CN108550159A - A kind of flue gas concentration identification method based on the segmentation of three color of image - Google Patents
A kind of flue gas concentration identification method based on the segmentation of three color of image Download PDFInfo
- Publication number
- CN108550159A CN108550159A CN201810191928.0A CN201810191928A CN108550159A CN 108550159 A CN108550159 A CN 108550159A CN 201810191928 A CN201810191928 A CN 201810191928A CN 108550159 A CN108550159 A CN 108550159A
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- flue gas
- gas concentration
- color
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Abstract
The invention discloses a kind of flue gas concentration identification methods based on the segmentation of three color of image, including：Image to be split is weighted average；The gray value of each pixel of arbitrary continuation multiframe described image to be split is compared analysis, obtains flue gas concentration gradient；Flue gas concentration gradient is come out with different single channel colour codes, realizes flue gas concentration mark.Therefore, gradient division is carried out to flue gas concentration, and is identified using different colours, and then realize the mark of flue gas concentration, this image partition method accuracy higher, method is easily achieved, with obvious effects.
Description
Technical field
The present invention relates to smoke exhaust ventilator technical field more particularly to a kind of flue gas concentration marks based on the segmentation of three color of image
Method.
Background technology
Image segmentation refers to that image is divided into the image group for not being overlapped mutually, being connected in itself according to the uniform criterion of phase Sihe
The process of member, is the committed step from image procossing to image analysis, the quality of image segmentation quality, after largely decide
The effect of continuous image analysis.Gray level image provides more succinct and effective information than coloured image, therefore to gray level image
The view synthesis field that is segmented in play increasingly important role.
It is usually manually that the color of desired extraction institute is right at this stage either to colored or gray level image segmentation
The image-region answered is marked, then the coordinate system where the image-region marked and image is converted, to really
The coordinate position for making the image-region corresponding to extraction color carries out analyzing processing further according to the region that coordinate pair marks.
However the marked region determined by artificial mode can have large error, the imaging to the stability of image capture device
The precision of system will also result in influence, while artificial mode efficiency is not high, be highly prone to interfere and occur marked erroneous and
Handle error.
Invention content
It is an object of the invention to propose a kind of flue gas concentration identification method divided based on three color of image, there is accuracy
High feature；
For this purpose, the present invention uses following technical scheme：
A kind of flue gas concentration identification method based on the segmentation of three color of image, including：
Image to be split is weighted average；
The gray value of each pixel of arbitrary continuation multiframe described image to be split is compared analysis, obtains cigarette
Gas concentration gradient；
Flue gas concentration gradient is come out with different single channel colour codes, realizes flue gas concentration mark.
Therefore, gradient division is carried out to flue gas concentration, and is identified using different colours, and then realize the mark of flue gas concentration
Know, this image partition method accuracy higher, method is easily achieved, with obvious effects.
Further, it obtains flue gas concentration gradient and realizes that the method that flue gas concentration identifies is：
The gray value of each pixel of arbitrary continuation multiframe image to be split is compared, continuous multiple frames is taken to wait for point
The pixel with minimum gradation value is assigned to a new picture in each image cut, by each image that continuous multiple frames are to be split
In the gray value with one of pixel maximum gradation value and pixel in new picture ask poor, acquisition pixel gray level absolute difference
Value generates gray-scale map；
In gray-scale map, absolute difference is divided by low middle high three shade of gray according to the flue gas threshold value of setting, obtains cigarette
Gas concentration gradient；
In gray-scale map, low middle high three shade of gray are come out with three kinds of single channel colour codes, realizes flue gas concentration
Mark.
Therefore, gradient division is carried out according to preset flue gas threshold value to the gray-scale map of generation, and is identified using different colours
Go out, and then realizes the mark of flue gas concentration, this image partition method accuracy higher, and need not be right to extraction gray value institute
The image answered carries out coordinate conversion, and method is easily achieved, with obvious effects, avoids the error and difficulty brought because of artificial divide
The shortcomings of to identify.
Further, continuous multiple frames imagery exploitation gaussian filtering to be split is smoothed, to eliminate image
Gaussian noise.By eliminating the gaussian noise of image, to image noise reduction, the error of picture processing is reduced.
Further, the method for generating gray-scale map is：
By the pixel gray value per frame image in arbitrary continuation multiframe image to be split, other pictures compare successively, obtain
Go out each pixel with minimum gradation value in multiple image, and these pixels with minimum gradation value are assigned to one
New picture；
The maximum frame of pixel gray value in multiple image is obtained in comparison procedure, then finds out the image slices vegetarian refreshments ash
The difference of angle value and new picture pixels point gray value, obtains pixel gray level absolute difference；
Generate gray-scale map.
Continuous multiple frames image compares generation gray-scale map as a result, generates gray-scale map using pixel grey scale absolute difference to weigh
Flue gas concentration need not carry out coordinate conversion to the image corresponding to extraction gray value, and method is easily achieved.
Further, absolute difference is divided by low middle high three shade of gray according to the flue gas threshold value of setting in gray-scale map
Method be：
Pixel gray level absolute difference is subjected to binaryzation；
By after pixel gray level absolute difference binaryzation in gray-scale map value meet 0-6.0/255 threshold transition be
First shade of gray region, that is, low oil smoke concentration region；
Value after pixel gray level absolute difference binaryzation in gray-scale map is met to 6.0/255-12.0/255 threshold value
Be converted to the i.e. medium oil smoke concentration region in the second shade of gray region；
Value after pixel gray level absolute difference binaryzation in gray-scale map is met to 12.0/255-20.0/255 threshold
Value is converted to the i.e. high oil smoke concentration region in third shade of gray region.
Setting flue gas threshold value is respectively 0-6.0/255,6.0/255-12.0/255,12.0/255-20.0/ as a result,
255, and then gray-scale map is divided into low middle high three shade of gray, realize the division of flue gas concentration, accuracy is high, with obvious effects,
The shortcomings of avoiding the error brought because of artificial divide and being difficult to.
Further, be partitioned into multiframe image to be split with the image corresponding to the first shade of gray region, make
With the first single channel colour code；
Be partitioned into multiframe image to be split with the image corresponding to the second shade of gray region, use the second single-pass
Road colour code；
Be partitioned into multiframe image to be split with the image corresponding to third shade of gray region, use third single-pass
Road colour code；
Generate three color segmentation effect figures.
The oil smoke region of various concentration is identified that segmentation effect figure is visual in image, more using different colours as a result,
It is easy to observe.
Further, three kinds of the first single channel color, the second single channel color and third single channel color colors are marked
The image of note carries out transparent processing, and then the image that three kinds of colors are marked is sequentially overlapped to gray-scale map, and it is dense to generate flue gas
The Overlay comparison diagram of three color segmentation figures and gray-scale map is spent, it is visual in image, it is easy to observe.
Further, acquisition arbitrary continuation multiframe image to be split, progress flue gas concentration mark realize mark in real time in real time
Know.Real-time identification, the real-time concentration dynamic of readily available flue gas are carried out by real-time image acquisition, and then is convenient for fume treatment
The control of device or smoking smoke machine.
Further, the size of image to be split be 640*480, in the case that image enough clearly,
There is higher position to manage speed, reduce the load of processor,
Further, ten frame of arbitrary continuation image to be split is subjected to flue gas concentration mark.Choose continuous ten frames image
Flue gas concentration mark is carried out, ensure that the accuracy of processing.
Beneficial effects of the present invention are：
The present invention makees the division that difference obtains three gradients of progress after absolute difference, then binaryzation according to gray value of image, will
The subregion for meeting corresponding flue gas threshold value in image carries out single pass colour code.Therefore, for flue gas threshold region into
The method accuracy higher of three kinds of color images of row segmentation, and coordinate need not be carried out to the image corresponding to extraction gray value and turned
It changes, method is easily achieved, the shortcomings of avoiding the error brought because of artificial divide and be difficult to.
Flue gas concentration identification method provided by the invention based on the segmentation of three color of image can identify flue gas concentration, and flue gas
The segmentation precision of concentration is not influenced by the distance of camera lens to hearth and hearth size and color, can effectively be applied in kitchen
Oil smoke concentration identification, the fields such as public arena smokescope identification.Three colors dividing method provided by the invention can be distinguished effectively
The distribution situation and change procedure of oil smoke concentration, more effectively drain oil smoke convenient for exhaust smoke system for kitchen.
The generation of gas-cooker flue gas has randomness, therefore the distribution of flue gas in the picture has uncertainty, in this hair
In bright, this uncertainty is the difficult point place of color segmentation.For the random distribution nature of flue gas in the picture, and do not lose
Important boundary information carries out traversal processing, identification using the powerful computing capability of computer according to the threshold value of setting to image
Go out different flue gas concentrations and carries out real-time mark.
Description of the drawings
Fig. 1 is the flow chart of the flue gas concentration identification method divided based on three color of image of one embodiment of the invention；
Fig. 2 is that the step S2 for the flue gas concentration identification method divided based on three color of image shown in Fig. 1 generates the original of gray-scale map
Reason figure；
Fig. 3 is the image segmentation effect of the step S4 for the flue gas concentration identification method divided based on three color of image shown in Fig. 1
Fruit is schemed.
Specific implementation mode
Below in conjunction with the accompanying drawings and the technical solution that further illustrates the present invention of specific implementation mode.
The present invention provides a kind of flue gas concentration identification method divided based on three color of image, including：
Image to be split is weighted average；
The gray value of each pixel of arbitrary continuation multiframe described image to be split is compared analysis, obtains cigarette
Gas concentration gradient；
Flue gas concentration gradient is come out with different single channel colour codes, realizes flue gas concentration mark.
Gradient division is carried out to flue gas concentration, and is identified using different colours, and then realizes the mark of flue gas concentration, this
Kind image partition method accuracy higher, method is easily achieved, with obvious effects.It is provided by the invention based on three color of image segmentation
Flue gas concentration identification method can identify flue gas concentration, can effectively apply in kitchen fume concentration identification, public arena smog
The fields such as concentration identification.
As shown in Figure 1, the flue gas concentration identification method based on the segmentation of three color of image of present embodiment, including step S1~
S5。
S1, continuous multiple frames imagery exploitation gaussian filtering to be split is smoothed, image to be split is carried out
Weighted average, the value of each pixel in image, is all passed through by the value of other pixels in the value and neighborhood of the pixel
It is obtained after weighted average.Wherein, the value of pixel refers to the gray value of pixel, and image to be split is gray level image.
Gaussian filtering process is carried out to eliminate the Gaussian noise of image to image.It is right by eliminating the gaussian noise of image
Image noise reduction reduces the error of picture processing.
Continuous multiple frames imagery exploitation gaussian filtering to be split, which is smoothed, is：Mould is generated using gaussian filtering
Plate, each pixel in scan image, then determine the weighted average gray value of pixel in neighborhood, utilize weighted average gray value
Instead of the pixel value of central point.The method of this gaussian filtering can effectively eliminate the gaussian noise of image, reject noise, improve
The accuracy of picture processing.Gaussian filtering is exactly that average process is weighted to entire image.
Preferably, the size of image to be split be 640*480, in the case that image enough clearly, have
Higher position manages speed, reduces the load of processor.
Preferably, ten frame of arbitrary continuation image to be split is subjected to flue gas concentration mark.Choose continuous ten frames image into
Row flue gas concentration identifies, and ensure that the accuracy of processing.
It should be noted that arbitrary continuation multiframe image to be split is selected from artwork collection, artwork collection is taken pictures by capture apparatus
It obtains.
S2, the gray value of each pixel of arbitrary continuation multiframe image to be split is compared, takes continuous multiple frames
It is assigned to a new picture with the pixel of minimum gradation value in each image to be split, by be split each of continuous multiple frames
Gray value with one of pixel maximum gradation value and pixel in new picture in image asks poor, and acquisition pixel gray level is exhausted
To difference, gray-scale map is generated.In Fig. 2, Fig. 2 a are the schematic diagram of pixel minimum gradation value, the ten frame image slices vegetarian refreshments that Fig. 2 b are
Gray value schematic diagram.
Specifically, the method for generating gray-scale map is：
S201, by the pixel gray value per frame image in arbitrary continuation multiframe image to be split successively other picture ratios
Compared with obtaining each pixel with minimum gradation value in multiple image, and these pixels with minimum gradation value are assigned
To a new picture；
S202, the maximum frame of pixel gray value in multiple image is obtained in comparison procedure, then find out the image slices
The difference of vegetarian refreshments gray value and new picture pixels point gray value, obtains pixel gray level absolute difference；
S203, gray-scale map is generated.
Continuous multiple frames image compares generation gray-scale map, and it is dense to weigh flue gas to generate gray-scale map using pixel grey scale absolute difference
Degree need not carry out coordinate conversion to the image corresponding to extraction gray value, and method is easily achieved.
S3, in gray-scale map, absolute difference is divided by low middle high three shade of gray according to the flue gas threshold value of setting, obtain
Smokescope gradient.
Specifically, absolute difference is divided into low middle high three shade of gray according to the flue gas threshold value of setting in gray-scale map
Method is：
S301, pixel gray level absolute difference is subjected to binaryzation；
S302, the threshold value turn that the value after pixel gray level absolute difference binaryzation in gray-scale map is met to 0-6.0/255
It is changed to the i.e. low oil smoke concentration region in the first shade of gray region；
S303, the value after pixel gray level absolute difference binaryzation in gray-scale map is met 6.0/255-12.0/255
Threshold transition be the second shade of gray region, that is, medium oil smoke concentration region；
S304, the value after pixel gray level absolute difference binaryzation in gray-scale map is met 12.0/255-20.0/255
Threshold transition be third shade of gray region, that is, high oil smoke concentration region.
It is respectively 0-6.0/255,6.0/255-12.0/255,12.0/255-20.0/255 to set flue gas threshold value, into
And gray-scale map is divided into low middle high three shade of gray, it realizes that the division of flue gas concentration, accuracy are high, with obvious effects, avoids
The error brought because of artificial divide and the shortcomings of being difficult to.
S4, in gray-scale map, low middle high three shade of gray are come out with three kinds of single channel colour codes, realize flue gas it is dense
Scale is known.
Specific steps are as follows：
S401, be partitioned into multiframe image to be split with the image corresponding to the first shade of gray region, use
One single channel colour code；
S402, be partitioned into multiframe image to be split with the image corresponding to the second shade of gray region, use
Two single channel colour codes；
S403, be partitioned into multiframe image to be split with the image corresponding to third shade of gray region, use
Three single channel colour codes；
S404, three color segmentation effect figures are generated；
S405, three kinds of the first single channel color, the second single channel color and third single channel color colors are marked
Image carries out transparent processing, and then the image that three kinds of colors are marked is sequentially overlapped to gray-scale map；
S406, the Overlay comparison diagram for generating flue gas concentration three color segmentation figures and gray-scale map, it is visual in image, it is easy to see
It examines.
The oil smoke region of various concentration is identified that segmentation effect figure is visual in image, more easily using different colours
Observation.Wherein, the first single channel color, the second single channel color and third single channel color are respectively single channel green, single-pass
Road blue and single channel are red.
The design sketch of image segmentation is completed as shown in figure 3, Fig. 3 a are left hearth, Fig. 3 b are right hearth.In Fig. 3, a-quadrant is
First shade of gray region uses the first single channel colour code；B area is the second shade of gray region, uses the second single-pass
Road colour code；The regions C are the first shade of gray region, use third single channel colour code.
S5, in real time acquisition arbitrary continuation multiframe image to be split, carry out flue gas concentration mark, realize real-time identification.It is logical
Cross real-time image acquisition and carry out real-time identification, the real-time concentration dynamic of readily available flue gas, and then convenient for flue-gas treater or
The control of smoking smoke machine.
The present invention makees the division that difference obtains three gradients of progress after absolute difference, then binaryzation according to gray value of image, will
The subregion for meeting corresponding flue gas threshold value in image carries out single pass colour code.Therefore, for flue gas threshold region into
The method accuracy higher of three kinds of color images of row segmentation, and coordinate need not be carried out to the image corresponding to extraction gray value and turned
It changes, method is easily achieved, the shortcomings of avoiding the error brought because of artificial divide and be difficult to.
Flue gas concentration identification method provided by the invention based on the segmentation of three color of image can identify flue gas concentration, can be effective
Apply in kitchen fume concentration identification, the fields such as public arena smokescope identification.
The technical principle of the present invention is described above in association with specific embodiment.These descriptions are intended merely to explain the present invention's
Principle, and it cannot be construed to limiting the scope of the invention in any way.Based on the explanation herein, the technology of this field
Personnel would not require any inventive effort the other specific implementation modes that can associate the present invention, these modes are fallen within
Within protection scope of the present invention.
Claims (10)
1. a kind of flue gas concentration identification method based on the segmentation of three color of image, which is characterized in that including：
Image to be split is weighted average；
The gray value of each pixel of arbitrary continuation multiframe described image to be split is compared analysis, it is dense to obtain flue gas
Spend gradient；
Flue gas concentration gradient is come out with different single channel colour codes, realizes flue gas concentration mark.
2. the flue gas concentration identification method according to claim 1 based on the segmentation of three color of image, which is characterized in that described to obtain
It obtains flue gas concentration gradient and realizes that the method that flue gas concentration identifies is：
The gray value of each pixel of arbitrary continuation multiframe described image to be split is compared, continuous multiple frames is taken to wait for point
It is assigned to a new picture with the pixel of minimum gradation value in each described image cut, by be split each of continuous multiple frames
Gray value with one of pixel maximum gradation value and pixel in the new picture in described image asks poor, acquisition pixel
Point gray scale absolute difference, generates gray-scale map；
In the gray-scale map, absolute difference is divided by low middle high three shade of gray according to the flue gas threshold value of setting, obtains cigarette
Gas concentration gradient；
In the gray-scale map, low middle high three shade of gray are come out with three kinds of single channel colour codes, realizes flue gas
Concentration identifies.
3. the flue gas concentration identification method according to claim 1 based on the segmentation of three color of image, which is characterized in that will be continuous
Multiframe described image to be split is smoothed using gaussian filtering, to eliminate the Gaussian noise of described image.
4. the flue gas concentration identification method according to claim 2 based on the segmentation of three color of image, which is characterized in that the life
It is at the method for gray-scale map：
By the pixel gray value per frame described image in arbitrary continuation multiframe described image to be split successively other picture ratios
Compared with obtaining each pixel with minimum gradation value in multiframe described image, and by these pixels with minimum gradation value
Point is assigned to a new picture；
The maximum frame of pixel gray value in multiframe described image is obtained in comparison procedure, then finds out the image slices vegetarian refreshments ash
The difference of angle value and new picture pixels point gray value, obtains pixel gray level absolute difference；
Generate gray-scale map.
5. the flue gas concentration identification method according to claim 2 or 4 based on the segmentation of three color of image, which is characterized in that
Absolute difference is divided into in the gray-scale map according to the flue gas threshold value of setting the method for low middle high three shade of gray is：
The pixel gray level absolute difference is subjected to binaryzation；
By after pixel gray level absolute difference binaryzation in the gray-scale map value meet 0-6.0/255 threshold transition be
First shade of gray region, that is, low oil smoke concentration region；
Value after pixel gray level absolute difference binaryzation in the gray-scale map is met to 6.0/255-12.0/255 threshold value
Be converted to the i.e. medium oil smoke concentration region in the second shade of gray region；
Value after pixel gray level absolute difference binaryzation in the gray-scale map is met to 12.0/255-20.0/255 threshold
Value is converted to the i.e. high oil smoke concentration region in third shade of gray region.
6. the flue gas concentration identification method according to claim 2 based on the segmentation of three color of image, which is characterized in that in multiframe
Be partitioned into described image to be split with the image corresponding to first shade of gray region, use the first single channel color
Mark；
Be partitioned into multiframe described image to be split with the image corresponding to second shade of gray region, use second
Single channel colour code；
Be partitioned into multiframe described image to be split with the image corresponding to third shade of gray region, use third
Single channel colour code；
Generate three color segmentation effect figures.
7. the flue gas concentration identification method according to claim 6 based on the segmentation of three color of image, which is characterized in that by first
The image that three kinds of single channel color, the second single channel color and third single channel color colors are marked carries out transparent processing, so
The image that three kinds of colors are marked is sequentially overlapped to the gray-scale map afterwards, generates three color segmentation figure of flue gas concentration and gray-scale map
Overlay comparison diagram.
8. the flue gas concentration identification method according to claim 1 based on the segmentation of three color of image, which is characterized in that adopt in real time
Collect arbitrary continuation multiframe described image to be split, carry out flue gas concentration mark, realizes real-time identification.
9. the flue gas concentration identification method according to claim 1 based on the segmentation of three color of image, which is characterized in that be split
Described image size be 640*480.
10. the flue gas concentration identification method according to claim 1 based on the segmentation of three color of image, which is characterized in that will appoint
Continuous ten frame of anticipating described image to be split carries out flue gas concentration mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810191928.0A CN108550159B (en) | 2018-03-08 | 2018-03-08 | Flue gas concentration identification method based on image three-color segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810191928.0A CN108550159B (en) | 2018-03-08 | 2018-03-08 | Flue gas concentration identification method based on image three-color segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108550159A true CN108550159A (en) | 2018-09-18 |
| CN108550159B CN108550159B (en) | 2022-02-15 |
Family
ID=63515988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810191928.0A Active CN108550159B (en) | 2018-03-08 | 2018-03-08 | Flue gas concentration identification method based on image three-color segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108550159B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109028234A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | It is a kind of can be to the kitchen ventilator that level of smoke is identified |
| CN109345483A (en) * | 2018-09-29 | 2019-02-15 | 佛山市云米电器科技有限公司 | Kitchen fume concentration identification method based on the segmentation of three color of image |
| CN109447087A (en) * | 2018-09-29 | 2019-03-08 | 佛山市云米电器科技有限公司 | A kind of oil smoke image dynamic area extracting method, identifying system and kitchen ventilator |
| CN109461165A (en) * | 2018-09-29 | 2019-03-12 | 佛山市云米电器科技有限公司 | Kitchen fume concentration based on the segmentation of three color of image divides identification method |
| CN113063170A (en) * | 2021-05-12 | 2021-07-02 | 佛山市顺德区美的洗涤电器制造有限公司 | Method for identifying oil smoke, processor and range hood |
| CN114387273A (en) * | 2022-03-24 | 2022-04-22 | 莱芜职业技术学院 | Environmental dust concentration detection method and system based on computer image recognition |
| CN116228590A (en) * | 2023-03-22 | 2023-06-06 | 新创碳谷集团有限公司 | Flame visual detection noise point elimination method, device and storage medium |
| CN116309505A (en) * | 2023-03-28 | 2023-06-23 | 北京理工大学 | Visual image calibration system, method and detection method for hydrogen concentration |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080106437A1 (en) * | 2006-11-02 | 2008-05-08 | Wei Zhang | Smoke and fire detection in aircraft cargo compartments |
| CN101738394A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for detecting indoor smog |
| CN102737247A (en) * | 2012-07-04 | 2012-10-17 | 中国科学技术大学 | Identification system of smoke intensity image of tail gas of diesel vehicle |
| CN102982313A (en) * | 2012-10-31 | 2013-03-20 | 深圳辉锐天眼科技有限公司 | Smog detecting method |
| JP2015145819A (en) * | 2014-02-03 | 2015-08-13 | 株式会社タカコ | Tool inspection method and tool inspection device |
| CN105550678A (en) * | 2016-02-03 | 2016-05-04 | 武汉大学 | Human body motion feature extraction method based on global remarkable edge area |
| CN105675625A (en) * | 2016-03-03 | 2016-06-15 | 浙江大学 | Method for detecting fruit surface defects by virtue of segmentation of gradient iteration threshold |
| CN106651885A (en) * | 2016-12-31 | 2017-05-10 | 中国农业大学 | Image segmentation method and apparatus |
| CN106680281A (en) * | 2016-12-31 | 2017-05-17 | 中国科学技术大学 | Diesel vehicle tail gas smoke intensity detection method based on deep residual error learning network |
| CN107644429A (en) * | 2017-09-30 | 2018-01-30 | 华中科技大学 | A kind of methods of video segmentation based on strong goal constraint saliency |
-
2018
- 2018-03-08 CN CN201810191928.0A patent/CN108550159B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080106437A1 (en) * | 2006-11-02 | 2008-05-08 | Wei Zhang | Smoke and fire detection in aircraft cargo compartments |
| CN101738394A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for detecting indoor smog |
| CN102737247A (en) * | 2012-07-04 | 2012-10-17 | 中国科学技术大学 | Identification system of smoke intensity image of tail gas of diesel vehicle |
| CN102982313A (en) * | 2012-10-31 | 2013-03-20 | 深圳辉锐天眼科技有限公司 | Smog detecting method |
| JP2015145819A (en) * | 2014-02-03 | 2015-08-13 | 株式会社タカコ | Tool inspection method and tool inspection device |
| CN105550678A (en) * | 2016-02-03 | 2016-05-04 | 武汉大学 | Human body motion feature extraction method based on global remarkable edge area |
| CN105675625A (en) * | 2016-03-03 | 2016-06-15 | 浙江大学 | Method for detecting fruit surface defects by virtue of segmentation of gradient iteration threshold |
| CN106651885A (en) * | 2016-12-31 | 2017-05-10 | 中国农业大学 | Image segmentation method and apparatus |
| CN106680281A (en) * | 2016-12-31 | 2017-05-17 | 中国科学技术大学 | Diesel vehicle tail gas smoke intensity detection method based on deep residual error learning network |
| CN107644429A (en) * | 2017-09-30 | 2018-01-30 | 华中科技大学 | A kind of methods of video segmentation based on strong goal constraint saliency |
Non-Patent Citations (3)
| Title |
|---|
| 宋海峰等: "运动背景下弱小目标的提取算法", 《强激光与粒子束》 * |
| 杨文明等: "结合时空信息的视频对象平面自动提取算法", 《计算机辅助设计与图形学学报》 * |
| 索振鹏等: "基于图像灰度梯度的圆度检测算法", 《激光杂志》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109028234A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | It is a kind of can be to the kitchen ventilator that level of smoke is identified |
| CN109345483A (en) * | 2018-09-29 | 2019-02-15 | 佛山市云米电器科技有限公司 | Kitchen fume concentration identification method based on the segmentation of three color of image |
| CN109447087A (en) * | 2018-09-29 | 2019-03-08 | 佛山市云米电器科技有限公司 | A kind of oil smoke image dynamic area extracting method, identifying system and kitchen ventilator |
| CN109461165A (en) * | 2018-09-29 | 2019-03-12 | 佛山市云米电器科技有限公司 | Kitchen fume concentration based on the segmentation of three color of image divides identification method |
| CN109028234B (en) * | 2018-09-29 | 2020-11-10 | 佛山市云米电器科技有限公司 | Range hood capable of identifying smoke grade |
| CN113063170B (en) * | 2021-05-12 | 2023-06-23 | 佛山市顺德区美的洗涤电器制造有限公司 | Method for identifying lampblack, processor and range hood |
| CN113063170A (en) * | 2021-05-12 | 2021-07-02 | 佛山市顺德区美的洗涤电器制造有限公司 | Method for identifying oil smoke, processor and range hood |
| CN114387273A (en) * | 2022-03-24 | 2022-04-22 | 莱芜职业技术学院 | Environmental dust concentration detection method and system based on computer image recognition |
| CN114387273B (en) * | 2022-03-24 | 2022-05-31 | 莱芜职业技术学院 | Environmental dust concentration detection method and system based on computer image recognition |
| CN116228590A (en) * | 2023-03-22 | 2023-06-06 | 新创碳谷集团有限公司 | Flame visual detection noise point elimination method, device and storage medium |
| CN116228590B (en) * | 2023-03-22 | 2024-01-26 | 新创碳谷集团有限公司 | Flame visual detection noise point elimination method, device and storage medium |
| CN116309505A (en) * | 2023-03-28 | 2023-06-23 | 北京理工大学 | Visual image calibration system, method and detection method for hydrogen concentration |
| CN116309505B (en) * | 2023-03-28 | 2024-04-05 | 北京理工大学 | Visual image calibration system, method and detection method for hydrogen concentration |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108550159B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108550159A (en) | A kind of flue gas concentration identification method based on the segmentation of three color of image | |
| CN108548199B (en) | A kind of intelligent fume exhauster wind speed is adjusted a wage scale method and device | |
| CN104392468B (en) | Based on the moving target detecting method for improving visual background extraction | |
| CN111402209B (en) | U-Net-based high-speed railway steel rail damage detection method | |
| CN104951742B (en) | The detection method and system of objectionable video | |
| CN104504722B (en) | Method for correcting image colors through gray points | |
| CN103914699A (en) | Automatic lip gloss image enhancement method based on color space | |
| CN110163219A (en) | Object detection method based on image border identification | |
| CN112733950A (en) | Power equipment fault diagnosis method based on combination of image fusion and target detection | |
| CN108573222A (en) | The pedestrian image occlusion detection method for generating network is fought based on cycle | |
| CN111062331B (en) | Image mosaic detection method and device, electronic equipment and storage medium | |
| CN106951891A (en) | Spot detection method and apparatus | |
| CN105869148A (en) | Target detection method and device | |
| CN108305232A (en) | A kind of single frames high dynamic range images generation method | |
| CN109741285A (en) | A kind of construction method and system of underwater picture data set | |
| CN108711160A (en) | A kind of Target Segmentation method based on HSI enhancement models | |
| CN104282013B (en) | A kind of image processing method and device for foreground target detection | |
| CN108830856A (en) | A kind of GA automatic division method based on time series SD-OCT retinal images | |
| CN111985435A (en) | Unmanned aerial vehicle water area monitoring and cruising method based on machine vision | |
| CN114187201A (en) | Model training method, image processing method, device, equipment and storage medium | |
| CN117115171B (en) | Slight bright point defect detection method applied to subway LCD display screen | |
| WO2019106946A1 (en) | Image coloring device, image coloring method, image learning device, image learning method, program, and image coloring system | |
| CN110349171B (en) | Scoliosis back contour curve extraction method based on gray median | |
| CN116883887A (en) | Leakage gas detection method for infrared video | |
| JP2005283197A (en) | Detecting method and system for streak defect of screen |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |