CN116665136A - Chemical production safety risk real-time monitoring system - Google Patents
Chemical production safety risk real-time monitoring system Download PDFInfo
- Publication number
- CN116665136A CN116665136A CN202310942760.3A CN202310942760A CN116665136A CN 116665136 A CN116665136 A CN 116665136A CN 202310942760 A CN202310942760 A CN 202310942760A CN 116665136 A CN116665136 A CN 116665136A
- Authority
- CN
- China
- Prior art keywords
- brightness
- chemical
- image
- flame
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 238000012824 chemical production Methods 0.000 title claims abstract description 28
- 239000000126 substance Substances 0.000 claims abstract description 219
- 238000009826 distribution Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 38
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 7
- 230000000903 blocking effect Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 3
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 4
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 239000004973 liquid crystal related substance Substances 0.000 description 14
- 238000010586 diagram Methods 0.000 description 8
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000002360 explosive Substances 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007665 sagging Methods 0.000 description 1
- HOWHQWFXSLOJEF-MGZLOUMQSA-N systemin Chemical compound NCCCC[C@H](N)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CC(O)=O)C(=O)OC(=O)[C@@H]1CCCN1C(=O)[C@H]1N(C(=O)[C@H](CC(O)=O)NC(=O)[C@H](CCCN=C(N)N)NC(=O)[C@H](CCCCN)NC(=O)[C@H](CO)NC(=O)[C@H]2N(CCC2)C(=O)[C@H]2N(CCC2)C(=O)[C@H](CCCCN)NC(=O)[C@H](CO)NC(=O)[C@H](CCC(N)=O)NC(=O)[C@@H](NC(=O)[C@H](C)N)C(C)C)CCC1 HOWHQWFXSLOJEF-MGZLOUMQSA-N 0.000 description 1
- 108010050014 systemin Proteins 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of image processing, in particular to a chemical production safety risk real-time monitoring system. The system firstly acquires a gray level image of the internal environment of a chemical plant, detects the edge straight line of a chemical pipeline in the gray level image, acquires an interruption line segment on the edge straight line, acquires interruption line segment shielding coefficients according to the brightness distribution condition of pixel points on the interruption line segment and the length difference between the interruption line segments, divides an ROI image only comprising the chemical pipeline into a plurality of local areas, acquires a fire surrounding coefficient of the local areas according to the brightness characteristics and the brightness change direction of the chemical pipeline in the local areas, acquires a flame characteristic image according to the interruption line segment shielding coefficients and the fire surrounding coefficient, further acquires a flame salient image, and monitors the risk condition in the chemical plant according to the flame salient image. And monitoring the risk condition in the chemical plant according to the flame obvious image, and enhancing the monitoring effect of the safety risk of the chemical production.
Description
Technical Field
The invention relates to the field of image processing, in particular to a chemical production safety risk real-time monitoring system.
Background
The chemical plant usually stores a large amount of inflammable and explosive articles, and fire accidents frequently occur in the chemical plant due to internal factors and external factors, and fires generated in the chemical production process mainly cause artificial misoperations to cause fires and fire caused by natural factors such as lightning, earthquakes and the like, and also cause fires caused by excessive temperature to ignite inflammables, so that a large amount of toxic and harmful gases can be generated when the fires occur, and a large amount of casualties and property losses are caused, so that the method is particularly important for monitoring the fire risks in the chemical plant.
In the process of monitoring fire risks, the prior art often judges whether the surrounding environment is in fire according to the change of the surrounding environment temperature and the growing trend of the pyrotechnic region range in the multi-frame image, but because a large number of inflammable and explosive objects exist in a chemical plant, the generated flames need to be treated in time, the flames are smaller in the initial stage of fire, the change of the flames to the surrounding environment temperature is not obvious, and the growing trend of the pyrotechnic region range in the image is not obvious in a short time, so that the existence of the flames cannot be accurately detected, the flames are not found timely, and further the flames cannot be effectively controlled in time to form the fire.
Disclosure of Invention
In order to solve the technical problems that the flame is not found timely and the flame cannot be effectively controlled timely to form a fire disaster due to smaller flame in the initial stage of the fire, the invention aims to provide a chemical production safety risk real-time monitoring system, which adopts the following technical scheme:
the invention provides a real-time monitoring system for safety risk of chemical production, which comprises:
the image acquisition module is used for acquiring a gray image of the internal environment of the chemical plant;
the broken line analysis module is used for acquiring broken line segments on the chemical pipeline edge line according to the gray level image; obtaining brightness characteristic parameters of the interrupt line segments according to the overall brightness values and the overall brightness change rates of all pixel points on each interrupt line segment; obtaining interrupt segment shielding coefficients according to the length difference between each interrupt segment and the reference interrupt segment and the brightness characteristic parameters;
the fire-light surrounding coefficient analysis module is used for acquiring an ROI image only comprising a chemical pipeline and dividing the ROI image into a preset number of local areas; obtaining the brightness direction confusion of the local areas according to the difference of the brightness change directions among the chemical pipelines in each local area; obtaining the brightness parameter of the local area according to the maximum brightness and the brightness range of each chemical pipeline; obtaining the fire surrounding coefficient of each local area according to the brightness direction confusion degree and the brightness parameter;
The flame significant image acquisition module is used for acquiring a flame characteristic image according to the interrupt segment shielding coefficient and the flare surrounding coefficient and acquiring a flame significant image according to the flame characteristic image and the gray level image;
and the risk monitoring module is used for monitoring the risk condition in the chemical plant according to the flame significant image.
Further, the method for acquiring the broken line segment on the chemical pipeline edge line comprises the following steps:
carrying out Hough straight line detection on the gray level image to obtain a straight line region in the gray level image, and taking a straight line with the length larger than a preset length threshold value in the straight line region as an edge straight line, wherein the edge straight line is a horizontal straight line or a vertical straight line;
calculating an included angle between each edge straight line and the horizontal direction while moving along the edge straight line from any point of each edge straight line by using a single-pixel point sliding window, taking the position where the included angle changes as a break point on the edge straight line, and taking a connecting line between the break points as a break line segment.
Further, the method for acquiring the brightness characteristic parameter of the interrupt line comprises the following steps:
taking the average brightness value of all pixel points on each interrupt line segment as the integral brightness value; taking the square of the brightness difference between adjacent pixel points on each interrupt line segment as the brightness difference of the adjacent pixel points, and taking the average value of all the brightness differences on each interrupt line segment as the integral brightness change rate;
And taking the ratio of the overall brightness value to the overall brightness change rate as the brightness characteristic parameter of each interrupt line segment.
Further, the method for obtaining the interrupt segment shielding coefficient comprises the following steps:
taking other interrupt line segments which are parallel to the interrupt line segment and are closest to the interrupt line segment as reference interrupt line segments of the interrupt line segment;
taking the absolute value of the length difference value of the interrupt line segment and the reference interrupt line segment as a length difference;
and obtaining the interrupt segment shielding coefficient of each interrupt segment according to the product of the length difference and the brightness characteristic parameter.
Further, the method for obtaining the brightness direction confusion of the local area comprises the following steps:
in each local area, a label value corresponding to each chemical pipeline is given according to the brightness change direction on each chemical pipeline, wherein the label value is 1 and-1, if the brightness change direction on the chemical pipeline is upward or leftward, the label value is 1, and if the brightness change direction on the chemical pipeline is downward or rightward, the label value is-1;
in each local area, a horizontal chemical pipeline and a vertical chemical pipeline are selected at will, the accumulated value of the square difference of the tag values between the horizontal chemical pipeline and all other horizontal chemical pipelines is used as the horizontal mess, and the accumulated value of the square difference of the tag values between the vertical chemical pipeline and all other vertical chemical pipelines is used as the vertical mess;
And taking the sum value of the horizontal confusion and the vertical confusion as a numerator, and taking the sum value of the number of the horizontal chemical pipelines and the number of the vertical chemical pipelines as a denominator to obtain the brightness direction confusion of each local area.
Further, the method for acquiring the luminance parameter of the local area includes:
taking the difference value between the maximum brightness value and the minimum brightness value on each chemical pipeline as the brightness range, and obtaining the brightness distribution parameter of each chemical pipeline according to the product of the maximum brightness value and the brightness range on each chemical pipeline;
and taking the accumulated value of the brightness distribution parameters of all chemical pipelines in the local area as the brightness parameter of the local area.
Further, the method for acquiring the fire surrounding coefficient of each local area comprises the following steps:
and obtaining the fire surrounding coefficient of each local area according to the product of the brightness direction confusion degree and the brightness parameter.
Further, the method for acquiring the flame characteristic image comprises the following steps:
taking the average value of the blocking coefficients of all the broken line segments on each chemical pipeline as the integral blocking coefficient of the chemical pipeline; obtaining a flame shielding coefficient of each chemical pipeline in each local area according to the product of the integral shielding coefficient and the fire surrounding coefficient;
And taking the flame shielding coefficient as a flame characteristic value of the shielded pixel point on each corresponding chemical pipeline, taking the flame surrounding coefficient as a flame characteristic value of the non-shielded pixel point on the chemical pipeline, and mapping the flame characteristic value of each pixel point into a gray value to obtain a flame characteristic image.
Further, the method for acquiring the flame saliency image comprises the following steps:
acquiring an LBP image and a gradient image of the gray image;
based on the quaternion matrix, performing quaternion Fourier transform on the flame characteristic image, the gray level image, the LBP image and the gradient image, performing inverse transform, and obtaining a flame salient image through Gaussian filtering on the inverse transform result.
Further, the monitoring the risk condition in the chemical plant according to the flame saliency image comprises:
detecting whether the significance value of each pixel point in the flame significance image exceeds a preset significance threshold, if so, considering that the risk of fire occurs, otherwise, considering that the risk of fire does not occur.
The invention has the following beneficial effects:
according to the invention, the gray level image of the internal environment of the chemical plant is firstly obtained, and the characteristics that the chemical pipeline edge line in the gray level image is discontinuous due to the fact that a large number of chemical pipelines exist in the chemical plant and flame is specific and physical in vision and can shade the rear chemical pipeline are considered, so that the interrupt line segment on the chemical pipeline edge line can be obtained according to the gray level image, and the subsequent analysis of the interrupt line segment is facilitated; considering that the existence of flame can increase the brightness of the pixel points on the interrupt line segment and the brightness change trend of the pixel points on the interrupt line segment is stable, the brightness characteristic parameters of the interrupt line segment can be obtained according to the integral brightness values and the integral brightness change rates of all the pixel points on each interrupt line segment, and the interrupt line segment shielding coefficient can be conveniently obtained according to the brightness characteristic parameters; considering the initial stage of flame generation, the flame presents an irregular shape with narrow upper part and wide lower part, and the lengths of the interrupt line segments generated by shielding the chemical pipeline by the flame are different, so that the interrupt line segment shielding coefficient can be obtained according to the length difference between each interrupt line segment and the reference interrupt line segment and the brightness characteristic parameter, and the possibility of the interrupt line segment formed by shielding the flame can be reflected by the interrupt line segment shielding coefficient; considering that the influence of flame at different positions on the pipeline in the local area is different, dividing the ROI image into a preset number of local areas, and analyzing each local area independently; when flames exist in the local area, the inconsistency of the overall directions of brightness changes of all chemical pipelines in the local area can be caused, the flames in the local area are closer to the chemical pipelines in the local area, the maximum brightness of the chemical pipelines closer to the flames is larger, and the brightness is extremely poor, so that the fire surrounding coefficients of each local area can be obtained by combining brightness direction confusion and brightness difference parameters, the fire surrounding coefficients can reflect the possibility of the existence of fire points in the local area, the follow-up combination of the fire surrounding coefficients and interruption line segment shielding coefficients is convenient to obtain flame characteristic images, and further flame salient images are obtained, the salient values of the pixel points in the flame salient images can reflect whether flames exist in a chemical plant or not, and the accuracy of detecting the existence of the flames can be improved according to the risk conditions in the flame salient images monitoring chemical plant. According to the invention, the interruption line segment generated when the chemical pipeline is shielded by flame is analyzed to obtain interruption line segment shielding coefficients, each local area is analyzed to obtain a fire surrounding coefficient of each local area, the interruption line segment shielding coefficients and the fire surrounding coefficients are combined to obtain a flame characteristic image, a flame obvious image is further obtained, the risk condition in a chemical plant is monitored according to the flame obvious image, and the monitoring effect of the safety risk of chemical production is enhanced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a real-time monitoring system for safety risk of chemical production according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an interrupt segment according to an embodiment of the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a specific implementation, structure, characteristics and effects of the real-time monitoring system for safety risk of chemical production according to the invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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 invention belongs.
An embodiment of a real-time monitoring system for safety risk of chemical production:
the invention provides a specific scheme of a chemical production safety risk real-time monitoring system, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a block diagram of a real-time monitoring system for safety risk of chemical production according to an embodiment of the present invention is shown, where the system includes: the system comprises an image acquisition module 101, an interruption line segment analysis module 102, a fire surrounding coefficient analysis module 103, a flame saliency map acquisition module 104 and a risk monitoring module 105.
The image acquisition module 101 is used for acquiring a gray scale image of the internal environment of the chemical plant.
In the embodiment of the invention, the original image of the internal environment of the chemical plant workshop is acquired through the CCD camera, when the internal of the chemical plant fires, a great amount of smoke is often accompanied, the existence of the smoke can reduce the definition of flame in the original image, and can shield chemical pipelines in the original image, so that the subsequent analysis on the chemical pipelines is influenced. It should be noted that the dark channel defogging algorithm is a technical means well known to those skilled in the art, and will not be described herein.
It should be noted that, in order to reduce the calculation amount in the subsequent image processing process, in one embodiment of the present invention, the acquired original image is subjected to a graying process to obtain a single-channel gray image, and the specific graying process operation is a technical means well known to those skilled in the art, which is not described herein and is not limited thereto.
The broken line analysis module 102 is used for acquiring broken line segments on the chemical pipeline edge line according to the gray level image; obtaining brightness characteristic parameters of the interrupt line segments according to the overall brightness values and the overall brightness change rates of all pixel points on each interrupt line segment; and obtaining the interrupt segment shielding coefficient according to the length difference between each interrupt segment and the reference interrupt segment and the brightness characteristic parameter.
In the embodiment of the invention, a large number of chemical pipelines exist in a chemical plant, flames are physically seen, the rear chemical pipelines can be shielded, the flames are small in the initial stage of firing, only partial areas of the chemical pipelines can be shielded, and the edge lines of the chemical pipelines in gray images are discontinuous.
Preferably, in one embodiment of the present invention, the method for acquiring the break line segment on the chemical pipeline edge line specifically includes:
carrying out Hough straight line detection on the gray level image to obtain a straight line region in the gray level image, taking a straight line with the length of the straight line being greater than a preset length threshold value in the straight line region as an edge straight line, wherein the edge straight line is a horizontal straight line or a vertical straight line; calculating the included angle between the edge straight line and the horizontal direction while moving along the edge straight line from any point of each edge straight line by utilizing the single-pixel point sliding window, taking the position where the included angle changes as a break point on the edge straight line, and taking a connecting line between the break points as a break line segment. The preset length threshold is set to 20 in one embodiment of the invention.
Referring to fig. 2, fig. 2 is a schematic diagram of an interruption line provided by an embodiment of the present invention, where an interruption line L1 and an interruption line L2 are interruption lines formed by shielding chemical pipelines by flame, and an interruption line L3 is an interruption line formed by shielding between chemical pipelines.
As the flame is used as a light source, the brightness of the flame in the image is larger, the trend of brightness change is stable, compared with the broken line segment formed by shielding among chemical pipelines, the brightness of the pixel points on the broken line segment formed by shielding of the flame is larger, and the trend of brightness change of the pixel points is stable, so that the brightness characteristic parameters of the broken line segments can be obtained according to the integral brightness values and the integral brightness change rates of all the pixel points on each broken line segment, and the larger the brightness characteristic parameters of the broken line segments are, the greater the possibility that the broken line segments are shielded by the flame is indicated. In one embodiment of the present invention, the collected original image may be converted into a Lab image, where the L component of the pixel point in the Lab image represents the brightness of the pixel point, so the value of the L component of the pixel point on the interrupt line segment in the Lab image may be used as the brightness value of the pixel point.
Preferably, in one embodiment of the present invention, the method for acquiring the luminance characteristic parameter of the interrupt line segment specifically includes:
taking the average brightness value of all pixel points on each interrupt line segment as an overall brightness value; taking the square of the brightness difference value between adjacent pixel points on each interrupt line segment as the brightness difference of the adjacent pixel points, and taking the average value of all the brightness differences on each interrupt line segment as the overall brightness change rate; and taking the ratio of the overall brightness value to the overall brightness change rate as the brightness characteristic parameter of each interrupt line segment. The specific expression is:
wherein, the liquid crystal display device comprises a liquid crystal display device,a brightness characteristic parameter representing each interrupt segment; />Representing the overall brightness value of the pixel points on each interrupt line segment; />Representing the overall brightness change rate of the pixel points on each interrupt line segment; />Representing the%>Brightness values of the individual pixel points; />Representing the%>Brightness values of the individual pixel points; />Representing the number of pixel points on the interrupt line segment; />Representing the summation symbol.
In the process of acquiring the brightness characteristic parameters of the interrupt line segments, the brightness characteristic parametersThe possibility of being blocked by flame can be reflected, and the larger the brightness characteristic parameter is, the larger the possibility of being blocked by flame is; overall brightness value- >The overall brightness of the pixel points on the interrupt line can be reflected, and if the interrupt line is formed by flame shielding, the brightness of the pixel points on the interrupt line is large, so the overall brightness value +.>The larger the interrupt is, the brightness characteristic parameter of the interrupt is +.>The larger; />Representing the brightness difference of adjacent pixels on the interrupt line segment, if the interrupt line segment is formed due to flame shielding, the brightness change trend of the pixels on the interrupt line segment is stable, the brightness difference is small, and the average value of the brightness differences of all the adjacent pixels on the interrupt line segment is taken as the overall brightness change rate +.>So the overall brightness change rate +.>The smaller, the interruption is due to flame shielding, the brightness characteristic parameter +.>The larger the overall brightness value is, the more is the overall brightness value in the embodiment of the invention>And the overall brightness change rate +.>As luminance characteristic parameter +.>。
In the embodiment of the invention, the chemical pipelines are regular cylinders, and the lengths of a plurality of interrupt line segments formed by shielding among the chemical pipelines are the same; in the initial stage of flame formation, the flame presents an irregular shape with a narrow upper part and a wide lower part, the lengths of a plurality of interrupt line segments formed by flame shielding are different, in order to further highlight the difference of the two shielding conditions and reduce the possibility of misjudgment, a reference interrupt line segment is selected, an interrupt line segment shielding coefficient is obtained according to the length difference between each interrupt line segment and the reference interrupt line segment and by combining brightness characteristic parameters, the interrupt line segment shielding coefficient can reflect the possibility that the interrupt line segment is shielded by the flame, and the larger the interrupt line segment shielding coefficient is, the more likely the interrupt line segment is shielded by the flame is, and the greater the possibility that the flame exists in an image is further explained.
Preferably, in one embodiment of the present invention, the method for acquiring the interrupt segment occlusion coefficient specifically includes:
taking other interrupt line segments which are parallel to the interrupt line segment and are closest to the interrupt line segment as reference interrupt line segments of the interrupt line segment; taking the absolute value of the length difference value of the interrupt line segment and the reference interrupt line segment as the length difference; and obtaining the interrupt segment shielding coefficient of each interrupt segment according to the product of the length difference and the brightness characteristic parameter. The specific expression is:
wherein, the liquid crystal display device comprises a liquid crystal display device,interrupt segment shading coefficients representing interrupt segments; />Representing the length of the interrupt line segment; />Representing the length of the reference interrupt line segment; />Representing a luminance characteristic parameter representing each interrupt segment.
In the acquisition process of the interrupt segment occlusion coefficients,representing the difference in length between the interruption line and the reference interruption line, the difference in length between the interruption line due to the shielding between chemical pipelines is almost 0, and the difference in length between the interruption line due to the shielding of flame is large, so the difference in length ∈ ->The larger the interrupt line segment is, the more inconsistent the length of the interrupt line segment is, and the more likely the interrupt line segment is formed by flame shielding is, the interrupt line segment shielding coefficient is + >The larger; />Representing the brightness characteristic parameter of each interrupt line segment by the above-mentioned pair brightness characteristic parameter +.>Analysis of the acquisition procedure shows that the luminance characteristic parameter +.>The larger the brightness of the pixel point on the interrupt line segment is, the more the brightness accords with the characteristics of flame, the interrupt line segment shielding coefficient +.>The larger.
The reasons for the formation of the broken line segments can be effectively distinguished through the length difference between the broken line segments and the broken line segment shielding coefficient obtained by the brightness characteristic parameters of the pixel points, whether the chemical pipeline is shielded by flame can be judged according to the broken line segment shielding coefficient, and the accuracy of subsequently obtaining the flame characteristic images is improved.
The fire surrounding coefficient analysis module 103 is used for acquiring an ROI image only comprising the chemical pipeline and dividing the ROI image into a preset number of local areas; obtaining the brightness direction confusion of the local areas according to the difference of the brightness change directions among the chemical pipelines in each local area; obtaining brightness variation parameters of the local area according to the maximum brightness and the brightness range of each chemical pipeline; and obtaining the fire surrounding coefficient of each local area according to the brightness direction confusion degree and the brightness difference parameter.
When a fire is generated in a chemical plant, the chemical pipeline has a strong light reflection effect, so that the flame has a large influence on the brightness of the chemical pipeline, and And in the initial period of flame formation, the range that can influence of flame is less, so can divide into the ROI image that only contains chemical pipeline into and predetermine a plurality of local areas, for each local area analysis, because chemical pipeline is cylindric, so the luminance on the whole of chemical pipeline appears as one side luminance higher, and the opposite side luminance is lower, for example when chemical pipeline is the perpendicular luminance of arranging, probably is the luminance of chemical pipeline left side part low and the luminance of right side part high, and the luminance change direction on the chemical pipeline can appear to be from the left side that the luminance is low to the right side that the luminance is high this moment. When no ignition point exists in the local area, the brightness change directions of all chemical pipelines in the local area point to the same direction, when an ignition point exists in the local area, the brightness change directions of one part of chemical pipelines in the local area point to the same direction, and the brightness change directions of the other part of chemical pipelines point to opposite directions, namely, when the ignition point exists, the brightness change directions of the chemical pipelines in the local area have differences, so that the brightness direction confusion degree of the local area can be obtained according to the differences of the brightness change directions among the chemical pipelines in each local area, the brightness direction confusion degree reflects the possibility that the ignition point exists in the local area, and the greater the brightness direction confusion degree, the more likely the ignition point exists in the local area. It should be noted that, in one embodiment of the present invention, the preset number of local areas is set as 。
Preferably, in one embodiment of the present invention, the method for obtaining the brightness direction confusion of the local area specifically includes:
in each local area, a label value corresponding to each chemical pipeline is given according to the brightness change direction on each chemical pipeline, wherein the label value is 1 and-1, if the brightness change direction on the chemical pipeline is upward or leftward, the label value is 1, if the brightness change direction on the chemical pipeline is downward or rightward, the label value is-1, the fact that the chemical pipelines in the local area are horizontally distributed and vertically distributed at the same time is considered, in each local area, one horizontal chemical pipeline and one vertical chemical pipeline are arbitrarily selected, the accumulated value of the square difference value of the label values between the horizontal chemical pipeline and all other horizontal chemical pipelines is used as horizontal confusion, and the accumulated value of the square difference value of the label values between the vertical chemical pipeline and all other vertical chemical pipelines is used as vertical confusion; and taking the sum of the horizontal mess and the vertical mess as a numerator, and taking the sum of the number of the horizontal chemical pipelines and the number of the vertical chemical pipelines as a denominator to obtain the brightness direction mess of each local area. The specific expression is:
Wherein, the liquid crystal display device comprises a liquid crystal display device,a luminance direction confusion representing each local area; />A label value representing a horizontal chemical pipeline arbitrarily selected in each local area; />Representing the +.>Tag values of the individual horizontal chemical pipelines; />A label value representing a vertical chemical pipeline arbitrarily selected in each local area; />Representing the +.>The label value of each vertical chemical pipeline; />Representing horizontal chemical pipelines in each local areaIs the number of (3); />Indicating the number of vertical chemical pipelines in each local area, < > or->Representing the summation symbol.
It should be noted that, the tag value is only for illustrating the difference of the brightness change direction on the chemical pipeline, in one embodiment of the present invention, the brightness change direction is expressed as a direction from brightness low to brightness high, for a certain horizontal chemical pipeline, if the chemical pipeline brightness change direction is upward, the tag value of the chemical pipeline is 1, and if the chemical pipeline brightness change direction is downward, the tag value of the chemical pipeline is-1; for a certain vertical chemical pipeline, if the brightness change direction of the chemical pipeline is leftward, the label value of the chemical pipeline is 1, and if the brightness change direction of the chemical pipeline is rightward, the label value of the chemical pipeline is-1.
During the acquisition of the luminance direction confusion of each partial area,the level confusion degree is represented, the difference degree of the level chemical pipelines in the brightness change direction in each local area is reflected, if no ignition point exists in the local area, the tag values of all the level chemical pipelines are the same, the level confusion degree is equal to 0, if an ignition point exists in the local area, the tag values of one part of the level chemical pipelines are different from the tag values of the other part of the level chemical pipelines, and the level confusion degree is not equal to 0, so that the greater the level confusion degree is, the greater the difference degree of the brightness change direction of the level chemical pipelines in the local area is, the greater the brightness direction confusion degree of the local area is>The larger the same vertical confusion +.>The larger the indication of sagging in the local areaThe greater the degree of difference in the brightness variation direction of the straight chemical pipeline, the greater the degree of confusion of the brightness direction of the local area +>The larger; />The method is used for averaging the sum value of the horizontal disorder degree and the vertical disorder degree, and because the chemical pipelines in the local area are denser and more in number, the method is suitable for the use of the horizontal disorder degree and the vertical disorder degree>It is not possible to be 0.
The brightness change of each chemical pipeline in the direction perpendicular to the edge line shows parabolic change, the maximum brightness exists in the direction perpendicular to the edge line of the chemical pipeline, the minimum brightness exists at the edge line of the chemical pipeline, and when a fire point exists in a local area, the maximum brightness and the brightness range on the chemical pipeline can be increased, so that the brightness change parameters of the local area can be obtained according to the maximum brightness and the brightness range of each chemical pipeline, and the accuracy of the acquired fire surrounding coefficient can be improved by combining the brightness change parameters and the brightness direction confusion.
Preferably, in one embodiment of the present invention, the method for acquiring the luminance parameter of the local area specifically includes:
taking the difference value of the maximum brightness value and the minimum brightness value on each chemical pipeline as the brightness range, and obtaining the brightness distribution parameter of each chemical pipeline according to the product of the maximum brightness value and the minimum brightness value on each chemical pipeline; and taking the accumulated value of the brightness distribution parameters of all chemical pipelines in the local area as the brightness parameter of the local area. The specific expression is:
wherein, the liquid crystal display device comprises a liquid crystal display device,a luminance parameter representing each local region; />Indicating the% >Maximum brightness value on individual chemical pipelines; />Indicate the%>Minimum brightness value on individual chemical pipelines; />Indicating the number of chemical pipelines in each local area, < >>Representing the summation symbol.
In the process of acquiring the brightness change parameters of each local area, when a fire point exists in the local area, the brightness on the chemical pipeline is influenced by flame, and the maximum value of the brightness on the chemical pipelineWill increase and the brightness is extremely poorAlso increases; />Representing the brightness distribution parameter of each chemical pipeline, wherein the larger the brightness distribution parameter is, the larger the brightness on the chemical pipeline is influenced by flame, so the accumulated value of the brightness distribution parameters of all chemical pipelines in the local area is +.>As luminance parameter +.>Luminance parameter->The larger indicates a greater number of chemical conduits in the localized area that are affected by the flame, and thus indicates a greater likelihood of fire in the localized area.
After the brightness direction confusion and the brightness parameters are obtained, the fire surrounding coefficient of each local area can be obtained according to the brightness direction confusion and the brightness parameters, the fire surrounding coefficient can reflect the possibility of fire points in the local area, and the corresponding flame characteristic diagram can be conveniently obtained according to the fire surrounding coefficient.
Preferably, in one embodiment of the present invention, the method for acquiring the fire surrounding coefficient of each local area specifically includes:
and obtaining the fire surrounding coefficient of each local area according to the product of the brightness direction confusion and the brightness parameter. The specific expression is:
wherein, the liquid crystal display device comprises a liquid crystal display device,a flare wrapping coefficient representing each partial region; />A luminance direction confusion representing each local area; />Representing the luminance parameter of each local area.
The fire surrounding coefficients of the local areas can reflect the possibility of fire points in each local area, and the larger the fire surrounding coefficients are, the more possible flames exist in the local areas, and an accurate flame characteristic diagram can be obtained by combining the fire surrounding coefficients and the interruption line segment shielding coefficients.
The flame saliency map obtaining module 104 is configured to obtain a flame characteristic image according to the interruption line segment shielding coefficient and the flare surrounding coefficient, and obtain a flame saliency image according to the flame characteristic image and the gray level image.
After the interruption line segment shielding coefficient and the fire surrounding coefficient are obtained according to the analysis, the flame characteristic image can be obtained according to the interruption line segment shielding coefficient and the fire surrounding coefficient.
Preferably, in one embodiment of the present invention, the method for acquiring a flame characteristic image specifically includes:
Taking the average value of the interruption line segment shielding coefficients of all the interruption line segments on each chemical pipeline as the integral shielding coefficient of the chemical pipeline; obtaining the flame shielding coefficient of each chemical pipeline in each local area according to the product of the integral shielding coefficient and the fire surrounding coefficient; and taking the flame shielding coefficient as a flame characteristic value of the shielded pixel point on each corresponding chemical pipeline, taking the flame surrounding coefficient as a flame characteristic value of the non-shielded pixel point on the chemical pipeline, and mapping the flame characteristic value of each pixel point into a gray value to obtain a flame characteristic image. The expression of the flame shielding coefficient of each chemical pipeline is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing the flame shielding coefficient of each chemical pipeline; />A flare wrapping coefficient representing a local area; />Interrupt segment shielding coefficients representing interrupt segments on one edge line of the chemical pipeline; />And the interruption line segment shielding coefficient of the interruption line segment on the other edge line of the chemical pipeline is represented.
In each chemical pipeline flame shielding systemIn the acquisition process of the number, in the ROI image, if two edge lines exist in one chemical pipeline, one chemical pipeline comprises two interrupt line segments, so that the interrupt line segment shielding coefficients of the two interrupt line segments are averaged As the integral shielding coefficient of the chemical pipeline, and taking the product of the integral shielding coefficient and the fire surrounding coefficient as the flame shielding coefficient of the chemical pipeline.
Because the obtained flame characteristic diagram has low significance, the risk condition in the chemical plant can not be judged directly according to the flame characteristic diagram, so that the flame significant image can be obtained according to the flame characteristic image and the gray level image, and the accuracy of fire prediction is improved.
Preferably, in one embodiment of the present invention, the method for acquiring the flame saliency image specifically includes:
obtaining an LBP image and a gradient image of the gray image; based on the quaternion matrix, performing quaternion Fourier transform on the flame characteristic image, the gray level image, the LBP image and the gradient image, performing inverse transform, and performing Gaussian filtering on the inverse transform result to obtain a flame salient image.
The expression of the quaternion matrix used for the quaternion Fourier transform in the embodiment of the invention is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing a flame signature image; />Representing an LBP image; />Representing a gray scale image; />Representing a gradient image; />、/>、/>Are respectively imaginary units ++>、/>、/>The size of (2) satisfies->And (2) and，/>，/>。
it should be noted that, the quaternion fourier transform and the inverse transform are technical means well known to those skilled in the art, and are not described herein.
After the flame significant image is obtained, the fire risk of the internal environment of the chemical plant can be analyzed according to the flame significant image.
The risk monitoring module 105 is used to monitor risk situations within the chemical plant based on the flame signature.
The significance of each pixel point in the flame significant image is improved, the quality of the image is obviously improved, and the significance value of each pixel point in the flame significant image can accurately reflect the existence condition of flame in the image, so that the risk condition in a chemical plant can be directly monitored according to the flame significant image.
Preferably, in one embodiment of the present invention, the method for monitoring the risk condition in the chemical plant according to the flame saliency image specifically includes:
detecting whether the significance value of each pixel point in the flame significance image exceeds a preset significance threshold value, if any pixel point exceeds the preset significance threshold value, considering that the risk of fire occurs, otherwise, considering that the risk of fire does not occur. The preset significance threshold is set to 10 in one embodiment of the present invention.
After the fire risk in the chemical plant is detected through the flame obvious image, an alarm can be sent out to remind workers of timely treating the fire, and casualties and property loss are avoided.
In summary, the embodiment of the invention firstly obtains the gray level image of the internal environment of the chemical plant, carries out hough line detection on the gray level image to obtain the broken line segments, and obtains the brightness characteristic parameters of the broken line segments according to the overall brightness values and the overall brightness change rates of all the pixel points on each broken line segment; obtaining a blocking coefficient of each interrupt line segment according to the length difference between the interrupt line segment and the reference interrupt line segment and the brightness characteristic parameter; then dividing a preset number of local areas for the ROI image only containing the chemical pipelines, and obtaining the brightness direction confusion of the local areas according to the brightness change direction difference between the chemical pipelines in each local area; obtaining the brightness parameter of the local area according to the maximum brightness and the brightness range of each chemical pipeline; obtaining the fire surrounding coefficient of each local area according to the brightness direction confusion degree and the brightness parameter; and obtaining a flame characteristic image according to the interruption line segment shielding coefficient and the fire surrounding coefficient, obtaining a flame significant image according to the flame characteristic image and the gray level image based on quaternion Fourier transform and inverse transform, and monitoring the risk condition in the chemical plant according to the flame significant image. According to the embodiment of the invention, the interruption line segment generated when the chemical pipeline is shielded by flame is analyzed to obtain interruption line segment shielding coefficients, each local area is analyzed to obtain a fire surrounding coefficient of each local area, the interruption line segment shielding coefficients and the fire surrounding coefficients are combined to obtain a flame characteristic image, a flame obvious image is further obtained, and the risk condition in a chemical plant is monitored according to the flame obvious image.
An embodiment of a chemical production safety flame detection system:
the existing chemical production safety flame detection method comprises the following steps: the gray value range of the flame pixel points is determined in advance, the pixel points with gray values within the preset flame gray value range in the image are taken as the suspected flame pixel points, and all the suspected flame pixel points are detected to be taken as flame areas. However, as a large number of chemical pipelines exist in the chemical plant, the surfaces of the chemical pipelines are smooth, when flames exist, the surfaces of the chemical pipelines can generate a light reflection phenomenon, the brightness is improved, the gray values between the chemical pipelines and the flame pixel points are close, the existence of the flames cannot be accurately detected, and the accuracy of the detected flame areas is reduced.
To solve this problem, the present embodiment provides a chemical production safety flame detection system, including:
the image acquisition module is used for acquiring a gray image of the internal environment of the chemical plant;
the broken line analysis module is used for acquiring broken line segments on the chemical pipeline edge line according to the gray level image; obtaining brightness characteristic parameters of the interrupt line segments according to the overall brightness values and the overall brightness change rates of all pixel points on each interrupt line segment; obtaining interrupt segment shielding coefficients according to the length difference between each interrupt segment and the reference interrupt segment and the brightness characteristic parameters;
The fire-light surrounding coefficient analysis module is used for acquiring an ROI image only comprising a chemical pipeline and dividing the ROI image into a preset number of local areas; obtaining the brightness direction confusion of the local areas according to the difference of the brightness change directions among the chemical pipelines in each local area; obtaining the brightness parameter of the local area according to the maximum brightness and the brightness range of each chemical pipeline; obtaining the fire surrounding coefficient of each local area according to the brightness direction confusion degree and the brightness parameter;
the flame significant image acquisition module is used for acquiring a flame characteristic image according to the interrupt segment shielding coefficient and the flare surrounding coefficient and acquiring a flame significant image according to the flame characteristic image and the gray level image;
the image acquisition module, the interrupt segment analysis module, the fire surrounding coefficient analysis module, and the flame significant image acquisition module are described in detail in the embodiment of the chemical production safety risk real-time monitoring system, and are not described in detail herein.
The beneficial effects brought by the embodiment are as follows: considering the fact that a large number of chemical pipelines exist in a chemical plant, flames are specific and physical in vision and can shade the chemical pipelines at the rear, and the edge lines of the chemical pipelines in the gray level images are discontinuous, the broken line segments on the edge lines of the chemical pipelines can be obtained according to the gray level images, and the subsequent analysis of the broken line segments is facilitated; considering that the existence of flame can increase the brightness of the pixel points on the interrupt line segment and the brightness change trend of the pixel points on the interrupt line segment is stable, the brightness characteristic parameters of the interrupt line segment can be obtained according to the integral brightness values and the integral brightness change rates of all the pixel points on each interrupt line segment, and the interrupt line segment shielding coefficient can be conveniently obtained according to the brightness characteristic parameters; considering the initial stage of flame generation, the flame presents an irregular shape with narrow upper part and wide lower part, and the lengths of the interrupt line segments generated by shielding the chemical pipeline by the flame are different, so that the interrupt line segment shielding coefficient can be obtained according to the length difference between each interrupt line segment and the reference interrupt line segment and the brightness characteristic parameter, and the possibility of the interrupt line segment formed by shielding the flame can be reflected by the interrupt line segment shielding coefficient; considering that the influence of flame at different positions on the pipeline in the local area is different, dividing the ROI image into a preset number of local areas, and analyzing each local area independently; when flames exist in the local area, the inconsistency of the overall directions of brightness changes of all chemical pipelines in the local area can be caused, the flames in the local area are closer to the chemical pipelines in the local area, the maximum brightness of the chemical pipelines closer to the flames is larger, and the brightness is extremely poor, so that the fire surrounding coefficient of each local area can be obtained by combining brightness direction confusion and brightness difference parameters, the fire surrounding coefficient can reflect the possibility that a fire point exists in the local area, the fire surrounding coefficient and the interruption line segment shielding coefficient are combined later to obtain a flame characteristic image conveniently, the flame obvious image is further obtained, and the accuracy of the detected flame area is improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. A real-time monitoring system for safety risk of chemical production, the system comprising:
the image acquisition module is used for acquiring a gray image of the internal environment of the chemical plant;
the broken line analysis module is used for acquiring broken line segments on the chemical pipeline edge line according to the gray level image; obtaining brightness characteristic parameters of the interrupt line segments according to the overall brightness values and the overall brightness change rates of all pixel points on each interrupt line segment; obtaining interrupt segment shielding coefficients according to the length difference between each interrupt segment and the reference interrupt segment and the brightness characteristic parameters;
The fire-light surrounding coefficient analysis module is used for acquiring an ROI image only comprising a chemical pipeline and dividing the ROI image into a preset number of local areas; obtaining the brightness direction confusion of the local areas according to the difference of the brightness change directions among the chemical pipelines in each local area; obtaining the brightness parameter of the local area according to the maximum brightness and the brightness range of each chemical pipeline; obtaining the fire surrounding coefficient of each local area according to the brightness direction confusion degree and the brightness parameter;
the flame significant image acquisition module is used for acquiring a flame characteristic image according to the interrupt segment shielding coefficient and the flare surrounding coefficient and acquiring a flame significant image according to the flame characteristic image and the gray level image;
and the risk monitoring module is used for monitoring the risk condition in the chemical plant according to the flame significant image.
2. The real-time monitoring system for safety risk of chemical production according to claim 1, wherein the method for acquiring the broken line on the edge line of the chemical pipeline comprises the following steps:
carrying out Hough straight line detection on the gray level image to obtain a straight line region in the gray level image, and taking a straight line with the length larger than a preset length threshold value in the straight line region as an edge straight line, wherein the edge straight line is a horizontal straight line or a vertical straight line;
Calculating an included angle between each edge straight line and the horizontal direction while moving along the edge straight line from any point of each edge straight line by using a single-pixel point sliding window, taking the position where the included angle changes as a break point on the edge straight line, and taking a connecting line between the break points as a break line segment.
3. The system for monitoring the safety risk of chemical production in real time according to claim 1, wherein the method for acquiring the brightness characteristic parameter of the interrupt line comprises the following steps:
taking the average brightness value of all pixel points on each interrupt line segment as the integral brightness value; taking the square of the brightness difference between adjacent pixel points on each interrupt line segment as the brightness difference of the adjacent pixel points, and taking the average value of all the brightness differences on each interrupt line segment as the integral brightness change rate;
and taking the ratio of the overall brightness value to the overall brightness change rate as the brightness characteristic parameter of each interrupt line segment.
4. The real-time monitoring system for safety risk of chemical production according to claim 1, wherein the method for obtaining the interruption line segment shielding coefficient comprises the following steps:
Taking other interrupt line segments which are parallel to the interrupt line segment and are closest to the interrupt line segment as reference interrupt line segments of the interrupt line segment;
taking the absolute value of the length difference value of the interrupt line segment and the reference interrupt line segment as a length difference;
and obtaining the interrupt segment shielding coefficient of each interrupt segment according to the product of the length difference and the brightness characteristic parameter.
5. The system for monitoring the safety risk of chemical production in real time according to claim 1, wherein the method for acquiring the brightness direction confusion of the local area comprises the following steps:
in each local area, a label value corresponding to each chemical pipeline is given according to the brightness change direction on each chemical pipeline, wherein the label value is 1 and-1, if the brightness change direction on the chemical pipeline is upward or leftward, the label value is 1, and if the brightness change direction on the chemical pipeline is downward or rightward, the label value is-1;
in each local area, a horizontal chemical pipeline and a vertical chemical pipeline are selected at will, the accumulated value of the square difference of the tag values between the horizontal chemical pipeline and all other horizontal chemical pipelines is used as the horizontal mess, and the accumulated value of the square difference of the tag values between the vertical chemical pipeline and all other vertical chemical pipelines is used as the vertical mess;
And taking the sum value of the horizontal confusion and the vertical confusion as a numerator, and taking the sum value of the number of the horizontal chemical pipelines and the number of the vertical chemical pipelines as a denominator to obtain the brightness direction confusion of each local area.
6. The system for monitoring the safety risk of chemical production in real time according to claim 1, wherein the method for acquiring the brightness parameter of the local area comprises the following steps:
taking the difference value between the maximum brightness value and the minimum brightness value on each chemical pipeline as the brightness range, and obtaining the brightness distribution parameter of each chemical pipeline according to the product of the maximum brightness value and the brightness range on each chemical pipeline;
and taking the accumulated value of the brightness distribution parameters of all chemical pipelines in the local area as the brightness parameter of the local area.
7. The system for monitoring the safety risk of chemical production in real time according to claim 1, wherein the method for acquiring the fire-light surrounding coefficient of each local area comprises the following steps:
and obtaining the fire surrounding coefficient of each local area according to the product of the brightness direction confusion degree and the brightness parameter.
8. The real-time monitoring system for safety risk of chemical production according to claim 1, wherein the method for acquiring the flame characteristic image comprises the following steps:
Taking the average value of the blocking coefficients of all the broken line segments on each chemical pipeline as the integral blocking coefficient of the chemical pipeline; obtaining a flame shielding coefficient of each chemical pipeline in each local area according to the product of the integral shielding coefficient and the fire surrounding coefficient;
and taking the flame shielding coefficient as a flame characteristic value of the shielded pixel point on each corresponding chemical pipeline, taking the flame surrounding coefficient as a flame characteristic value of the non-shielded pixel point on the chemical pipeline, and mapping the flame characteristic value of each pixel point into a gray value to obtain a flame characteristic image.
9. The real-time monitoring system for safety risk of chemical production according to claim 1, wherein the method for acquiring the flame saliency image comprises the following steps:
acquiring an LBP image and a gradient image of the gray image;
based on the quaternion matrix, performing quaternion Fourier transform on the flame characteristic image, the gray level image, the LBP image and the gradient image, performing inverse transform, and obtaining a flame salient image through Gaussian filtering on the inverse transform result.
10. The system for monitoring the risk of chemical production safety in real time according to claim 1, wherein the monitoring the risk condition in the chemical plant according to the flame saliency image comprises:
Detecting whether the significance value of each pixel point in the flame significance image exceeds a preset significance threshold, if so, considering that the risk of fire occurs, otherwise, considering that the risk of fire does not occur.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310942760.3A CN116665136B (en) | 2023-07-31 | 2023-07-31 | Chemical production safety risk real-time monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310942760.3A CN116665136B (en) | 2023-07-31 | 2023-07-31 | Chemical production safety risk real-time monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116665136A true CN116665136A (en) | 2023-08-29 |
| CN116665136B CN116665136B (en) | 2023-10-31 |
Family
ID=87722776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310942760.3A Active CN116665136B (en) | 2023-07-31 | 2023-07-31 | Chemical production safety risk real-time monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665136B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117494483A (en) * | 2024-01-02 | 2024-02-02 | 中铁上海工程局集团第七工程有限公司 | Numerical optimization method for deformation data of double-hole tunnel section |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001067566A (en) * | 1999-08-30 | 2001-03-16 | Fujitsu Ltd | Fire detecting device |
| JP2014229156A (en) * | 2013-05-24 | 2014-12-08 | ホーチキ株式会社 | Fire detection device and fire detection method |
| JP2016035747A (en) * | 2014-07-31 | 2016-03-17 | ホーチキ株式会社 | Fire detection device and fire detection method |
| JP2017102719A (en) * | 2015-12-02 | 2017-06-08 | 能美防災株式会社 | Flame detection device and flame detection method |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| JP2020021300A (en) * | 2018-08-01 | 2020-02-06 | 株式会社シー・イー・デー・システム | Fire monitoring device, fire monitoring system, and program for fire monitoring device |
| CN113221763A (en) * | 2021-05-18 | 2021-08-06 | 东南大学 | Flame identification method based on video image brightness |
| CN115691026A (en) * | 2022-12-29 | 2023-02-03 | 湖北省林业科学研究院 | Intelligent early warning monitoring management method for forest fire prevention |
| CN116229668A (en) * | 2022-12-05 | 2023-06-06 | 江苏弘业环保科技产业有限公司 | Fire disaster positioning system based on infrared video monitoring |
-
2023
- 2023-07-31 CN CN202310942760.3A patent/CN116665136B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001067566A (en) * | 1999-08-30 | 2001-03-16 | Fujitsu Ltd | Fire detecting device |
| JP2014229156A (en) * | 2013-05-24 | 2014-12-08 | ホーチキ株式会社 | Fire detection device and fire detection method |
| JP2016035747A (en) * | 2014-07-31 | 2016-03-17 | ホーチキ株式会社 | Fire detection device and fire detection method |
| JP2017102719A (en) * | 2015-12-02 | 2017-06-08 | 能美防災株式会社 | Flame detection device and flame detection method |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| JP2020021300A (en) * | 2018-08-01 | 2020-02-06 | 株式会社シー・イー・デー・システム | Fire monitoring device, fire monitoring system, and program for fire monitoring device |
| CN113221763A (en) * | 2021-05-18 | 2021-08-06 | 东南大学 | Flame identification method based on video image brightness |
| CN116229668A (en) * | 2022-12-05 | 2023-06-06 | 江苏弘业环保科技产业有限公司 | Fire disaster positioning system based on infrared video monitoring |
| CN115691026A (en) * | 2022-12-29 | 2023-02-03 | 湖北省林业科学研究院 | Intelligent early warning monitoring management method for forest fire prevention |
Non-Patent Citations (3)
| Title |
|---|
| GOMES P等: ""A Vision-Based Approach to Fire Detection"", 《INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS》, vol. 11, no. 9 * |
| 李婷雪;: "基于亮度守恒假设的火灾图像运动特征提取", 沈阳大学学报(自然科学版), no. 03 * |
| 赵齐;韩宁;罗琴娟;: "基于三角扩散模型的遮挡林火图像中火源点确定", 林业机械与木工设备, no. 09 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117494483A (en) * | 2024-01-02 | 2024-02-02 | 中铁上海工程局集团第七工程有限公司 | Numerical optimization method for deformation data of double-hole tunnel section |
| CN117494483B (en) * | 2024-01-02 | 2024-03-19 | 中铁上海工程局集团第七工程有限公司 | Numerical optimization method for deformation data of double-hole tunnel section |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116665136B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116665136B (en) | Chemical production safety risk real-time monitoring system | |
| US20030141980A1 (en) | Smoke and flame detection | |
| JP4705090B2 (en) | Smoke sensing device and method | |
| US8462980B2 (en) | System and method for video detection of smoke and flame | |
| CN110458157B (en) | Intelligent monitoring system for power cable production process | |
| CN115240353B (en) | Fire-fighting dangerous case processing method based on Internet of things sensing | |
| CN102881106A (en) | Dual-detection forest fire identification system through thermal imaging video and identification method thereof | |
| CN110009651B (en) | Anti-interference method of instrument visual reading on-line monitoring system | |
| US6956485B1 (en) | Fire detection algorithm | |
| EP1256105B1 (en) | Smoke and flame detection | |
| CN111899210A (en) | Arc detection method based on image recognition | |
| JP6074304B2 (en) | Smoke detection device and smoke detection method | |
| JP6166650B2 (en) | Flame detection apparatus and flame detection method | |
| JP6140599B2 (en) | Flame detection device | |
| JP6166651B2 (en) | Flame detection apparatus and flame detection method | |
| CN104850826B (en) | A kind of fire infrared band detection method | |
| CN110120142B (en) | Fire smoke video intelligent monitoring early warning system and early warning method | |
| JP5309069B2 (en) | Smoke detector | |
| CN112435268A (en) | Method and device for extracting fire passing area based on multi-source remote sensing image | |
| CN113362563B (en) | Method and device for determining abnormal condition of power tunnel | |
| CN114459606B (en) | Thermal imager sun protection method and system, intelligent terminal and storage medium | |
| Yang et al. | A fire detection method based on computer vision | |
| CN111179209A (en) | Infrared and visible light image information fusion method and device based on feature guidance | |
| CN115797372B (en) | Flame target extraction method based on combined image segmentation | |
| JP2015108922A (en) | Flame detector and flame detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: No. 5 Chenyang Road, New Materials Park, Yunhe Economic Development Zone, Rencheng District, Jining City, Shandong Province, 272053 Applicant after: Shandong Changxing Plastic Additives Co.,Ltd. Address before: No. 5 Chenyang Road, New Materials Park, Yunhe Economic Development Zone, Rencheng District, Jining City, Shandong Province, 272053 Applicant before: JINING CHANGXING PLASTIC ADDITIVE CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A real-time monitoring system for chemical production safety risks Granted publication date: 20231031 Pledgee: Jining Rushang Rural Bank Co.,Ltd. Nanzhang Branch Pledgor: Shandong Changxing Plastic Additives Co.,Ltd. Registration number: Y2024980003698 |