and the like of the respective members of the present invention. Those skilled in the art, having the benefit of the teachings of this invention, may choose from the various possible shapes and proportional sizes to implement the invention as a matter of case.
Fig. 1 is a schematic view of a scene implemented by a raw material blank charging positioning detection method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a method for positioning and detecting charging of raw material blanks according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of RIO zone calibration at the entrance of a furnace according to an embodiment of the present invention;
FIG. 4 is a flow chart of the procedure of the identification mode corresponding to the hot-feeding billet when the material blank is the hot-feeding billet;
FIG. 5 is a flow chart of the steps of the identification method corresponding to the cold billet when the material billet is the cold billet;
FIG. 6 is a schematic diagram illustrating the determination of the in-place of charging a raw material blank;
FIG. 7 is a schematic block diagram of a raw material blank charging positioning detection apparatus according to an embodiment of the present invention;
FIG. 8 is a schematic layout view of a raw material blank in-furnace positioning detection system according to an embodiment of the present invention;
fig. 9 is a data flow diagram of various parts of a raw material blank furnace-entering positioning detection system according to an embodiment of the present invention.
Reference numerals of the above figures:
1. heating furnace;
10. inlet port
2. Raw material blanks;
3. an image acquisition device;
4. a conveying roller way;
5. an image processing server;
6. a controller;
7. a switch;
81. a rectangular frame;
100. an image processing fixed area creating module;
200. a raw material moving position identification module;
300. and the raw material blank moves in place judgment module.
Detailed Description
The details of the present invention can be more clearly understood in conjunction with the accompanying drawings and the description of the embodiments of the present invention. However, the specific embodiments of the present invention described herein are for the purpose of illustration only and are not to be construed as limiting the invention in any way. Any possible variations based on the present invention may be conceived by the skilled person in the light of the teachings of the present invention, and these should be considered to fall within the scope of the present invention. It will be understood that when an element is referred to as being "disposed on" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "mounted," "connected," and "connected" are to be construed broadly and may include, for example, mechanical or electrical connections, communications between two elements, direct connections, indirect connections through intermediaries, and the like. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and the like as used herein are for illustrative purposes only and do not denote a unique embodiment.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In the production process of the rod and wire, after the blank enters a heating furnace, whether the blank runs in place needs to be detected, however, an effective detection means is lacked, closed-loop control cannot be formed, and most of the closed-loop control is finished by a manual visual inspection mode at present. Aiming at the problem, the invention provides a raw material blank charging positioning method by adopting an image processing mode, improves the detection accuracy and efficiency and provides a technical means for realizing unmanned automatic production.
The scene of the method for positioning and detecting the charging of the raw material blank provided by the application can be shown in fig. 1, the image acquisition device 3 is arranged above the conveying roller way 4, the image acquisition device 3 can be an industrial camera, of course, the image acquisition device 3 can also be other equipment capable of realizing image acquisition, the application is not specifically limited herein, and in the implementation mode provided by the application specification, the industrial camera is mainly taken as an example for illustration. The image acquisition device 3 is used for carrying out image acquisition aiming at the inlet 10 of the heating furnace 1 so as to complete the detection of the end face position of the raw material blank 2. In the present specification, the material blank 2 is mainly exemplified by a billet.
The industrial camera is arranged right above the billet and right opposite to the inlet 10 of the heating furnace 1, so that the lower edge of the inlet 10 of the heating furnace 1 can be kept as horizontal as possible in the image, and the slight inclination is within the error range allowed by the measurement). Referring to fig. 1, the lower edge of the inlet 10 of the heating furnace 1 is shown in the dotted line position in fig. 1, and is kept as horizontal as possible, so that the calibrated reference line can be parallel to the inlet when the furnace is determined to be in place, and the comparison is convenient. Because the application has low requirement on the measurement precision, the inclination angle of the dotted line can meet the requirement at plus or minus 10 degrees.
Referring to fig. 2, an embodiment of the present invention provides a raw material blank charging positioning detection method based on image processing, and specifically, the raw material blank charging positioning detection method may include the following steps:
step S10: based on the image acquired by the received image acquisition device 3, an image processing fixed area for extracting the appearance position of the raw material blank 2 is calibrated on the image;
step S12: identifying the type of the current raw material blank 2 within the image processing fixed area range, and matching corresponding identification modes aiming at different types of raw material blanks 2 to identify the movement position of the raw material blank 2;
step S14: and calibrating a judgment reference in the image processing fixed area, comparing the identified movement position of the raw material blank 2 with the judgment reference, and judging whether the raw material blank 2 moves in place.
Step S10: an image processing fixed Region for extracting the appearance position of the raw material blank 2 is marked on the image, namely, a Region for creating ROI (Region of Interest).
For the purpose of image analysis, a fixed region of the raw material blank 2 is first identified and extracted from the image, and this region is called a region of interest (ROI).
The specific method comprises the following steps: referring to FIG. 3, 1 line frame, such as a rectangular frame, is marked on the image81 (the rectangular frame 81 is relatively simple to label, and may have other shapes, and in the present specification, the rectangular frame 81 is mainly used as an example for illustration), and both end points of the rectangular frame 81 are (x) 1 ,y 1 )、(x 2 ,y 2 ). Selection principle of the rectangular frame 81: ensuring that the end surface of the raw material blank 2 is positioned in the rectangular frame 81 within 50cm before the raw material blank is put into the furnace. Subsequent image processing is only performed on the area of the rectangular frame 81, so that unnecessary noise information such as other equipment, background and the like on the image can be filtered.
Step S12: and identifying the category of the current raw material blank 2 within the image processing fixed region, matching corresponding identification modes aiming at different types of raw material blanks 2, and identifying the movement position of the raw material blank 2.
This step is mainly used for the positioning of the charge blank 2. In this embodiment, the material blank 2 may include a billet, and the types of the billet include: hot-feeding steel billets with red bodies and cold-feeding steel billets with gray bodies.
Finding out the edge of the raw billet 2 in the image through target extraction, and considering 2 conditions, namely, hot delivery of the billet, namely, the temperature of the billet is high and the body is red; one is cold feeding steel billet, which is at normal temperature and has gray body.
Referring to fig. 4, when the type of the billet is a hot-rolled billet, the identification method corresponding to the hot-rolled billet comprises the following substeps:
step S120: acquiring a gray value of an image red channel in an image processing fixed area, and generating a corresponding gray image;
step S122: carrying out contrast enhancement processing on the generated gray level image to obtain an enhanced image;
step S124: carrying out binarization processing on the enhanced image to obtain an image after binarization processing;
step S126: traversing all the regions in the image after the binarization processing, and calculating the area of each region;
step S128: when the sum of the calculated areas is larger than a first threshold value, determining that the current hot-delivery steel billet has reached a specified position;
step S130: traversing all points of the hot steel conveying billet, and taking the minimum value in the moving direction of the hot steel conveying billet as the current moving position of the hot steel conveying billet.
In step S122, the performing contrast enhancement processing on the generated grayscale image may include: substituting the original gray scale of the gray scale image into a first calculation formula, wherein the first calculation formula is as follows:
G new ＝G old *a+N，
where Gold is the original gray level of the image, G new Is the gray scale after image enhancement, a and N are preset parameters;
when G is new <0, then G new ＝0；
When G is new >255, then G new ＝255；
When G is new Between 0 and 255, take G new The actual value.
In step S124, the binarizing process on the enhanced image is specifically a binarizing process on the enhanced image by using a threshold segmentation algorithm, where G new Is the gray scale after the image enhancement,
when G is new <=125, gray =0 is set;
when G is new >125, gray =255 is set.
Specifically, the hot steel billet feeding body is red, one color picture comprises R, G, B three color channels (corresponding to red, green and blue), and on the red color channel of the picture, the gray value of the hot steel billet feeding is higher (because the red steel billet has a higher gray value on the red color channel of the image, the target extraction is more convenient), so that only the gray value of the red color channel of the picture is taken, and the corresponding gray image Img _ red is generated.
And performing contrast enhancement on the generated gray level image Img _ red, wherein the purpose of performing contrast enhancement is to enable the part with high gray level value to be higher and the part with low gray level value to be lower, so that the extraction of the raw material blank 2 body is facilitated. Specifically, the adopted calculation formula is as follows: g new ＝G old * a + N, where Gold is the original gray level of the image, G new The gray scale after image enhancement is obtained, a and N are preset parameters (the preset parameters can be adjusted according to needs, the adjustment here refers to selecting a more suitable contrast effect in an actual field light environment, generally, the 2 preset parameters can be fixed only by adjusting once), and generally, a =3,N = -400 can be set.
If G is new <0, then G new =0; if G is new >255, then G new =255; if G is new The actual value is taken between 0 and 255. And obtaining an enhanced image Img _ enhanced after processing.
The threshold segmentation algorithm can be used for carrying out binarization processing on Img _ enhanced, and because the gray value of the body of the billet is high, the part with low gray value can be filtered through the binarization processing.
Specifically, if G (here G is G) new )<=125, then G =0; if G is>125, then G =255; where G is the gray scale value. After processing, an image Img _ twovalaue is obtained. There may be multiple regions (regions) in the image, where all other regions are background noise, and only one region corresponds to the billet body.
Traversing all regions in the Img _ twovalaue image, automatically calculating the area of each region by the computer, and screening if the area S of the object is O >Sigma, the object is considered as the raw material billet O slab . Wherein, sigma can be adjusted according to the actual situation. It should be noted that: the area of the billet in the image is related to the actual installation distance of the industrial camera, the adjustment is carried out according to the actual installation distance on site, an actual picture is taken firstly, the area of the billet body is estimated, a proper threshold value is set according to the area value, the value is 300 in the invention, the area refers to the number of pixel points of the image, and 300 refers to the number of pixel points. The connected region of the raw material blank 2 has the largest area, and most of noise regions can be filtered by the ROI selection; meanwhile, the steel billet can have the highest ash content through red channel selection, contrast enhancement and the likeThe value can ensure that the area of the communicating area of the raw material blank 2 is the maximum. Furthermore, if the area of all regions is less than σ, then the image is considered to have no raw material patch 2.
Traverse O slab Taking the minimum value of all the points in the Y direction, namely the movement position P of the raw material blank 2 slab 。
Referring to fig. 5, in another case, when the type of the steel billet is a cold-fed steel billet, the identification method of the cold-fed steel billet may include the following sub-steps:
step S121: acquiring a gray value of an image blue channel in an image processing fixed area, and generating a corresponding gray image;
step S123: performing edge detection on the generated gray level image to obtain an edge image after edge detection;
step S125: performing binarization processing on the edge image after the edge detection to obtain an edge image after the binarization processing;
step S127: traversing all the areas in the edge image after the binarization processing, and calculating all pixel values on the edge image;
step S129: and traversing all the points with the pixel value of 1 in the edge image to obtain the contour line of the cold-fed steel billet, and taking the minimum value in the moving direction of the cold-fed steel billet as the current moving position of the cold-fed steel billet.
The step S125 of binarizing the edge image after edge detection specifically includes: performing binarization processing on the edge image through a threshold segmentation algorithm, wherein if the gray level of the edge image is less than or equal to a preset gray level, the gray level of the current position of the edge image is set to be 0; and if the gray scale of the edge image is greater than the preset gray scale, setting the gray scale of the current position of the edge image to be 255. When the gray levels of all positions on the edge image are zero, all pixel values on the corresponding edge image are zero; indicating that the image does not contain the raw material 2.
Specifically, the cold-fed steel billet body is gray, the gray value of the blue channel of the image is taken (because the cold-fed steel billet has a higher gray value on the blue channel of the image, the target is more conveniently extracted), and the corresponding gray image Img _ blue is generated.
At the moment, the edge of the billet and the background on the image is clearer, and the method is suitable for an edge detection algorithm. Specifically, the edge detection can be performed on the Img _ blue by adopting a standard kirsch operator to obtain the image Img _ kirsch. On this image, the edge of the billet has a high grayscale value. It should be noted that: the edge detection algorithm may also use other edge detection operators such as sobel and canny, besides the kirsch operator, and the application is not limited in this application.
Performing binarization processing on Img _ kirsch through a threshold segmentation algorithm, and if G < =240 (the value can be adjusted according to the actual situation, the threshold is selected by performing the above analysis on an actual picture on site and setting a proper threshold according to the gray value of the extracted edge contour line), G =0; if G >240, G =255; where G is the gray scale value. After the treatment, the mixture is subjected to a treatment, an image Img _ edge is obtained. If the raw material blank 2 exists in the image, the contour line of the raw material blank 2 is displayed on the image Img _ edge at the moment; if all the pixel values on the image Img _ edge are 0, it indicates that there is no blank 2 in the image at this time.
If the raw material blank 2 exists in Img _ edge, traversing all the points with the pixel value of 1 in Img _ edge, and taking the minimum value of the points in the Y direction, namely the movement position P of the raw material blank 2 slab 。
After the positioning of the different kinds of the raw material blanks 2 is completed, the determination of the in-place of the charging can be performed.
Specifically, referring to fig. 6 in combination, in step S14, the determination criterion is a reference line y = d marked on the image along the conveyance direction of the raw material 2, specifically,
when the position P of the raw material blank 2 slab When d is more than or equal to d, the raw material blank 2 is moved in place;
when the position P of the raw material blank 2 slab <d, the raw material blank 2 is not moved in place.
The value of d may be selected according to actual situations in the field, and the present application is not limited specifically herein.
On the whole, the raw material blank furnace-entering positioning detection method provided by the application can replace manual detection and can be combined with an automatic control system to realize unmanned production; the detection precision and the detection efficiency are higher; can achieve the effects of reducing personnel and improving efficiency.
Referring to fig. 7, based on the raw material blank charging positioning and detecting method provided in the foregoing embodiment, an apparatus for detecting raw material blank charging positioning is further provided in the embodiment of the present application, which may include:
an image processing fixed region creating module 100 configured to calibrate an image processing fixed region for extracting an appearance position of the raw material blank 2 on the image based on the image acquired by the received image acquiring device 3;
the raw material blank motion position identification module 200 is used for identifying the type of the current raw material blank 2 in the image processing fixed region range, matching corresponding identification modes aiming at different types of raw material blanks 2 and identifying the motion position of the raw material blank 2;
and the raw material blank in-place movement judging module 300 is used for calibrating a judgment reference in the image processing fixed area, comparing the identified movement position of the raw material blank 2 with the judgment reference and judging whether the raw material blank 2 moves in place.
It should be noted that: the functions of the image processing fixed area creating module 100, the raw material blank movement position identifying module 200, and the raw material blank movement in-place judging module 300 correspond to the steps of the raw material blank charging positioning detection method provided in the above embodiment, and the technical problems solved by the raw material blank charging positioning detection apparatus are similar to those of the raw material blank charging positioning detection method. Therefore, the using process of the raw material blank charging positioning detection device can refer to the raw material blank charging positioning detection method in the foregoing embodiment, and details are not repeated herein.
Based on the raw material billet charging positioning detection method provided in the foregoing embodiment, the embodiment of the present application further provides an image processing server 5, which may include: the present invention relates to a method for detecting the position of a raw material charge in a furnace, and more particularly, to a method for detecting the position of a raw material charge in a furnace, which is capable of detecting the position of a raw material charge in a furnace.
The image processing server 5 may specifically include: a processor (processor), a memory (memory), a communications interface (communications interface), and a communications bus. The processor, the memory and the communication interface complete mutual communication through the communication bus, and the communication interface is used for realizing information transmission among related devices. The processor is configured to call a computer program in the memory, and when the processor executes the computer program, the raw material blank charging positioning detection method in the above embodiment is implemented.
Referring to fig. 8 and 9, based on the image processing server 5 provided in the above embodiment, the present application also provides a raw material blank 2 charging positioning detection system, which may include: the image processing server 5 described above, and a controller 6 and an image capture device 3 that can communicate with the image processing server 5. The image processing server 5, the controller 6 and the image capturing device 3 may communicate through the switch 7, or may communicate through other methods, and the present application is not limited in this respect.
The controller 6 may specifically be a PLC controller 6, and of course, other types of controllers 6 may also be adopted, and specifically, the present application is not limited in this respect. In the embodiment of the present specification, the controller 6 will be described by taking the PLC controller 6 as an example.
After detecting that the raw material blank 2 passes through, the field PLC controller 6 sends a trigger signal to the image processing server 5, and the image processing server 5 identifies whether the current steel blank is a hot steel blank or a cold steel blank; of course, the type of the current billet may be automatically identified by the PLC controller 6, or the type of the billet may be identified by other devices. The image processing server 5 requests the industrial camera to acquire an image, the industrial camera acquires the image and sends the image to the image processing server 5, the image processing server 5 calls a corresponding positioning detection algorithm to identify the image after acquiring image data returned by the industrial camera, the identification result is sent to the PLC controller 6, and the PLC controller 6 completes corresponding operation subsequently.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (12)
1. A raw material blank charging positioning detection method is characterized by comprising the following steps:
based on the image acquired by the image acquisition device, calibrating an image processing fixed area for extracting the appearance position of the raw material blank on the image;
identifying the category of the current raw material blank within the image processing fixed region range, and matching corresponding identification modes aiming at different categories of raw material blanks to identify the movement position of the raw material blank;
and calibrating a judgment reference in the image processing fixed area, comparing the identified movement position of the raw material blank with the judgment reference, and judging whether the raw material blank moves in place.
2. The method of claim 1, wherein the material blank comprises a steel blank, and the categories of the steel blank include: hot-feeding steel billets with red bodies and cold-feeding steel billets with gray bodies.
3. The method of claim 2, wherein when the type of the slab is a hot-fed slab, the identifying method for the hot-fed slab includes:
acquiring a gray value of a red channel of an image in an image processing fixed area, and generating a corresponding gray image;
carrying out contrast enhancement processing on the generated gray level image to obtain an enhanced image;
carrying out binarization processing on the enhanced image to obtain an image after binarization processing;
traversing all the regions in the image after the binarization processing, and calculating the area of each region;
when the sum of the calculated areas is larger than a first threshold value, determining that the current hot-delivery steel billet has reached a specified position;
traversing all points of the hot steel conveying billet, and taking the minimum value in the moving direction of the hot steel conveying billet as the current moving position of the hot steel conveying billet.
4. The method for detecting the position of the raw material blank entering the furnace according to claim 3, wherein the step of performing contrast enhancement processing on the generated gray scale image comprises the steps of:
substituting the original gray scale of the gray scale image into a first calculation formula, wherein the first calculation formula is as follows:
G new ＝G old *a+N
wherein G is old Is the original gray scale of the image, G new Is the gray scale after image enhancement, a and N are preset parameters;
when G is new <0, then G new ＝0；
When G is new >255, then G new ＝255；
When G is new Between 0 and 255, take G new The actual value.
5. The raw material blank furnace-entering positioning detection method as claimed in claim 3, wherein the binarization processing on the enhanced image is specifically binarization processing on the enhanced image by a threshold segmentation algorithm, wherein G is new Is the gray scale after the image enhancement,
when G is new <=125, gray =0 is set;
when G is new >125, gray =255 is set.
6. The method of claim 2, wherein when the type of the slab is a cold-fed slab, the identifying method for the cold-fed slab includes:
acquiring a gray value of an image blue channel in an image processing fixed area, and generating a corresponding gray image;
performing edge detection on the generated gray level image to obtain an edge image after edge detection;
performing binarization processing on the edge image after edge detection to obtain an edge image after binarization processing;
traversing all the areas in the edge image after the binarization processing, and calculating all pixel values on the edge image;
and traversing all the points with the pixel value of 1 in the edge image to obtain the contour line of the cold-fed steel billet, and taking the minimum value in the moving direction of the cold-fed steel billet as the current moving position of the cold-fed steel billet.
7. The method for positioning and detecting the charging of raw material blank according to claim 6, wherein the binarizing process is performed on the edge image after the edge detection, specifically, the binarizing process is performed on the edge image by a threshold segmentation algorithm, wherein,
if the gray scale of the edge image is less than or equal to the preset gray scale, setting the gray scale of the current position of the edge image as 0;
and if the gray scale of the edge image is greater than the preset gray scale, setting the gray scale of the current position of the edge image to be 255.
8. The raw material blank charging positioning detection method according to claim 7, wherein when the gray scale of all positions on the edge image is zero, all pixel values on the corresponding edge image are zero; indicating that no material blank was present in the image at this time.
9. The method of claim 1, wherein the determination reference is a reference line y = d marked on the image along the billet conveyance direction,
when the position P of the raw material blank slab When d is more than or equal to d, indicating that the raw material base moves in place;
when the position P of the raw material blank slab <d, indicating that the raw material blank is not moved in place.
10. The utility model provides a raw materials base goes into stove location detection device which characterized in that includes:
the image processing fixed area creating module is used for calibrating an image processing fixed area for extracting the appearance position of the raw material blank on the image based on the image acquired by the image receiving and acquiring device;
the raw material blank motion position identification module is used for identifying the type of the current raw material blank within the image processing fixed region range, matching corresponding identification modes aiming at different types of raw material blanks and identifying the motion position of the raw material blank;
and the raw material blank in-place movement judging module is used for calibrating a judgment reference in the image processing fixed area, comparing the identified movement position of the raw material blank with the judgment reference and judging whether the raw material blank moves in place.
11. An image processing server, comprising: memory, processor and computer program stored on the memory and executable on the processor, the processor implementing the method of any of claims 1 to 9 when executing the computer program.
12. The utility model provides a raw materials base goes into stove location detecting system which characterized in that includes: the image processing server of claim 11, and a controller and image capture device capable of communicating with the image processing server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210944782.9A CN115272269A (en) | 2022-08-08 | 2022-08-08 | Raw material blank furnace-entering positioning detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210944782.9A CN115272269A (en) | 2022-08-08 | 2022-08-08 | Raw material blank furnace-entering positioning detection method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115272269A true CN115272269A (en) | 2022-11-01 |
Family
ID=83749541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210944782.9A Pending CN115272269A (en) | 2022-08-08 | 2022-08-08 | Raw material blank furnace-entering positioning detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115272269A (en) |
-
2022
- 2022-08-08 CN CN202210944782.9A patent/CN115272269A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| CN109167928B (en) | Rapid automatic exposure method and system based on display panel defect detection | |
| CN104101600B (en) | Cross Section of CC Billet testing of small cracks method | |
| CN106248686A (en) | Glass surface defects based on machine vision detection device and method | |
| CN111521129B (en) | Machine vision-based slab warping detection device and method | |
| CN102441581A (en) | Machine vision-based device and method for online detection of structural steel section size | |
| CN108662977A (en) | A kind of refractory brick geometric dimension measurement method | |
| CN114881915A (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
| CN116136393B (en) | Bearing ring inner ring detection system and method | |
| CN104637067A (en) | Method for detecting defect of textured surface | |
| CN113894055A (en) | Hardware surface defect detection and classification system and method based on machine vision | |
| CN111539927A (en) | Detection process and algorithm of automobile plastic assembly fastening buckle lack-assembly detection device | |
| US20150254830A1 (en) | Shape Inspecting Device And Shape Inspecting Method | |
| CN110751669A (en) | Novel CBOCP online infrared converter tapping steel flow automatic detection and tracking method and system | |
| CN111307812A (en) | Welding spot appearance detection method based on machine vision | |
| KR102000907B1 (en) | Appearance vision inspection method for ferrite part | |
| CN104614386A (en) | Lens defects type identification method | |
| CN114663427B (en) | Boiler part size detection method based on image processing | |
| CN109277568B (en) | Real-time monitoring method, device and system for selective laser melting | |
| CN111539951B (en) | Visual detection method for outline size of ceramic grinding wheel head | |
| CN111222360A (en) | Method and device for detecting melting state of silicon material and storage medium | |
| CN115272269A (en) | Raw material blank furnace-entering positioning detection method, device and system | |
| CN112213320A (en) | Biscuit detection device and biscuit detection method based on machine vision | |
| CN116681664A (en) | Detection method and device for operation of stamping equipment | |
| CN115638742B (en) | Reinforcing bar shape quality inspection system based on image recognition |
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 |