CN112669369A - Quantitative determination method for degree of yellow flame of hydrocarbon flame - Google Patents
Quantitative determination method for degree of yellow flame of hydrocarbon flame Download PDFInfo
- Publication number
- CN112669369A CN112669369A CN202110075134.XA CN202110075134A CN112669369A CN 112669369 A CN112669369 A CN 112669369A CN 202110075134 A CN202110075134 A CN 202110075134A CN 112669369 A CN112669369 A CN 112669369A
- Authority
- CN
- China
- Prior art keywords
- flame
- yellow
- image
- color
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention discloses a method for quantitatively judging the degree of yellow flame of hydrocarbon flame, which relates to the field of hydrocarbon fuel combustion flame characteristic analysis, and comprises the steps of obtaining image information, preprocessing the image information, carrying out secondary processing on the preprocessed image information, respectively calculating the area and the brightness of a first color image and a second color image, and solving the area ratio and the brightness ratio of the first color image and the second color image; and judging the soot degree in the flame according to the area ratio and the brightness ratio. The invention realizes the aim of quantitatively judging the degree of the yellow flame by acquiring the self-luminous signals of the flame through the color CCD, dividing a yellow area and a non-yellow flame (usually blue) area in a flame image, and determining the area ratio and the brightness ratio of the yellow flame to the whole flame through mathematical operation in image processing.
Description
Technical Field
The invention relates to the field of hydrocarbon fuel combustion flame characteristic analysis, in particular to a hydrocarbon flame yellow flame degree quantitative determination method.
Background
More than 80% of the world primary energy supply still comes from fossil fuel combustion, and various pollutants are generated while chemical energy is released by fuel combustion to provide heat, wherein soot caused by incomplete combustion is a main source pollutant of PM2.5 in the atmosphere, and belongs to emission pollutants under strict control. Therefore, the generation and degree of soot in the flame need to be judged and analyzed, so that the combustion system is adjusted, the combustion and emission are improved, and the purposes of energy conservation and clean combustion are achieved.
For the judgement and detection of the soot level characteristics in a flame, the prior art mainly comprises: firstly, the existence of yellow flame and black smoke is visually judged through visual inspection, but the method cannot provide a quantitative judgment basis depending on human eyes, and the defining standard has great subjectivity; secondly, the appearance and concentration characteristics of the soot in the flame can be accurately and quantitatively analyzed by analyzing the soot flame through a sampling method, but the method has low time and space resolution, is relatively suitable for the flame with uniformly distributed soot, and cannot meet the requirement of quickly judging all the characteristics of the soot in the flame; another method is online measurement by optical method, which can accurately determine the soot level in the flame, however, this method usually requires a laser system, and has the disadvantages of relatively complicated equipment and high cost. Therefore, there is an urgent need for a convenient and economical method and technique for determining the soot level in a flame by energy. In general, when soot is generated in a flame, the flame with the soot presents yellow to different degrees, and the existence of the soot can be judged by visual inspection, but quantitative parameters of the yellow flame degree of the flame cannot be obtained.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a quantitative determination method for the degree of yellow flame of hydrocarbon flame, which comprises the steps of collecting a self-luminous signal of flame by a color CCD, segmenting a yellow area and a non-yellow flame (usually blue) area in a flame image, and determining the area ratio and the brightness ratio of a yellow flame area to the non-yellow flame area by mathematical operation in image processing to realize the aim of quantitatively determining the degree of yellow flame.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a quantitative determination method for the degree of yellow flame of hydrocarbon flame comprises the following steps:
acquiring image information, wherein the image information comprises flame generated during combustion of hydrocarbon fuel;
preprocessing the image information, wherein the preprocessing comprises converting the image information from an RGB color space to an HSV color space;
performing secondary processing on the preprocessed image information, wherein the secondary processing comprises classifying the preprocessed image information through a K-means clustering method, and flame in the image information is segmented according to colors to form a first color image and a second color image;
calculating the area and the brightness of the first color image and the second color image respectively, and solving the area ratio and the brightness ratio of the first color image and the second color image;
and judging the soot degree in the flame according to the area ratio and the brightness ratio.
The method for quantitatively determining the degree of the yellow flame of the hydrocarbon flame further comprises the steps that the HSV color space comprises a numerical array consisting of a plurality of values from 0 to 1, wherein the hue value is from 0 to 1 and corresponds to the position of the color on a color circle; the saturation is from 0 to 1, the saturation refers to the amount of hue or distance from the neutral color, 0 represents the neutral color, 1 represents the maximum saturation, and the lightness value corresponds to the maximum lightness of the red, green, and blue components of a particular color.
The method for quantitatively determining the degree of yellow flame of hydrocarbon flame further classifies the preprocessed image information by a K-means clustering method, specifically comprising:
dividing the digital array into a plurality of objects according to the numerical value array in the HSV color space;
a plurality of objects are used as initial centers, and each object represents a clustering center;
and for the numerical arrays in the HSV color space, according to Euclidean distances between the numerical arrays and the clustering centers, classifying the numerical arrays into classes corresponding to the clustering centers closest to the numerical arrays according to the closest criterion, wherein the classes at least comprise yellow flame regions and blue flame regions.
The method for quantitatively determining the degree of yellow flame of hydrocarbon flame further includes calculating the areas and the brightness of the first color image and the second color image, specifically:
let the image information be a two-dimensional function f (x, y), where x and y are the spatial (planar) coordinates, the magnitude f at any coordinate (x, y) is referred to as the brightness of the image at that location, and the image information is continuous in x and y coordinates, and in magnitude;
setting a pixel matrix of a yellow flame region extracted after the gray clustering segmentation of an original image as A, wherein elements in the A are A (i, j), a pixel matrix of a blue flame region is B, and elements in the B are B (i, j);
setting all pixel values of the yellow flame region to be 1 in the matrix A, and setting all pixel values outside the yellow flame region to be 0; similarly, the pixel values of the blue flame region are all 1 in the matrix B, the pixel values outside the blue color region are all 0,
the index of elements i and j in matrix a and matrix B range from 1 to m and 1 to n, respectively;
yellow flame area of SyBlue flame area of SbThen the pixel summation formula for the yellow flame area:
pixel summation formula for blue flame area:
extracting V-channel information of the image information to obtain a brightness matrix C, wherein each element in the matrix is between 0 and 1, and the brightness of a yellow flame area isIyBlue flame region brightness of Ib，
Pixel summation formula for yellow flame brightness:
pixel summation formula for blue flame brightness:
the method for quantitatively determining the degree of yellow flame of hydrocarbon flame further comprises the following steps of calculating the area ratio and the brightness ratio of the first color image and the second color image:
formula of area ratio of yellow flame and blue flame:
formula for yellow and blue flame luminance ratio:
and quantitatively judging the soot degree in the flame according to the area proportion value and the intensity proportion value of the yellow flame area.
Compared with the prior art, the invention has the beneficial effects that: visual judgment is not required to be relied on, and a quantification means is provided, so that the combustion degree of the hydrocarbon fuel is more accurate; the soot flame does not need to be analyzed by a sampling method, so that the efficiency of judging the combustion degree of the hydrocarbon fuel is improved; according to the invention, judgment can be carried out only through image acquisition and processing, a laser system which is complex and high in cost does not need to be built, and the convenience of an experiment is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of detecting the degree of yellow flame;
FIG. 2 is an image of an untreated raw color flame;
FIG. 3 is another image of an untreated raw colored flame;
FIG. 4 is an image of the flame of FIG. 2 after segmentation of the yellow flame region and the blue flame region;
FIG. 5 is an image of the flame of FIG. 3 after segmentation of the yellow flame region and the blue flame region;
FIG. 6 is the area and ratio of the yellow flame region and the blue flame region corresponding to FIGS. 2 and 3;
FIG. 7 is a graph showing the brightness and ratio of the yellow flame region and the blue flame region corresponding to FIGS. 2 and 3;
fig. 8 is a numerical display of the area (ratio) and the brightness (ratio) of the yellow flame region and the blue flame region in fig. 2 and 3.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying 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 application, 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 application.
Example (b):
it should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Further, in the description of the present invention, "a plurality" and "several" mean at least two, e.g., two, three, etc., unless explicitly specified otherwise.
Referring to fig. 1 to 8, fig. 1 is a flowchart for detecting a degree of yellow flame; FIG. 2 is an image of an untreated raw color flame; FIG. 3 is another image of an untreated raw colored flame; FIG. 4 is an image of the flame of FIG. 2 after segmentation of the yellow flame region and the blue flame region; FIG. 5 is an image of the flame of FIG. 3 after segmentation of the yellow flame region and the blue flame region; FIG. 6 is the area and ratio of the yellow flame region and the blue flame region corresponding to FIGS. 2 and 3; FIG. 7 is a graph showing the brightness and ratio of the yellow flame region and the blue flame region corresponding to FIGS. 2 and 3; fig. 8 is a numerical display of the area (ratio) and the brightness (ratio) of the yellow flame region and the blue flame region in fig. 2 and 3.
In order to better understand the invention, the detection principle of the invention is explained, and the invention judges the position and the overall quantitative information of the flame by accurately acquiring and extracting the yellow flame signal information in the flame. In the method, the high-resolution color camera is adopted to collect the hydrocarbon fuel combustion yellow flame with different degrees of soot content, then the collected image is input into a calculation processing program, and finally the area proportion value and the intensity proportion value of the yellow flame part in the flame in the whole flame are output. In the calculation procedure, an image segmentation technology is required to be used for dividing and extracting yellow flame and non-yellow flame regions in the whole flame, the region contour is measured by judging the yellow flame, then the area of the yellow flame envelope region and the gray intensity value under the corresponding pixel are accumulated and summed, finally, the area ratio and the intensity ratio of the yellow flame region and the whole flame are calculated, and the quantitative judgment of the flame yellow flame degree is realized.
A quantitative determination method for the degree of yellow flame of hydrocarbon flame comprises the following steps:
acquiring image information, wherein the image information comprises flame generated during combustion of hydrocarbon fuel;
preprocessing the image information, wherein the preprocessing comprises converting the image information from an RGB color space to an HSV color space;
performing secondary processing on the preprocessed image information, wherein the secondary processing comprises classifying the preprocessed image information through a K-means clustering method, and flame in the image information is segmented according to colors to form a first color image and a second color image;
calculating the area and the brightness of the first color image and the second color image respectively, and solving the area ratio and the brightness ratio of the first color image and the second color image;
and judging the soot degree in the flame according to the area ratio and the brightness ratio.
As an alternative, in some embodiments, the HSV color space contains an array of values having values from 0 to 1, where hue values from 0 to 1 correspond to the position of a color on a color circle; the saturation is from 0 to 1, the saturation refers to the amount of hue or distance from the neutral color, 0 represents the neutral color, 1 represents the maximum saturation, and the lightness value corresponds to the maximum lightness of the red, green, and blue components of a particular color.
As an optional implementation manner, in some embodiments, the classifying the preprocessed image information by using a K-means clustering method specifically includes:
dividing the digital array into a plurality of objects according to the numerical value array in the HSV color space;
a plurality of objects are used as initial centers, and each object represents a clustering center;
and for the numerical arrays in the HSV color space, according to Euclidean distances between the numerical arrays and the clustering centers, classifying the numerical arrays into classes corresponding to the clustering centers closest to the numerical arrays according to the closest criterion, wherein the classes at least comprise yellow flame regions and blue flame regions.
As an optional implementation manner, in some embodiments, the calculating the areas and the luminances of the first color image and the second color image specifically includes:
let the image information be a two-dimensional function f (x, y), where x and y are the spatial (planar) coordinates, the magnitude f at any coordinate (x, y) is referred to as the brightness of the image at that location, and the image information is continuous in x and y coordinates, and in magnitude;
setting a pixel matrix of a yellow flame region extracted after the gray clustering segmentation of an original image as A, wherein elements in the A are A (i, j), a pixel matrix of a blue flame region is B, and elements in the B are B (i, j);
setting all pixel values of the yellow flame region to be 1 in the matrix A, and setting all pixel values outside the yellow flame region to be 0; similarly, the pixel values of the blue flame region are all 1 in the matrix B, the pixel values outside the blue color region are all 0,
the index of elements i and j in matrix a and matrix B range from 1 to m and 1 to n, respectively;
yellow flame area of SyBlue flame area of SbThen the pixel summation formula for the yellow flame area:
pixel summation formula for blue flame area:
extracting V-channel information of the image information to obtain a brightness matrix C, wherein each element in the matrix is between 0 and 1, and the brightness of a yellow flame area is IyBlue flame region brightness of Ib，
Pixel summation formula for yellow flame brightness:
pixel summation formula for blue flame brightness:
as an optional implementation manner, in some embodiments, the obtaining an area ratio and a luminance ratio of the first color image and the second color image is specifically:
formula of area ratio of yellow flame and blue flame:
formula for yellow and blue flame luminance ratio:
and quantitatively judging the soot degree in the flame according to the area proportion value and the intensity proportion value of the yellow flame area.
The specific steps of the present invention are explained below:
1. converting an image from an RGB (R: red, G: green, B: blue) color space to an H S V (hue, saturation, value) color space
Firstly, a color camera is used for directly photographing a high-resolution color image of the flame of the hydrocarbon fuel to obtain original image data of the flame. If the variation of brightness is neglected, the color image comprises three colors: black, blue and yellow areas. H S V color space is able to quantify these visual differences. The red, green and blue values of the RGB image are converted into hue, saturation and value (HSV) values of the HSV image by a calculation program. An HSV image consists of an m x n x 3 array of values within the range [0,1 ]. The hue value is from 0 to 1, corresponding to the position of the color on the color circle. As the hue goes from 0 to 1, the color transitions from red to orange, yellow, green, cyan, blue, magenta, and finally back to red; the saturation refers to the amount of hue or the amount from neutral color, 0 represents neutral color, and 1 represents maximum saturation; the brightness value refers to the maximum brightness of the red, green and blue components of a particular color.
2. Classifying HSV space based colors
The method classifies the processed HSV image matrix through a K-means clustering method. Clustering is a method of separating groups of objects, and K-means clustering considers each object as having a position in space. It divides objects into partitions, with the objects in each cluster as close to each other as possible and as far away from objects in other clusters as possible, K-means clustering requires specifying the number of clusters divided and a distance metric for quantifying the distance between two objects.
3. Creating images of segmented flames by color
The objects in the picture are separated by color, the yellow flame region in the image can be marked as 1, the blue flame region can be marked as 2, and the two regions are divided, and each region is composed of a plurality of pixel values.
4. Matrix operation is carried out to obtain the area ratio and the brightness ratio of the yellow flame and the blue flame
An image can be defined as a two-dimensional function f (x, y), where x and y are spatial (planar) coordinates and the magnitude f at any coordinate (x, y) is referred to as the brightness of the image at that location. The image is continuous in x and y coordinates, as well as in magnitude. To convert an image to digital form requires digitizing the coordinates and amplitudes, the image belongs to a digital image when the x, y components and the amplitude f are finite and discrete quantities. A digital image is composed of a finite number of pixels, each having a particular location and value, and can therefore be represented as a matrix.
According to the matrix operation idea, the area of one color area in the digital image is calculated, the matrix pixel values of the area can be summed twice, because the digital image is a two-dimensional matrix, the first summation is to sum the columns of the matrix by default, the second summation is to sum the rows of the matrix, and the row and column are obtained after the two summationsThe total number of all pixel values belonging to a color region, i.e. the total area of this color region. Assume that a pixel matrix of a yellow flame region extracted after an original image is subjected to gray-scale clustering segmentation is a, an element in a is a (i, j), a pixel matrix of a blue flame region is B, and an element in B is B (i, j). Setting all pixel values of the yellow flame region to be 1 in the matrix A, and setting all pixel values outside the yellow flame region to be 0; similarly, the pixel values of the blue flame region are all 1 in the matrix B, and the pixel values outside the blue color region are all 0, so the element indices i and j in the matrix a and the matrix B range from 1 to m and 1 to n, respectively. Yellow flame area of SyBlue flame area of SbArea ratio of Syb. Respectively obtaining S by the above analysisy、Sb、Syb。
Pixel summation formula for yellow flame area:
pixel summation formula for blue flame area:
formula of area ratio of yellow flame and blue flame:
in the same way, the brightness of a color region in the digital image is obtained, and firstly, the third channel of the gray scale image, namely the V (brightness) channel is extracted according to the HSV theory to obtain a brightness matrix C. And each element in the matrix is located between 0 and 1, the brightness value of each pixel of the whole image is displayed, then the pixel matrix A of the yellow flame area and the pixel matrix B of the blue flame area are point-multiplied by the matrix C, and finally the brightness pixel values of the two products are respectively summed twice to obtain the brightness value of the yellow flame and the brightness value of the blue flame. Brightness of yellow flame region is IyBlue flame region brightness of IbBrightness ratio of Iyb. Respectively obtaining I by the above analysisy、Ib、Iyb。
Pixel summation formula for yellow flame brightness:
pixel summation formula for blue flame brightness:
formula for yellow and blue flame luminance ratio:
after the calculation of the steps, the area ratio value and the intensity ratio value of the yellow flame region can be obtained respectively, and both the values are between 0 and 1, so that the method can be used for quantitatively judging the soot degree in the flame.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The above embodiments are only for illustrating the technical concept and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention accordingly, and not to limit the protection scope of the present invention accordingly. All equivalent changes or modifications made in accordance with the spirit of the present disclosure are intended to be covered by the scope of the present disclosure.
Claims (5)
1. A quantitative determination method for the degree of yellow flame of hydrocarbon flame is characterized by comprising the following steps:
acquiring image information, wherein the image information comprises flame generated during combustion of hydrocarbon fuel;
preprocessing the image information, wherein the preprocessing comprises converting the image information from an RGB color space to an HSV color space;
performing secondary processing on the preprocessed image information, wherein the secondary processing comprises classifying the preprocessed image information through a K-means clustering method, and flame in the image information is segmented according to colors to form a first color image and a second color image;
calculating the area and the brightness of the first color image and the second color image respectively, and solving the area ratio and the brightness ratio of the first color image and the second color image;
and judging the soot degree in the flame according to the area ratio and the brightness ratio.
2. The method for quantitatively determining the degree of yellow flame of hydrocarbon flame as claimed in claim 1, wherein said HSV color space comprises a numerical array of values from 0 to 1, wherein hue values from 0 to 1 correspond to the positions of colors on a color circle; the saturation is from 0 to 1, the saturation refers to the amount of hue or distance from the neutral color, 0 represents the neutral color, 1 represents the maximum saturation, and the lightness value corresponds to the maximum lightness of the red, green, and blue components of a particular color.
3. The method for quantitatively determining the degree of yellow flame of hydrocarbon flame according to claim 1, wherein the preprocessed image information is classified by a K-means clustering method, and specifically comprises:
dividing the digital array into a plurality of objects according to the numerical value array in the HSV color space;
a plurality of objects are used as initial centers, and each object represents a clustering center;
and for the numerical arrays in the HSV color space, according to Euclidean distances between the numerical arrays and the clustering centers, classifying the numerical arrays into classes corresponding to the clustering centers closest to the numerical arrays according to the closest criterion, wherein the classes at least comprise yellow flame regions and blue flame regions.
4. The method for quantitatively determining the degree of yellow flame of hydrocarbon flame according to claim 3, wherein the calculating the areas and the brightnesses of the first color image and the second color image specifically comprises:
let the image information be a two-dimensional function f (x, y), where x and y are the spatial (planar) coordinates, the magnitude f at any coordinate (x, y) is referred to as the brightness of the image at that location, and the image information is continuous in x and y coordinates, and in magnitude;
setting a pixel matrix of a yellow flame region extracted after the gray clustering segmentation of an original image as A, wherein elements in the A are A (i, j), a pixel matrix of a blue flame region is B, and elements in the B are B (i, j);
setting all pixel values of the yellow flame region to be 1 in the matrix A, and setting all pixel values outside the yellow flame region to be 0; similarly, the pixel values of the blue flame region are all 1 in the matrix B, the pixel values outside the blue color region are all 0,
the index of elements i and j in matrix a and matrix B range from 1 to m and 1 to n, respectively;
yellow flame area of SyBlue flame area of SbThen the pixel summation formula for the yellow flame area:
pixel summation formula for blue flame area:
extracting V-channel information of the image information to obtain a brightness matrix C, wherein each element in the matrix is between 0 and 1, and the brightness of a yellow flame area is IyBlue flame region brightness of Ib，
Pixel summation formula for yellow flame brightness:
pixel summation formula for blue flame brightness:
5. the method for quantitatively determining the degree of yellow flame of hydrocarbon flame according to claim 4, wherein the calculating of the area ratio and the brightness ratio of the first color image and the second color image is specifically:
formula of area ratio of yellow flame and blue flame:
formula for yellow and blue flame luminance ratio:
and quantitatively judging the soot degree in the flame according to the area proportion value and the intensity proportion value of the yellow flame area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110075134.XA CN112669369A (en) | 2021-01-20 | 2021-01-20 | Quantitative determination method for degree of yellow flame of hydrocarbon flame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110075134.XA CN112669369A (en) | 2021-01-20 | 2021-01-20 | Quantitative determination method for degree of yellow flame of hydrocarbon flame |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112669369A true CN112669369A (en) | 2021-04-16 |
Family
ID=75415826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110075134.XA Pending CN112669369A (en) | 2021-01-20 | 2021-01-20 | Quantitative determination method for degree of yellow flame of hydrocarbon flame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112669369A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678295A (en) * | 2016-01-04 | 2016-06-15 | 武汉科技大学 | Method for real-time monitoring gas heating furnace flame on the basis of ROI average image analysis |
| CN108052950A (en) * | 2017-12-08 | 2018-05-18 | 东北大学 | A kind of segmentation of electric melting magnesium furnace dynamic flame and feature extracting method based on MIA |
| CN109598193A (en) * | 2018-10-25 | 2019-04-09 | 安徽新浩信息科技有限公司 | A kind of flame image recognition methods based on artificial intelligence |
| CN110675588A (en) * | 2019-09-30 | 2020-01-10 | 北方民族大学 | Forest fire detection device and method |
-
2021
- 2021-01-20 CN CN202110075134.XA patent/CN112669369A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678295A (en) * | 2016-01-04 | 2016-06-15 | 武汉科技大学 | Method for real-time monitoring gas heating furnace flame on the basis of ROI average image analysis |
| CN108052950A (en) * | 2017-12-08 | 2018-05-18 | 东北大学 | A kind of segmentation of electric melting magnesium furnace dynamic flame and feature extracting method based on MIA |
| CN109598193A (en) * | 2018-10-25 | 2019-04-09 | 安徽新浩信息科技有限公司 | A kind of flame image recognition methods based on artificial intelligence |
| CN110675588A (en) * | 2019-09-30 | 2020-01-10 | 北方民族大学 | Forest fire detection device and method |
Non-Patent Citations (4)
| Title |
|---|
| 吴强等: "进气滚流强度对直喷发动机燃烧特性的影响", 《车用发动机》 * |
| 张周等: "均质化学计量比燃烧下GDI 发动机碳烟生成可视化解析", 《内燃机学报》 * |
| 徐睿: "基于光学诊断与图像处理技术的乙醇汽油扩散火焰研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅰ辑》 * |
| 王勇等: "基于数字图像处理的微火焰测量技术", 《应用光学》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7936377B2 (en) | Method and system for optimizing an image for improved analysis of material and illumination image features | |
| US7995058B2 (en) | Method and system for identifying illumination fields in an image | |
| JP2012013675A (en) | Device and method for analyzing corrosion inside steel pipe | |
| US8064691B2 (en) | Method for identifying color in machine and computer vision applications | |
| US8700498B2 (en) | Feature analyzing apparatus for a surface of an object | |
| CN112950606A (en) | Mobile phone screen defect segmentation method based on small samples | |
| JP3581149B2 (en) | Method and apparatus for identifying an object using a regular sequence of boundary pixel parameters | |
| JP2018190329A (en) | Image processing apparatus, image processing program, and image processing system | |
| CN110599552A (en) | pH test paper detection method based on computer vision | |
| CN106483143A (en) | A kind of solar energy photovoltaic panel dust stratification on-Line Monitor Device and its detection method | |
| CN109948566A (en) | A kind of anti-fraud detection method of double-current face based on weight fusion and feature selecting | |
| CN103020198B (en) | One searches for mesh calibration method in video | |
| CN113033385A (en) | Deep learning-based violation building remote sensing identification method and system | |
| CN110319933B (en) | Light source spectrum optimization method based on CAM02-UCS color appearance model | |
| JP3608106B2 (en) | Degradation evaluation system for steel surface using image processing | |
| CN105787955A (en) | Sparse segmentation method and device of strip steel defect | |
| CN112164055A (en) | Photovoltaic cell color difference classification method based on color segmentation | |
| CN108830834B (en) | Automatic extraction method for video defect information of cable climbing robot | |
| CN112132823A (en) | Photovoltaic cell image local uneven illumination processing method based on artificial intelligence | |
| CN112669369A (en) | Quantitative determination method for degree of yellow flame of hydrocarbon flame | |
| CN102999622B (en) | A kind of mesh calibration method of search in video based on database | |
| CN109658405B (en) | Image data quality control method and system in crop live-action observation | |
| CN103020995B (en) | A kind of object feature comparison method being applicable to search for target in video | |
| CN111242053B (en) | Power transmission line flame detection method and system | |
| CN112686105B (en) | Fog concentration grade identification method based on video image multi-feature fusion |
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 |