CN113052816A - Furnace mouth image identification method, device, equipment and storage medium - Google Patents
Furnace mouth image identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113052816A CN113052816A CN202110314254.0A CN202110314254A CN113052816A CN 113052816 A CN113052816 A CN 113052816A CN 202110314254 A CN202110314254 A CN 202110314254A CN 113052816 A CN113052816 A CN 113052816A
- Authority
- CN
- China
- Prior art keywords
- area
- furnace mouth
- image
- furnace
- slag
- 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
- 238000000034 method Methods 0.000 title claims abstract description 74
- 239000002893 slag Substances 0.000 claims abstract description 68
- 238000012545 processing Methods 0.000 claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000004544 sputter deposition Methods 0.000 claims description 25
- 238000012216 screening Methods 0.000 claims description 22
- 238000010586 diagram Methods 0.000 claims description 14
- 238000003708 edge detection Methods 0.000 claims description 14
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 239000012634 fragment Substances 0.000 claims description 5
- 238000001035 drying Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 15
- 238000009628 steelmaking Methods 0.000 abstract description 10
- 238000003723 Smelting Methods 0.000 abstract description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 abstract description 5
- 229910052760 oxygen Inorganic materials 0.000 abstract description 5
- 239000001301 oxygen Substances 0.000 abstract description 5
- 230000009466 transformation Effects 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 239000000779 smoke Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 102100037651 AP-2 complex subunit sigma Human genes 0.000 description 1
- 101000806914 Homo sapiens AP-2 complex subunit sigma Proteins 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 239000010959 steel Substances 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
-
- G06T5/70—
-
- 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
- G06T7/60—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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/30204—Marker
Abstract
The application discloses a furnace mouth image identification method, a furnace mouth image identification device, furnace mouth image identification equipment and a storage medium, wherein the method comprises the following steps: acquiring a furnace mouth image in real time; preprocessing the furnace mouth image to obtain a furnace mouth area; acquiring the area and the number of slag sheets in a furnace mouth area, and obtaining a pre-splashing identification result according to the area and the number of the slag sheets in a first set time period; and translating the furnace mouth area along the height of the furnace mouth area up and down to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, acquiring corresponding areas, comparing the areas with corresponding set area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period. The method has the advantages that the pre-splashing state and the splashing state are identified by extracting, analyzing and judging the information and the characteristics contained in the furnace mouth image, the pre-splashing state and the splashing state can be well used for controlling the feeding mode and the oxygen lance adjusting mode in the smelting process, so that the aim of automatic steel making is fulfilled, and the method has the characteristics of accurate prediction and high processing speed.
Description
Technical Field
The invention relates to the field of image recognition, in particular to a furnace mouth image recognition method, a furnace mouth image recognition device, furnace mouth image recognition equipment and a storage medium.
Background
Converter steelmaking is the current mainstream steelmaking mode, and during the converter steelmaking process, a steelmaking worker generally observes the states of slag and flame at a furnace mouth through human eyes to control the gun position and add auxiliary materials, so that a good furnace of steel is blown to reach the tapping standard.
However, the states of the slag splashed from the furnace mouth and the slag pre-splashed from the furnace mouth are recognized by human eyes, and the states are judged by the human experience of operators, so that the differences in operation exist, the prediction accuracy is low, and the processing speed is low.
Therefore, how to solve the problems of low prediction accuracy, low processing speed and the like of the furnace mouth splashing and pre-splashing identification is a technical problem to be solved urgently by the technical personnel in the field.
Disclosure of Invention
In view of the above, the present invention provides a furnace mouth image recognition method, device, equipment and storage medium, which can achieve the purpose of automatic steel making, and has high accuracy and high processing speed for forecasting pre-sputtering and sputtering recognition. The specific scheme is as follows:
a furnace mouth image identification method comprises the following steps:
acquiring a furnace mouth image in real time;
preprocessing the furnace mouth image to obtain a furnace mouth area of the furnace mouth image;
acquiring the area and the number of the slag sheets in the furnace mouth area, and obtaining a pre-splashing identification result according to the area and the number of the slag sheets in a first set time period;
and translating the furnace mouth area along the height of the furnace mouth area up and down to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, acquiring corresponding areas, comparing the areas with corresponding set area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period.
Preferably, in the method for identifying an image of a furnace mouth provided in an embodiment of the present invention, the preprocessing the image of the furnace mouth to obtain a furnace mouth region of the image of the furnace mouth specifically includes:
carrying out drying removal treatment on the furnace mouth image by using median filtering;
carrying out scale conversion on the furnace mouth image, and enhancing the brightness of the furnace mouth image through a scale conversion factor;
segmenting the furnace mouth image through an OTSU automatic threshold algorithm and acquiring a segmentation threshold;
and adjusting the segmentation threshold value and carrying out binarization on the furnace opening image according to the average value of the segmented furnace opening image to obtain the furnace opening area of the furnace opening image.
Preferably, in the method for identifying an image of a furnace mouth provided in an embodiment of the present invention, the acquiring an area and a number of slag sheets in the furnace mouth region specifically includes:
carrying out edge detection on the furnace mouth area through a Canny edge operator to obtain the area and the number of slag fragments of an edge detection result;
converting the furnace mouth image through a Gaussian derivative matrix to obtain a derivative diagram of the Hessian rule, extracting the characteristics of the derivative diagram and processing to obtain the area and the number of slag sheets in the derivative diagram;
and carrying out merging operation on the area and the number of the slag sheets of the obtained edge detection result and the area and the number of the slag sheets in the derivative diagram to obtain the area and the number of the slag sheets in the furnace mouth area.
Preferably, in the method for identifying an image of a furnace mouth provided in an embodiment of the present invention, edge detection is performed on the furnace mouth region by a Canny edge operator to obtain an area and a number of slag fragments of an edge detection result, and the method specifically includes:
extracting the contour line of the slag sheet in the area of the furnace mouth through a Canny edge operator;
carrying out roundness screening on the extracted contour line;
converting the screened contour lines into areas and filling;
and (4) carrying out area screening on the filled areas, selecting the areas with the areas in a set interval, identifying the areas into the furnace mouth image, obtaining the identified slag sheets, and obtaining the areas and the number of the slag sheets.
Preferably, in the method for identifying an image of a furnace mouth according to an embodiment of the present invention, the performing roundness screening on the extracted contour line specifically includes:
removing the non-arc-shaped edge in the extracted contour line;
and (4) carrying out closed contour screening on the rest contour lines to obtain the contour lines of which the distance between the starting point and the ending point is less than a set distance threshold.
Preferably, in the method for identifying an image of a furnace mouth provided in an embodiment of the present invention, extracting and processing features of the derivative graph to obtain areas and numbers of slag pieces in the derivative graph, specifically including:
performing background removal processing on the derivative graph;
screening out the area with the pixel value larger than the set pixel threshold value;
and (4) carrying out furnace mouth frame removal and area screening on the screened area to obtain the identified slag pieces, and obtaining the area and the number of the slag pieces.
Preferably, in the method for identifying an image of a furnace mouth according to an embodiment of the present invention, obtaining a spatter identification result according to a comparison result in a second set time period specifically includes:
when the area of the sputtering detection area obtained by downward shifting after threshold processing is larger than a first set area threshold, and the area of the sputtering detection area obtained by upward shifting after threshold processing is smaller than a second set area threshold, and the number of the furnace opening images meeting the condition in a second set time period is larger than a set number threshold, determining that the furnace opening images contain sputtering phenomena; or the like, or, alternatively,
and when the area of the sputtering detection area obtained by downward moving after threshold processing is larger than half of the total area of the furnace opening area, and the area of the sputtering detection area obtained by upward moving after threshold processing is smaller than the second set area threshold, determining that the furnace opening image contains sputtering.
The embodiment of the invention also provides a furnace mouth image recognition device, which comprises:
the image acquisition module is used for acquiring furnace mouth images in real time;
the image processing module is used for preprocessing the furnace mouth image to obtain a furnace mouth area of the furnace mouth image;
the pre-sputtering identification module is used for acquiring the area and the number of the slag sheets in the furnace mouth area and obtaining a pre-sputtering identification result according to the area and the number of the slag sheets in a first set time period;
and the splash identification module is used for translating up and down along the height of the furnace mouth area to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, acquiring corresponding areas, comparing the corresponding areas with corresponding area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period.
The embodiment of the invention also provides furnace mouth image identification equipment which comprises a processor and a memory, wherein the furnace mouth image identification method provided by the embodiment of the invention is realized when the processor executes the computer program stored in the memory.
The embodiment of the invention also provides a computer-readable storage medium for storing a computer program, wherein the computer program is executed by a processor to implement the furnace mouth image identification method provided by the embodiment of the invention.
According to the technical scheme, the furnace mouth image identification method provided by the invention comprises the following steps: acquiring a furnace mouth image in real time; preprocessing the furnace mouth image to obtain a furnace mouth area of the furnace mouth image; acquiring the area and the number of slag sheets in a furnace mouth area, and obtaining a pre-splashing identification result according to the area and the number of the slag sheets in a first set time period; and translating the furnace mouth area along the height of the furnace mouth area up and down to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, acquiring corresponding areas, comparing the areas with corresponding set area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period.
The invention extracts, analyzes and judges the information and the characteristics contained in the furnace mouth image so as to obtain the states of the pre-splashing and the splashing, thus the pre-splashing and the splashing identification of the furnace mouth image can be well used for controlling the feeding mode and the oxygen lance adjusting mode in the smelting process to replace the operation of an operator through visual observation so as to achieve the aim of automatic steel making. In addition, the invention also provides a corresponding device, equipment and a computer readable storage medium for the furnace mouth image identification method, so that the method has higher practicability, and the device, the equipment and the computer readable storage medium have corresponding advantages.
Drawings
In order to more clearly illustrate the embodiments of the present invention or technical solutions in related arts, the drawings used in the description of the embodiments or related arts will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flowchart of a furnace mouth image identification method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for identifying furnace mouth images according to an embodiment of the present invention;
FIG. 3 is a furnace mouth image before the scale transformation provided by the embodiment of the invention;
FIG. 4 is a scaled furnace mouth image provided by an embodiment of the present invention;
FIG. 5 is a furnace mouth image after automatic threshold segmentation according to an embodiment of the present invention;
FIG. 6 is a furnace mouth image after binarization according to the embodiment of the invention;
FIG. 7 is an original furnace mouth image corresponding to furnace mouth pre-sputtering provided by an embodiment of the present invention;
fig. 8 is an image after Canny subpixel edge extraction according to an embodiment of the present invention;
FIG. 9 is an image of a roundness screen provided by an embodiment of the present invention;
FIG. 10 is an image after screening out a closed contour according to an embodiment of the present invention;
fig. 11 is a slag slice image identified by Canny edge operator processing according to an embodiment of the present invention;
FIG. 12 is an image transformed into a Hessian matrix according to an embodiment of the present invention;
FIG. 13 is an image with salient regions after background removal processing according to an embodiment of the present invention;
FIG. 14 is an image of an area screen having protruding regions according to an embodiment of the present invention;
FIG. 15 is a furnace mouth image after gross pre-spatter identification provided by an embodiment of the present invention;
fig. 16 is an identification area diagram obtained after the furnace mouth area provided by the embodiment of the invention is translated up and down;
FIG. 17 is a basic view of a fire port fire blast provided by an embodiment of the present invention;
FIG. 18 is a spatter image in the case of slag accretion at the furnace mouth according to an embodiment of the present invention;
FIG. 19 is an image of a splash detection area obtained under slag accumulation and splash conditions provided by embodiments of the present invention;
FIG. 20 shows the pre-sputter identification under normal conditions provided by an embodiment of the present invention;
FIG. 21 is a pre-splash recognition result under the condition of slag accretion at the furnace mouth according to the embodiment of the present invention;
FIG. 22 shows the pre-spatter recognition results under smoke interference according to an embodiment of the present invention;
FIG. 23 shows a sputter identification result under normal conditions according to an embodiment of the present invention;
FIG. 24 shows the spatter recognition results under smoke interference according to an embodiment of the present invention;
FIG. 25 is a view showing the result of identifying splashing in the case of slag accretion at the furnace mouth according to the embodiment of the present invention;
fig. 26 is a schematic structural diagram of a furnace mouth image recognition device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a furnace mouth image identification method, as shown in figure 1, comprising the following steps:
s101, acquiring furnace mouth images in real time.
S102, preprocessing the furnace mouth image to obtain a furnace mouth area of the furnace mouth image.
It should be noted that, because the environment of the converting is relatively harsh, the acquired furnace mouth image is subject to more interference factors, and in order to accurately obtain the furnace mouth region, some preprocessing needs to be performed on the image.
S103, acquiring the area and the number of the slag sheets in the furnace mouth area, and obtaining a pre-splashing identification result according to the area and the number of the slag sheets in a first set time period.
In practical application, the pre-sputtering actually belongs to the condition of slag chips thrown from the furnace mouth visual field in the converter smelting process, and in order to more accurately extract the slag chips thrown from the furnace mouth, the invention can extract and judge comprehensive characteristics of processing results of canny edge detection operators and Gaussian derivative matrix processing so as to identify the pre-sputtering phenomenon. The first set time period here may be set to be within the current 2 seconds.
S104, translating up and down along the height of the furnace mouth area to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, obtaining corresponding areas, comparing the areas with corresponding set area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period. The second set time period here may be set to within the current 1 second.
In the furnace mouth image identification method provided by the embodiment of the invention, the pre-splashing and splashing states are obtained by extracting, analyzing and judging the information and the characteristics contained in the furnace mouth image, so that the pre-splashing and splashing identification of the furnace mouth image can be well used for controlling the feeding mode and the oxygen lance adjusting mode in the smelting process to replace the operation of an operator through visual observation, thereby achieving the purpose of automatic steel making.
Further, in a specific implementation, in the method for identifying a furnace mouth image according to an embodiment of the present invention, as shown in fig. 2, the step S102 is to pre-process the furnace mouth image to obtain a furnace mouth region of the furnace mouth image, and specifically includes: firstly, carrying out drying treatment on a furnace mouth image by using median filtering; then carrying out scale transformation on the furnace mouth image, and enhancing the brightness of the furnace mouth image through a scale transformation factor; then, segmenting the furnace mouth image through an OTSU automatic threshold algorithm and acquiring a segmentation threshold; and finally, according to the average value of the furnace mouth image after segmentation, adjusting the segmentation threshold value and carrying out binarization on the furnace mouth image to obtain the furnace mouth area of the furnace mouth image. In order to make the processing effect better, after the furnace mouth area of the furnace mouth image is obtained, the furnace mouth image can be subjected to equalization processing according to the mean value and the variance of the furnace mouth area, and the basic characteristics of the furnace mouth, such as width and the like, can be accurately obtained.
Specifically, taking fig. 3 to 6 as an example, first, the I _ I image before transformation shown in fig. 3 is passed throughThe transformed image I _ o shown in fig. 4 is obtained, and the brightness of the image is enhanced by the scaling factor num _ scale. Then, the segmented image and the segmentation threshold shown in fig. 5 are obtained through an OTSU automatic threshold algorithm, the segmentation threshold is adjusted according to the mean value of the image in fig. 5, and the furnace mouth is obtained through binarization, so that the furnace mouth area of the furnace mouth image shown in fig. 6 is obtained.
Further, in a specific implementation, in the method for identifying an image of a furnace mouth provided in an embodiment of the present invention, the step S103 may specifically include the following steps:
step one, carrying out edge detection on the furnace mouth area through a Canny edge operator to obtain the area and the number of slag fragments of an edge detection result.
Specifically, the contour line of the slag sheet in the furnace mouth area can be extracted through a Canny edge operator; then, carrying out roundness screening on the extracted contour line; then converting the screened contour lines into regions and filling; and finally, area screening is carried out on the filled areas, the areas with the areas within the set interval are selected, the areas are marked in the furnace mouth image, the identified slag sheets are obtained, and the areas and the number of the slag sheets are obtained.
Fig. 7 shows an image of a furnace mouth containing a slag throwing sheet in practice. Fig. 8 shows contour lines of canny edge subpixel extraction obtained by setting corresponding parameters. The roundness value of the extracted contour line subjected to roundness screening can be [0.04559,1 ]]The roundness num _ r is obtained byF is the area of the contour, and m _ dis is the pixel distance from the center of the area to each boundary. As shown in fig. 9 and 10, the roundness screening may remove non-circular arc-shaped edges in the contour lines, and then perform closed contour screening on the remaining contour lines, where the closed contour is obtained by calculating a distance between a start point and an end point of one contour line and screening out points having a distance greater than a set distance threshold, converting the contour lines into regions and filling, then performing area screening, selecting a region having an area within a certain threshold interval, and as shown in fig. 11, identifying the region in the image to obtain identified slag flakes.
And step two, converting the furnace mouth image through a Gaussian derivative matrix to obtain a derivative diagram of the Hessian rule, extracting the characteristics of the derivative diagram and processing to obtain the area and the number of the slag sheets in the derivative diagram.
Specifically, the acquired furnace mouth region is first extracted from the furnace mouth image, and then, as shown in fig. 12, the gaussian filtered image with sigma 2 is passed throughThe image is converted into a derivative map (namely a Hessian matrix image), and areas with obvious pixel transformation in the derivative map can be displayed more clearly and intuitively. During the subsequent processing of the derivative graph, the derivative graph can be first subjected to back removingScene processing; as shown in fig. 13, the background pixels of the matrix image are around 0, and the more abrupt the pixel values are, the larger the area of the pixel value is screened out, and at this time, the area of the pixel value larger than the set pixel threshold value is screened out, as shown in fig. 14, the convex area in the image can be obtained by selecting the threshold value larger than 2; and finally, carrying out furnace mouth frame removal and area screening on the screened area to obtain the identified slag pieces, and obtaining the area and the number of the slag pieces.
And step three, carrying out merging operation on the area and the number of the slag sheets of the obtained edge detection result and the area and the number of the slag sheets in the derivative diagram to obtain the area and the number of the slag sheets in the furnace mouth area.
Specifically, the result of canny edge operator processing is combined with the result of gaussian derivative matrix processing, and the areas obtained by the two modes are merged, so as to obtain the state and position of the pre-sputtering identification block in the furnace mouth image as shown in fig. 15.
Further, in a specific implementation, in the above furnace mouth image identification method provided by the embodiment of the present invention, in the process of performing step S104, the furnace mouth area obtained by preprocessing is translated up and down to obtain the splash detection area1 and the splash detection area2 as shown in fig. 16, because the fire condition as shown in fig. 17 exists in the furnace mouth blowing process, the fire condition can seriously affect the judgment of the furnace mouth and the judgment of the splash, but the greatest characteristic difference between the fire and the splash is that the flame has an upward trend, so that the fire can be filtered and screened by the splash detection area2 obtained by moving up, in addition, the contraction speed of the flame is very fast, the cooling speed of the splashed liquid is much slower, and the splash image meeting the conditions by using the upward trend is stored in an array for comprehensive judgment, thereby achieving the splash identification.
In the case where the furnace mouth has a large amount of slag deposited and the furnace mouth region becomes small and difficult to recognize, the splash in this case is, as shown in fig. 18, a black oval region in the image is extracted by screening the characteristics of the threshold value and the coordinates (if there is no significant furnace mouth, the lower 1/3 region in the image is taken as the splash detection region 3 if there is no black oval region), the fixed splash detection region 3 having a height of 200 pixels is planned with the uppermost line coordinate as the start line coordinate, e.g., the white dot position in fig. 19, and a portion having a pixel value larger than the threshold value 30 is extracted from the fixed splash detection region 3, and the area thereof is calculated and stored, and the comprehensive judgment can be such that it is possible to judge that the area is small and difficult to recognize
Wherein, Area1, Area2 and Area3 are threshold areas of the splash detection Area1, the splash detection Area2 and the splash detection Area3, respectively, TH _ Area1, TH _ Area2 and TH _ Area3 are a first set Area threshold corresponding to the splash detection Area1, a second set Area threshold corresponding to the splash detection Area2 and a third Area threshold corresponding to the splash detection Area3, respectively, num is the number of images matching the case in which (Area1 > TH _ Area1) & (Area2 < TH _ Area2) or (Area3 > TH _ Area3) & (Area2 < TH _ Area2) in the current 1s, TH _ num is a set number threshold, and TH _ Area _ all is the total Area of the furnace mouth Area. When one of the three conditions is satisfied, the splash phenomenon is considered.
That is to say, the step S104 obtains the spatter identification result according to the comparison result in the second set time period, and specifically includes: when the Area1 obtained after the threshold processing of the spatter detection Area1 obtained by the downward shifting is larger than a first set Area threshold TH _ Area1, and the Area2 obtained after the threshold processing of the spatter detection Area2 obtained by the upward shifting is smaller than a second set Area threshold TH _ Area2, and the number of the furnace mouth images satisfying the condition in a second set time period is larger than a set number threshold TH _ num, determining that the furnace mouth images contain the spatter phenomenon; or, when the Area3 acquired after the thresholding of the splash detection Area3 is greater than the third set Area threshold TH _ Area3, and the Area2 acquired after the thresholding of the upwardly shifted splash detection Area2 is less than the second set Area threshold TH _ Area2, and the number of furnace mouth images satisfying this condition within the second set time period is greater than the set number threshold TH _ num, it is determined that the furnace mouth images contain the splash phenomenon; or, when the Area1 acquired after the thresholding of the spatter detecting region 1 obtained by moving down is larger than half of the total Area TH _ Area _ all of the furnace opening region and the Area2 acquired after the thresholding of the spatter detecting region 2 obtained by moving up is smaller than the second set Area threshold TH _ Area2, it is determined that the furnace opening image contains the spatter phenomenon.
After the experiment, the pre-sputtering under the normal condition, the pre-sputtering under the condition that the furnace mouth has certain slag deposit, or the pre-sputtering under the condition of being interfered by large smoke can be accurately identified, and the identification result is shown in fig. 20, 21 and 22. Similarly, whether the spatter is normal, disturbed by smoke, or deposited on the furnace mouth can be accurately identified, and the identification results are shown in fig. 23, 24, and 25, respectively. Therefore, the furnace mouth image identification method provided by the embodiment can accurately identify the pre-splashing or splashing result under various conditions.
Based on the same inventive concept, the embodiment of the invention also provides a furnace mouth image identification device, and as the principle of solving the problems of the device is similar to the furnace mouth image identification method, the implementation of the device can refer to the implementation of the furnace mouth image identification method, and repeated parts are not described again.
In specific implementation, the furnace mouth image recognition apparatus provided in the embodiment of the present invention, as shown in fig. 26, specifically includes:
the image acquisition module 11 is used for acquiring furnace mouth images in real time;
the image processing module 12 is used for preprocessing the furnace mouth image to obtain a furnace mouth area of the furnace mouth image;
the pre-splashing identification module 13 is used for acquiring the area and the number of the slag sheets in the furnace mouth area and obtaining a pre-splashing identification result according to the area and the number of the slag sheets in a first set time period;
and the splash identification module 14 is used for translating up and down along the height of the furnace mouth area to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, acquiring corresponding areas, comparing the corresponding areas with corresponding area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period.
In the furnace mouth image recognition device provided by the embodiment of the invention, the states of pre-splashing and splashing can be obtained through the interaction of the four modules, and the device can be further well used for controlling the feeding mode and the oxygen lance adjusting mode in the smelting process to replace the operation of an operator through visual observation, so that the purpose of automatic steel making is achieved, and the device has the characteristics of accurate prediction and high processing speed.
For more specific working processes of the modules, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Correspondingly, the embodiment of the invention also discloses a furnace mouth image identification device, which comprises a processor and a memory; the furnace mouth image recognition method disclosed in the foregoing embodiments is realized when the processor executes the computer program stored in the memory.
For more specific processes of the above method, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Further, the present invention also discloses a computer readable storage medium for storing a computer program; the computer program, when executed by a processor, implements the fire door image identification method disclosed above.
For more specific processes of the above method, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device, the equipment and the storage medium disclosed by the embodiment correspond to the method disclosed by the embodiment, so that the description is relatively simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The furnace mouth image identification method provided by the embodiment of the invention comprises the following steps: acquiring a furnace mouth image in real time; preprocessing the furnace mouth image to obtain a furnace mouth area of the furnace mouth image; acquiring the area and the number of slag sheets in a furnace mouth area, and obtaining a pre-splashing identification result according to the area and the number of the slag sheets in a first set time period; and translating the furnace mouth area along the height of the furnace mouth area up and down to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, acquiring corresponding areas, comparing the areas with corresponding set area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period. The method has the advantages that the information and the characteristics contained in the furnace mouth image are extracted, analyzed and judged, so that the states of pre-splashing and splashing are recognized, the method can be well used for controlling the feeding mode and the oxygen lance adjusting mode in the smelting process to replace the operation of an operator through visual observation, and the purpose of automatic steel making is achieved. In addition, the invention also provides a corresponding device, equipment and a computer readable storage medium for the furnace mouth image identification method, so that the method has higher practicability, and the device, the equipment and the computer readable storage medium have corresponding advantages.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The furnace mouth image recognition method, device, equipment and storage medium provided by the invention are described in detail, and the principle and the implementation mode of the invention are explained by applying specific examples, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A furnace mouth image identification method is characterized by comprising the following steps:
acquiring a furnace mouth image in real time;
preprocessing the furnace mouth image to obtain a furnace mouth area of the furnace mouth image;
acquiring the area and the number of the slag sheets in the furnace mouth area, and obtaining a pre-splashing identification result according to the area and the number of the slag sheets in a first set time period;
and translating the furnace mouth area along the height of the furnace mouth area up and down to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, acquiring corresponding areas, comparing the areas with corresponding set area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period.
2. The furnace mouth image recognition method according to claim 1, wherein the furnace mouth image is preprocessed to obtain a furnace mouth area of the furnace mouth image, and the method specifically comprises the following steps:
carrying out drying removal treatment on the furnace mouth image by using median filtering;
carrying out scale conversion on the furnace mouth image, and enhancing the brightness of the furnace mouth image through a scale conversion factor;
segmenting the furnace mouth image through an OTSU automatic threshold algorithm and acquiring a segmentation threshold;
and adjusting the segmentation threshold value and carrying out binarization on the furnace opening image according to the average value of the segmented furnace opening image to obtain the furnace opening area of the furnace opening image.
3. The furnace mouth image identification method according to claim 1, wherein the obtaining of the area and the number of the slag sheets in the furnace mouth region specifically comprises:
carrying out edge detection on the furnace mouth area through a Canny edge operator to obtain the area and the number of slag fragments of an edge detection result;
converting the furnace mouth image through a Gaussian derivative matrix to obtain a derivative diagram of the Hessian rule, extracting the characteristics of the derivative diagram and processing to obtain the area and the number of slag sheets in the derivative diagram;
and carrying out merging operation on the area and the number of the slag sheets of the obtained edge detection result and the area and the number of the slag sheets in the derivative diagram to obtain the area and the number of the slag sheets in the furnace mouth area.
4. The furnace mouth image identification method according to claim 3, wherein edge detection is performed on the furnace mouth region through a Canny edge operator to obtain the area and the number of slag fragments of an edge detection result, and the method specifically comprises the following steps:
extracting the contour line of the slag sheet in the area of the furnace mouth through a Canny edge operator;
carrying out roundness screening on the extracted contour line;
converting the screened contour lines into areas and filling;
and (4) carrying out area screening on the filled areas, selecting the areas with the areas in a set interval, identifying the areas into the furnace mouth image, obtaining the identified slag sheets, and obtaining the areas and the number of the slag sheets.
5. The furnace mouth image recognition method according to claim 4, wherein the roundness screening of the extracted contour line specifically comprises:
removing the non-arc-shaped edge in the extracted contour line;
and (4) carrying out closed contour screening on the rest contour lines to obtain the contour lines of which the distance between the starting point and the ending point is less than a set distance threshold.
6. The furnace mouth image identification method according to claim 3, wherein the extracting and processing of the characteristics of the derivative graph to obtain the area and number of the slag pieces in the derivative graph specifically comprises:
performing background removal processing on the derivative graph;
screening out the area with the pixel value larger than the set pixel threshold value;
and (4) carrying out furnace mouth frame removal and area screening on the screened area to obtain the identified slag pieces, and obtaining the area and the number of the slag pieces.
7. The furnace mouth image recognition method according to claim 1, wherein obtaining the spatter recognition result according to the comparison result in the second set time period specifically comprises:
when the area of the sputtering detection area obtained by downward shifting after threshold processing is larger than a first set area threshold, and the area of the sputtering detection area obtained by upward shifting after threshold processing is smaller than a second set area threshold, and the number of the furnace opening images meeting the condition in a second set time period is larger than a set number threshold, determining that the furnace opening images contain sputtering phenomena; or the like, or, alternatively,
and when the area of the sputtering detection area obtained by downward moving after threshold processing is larger than half of the total area of the furnace opening area, and the area of the sputtering detection area obtained by upward moving after threshold processing is smaller than the second set area threshold, determining that the furnace opening image contains sputtering.
8. A fire door image recognition apparatus, comprising:
the image acquisition module is used for acquiring furnace mouth images in real time;
the image processing module is used for preprocessing the furnace mouth image to obtain a furnace mouth area of the furnace mouth image;
the pre-sputtering identification module is used for acquiring the area and the number of the slag sheets in the furnace mouth area and obtaining a pre-sputtering identification result according to the area and the number of the slag sheets in a first set time period;
and the splash identification module is used for translating up and down along the height of the furnace mouth area to obtain two splash detection areas, performing threshold processing on the images of the two splash detection areas, acquiring corresponding areas, comparing the corresponding areas with corresponding area thresholds respectively, and obtaining a splash identification result according to a comparison result in a second set time period.
9. A fire door image recognition apparatus comprising a processor and a memory, wherein the processor implements the fire door image recognition method according to any one of claims 1 to 7 when executing a computer program stored in the memory.
10. A computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the furnace mouth image recognition method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110314254.0A CN113052816A (en) | 2021-03-24 | 2021-03-24 | Furnace mouth image identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110314254.0A CN113052816A (en) | 2021-03-24 | 2021-03-24 | Furnace mouth image identification method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113052816A true CN113052816A (en) | 2021-06-29 |
Family
ID=76514970
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110314254.0A Pending CN113052816A (en) | 2021-03-24 | 2021-03-24 | Furnace mouth image identification method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113052816A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115761604A (en) * | 2023-01-10 | 2023-03-07 | 矿冶科技集团有限公司 | Furnace mouth opening and closing state identification method and device |
CN116452595A (en) * | 2023-06-19 | 2023-07-18 | 烟台金丝猴食品科技有限公司 | Control method and device based on image processing |
-
2021
- 2021-03-24 CN CN202110314254.0A patent/CN113052816A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115761604A (en) * | 2023-01-10 | 2023-03-07 | 矿冶科技集团有限公司 | Furnace mouth opening and closing state identification method and device |
CN116452595A (en) * | 2023-06-19 | 2023-07-18 | 烟台金丝猴食品科技有限公司 | Control method and device based on image processing |
CN116452595B (en) * | 2023-06-19 | 2023-08-18 | 烟台金丝猴食品科技有限公司 | Control method and device based on image processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110163219B (en) | Target detection method based on image edge recognition | |
CN113592861B (en) | Bridge crack detection method based on dynamic threshold | |
US20070253040A1 (en) | Color scanning to enhance bitonal image | |
CN113052816A (en) | Furnace mouth image identification method, device, equipment and storage medium | |
CN110210440B (en) | Table image layout analysis method and system | |
CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
CN105427323B (en) | A kind of laser melting coating welding pool edge extraction method based on phase equalization | |
CN108323203A (en) | A kind of method, apparatus and intelligent terminal quantitatively detecting face skin quality parameter | |
CN113096083B (en) | Method, device and equipment for identifying steel slag at furnace mouth and storage medium | |
CN112529853A (en) | Method and device for detecting damage of netting of underwater aquaculture net cage | |
CN116524205A (en) | Sewage aeration automatic detection and identification method | |
CN113063474A (en) | Slag liquid level real-time detection method, device, equipment and storage medium | |
CN106530292B (en) | A kind of steel strip surface defect image Fast Identification Method based on line scan camera | |
CN115880289A (en) | Steel coil burr identification method, system and medium based on big data processing | |
CN109211919B (en) | Method and device for identifying magnetic tile defect area | |
CN114187368B (en) | Dark stripe detection method and device for building board, electronic equipment and storage medium | |
CN105389805A (en) | Optical detection method of component shortage, wrong component and reverse component in plug-in operation | |
CN108171235A (en) | Title area detection method and system | |
CN112634240B (en) | Thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation | |
CN114723728A (en) | Method and system for detecting CD line defects of silk screen of glass cover plate of mobile phone camera | |
CN114463283A (en) | Metal surface damage detection method and system, storage medium and electronic equipment | |
CN112541896B (en) | Furnace mouth slag stacking condition identification method and system | |
CN112801963A (en) | Video image occlusion detection method and system | |
CN112150433A (en) | Method for detecting whisker substance of circuit board, computer equipment and storage medium | |
CN111028258A (en) | Self-adaptive threshold value extraction method for large-scale gray level image |
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 |