CN108564091A - Target area weak boundary extracting method and oil smoke concentration detection and interference elimination method - Google Patents
Target area weak boundary extracting method and oil smoke concentration detection and interference elimination method Download PDFInfo
- Publication number
- CN108564091A CN108564091A CN201810191909.8A CN201810191909A CN108564091A CN 108564091 A CN108564091 A CN 108564091A CN 201810191909 A CN201810191909 A CN 201810191909A CN 108564091 A CN108564091 A CN 108564091A
- Authority
- CN
- China
- Prior art keywords
- image
- oil smoke
- area
- region
- interest
- 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
Classifications
-
- 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
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
Target area weak boundary extracting method, includes the following steps：Eliminate picture noise, smoothed image；The point that gray value in frontier area has significant change is highlighted；Define 3*3 filters；Image is traversed with 3*3 filters, calculates the convolution results of each pixel；Judge whether calculated pixel is marginal point, if marginal point is then marked；Obtain it is labeled after target area weak edge.It is an object of the invention to propose target area weak boundary extracting method and oil smoke concentration detection and interference elimination method, method based on wavelet transformation, accurate image weak boundary extracting effect can be obtained by not needing prodigious calculation amount, the portability of the algorithm is stronger, can be applied in the product of portable image procossing.
Description
Technical field
Power method is put forward the present invention relates to the weak edge of oil smoke detection technique field more particularly to a kind of target area and oil smoke is dense
Degree detection and interference elimination method.
Background technology
It is directed to Image Edge-Detection at this stage and there are many algorithm of extraction, but often all relies on a large amount of calculating, needs
Consumption is a large amount of to calculate power to obtain accurate edge detection results, this is not applicable on embedded image processing product
's.And traditional Edge extraction algorithm is pretty good to the apparent strong edge effect of gray value mutation, but to image object area
The detection at the weak edge in domain just seems awkward.
Invention content
It is an object of the invention to solve the above problems to propose target area weak boundary extracting method and oil smoke concentration detection
With interference elimination method, this method is simple and practicable, need not consume a large amount of calculating, has higher standard to the detection at weak edge
True property.
In order to reach this purpose, the present invention uses following technical scheme：
Target area weak boundary extracting method, includes the following steps：
Step A1 eliminates picture noise, smoothed image；
Step A2 highlights the point that gray value in frontier area has significant change；
Step A3 defines 3*3 filters；
Step A4 traverses image with 3*3 filters, calculates the convolution results of each pixel；
Step A5 judges whether calculated pixel is marginal point, if marginal point is then marked；
Step A6, obtain it is labeled after target area weak edge.
More preferably, calculated in the step A4 in each position central pixel point and field the gray value of eight pixels with
Corresponding value is multiplied and seeks the edge detection value of pixel centered on summation in filter.
More preferably, judge whether calculated pixel is that marginal point includes the following steps in the step A5：If edge
Detected value differs larger with the pixel gray value more than half in field, then this pixel is determined as marginal point, gone forward side by side
Line flag.
More preferably, using the detection of the oil smoke concentration of target area weak boundary extracting method and interference elimination method, including with
Lower step：
Step B1 acquires the oil smoke image above hearth in real time；
Step B2, image processing unit carry out frame difference operation to collected front and back frame image, obtain the dynamic after frame difference
Area image；
Step B3, image processing unit carry out opening operation to the image after frame difference, remove image noise；
Step B4, using wavelet transformation, the edge of detection frame difference figure highlight regions is simultaneously marked, the region that will be marked
It is set as area-of-interest；
Step B5 identifies oil smoke using Image Smoothness and the method for gray value threshold value comprehensive descision come exclusive PCR
Moving region；
Step B6 carries out statistics of histogram to the oil smoke region identified, judges oil smoke concentration grade.
More preferably, it is camera oil smoke image to be acquired in the step B1, and the camera is mounted on kitchen ventilator ontology.
More preferably, image processing unit can be utilized according to the sequencing of the gray level image received in the step B2
A later frame image makes the difference with previous frame image.
More preferably, further comprising the steps of in the step B3：
Step C1 carries out etching operation to image, eliminates the noise in image and tiny spine, disconnect narrow company
It connects；
Step C2 carries out expansive working to the image corroded, restores the obvious characteristic on former frame difference image.
More preferably, the step B5 exclusive PCRs region includes the following steps：
Step D1 finds out the segmentation threshold of oil smoke region and interference region, is set when the gray average of area-of-interest is more than
When fixed gray threshold, judgement area-of-interest is that may interfere with region；When the gray average of area-of-interest is less than setting
When gray threshold, judgement area-of-interest is possible oil smoke region；
Step D2 calculates the smoothness of each area-of-interest on the basis of area grayscale mean value, if some region of interest
When the variance in domain is greater than the set value, judgement area-of-interest is that may interfere with region；If the variance of some area-of-interest is less than
When setting value, judgement area-of-interest is possible oil smoke region；
Step D3, when step D1 and step D2 be all possible oil smoke region when, then judge area-of-interest for oil smoke region,
Other regions are all determined as interference region.
It is an object of the invention to propose target area weak boundary extracting method and oil smoke concentration detection and interference elimination side
Method, the method based on wavelet transformation, accurate image weak boundary extracting effect can be obtained by not needing prodigious calculation amount,
The portability of the algorithm is stronger, can be applied in the product of portable image procossing.
Description of the drawings
Fig. 1 is the flow chart of one embodiment of the present of invention；
Fig. 2 is the flow chart of one embodiment of the present of invention；
Fig. 3 is the schematic diagram of the oil smoke region recognition of one embodiment of the present of invention.
Specific implementation mode
The technical solution further illustrated the present invention below in conjunction with the accompanying drawings and by specific embodiment mode.
As shown in Figure 1, target area weak boundary extracting method, includes the following steps：
Step A1 eliminates picture noise, smoothed image；
Step A2 highlights the point that gray value in frontier area has significant change；
Step A3 defines 3*3 filters；
Step A4 traverses image with 3*3 filters, calculates the convolution results of each pixel；
Step A5 judges whether calculated pixel is marginal point, if marginal point is then marked；
Step A6, obtain it is labeled after target area weak edge.
Further description calculates each position central pixel point and eight pixels in field in the step A4
Gray value value corresponding in filter is multiplied and seeks the edge detection value of pixel centered on summation.
Further description judges that calculated pixel whether be marginal point includes following step in the step A5
Suddenly：If edge detection value differs larger with the pixel gray value more than half in field, this pixel is determined as side
Edge point, and be marked.
Further description, as shown in Fig. 2, detecting and doing using the oil smoke concentration of target area weak boundary extracting method
Method for removing is disturbed, is included the following steps：
Step B1 acquires the oil smoke image above hearth in real time；
Step B2, image processing unit carry out frame difference operation to collected front and back frame image, obtain the dynamic after frame difference
Area image；
Step B3, image processing unit carry out opening operation to the image after frame difference, remove image noise；
Step B4, using wavelet transformation, the edge of detection frame difference figure highlight regions is simultaneously marked, the region that will be marked
It is set as area-of-interest；
Step B5 identifies oil smoke using Image Smoothness and the method for gray value threshold value comprehensive descision come exclusive PCR
Moving region；
Step B6 carries out statistics of histogram to the oil smoke region identified, judges oil smoke concentration grade.
Further description, acquisition oil smoke image is camera in the step B1, and the camera is mounted on kitchen ventilator
On ontology.Camera fields of view can cover entire hearth, and through the real-time gray level image of lens protection glass acquisition hearth oil smoke
And it is transmitted to image processing unit.
Further description, image processing unit can be suitable according to the priority of the gray level image received in the step B2
Sequence is made the difference using a later frame image with previous frame image.Since static region is constant, dynamic area in front and back two field pictures
(such as oil smoke drifts, and human hand is brandished) is variation, so black is presented in static region after frame difference, table after the frame difference of dynamic area
It is now the highlight regions of edge blurry, so the highlighted frame difference image in dynamic area can be obtained by frame difference.
Further description, it is further comprising the steps of in the step B3：
Step C1 carries out etching operation to image, eliminates the noise in image and tiny spine, disconnect narrow company
It connects；
Step C2 carries out expansive working to the image corroded, restores the obvious characteristic on former frame difference image.
The noise of frame difference image is removed using the method for opening operation, concrete operations are first to corrode reflation.First to image into
Row etching operation can eliminate the noise in image and tiny spine, disconnect narrow connection.Expansion is the antithesis behaviour of corrosion
Make, expansive working is carried out to the image corroded, restores the obvious characteristic on former frame difference image.Figure can be eliminated using opening operation
As noise, the separating objects at very thin point, smooth larger object boundary, while can ensure highlight regions in original image
Area is basically unchanged, and ensures that the accuracy of subsequent detection is unaffected.
Further description, the step B5 exclusive PCRs region include the following steps：
Step D1 finds out the segmentation threshold of oil smoke region and interference region, is set when the gray average of area-of-interest is more than
When fixed gray threshold, judgement area-of-interest is that may interfere with region；When the gray average of area-of-interest is less than setting
When gray threshold, judgement area-of-interest is possible oil smoke region；
Step D2 calculates the smoothness of each area-of-interest on the basis of area grayscale mean value, if some region of interest
When the variance in domain is greater than the set value, judgement area-of-interest is that may interfere with region；If the variance of some area-of-interest is less than
When setting value, judgement area-of-interest is possible oil smoke region；
Step D3, when step D1 and step D2 be all possible oil smoke region when, then judge area-of-interest for oil smoke region,
Other regions are all determined as interference region.
Because people is when cooking operation, hand can be brandished always, can include that oil smoke and human hand are grasped in the image after frame difference is complete
The interference region for the moving objects such as making, needs the influence in exclusive PCR region before carrying out oil smoke concentration identification, but oil smoke
The direction of motion have randomness, human hand, the direction of motion of slice are relatively unambiguous, to as shown in Figure 3：A, the image after frame difference
Upper oil smoke moving region is lower than the brightness of human hand, slice moving region, so the gray value mean value in corresponding oil smoke region is also low
Gray average in the moving region of human hand, slice；B, the grey value profile of oil smoke moving region relatively collects on the image after frame difference
In, and the gray value of the motion region boundary of human hand, slice is larger compared with the jump of the central area in region, so the image in the region
Not smooth enough, the variance of corresponding gray value is larger.Feature according to A, we are largely tested, and find out oil smoke area
The segmentation threshold in domain and interference region judges the region when the gray average of area-of-interest is more than the gray threshold of setting
To may interfere with region；When the gray average of area-of-interest is less than the gray threshold of setting, judge the region for possible oil
Cigarette district domain.Feature according to B calculates the smoothness of each area-of-interest on the basis of area grayscale mean value, the present invention
It is middle to be indicated with gray value variance, if the variance of some area-of-interest is greater than the set value, judge that the region is that may interfere with area
Domain；If the variance of some area-of-interest is less than setting value, judge the region for possible oil smoke region.Only judge when twice
When (gray average and variance) is all possible oil smoke region, then the region is judged for oil smoke region, other area-of-interests are all sentenced
It is set to interference region.Complete the exclusion of the identification and interference region in oil smoke region.
The method that the present invention utilizes statistics of histogram delimit oil smoke concentration grade.Grey level histogram is about gray scale
The function of grade distribution, is the statistics to grey level distribution in image.Grey level histogram is to press all pixels in digital picture
According to the size of gray value, the frequency of its appearance is counted.The concentration scale quantity divided as needed, can use 10 is siding-to-siding block length,
The pixel number in each gray scale interval is counted, reaches the grade classification scheme set and then divides oil smoke as corresponding concentration etc.
Grade.
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 (8)
1. target area weak boundary extracting method, which is characterized in that include the following steps：
Step A1 eliminates picture noise, smoothed image；
Step A2 highlights the point that gray value in frontier area has significant change；
Step A3 defines 3*3 filters；
Step A4 traverses image with 3*3 filters, calculates the convolution results of each pixel；
Step A5 judges whether calculated pixel is marginal point, if marginal point is then marked；
Step A6, obtain it is labeled after target area weak edge.
2. weak boundary extracting method in target area according to claim 1, it is characterised in that：It is calculated in the step A4 every
The gray value of eight pixels value corresponding in filter is multiplied and asks summation conduct in one place-centric pixel and field
The edge detection value of central pixel point.
3. target area edge extracting method according to claim 2, which is characterized in that judge to calculate in the step A5
Whether the pixel gone out is that marginal point includes the following steps：If edge detection value and the pixel gray value in field being more than half
It differs larger, then this pixel is determined as marginal point, and be marked.
4. using the oil smoke concentration detection of target area weak boundary extracting method and interference elimination according to claim 1-3
Method, which is characterized in that include the following steps：
Step B1 acquires the oil smoke image above hearth in real time；
Step B2, image processing unit carry out frame difference operation to collected front and back frame image, obtain the dynamic area after frame difference
Image；
Step B3, image processing unit carry out opening operation to the image after frame difference, remove image noise；
Step B4, using wavelet transformation, the edge of detection frame difference figure highlight regions is simultaneously marked, and the region marked is set as
Area-of-interest；
Step B5 identifies that oil smoke moves using Image Smoothness and the method for gray value threshold value comprehensive descision come exclusive PCR
Region；
Step B6 carries out statistics of histogram to the oil smoke region identified, judges oil smoke concentration grade.
5. oil smoke concentration detection according to claim 4 and interference elimination method, it is characterised in that：It is adopted in the step B1
Oil smoke collection image is camera, and the camera is mounted on kitchen ventilator ontology.
6. oil smoke concentration detection according to claim 4 and interference elimination method, it is characterised in that：Scheme in the step B2
As processing unit can be made the difference using a later frame image with previous frame image according to the sequencing of the gray level image received.
7. oil smoke concentration detection according to claim 4 and interference elimination method, it is characterised in that：In the step B3 also
Include the following steps：
Step C1 carries out etching operation to image, eliminates the noise in image and tiny spine, disconnect narrow connection；
Step C2 carries out expansive working to the image corroded, restores the obvious characteristic on former frame difference image.
8. oil smoke concentration detection according to claim 4 and interference elimination method, it is characterised in that：The step B5 is excluded
Interference region includes the following steps：
Step D1 finds out the segmentation threshold of oil smoke region and interference region, when the gray average of area-of-interest is more than setting
When gray threshold, judgement area-of-interest is that may interfere with region；When the gray average of area-of-interest is less than the gray scale of setting
When threshold value, judgement area-of-interest is possible oil smoke region；
Step D2 calculates the smoothness of each area-of-interest on the basis of area grayscale mean value, if some area-of-interest
When variance is greater than the set value, judgement area-of-interest is that may interfere with region；If the variance of some area-of-interest is less than setting
When value, judgement area-of-interest is possible oil smoke region；
Step D3, when step D1 and step D2 be all possible oil smoke region when, then judge area-of-interest for oil smoke region, other
Region is all determined as interference region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810191909.8A CN108564091A (en) | 2018-03-08 | 2018-03-08 | Target area weak boundary extracting method and oil smoke concentration detection and interference elimination method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810191909.8A CN108564091A (en) | 2018-03-08 | 2018-03-08 | Target area weak boundary extracting method and oil smoke concentration detection and interference elimination method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108564091A true CN108564091A (en) | 2018-09-21 |
Family
ID=63531523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810191909.8A Pending CN108564091A (en) | 2018-03-08 | 2018-03-08 | Target area weak boundary extracting method and oil smoke concentration detection and interference elimination method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108564091A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109028237A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition |
| 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 |
| CN109028225A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator and oil smoke concentration detection method of the fixed vision detection system of band |
| CN109028224A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator and oil smoke concentration detection method having light self-adaptive visual function |
| CN109028227A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | Intelligent range hood and its mobile human body detection method |
| CN109028226A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | The kitchen ventilator of oil smoke concentration judgement is carried out based on dual area Image Acquisition |
| CN109028228A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator with Shockproof type vision-based detection module and oil smoke concentration detection method |
| CN109028232A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of band moves the kitchen ventilator and oil smoke concentration detection method of vision detection system |
| CN109028231A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of the cigarette stove all-in-one machine and oil smoke concentration detection method of view-based access control model gesture control |
| CN109084349A (en) * | 2018-09-29 | 2018-12-25 | 佛山市云米电器科技有限公司 | The noise minimizing technology and its Lampblack treatment system and kitchen ventilator of frame difference image |
| CN109325969A (en) * | 2018-09-29 | 2019-02-12 | 佛山市云米电器科技有限公司 | A kind of intelligence smoke machine hearth dynamic foreign matter detecting method |
| CN109344827A (en) * | 2018-09-29 | 2019-02-15 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator with light compensating apparatus and oil smoke concentration detection method |
| CN109360218A (en) * | 2018-09-29 | 2019-02-19 | 佛山市云米电器科技有限公司 | A kind of oil smoke image weak boundary extracting method and oil smoke image identification system and kitchen ventilator |
| CN109389604A (en) * | 2018-09-29 | 2019-02-26 | 佛山市云米电器科技有限公司 | A kind of kitchen fume image detection interference elimination method |
| 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 |
| CN109447063A (en) * | 2018-09-29 | 2019-03-08 | 佛山市云米电器科技有限公司 | A kind of kitchen fume concentration detection method based on image procossing |
| 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 |
| CN109472745A (en) * | 2018-09-29 | 2019-03-15 | 佛山市云米电器科技有限公司 | A kind of denoising method and oil smoke image identification system of oil smoke frame difference image |
| CN112989933A (en) * | 2021-02-05 | 2021-06-18 | 宁波方太厨具有限公司 | Oil smoke concentration identification method and system, electronic equipment and storage medium |
| CN115131387A (en) * | 2022-08-25 | 2022-09-30 | 山东鼎泰新能源有限公司 | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770646A (en) * | 2010-02-25 | 2010-07-07 | 昆山锐芯微电子有限公司 | Edge detection method based on Bayer RGB images |
| CN106228150A (en) * | 2016-08-05 | 2016-12-14 | 南京工程学院 | Smog detection method based on video image |
-
2018
- 2018-03-08 CN CN201810191909.8A patent/CN108564091A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770646A (en) * | 2010-02-25 | 2010-07-07 | 昆山锐芯微电子有限公司 | Edge detection method based on Bayer RGB images |
| CN106228150A (en) * | 2016-08-05 | 2016-12-14 | 南京工程学院 | Smog detection method based on video image |
Non-Patent Citations (1)
| Title |
|---|
| 王理强: "《智能视频监控烟火检测研究与实现》", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325969A (en) * | 2018-09-29 | 2019-02-12 | 佛山市云米电器科技有限公司 | A kind of intelligence smoke machine hearth dynamic foreign matter detecting method |
| 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 |
| CN109028237A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition |
| CN109028224A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator and oil smoke concentration detection method having light self-adaptive visual function |
| CN109028227A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | Intelligent range hood and its mobile human body detection method |
| CN109028226A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | The kitchen ventilator of oil smoke concentration judgement is carried out based on dual area Image Acquisition |
| CN109028228A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator with Shockproof type vision-based detection module and oil smoke concentration detection method |
| CN109028232A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of band moves the kitchen ventilator and oil smoke concentration detection method of vision detection system |
| CN109028231A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of the cigarette stove all-in-one machine and oil smoke concentration detection method of view-based access control model gesture control |
| CN109360218A (en) * | 2018-09-29 | 2019-02-19 | 佛山市云米电器科技有限公司 | A kind of oil smoke image weak boundary extracting method and oil smoke image identification system and kitchen ventilator |
| CN109028225A (en) * | 2018-09-29 | 2018-12-18 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator and oil smoke concentration detection method of the fixed vision detection system of band |
| CN109344827A (en) * | 2018-09-29 | 2019-02-15 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator with light compensating apparatus and oil smoke concentration detection method |
| CN109084349A (en) * | 2018-09-29 | 2018-12-25 | 佛山市云米电器科技有限公司 | The noise minimizing technology and its Lampblack treatment system and kitchen ventilator of frame difference image |
| CN109389604A (en) * | 2018-09-29 | 2019-02-26 | 佛山市云米电器科技有限公司 | A kind of kitchen fume image detection interference elimination method |
| 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 |
| CN109447063A (en) * | 2018-09-29 | 2019-03-08 | 佛山市云米电器科技有限公司 | A kind of kitchen fume concentration detection method based on image procossing |
| 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 |
| CN109472745A (en) * | 2018-09-29 | 2019-03-15 | 佛山市云米电器科技有限公司 | A kind of denoising method and oil smoke image identification system of oil smoke frame difference image |
| CN109344827B (en) * | 2018-09-29 | 2023-06-16 | 佛山市云米电器科技有限公司 | Range hood with light supplementing device and range hood concentration detection method |
| CN112989933A (en) * | 2021-02-05 | 2021-06-18 | 宁波方太厨具有限公司 | Oil smoke concentration identification method and system, electronic equipment and storage medium |
| CN112989933B (en) * | 2021-02-05 | 2024-09-20 | 宁波方太厨具有限公司 | Recognition method, system, electronic equipment and storage medium for lampblack concentration |
| CN115131387A (en) * | 2022-08-25 | 2022-09-30 | 山东鼎泰新能源有限公司 | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing |
| CN115131387B (en) * | 2022-08-25 | 2023-01-24 | 山东鼎泰新能源有限公司 | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564091A (en) | Target area weak boundary extracting method and oil smoke concentration detection and interference elimination method | |
| CN108563991A (en) | Kitchen fume concentration division methods and oil smoke concentration detection and interference elimination method | |
| CN108760590A (en) | A kind of kitchen fume Concentration Testing based on image procossing and interference elimination method | |
| Liu et al. | Single image dehazing via large sky region segmentation and multiscale opening dark channel model | |
| EP1697901B1 (en) | Method for modeling background and foreground regions | |
| KR100847143B1 (en) | System and Method for analyzing of human motion based silhouettes of real-time video stream | |
| CN102568005B (en) | Moving object detection method based on Gaussian mixture model | |
| CN109190624B (en) | Kitchen oil smoke concentration detection method based on image processing | |
| CN109028223B (en) | Range hood with gesture control visual detection function and range hood concentration detection method | |
| CN109447063A (en) | A kind of kitchen fume concentration detection method based on image procossing | |
| CN108765406A (en) | A kind of snow mountain detection method based on infrared remote sensing image | |
| CN109028230A (en) | Have the stove and oil smoke concentration detection method of gesture control vision-based detection function | |
| CN101930540A (en) | Video-based multi-feature fusion flame detecting device and method | |
| CN108827967A (en) | Oil smoke image-pickup method and oil smoke concentration detection and interference elimination method | |
| CN112070741B (en) | Rice chalkiness degree detecting system based on image salient region extracting method | |
| CN107992799B (en) | Preprocess method towards Smoke Detection application | |
| CN109028231A (en) | A kind of the cigarette stove all-in-one machine and oil smoke concentration detection method of view-based access control model gesture control | |
| Yu et al. | Skin detection for adult image identification | |
| CN209013299U (en) | Has the kitchen ventilator of gesture control vision-based detection function | |
| CN209013293U (en) | A kind of cigarette stove all-in-one machine of view-based access control model gesture control | |
| Zhang et al. | Motion detection based on improved Sobel and ViBe algorithm | |
| CN109028224A (en) | A kind of kitchen ventilator and oil smoke concentration detection method having light self-adaptive visual function | |
| CN209013295U (en) | Has the stove of gesture control vision-based detection function | |
| CN112926676B (en) | False target identification method and device and computer equipment | |
| CN109028225A (en) | A kind of kitchen ventilator and oil smoke concentration detection method of the fixed vision detection system of band |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180921 |