CN109028237A - The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition - Google Patents
The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition Download PDFInfo
- Publication number
- CN109028237A CN109028237A CN201811152689.4A CN201811152689A CN109028237A CN 109028237 A CN109028237 A CN 109028237A CN 201811152689 A CN201811152689 A CN 201811152689A CN 109028237 A CN109028237 A CN 109028237A
- Authority
- CN
- China
- Prior art keywords
- picture
- image
- frame
- imaging
- initial
- 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24C—DOMESTIC STOVES OR RANGES ; DETAILS OF DOMESTIC STOVES OR RANGES, OF GENERAL APPLICATION
- F24C15/00—Details
- F24C15/20—Removing cooking fumes
- F24C15/2021—Arrangement or mounting of control or safety systems
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
A kind of kitchen ventilator carrying out wind speed adjusting based on dual area Image Acquisition, visual imaging module are provided with the camera of 180 ° of wide-angle lens；Image processing module by frame difference method judge be imaged picture detection zone in whether have human body, if there is there are the imaging pictures that human body then gives up the corresponding moment in detection zone, there is no the imaging picture of human body as initial imaging picture using in the detection zone of reservation, it is handled to obtain oil smoke concentration information according to initial imaging picture, by oil smoke concentration information conveyance to blast velocity control module.The present invention passes through 180 ° of wide-angle lens, it may be implemented that hearth region and human body working region is imaged, image processing module excludes the imaging picture in detection zone there are human body, and to carry out oil smoke concentration judgement based on the initial picture for excluding human body, according to oil smoke concentration result controlled wind speed adjuster, it is accurate with result, the good feature of oil smoke suction effect.
Description
Technical field
The present invention relates to kitchen fume processing technology fields, carry out wind based on dual area Image Acquisition more particularly to one kind
The kitchen ventilator of velocity modulation section.
Background technique
Kitchen is one of configuration of herbal, and the effect of kitchen fume processing directly affects people's lives quality.It passes
Suction and pumping kitchen ventilator of uniting mainly realizes that this method realizes smoke exhaust ventilator by artificially manipulation to the control of wind speed by physical button
Wind speed is adjusted.There are many disadvantages in actual operation for such method: the differentiation of 1. level of smoke is indefinite, and manual operation can mostly be adjusted
It is high-power to prevent big smog from occurring, so cause electric power resource significant wastage；2. people is to adjust smoke exhaust ventilator wind speed to have delay,
Influence operating experience.
Existing automatic speed regulation smoke exhaust ventilator realizes the much progress in smoke exhaust ventilator performance, is mostly examined based on non-vision smog
Device is surveyed, can determine whether mist detecting device smokescope nearby, but this method can not carry out smog identification to entire hearth, it can not
It determines smog range, and insensitive to steam, so causing to very little range but highly concentrated smog is using maximum power, produces
Situations such as giving birth to false-alarm, reporting by mistake, misrepresent deliberately, at the same it is poor to steam detection effect.
Applicant's research and development judge smoke condition for oil smoke image recognition, for the accuracy for ensuring oil smoke image recognition, need
Will the human body to oil smoke and as interference differentiate, obtain accurate smoke region information.
Therefore, in view of the shortcomings of the prior art, providing a kind of kitchen ventilator for carrying out wind speed adjusting based on dual area Image Acquisition
It is very necessary to overcome the deficiencies of the prior art.
Summary of the invention
There is provided it is an object of the invention to avoid in place of the deficiencies in the prior art it is a kind of based on dual area Image Acquisition into
Row wind speed adjust kitchen ventilator, can root the outside human motion region on hearth region and top is imaged, to detection zone
Imaging picture in domain there are human body is excluded, and oil smoke concentration inspection is carried out based on excluding the initial picture there are human body
It surveys, wind speed adjusting is carried out according to smokescope situation controlled wind speed adjuster.
The object of the present invention is achieved by the following technical measures.
A kind of kitchen ventilator that wind speed adjusting is carried out based on dual area Image Acquisition is provided, smoke machine main body is provided with
Visual imaging module carries out continuous imaging to target area, and the Video stream information that picture is imaged is sent to place
Manage module；Visual imaging module is provided with camera, and the camera is equipped with 180 ° of wide-angle lens, a part of 180 ° of wide-angle lens
Visual zone covers hearth region, the human body workspace of a part of visual zone covering hearth upper outer of 180 ° of wide-angle lens
Domain；
Image processing module receives the Video stream information for the imaging picture that visual imaging module is sent, is sentenced by frame difference method
Whether have human body, if there is there are the imagings that human body then gives up the corresponding moment in detection zone if being broken into the detection zone as picture
Picture, does not have the imaging picture of human body using in the detection zone of reservation as initial imaging picture, according to initial imaging picture into
Row processing obtains oil smoke concentration information, by oil smoke concentration information conveyance to blast velocity control module；
Blast velocity control module carries out wind speed tune according to the oil smoke concentration information controlled wind speed adjuster that processing module is sent
Section.
Preferably, image processing module is handled based on picture is imaged, and imaging picture is grayscale image, is acquired
Imaging picture be serialized, the imaging picture of the imaging picture and previous frame that pass sequentially through rear frame carries out the processing of frame difference, obtains each
The human motion target area of frame imaging picture after a.
Specific steps process is as follows:
1) by the imaging picture of rear frame and the imaging picture of previous frame carry out frame difference handle to obtain be used for human testing frame it is poor
Image；
2) judges whether there is human body according to the gray average of each subregion of the frame difference image for human testing and moves
Moving-target region.
Preferably, the target area of imaging device acquisition is indicated with region S, and any one frame imaging picture is corresponding region S
Imaging；
Imaging picture is made of m*n pixel,
The gray value of the pixel of frame imaging picture A is indicated afterwards with matrix A H, AH={ ahi,j, ahi,jFrame image after representative
I-th row, the corresponding gray value of jth column pixel in piece A, i are the row where pixel, and j is the column where pixel, 1≤i≤m, 1≤j
≤n；The subregion in frame imaging picture A where the i-th row, jth column pixel is AS afterwardsi,j；
The gray value of pixel of previous frame imaging picture B indicates with matrix B H, BH={ bhi,j, bhi,jRepresent previous frame image
I-th row, the corresponding gray value of jth column pixel in piece B, the subregion that previous frame is imaged in picture B where the i-th row, jth column pixel are
BSi,j；
The grey scale pixel value of frame difference image D for human testing indicates with matrix D H, DH={ dhi,j}={ | ahi,j-
bhi,j|, dhi,jThe i-th row, the corresponding gray value of jth column pixel in the frame difference image D for human testing are represented, human body is used for
Subregion in the frame difference image D of detection where the i-th row, jth column pixel is DSi,j。
Preferably, the step 2) is specifically: statistics is for gray value in the frame difference image D of human testing | dhi,j| > θ's
For subregion as mobile human body target area, remaining regional determination is non-moving human region；
Wherein, θ is threshold value, and θ is more than or equal to 25.
Preferably, θ is equal to 30.
Preferably, the visual imaging module is additionally provided with light compensating lamp, the imaging of the irradiation area covering camera of light compensating lamp
Field range, the optical source wavelength of the light compensating lamp are 850-980nm.
Preferably, the light compensating lamp is infrared light compensating lamp, and the optical source wavelength of infrared light compensating lamp is 940nm, infrared light compensating lamp
Power be 6w.
Preferably, image processing module is handled based on picture initially is imaged, initial image collected
Piece is serialized, and the initial imaging picture of the initial imaging picture and previous frame that pass sequentially through rear frame is handled, obtain it is each after
The current kitchen fume concentration at moment locating for picture is initially imaged in frame；
Handled every time by the initial imaging picture of the initial imaging picture of rear frame and previous frame, obtain rear frame initially at
The step process of the current kitchen fume concentration at the moment as locating for picture is as follows:
(1) the initial imaging picture of rear frame and the initial imaging picture of previous frame frame difference is carried out to handle to obtain frame difference image；
(2) denoising is carried out to frame difference image in a manner of opening operation, obtains denoising image；
(3) edge detection is carried out to denoising image, marker motion region is as initial area-of-interest；
(4) gray average calculating is carried out to initial area-of-interest and segment smoothing degree calculates, it is equal gray scale will to be met simultaneously
The region of value and smoothness requirements is as next step area-of-interest, and other regions are as interference elimination；
(5) area-of-interest extracted to step (4) counts respectively, divides oil smoke concentration etc. according to statistical result
Grade.
Preferably, in step (1), to collected initial imaging picture carry out frame difference operate to obtain frame difference image it is specific
Be: image processing module does a later frame image with previous frame image according to the sequencing of the initial imaging picture received
Difference obtains the highlighted frame difference image in dynamic area；
The step (2) carries out denoising using opening operation to frame difference image, denoising image is obtained, especially by as follows
Mode carries out: first carrying out etching operation to frame difference image and disconnects narrow company to eliminate noise and the tiny spine in image
It connects；Expansive working is carried out to the image after corrosion again, restores the smoke characteristics in former frame difference image；
The step (3) carries out edge detection to denoising image, and marker motion region is as initial area-of-interest, specifically
Be: the edge of detection frame difference image highlight regions is simultaneously marked, using the region marked as initial area-of-interest；
The step (4) is specifically to carry out gray average, the calculating of segment smoothing degree to each initial area-of-interest, is obtained
Each initial corresponding gray average of area-of-interest and gray scale smoothness, will meet the gray average being calculated simultaneously and are less than
Gray threshold, gray scale smoothness be less than gray scale smoothness threshold initial area-of-interest be used as area-of-interest, will it is other at the beginning of
Beginning area-of-interest is determined as interference region；
Step (5), the area-of-interest extracted to step (4) carry out statistics of histogram respectively, are tied according to statistics
Fruit divides oil smoke concentration grade, specifically:
By all pixels in region of interest area image, according to the size of gray value, the frequency of its appearance is counted；
Further according to the concentration scale quantity that needs divide, the pixel number in each gray scale interval, each gray scale are counted
The corresponding oil smoke that divides of pixel number in section is corresponding concentration scale.
The of the invention kitchen ventilator that wind speed adjusting is carried out based on dual area Image Acquisition, smoke machine main body be provided with vision at
As module, continuous imaging is carried out to target area, and the Video stream information that picture is imaged is sent to processing module；Visual imaging
Module is provided with camera, and the camera is built in the shell of smoke machine main body, and the camera is equipped with 180 ° of wide-angle lens, 180 ° wide
A part of visual zone of angle mirror head covers hearth region, and a part of visual zone covering hearth top of 180 ° of wide-angle lens is outer
The human body working region of side；Image processing module receives the Video stream information for the imaging picture that visual imaging module is sent, passes through
Frame difference method judges to be imaged in the detection zone of picture whether have human body, if there is in detection zone there are human body then give up to it is corresponding when
The imaging picture at quarter, does not have the imaging picture of human body using in the detection zone of reservation as initial imaging picture, according to initially at
As picture is handled to obtain oil smoke concentration information, by oil smoke concentration information conveyance to blast velocity control module；Blast velocity control module,
Wind speed adjusting is carried out according to the oil smoke concentration information controlled wind speed adjuster that processing module is sent.It, can by 180 ° of wide-angle lens
Hearth region and human body working region are imaged with realizing, image processing module is to the imaging in detection zone there are human body
Picture is excluded, and to carry out oil smoke concentration judgement based on the initial picture for excluding human body, according to oil smoke concentration result control
Velocity regulator processed has result accurate, the good feature of oil smoke suction effect.
Figure of description
Using attached drawing, the present invention is further illustrated, but the content in attached drawing is not constituted to any limit of the invention
System.
Fig. 1 is a kind of structural representation for the kitchen ventilator that wind speed adjusting is carried out based on dual area Image Acquisition through the invention
Figure.
Fig. 2 is the structural schematic diagram of another angle of Fig. 1.
In Fig. 1, Fig. 2, comprising:
Smoke machine main body 100, camera 200, light compensating lamp 300, hearth 400, human body working region 500.
Specific embodiment
The invention will be further described with the following Examples.
Embodiment 1.
A kind of kitchen ventilator carrying out wind speed adjusting based on dual area Image Acquisition, as shown in Figure 1 and Figure 2, smoke machine main body 100
It is provided with
Visual imaging module is assemblied in smoke machine main body, carries out continuous imaging, and the video that picture will be imaged to target area
Stream information is sent to processing module.Visual imaging module is provided with camera 200, and camera 200 is built in the outer of smoke machine main body 100
Shell, camera are equipped with 180 ° of wide-angle lens, and a part of visual zone of 180 ° of wide-angle lens covers 400 region of hearth, 180 ° wide
The human body working region 500 of a part of visual zone covering hearth upper outer of angle mirror head.It, can be with by 180 ° of wide-angle lens
Hearth region and human body working region is imaged in realization, provides the imaging letter compared with broader region for kitchen ventilator processing module
Breath.
Image processing module receives the Video stream information for the imaging picture that visual imaging module is sent, is sentenced by frame difference method
Whether there is human body in the disconnected detection zone for judging imaging picture, if there is there are human bodies then to give up the corresponding moment in detection zone
Picture is imaged, does not have the imaging picture of human body as initial imaging picture using in the detection zone of reservation, according to initial image
Piece is handled to obtain oil smoke concentration information, by oil smoke concentration information conveyance to blast velocity control module.
Blast velocity control module carries out wind speed tune according to the oil smoke concentration information controlled wind speed adjuster that processing module is sent
Section.
Visual imaging module carries out target area imaging, determines imaging picture effect.Visual imaging module is additionally provided with benefit
Light lamp 300, the visual field range of the irradiation area covering camera of light compensating lamp.The optical source wavelength of light compensating lamp is preferably 850-
980nm。
The setting of light compensating lamp can be irradiated imaging region when camera 200 is imaged, and light compensating lamp 300 can allow smog
Feature is more obvious, and detection is easy in vision.There is no smoke characteristics under 300 irradiation condition of light compensating lamp unobvious.It needs to illustrate
, the preferred infrared light compensating lamp of light compensating lamp, naturally it is also possible to for other light compensating lamps.In the present embodiment, the position point of light compensating lamp
Camera two sides are distributed in, light compensating lamp can also be distributed in around camera, can also be integrated together, be may be set to be not with camera
In smoke machine main body, the other positions around camera.
In addition, camera, which is also equipped with, is provided with waterproof, antifog, lampblack-preventing eyeglass, to adapt to the oil smoke surroundings in kitchen.
This carries out kitchen ventilator of wind speed adjusting based on dual area Image Acquisition, and camera is equipped with 180 ° of wide-angle lens, and 180 °
A part of visual zone of wide-angle lens covers hearth region, a part of visual zone covering hearth top of 180 ° of wide-angle lens
The human body working region in outside may be implemented that hearth region and human body working region is imaged, and be kitchen ventilator processing module
It carries out human body judgement and provides important information.
Image processing module is handled based on picture is imaged, and imaging picture is grayscale image, imaging collected
Picture is serialized, and the imaging picture of the imaging picture and previous frame that pass sequentially through rear frame carries out the processing of frame difference, obtains each rear frame
The human motion target area of picture is imaged, specific steps process is as follows:
1) by the imaging picture of rear frame and the imaging picture of previous frame carry out frame difference handle to obtain be used for human testing frame it is poor
Image；
2) judges whether there is human body according to the gray average of each subregion of the frame difference image for human testing and moves
Moving-target region.
The target area of imaging device acquisition indicates that the imaging that picture is corresponding region S is imaged in any one frame with region S；
Imaging picture is made of m*n pixel,
The gray value of the pixel of frame imaging picture A is indicated afterwards with matrix A H, AH={ ahi,j, ahi,jFrame image after representative
I-th row, the corresponding gray value of jth column pixel in piece A, i are the row where pixel, and j is the column where pixel, 1≤i≤m, 1≤j
≤n；The subregion in frame imaging picture A where the i-th row, jth column pixel is AS afterwardsi,j；
The gray value of pixel of previous frame imaging picture B indicates with matrix B H, BH={ bhi,j, bhi,jRepresent previous frame image
I-th row, the corresponding gray value of jth column pixel in piece B, the subregion that previous frame is imaged in picture B where the i-th row, jth column pixel are
BSi,j；
The grey scale pixel value of frame difference image D for human testing indicates with matrix D H, DH={ dhi,j}={ | ahi,j-
bhi,j|, dhi,jThe i-th row, the corresponding gray value of jth column pixel in the frame difference image D for human testing are represented, human body is used for
Subregion in the frame difference image D of detection where the i-th row, jth column pixel is DSi,j。
Wherein, step 2) is specifically: statistics is for gray value in the frame difference image D of human testing | dhi,jThe subregion of | > θ
As mobile human body target area, remaining regional determination is non-moving human region.
Wherein, θ is threshold value, and θ is more than or equal to 25, and preferably θ is equal to 30.
The present invention handles to obtain frame difference image using before and after frames frames differencing, judges movement by the gray value of frame difference image
Whether human region can contain human body in recognition imaging picture, exclude to the imaging picture for having human body in detection zone.
After exclusion detection zone has the imaging picture of human body, kitchen is carried out based on the initial imaging picture based on not human body
The judgement of room oil smoke concentration.
Image processing module is handled based on picture initially is imaged, and initial imaging picture collected is by sequence
Change, the initial imaging picture of the initial imaging picture and previous frame that pass sequentially through rear frame handled, obtain it is each after frame initially at
The current kitchen fume concentration at the moment as locating for picture；
Handled every time by the initial imaging picture of the initial imaging picture of rear frame and previous frame, obtain rear frame initially at
The step process of the current kitchen fume concentration at the moment as locating for picture is as follows:
(1) the initial imaging picture of rear frame and the initial imaging picture of previous frame frame difference is carried out to handle to obtain frame difference image；
(2) denoising is carried out to frame difference image in a manner of opening operation, obtains denoising image；
(3) edge detection is carried out to denoising image, marker motion region is as initial area-of-interest；
(4) gray average calculating is carried out to initial area-of-interest and segment smoothing degree calculates, it is equal gray scale will to be met simultaneously
The region of value and smoothness requirements is as next step area-of-interest, and other regions are as interference elimination；
(5) area-of-interest extracted to step (4) counts respectively, divides oil smoke concentration etc. according to statistical result
Grade.
Specifically, in step (1), to collected initial imaging picture carry out frame difference operate to obtain frame difference image it is specific
Be: image processing module does a later frame image with previous frame image according to the sequencing of the initial imaging picture received
Difference obtains the highlighted frame difference image in dynamic area；
The step (2) carries out denoising using opening operation to frame difference image, denoising image is obtained, especially by as follows
Mode carries out: first carrying out etching operation to frame difference image and disconnects narrow company to eliminate noise and the tiny spine in image
It connects；Expansive working is carried out to the image after corrosion again, restores the smoke characteristics in former frame difference image；
The step (3) carries out edge detection to denoising image, and marker motion region is as initial area-of-interest, specifically
Be: the edge of detection frame difference image highlight regions is simultaneously marked, using the region marked as initial area-of-interest；
The step (4) is specifically to carry out gray average, the calculating of segment smoothing degree to each initial area-of-interest, is obtained
Each initial corresponding gray average of area-of-interest and gray scale smoothness, will meet the gray average being calculated simultaneously and are less than
Gray threshold, gray scale smoothness be less than gray scale smoothness threshold initial area-of-interest be used as area-of-interest, will it is other at the beginning of
Beginning area-of-interest is determined as interference region；
Step (5), the area-of-interest extracted to step (4) carry out statistics of histogram respectively, are tied according to statistics
Fruit divides oil smoke concentration grade, specifically:
By all pixels in region of interest area image, according to the size of gray value, the frequency of its appearance is counted；
Further according to the concentration scale quantity that needs divide, the pixel number in each gray scale interval, each gray scale are counted
The corresponding oil smoke that divides of pixel number in section is corresponding concentration scale.
Oil smoke concentration detection method of the invention, the influence of hardly examined distance is, it can be achieved that the non-of oil smoke concentration connects
Real-time detection is touched, has many advantages, such as high accuracy and real-time.
Processing module can choose the chip of model STM32, and the specific structure of blast velocity control module is known in this field
Common sense, this is no longer going to repeat them.
The present invention may be implemented that hearth region and human body working region is imaged, image by 180 ° of wide-angle lens
Processing module excludes the imaging picture in detection zone there are human body, and based on the initial picture for excluding human body into
The judgement of row oil smoke concentration has result accurate, oil smoke suction effect is good according to oil smoke concentration result controlled wind speed adjuster
Feature.
Visual imaging module is assemblied in smoke machine main body in the present embodiment, it should be noted that the installation of visual imaging module
Position is not limited to smoke machine main body in the present embodiment, can also the person's of being assemblied in smoke machine installation wall or be assemblied in around hearth
Or it is set to the peripheral location of other smoke machine main bodys, it can be to hearth corresponding position as long as can satisfy visual imaging module
Target area imaging.
Embodiment 2.
A kind of kitchen ventilator carrying out wind speed adjusting based on dual area Image Acquisition, other feature is same as Example 1, different
Place is: light compensating lamp is infrared light compensating lamp, and the optical source wavelength of infrared light compensating lamp is 940nm, and the power of infrared light compensating lamp is 6w.
The setting of infrared lamp can be irradiated imaging region in camera imaging, and infrared light compensating lamp can allow smog special
Sign is more preferably obvious, is more readily detected in vision.There is no smoke characteristics under infrared light compensating lamp irradiation condition unobvious.Infrared light filling
The on-off of lamp can be controlled by relay, and relay is electrically connected with processing module and is controlled by processing module.Experiment discovery, is adopted
It is best with infrared light compensating lamp effect.
Embodiment 3.
A kind of kitchen ventilator carrying out wind speed adjusting based on dual area Image Acquisition, other feature is same as Example 1, this reality
Oil smoke concentration in applying judges to carry out especially by following.
It is handled every time by the initial pictures of rear frame and the initial pictures of previous frame, when obtaining locating for rear frame initial pictures
The step process for the current kitchen fume concentration carved is as follows:
(1) initial pictures of rear frame and the initial pictures of previous frame frame difference is carried out to handle to obtain frame difference image；
(2) denoising is carried out to frame difference image in a manner of opening operation, obtains denoising image；
(3) edge detection is carried out to denoising image, marker motion region is as initial area-of-interest；
(4) gray average calculating is carried out to initial area-of-interest and segment smoothing degree calculates, it is equal gray scale will to be met simultaneously
The region of value and smoothness requirements is as next step area-of-interest, and other regions are as interference elimination；
(5) area-of-interest extracted to step (4) counts respectively, divides oil smoke concentration etc. according to statistical result
Grade.Statistical method can be statistics of histogram, also can choose other statistical methods.
In step (1), to collected initial pictures carry out frame difference operate to obtain frame difference image be specifically: image procossing mould
A later frame image is made the difference with previous frame image according to the sequencing of the initial pictures received, obtains dynamic area height by root tuber
Bright frame difference image.Due in the two field pictures of front and back static region be it is constant, (such as oil smoke drifts, and manpower is waved for dynamic area
Move) it is variation, so black is presented in static region after frame difference, the highlight bar of edge blurry is shown as after dynamic area frame difference
Domain, therefore the frame difference image highlighted by the available dynamic area of frame difference.
The target area of imaging device acquisition indicates that any one frame initial pictures are the imaging of corresponding region S with region S；
Initial pictures are made of m*n pixel.
The gray value of the pixel of frame initial pictures A is indicated afterwards with matrix A H, AH={ ahi,j, ahi,jFrame initial graph after representative
As the i-th row, the corresponding gray value of jth column pixel in A, i is the row where pixel, and j is the column where pixel, 1≤i≤m, 1≤j
≤n；The subregion in frame initial pictures A where the i-th row, jth column pixel is AS afterwardsi,j。
The gray value of the pixel of previous frame initial pictures B indicates with matrix B H, BH={ bhi,j, bhi,jRepresent previous frame initial graph
As the i-th row, the corresponding gray value of jth column pixel in B, the subregion in previous frame initial pictures B where the i-th row, jth column pixel is
BSi,j。
The grey scale pixel value of frame difference image D indicates with matrix D H, DH={ dhi,j}={ | ahi,j-bhi,j|, dhi,jIt represents
I-th row, the corresponding gray value of jth column pixel in frame difference image D, the subregion in frame difference image D where the i-th row, jth column pixel
For DSi,j；
In frame difference image, | dhi,j|=0 region is in black；|dhi,j| ≠ 0 region is in be highlighted.
After the operation of frame difference, (2) are entered step.Denoising is carried out using opening operation to frame difference image, obtains denoising image,
It is carried out especially by such as under type: etching operation first being carried out to frame difference image, to eliminate noise and the tiny spine in image, broken
Open narrow connection；Expansive working is carried out to the image after corrosion again, restores the obvious characteristic in former frame difference image.
Etching operation is carried out to frame difference image in step (2), is specifically comprised the following steps:
2-11 arbitrarily defines a convolution kernel θ；
Convolution kernel θ and frame difference image are carried out convolution by 2-12；When convolution kernel θ traverses frame difference image, convolution kernel institute is extracted
The pixel grey scale minimum value p of the convolution results and pixel C being overlapped with convolution kernel center in overlay area；
The gray scale of pixel C passes through Matrix C H={ ck,qIndicate, k, q are the row serial number and column serial number of pixel C,
Obtain the convolution results minimum value pixel matrix P obtained in convolution kernel θ traversal frame difference image process, minimum value
The gray scale of pixel matrix P passes through matrix PH={ pk,qIndicate；
The corresponding imparting pixel C of the gray scale of pixel matrix P is obtained corrosion image by 2-13.
Expansive working is carried out to corrosion image in step (2), is specifically comprised the following steps:
2-21 arbitrarily defines a convolution kernel β；
Convolution kernel β and corrosion image are carried out convolution by 2-22；When convolution kernel β traverses corrosion image, convolution kernel institute is extracted
The pixel grey scale maximum value o of the convolution results and pixel R being overlapped with convolution kernel center in overlay area；
The gray scale of pixel R passes through matrix RH={ rl,vIndicate, l, v are the row serial number and column serial number of pixel R,
Obtain the convolution results maximum value pixel matrix O obtained in convolution kernel β traversal corrosion image process, maximum value
The gray scale of pixel matrix O passes through matrix OH={ ol,vIndicate；
The corresponding imparting pixel R of the gray scale of maximum value pixel matrix O is obtained expanding image, obtained expansion by 2-13
Image is to denoise image.
Image noise can be eliminated using opening operation, the separating objects at very thin point, smooth biggish object boundary, simultaneously
Also it can guarantee that the area of highlight regions in original image is basically unchanged, guarantee that the accuracy of subsequent detection is unaffected.
Step (3) carries out edge detection to denoising image, and marker motion region is as initial area-of-interest, specifically:
Using wavelet transformation, the edge for detecting frame difference image highlight regions is simultaneously marked, using the region marked as initially feeling emerging
Interesting region.
Since the gray value of image border and the gray value of neighbor pixel can generate biggish gray value gradient, according to side
This feature of edge sets a filter, traverses frame difference image with the filter.Step (3) carries out as follows:
3-1 defines a filter Y, and filter is t*t matrix, and t is odd number.Filter selects odd matrix, to ensure
Only one central point, preferably 3*3 matrix, have the characteristics that calculation amount is small.
3-2 makes filter Y traversal denoising image, calculates filter and go where the central pixel point at each position
It makes an uproar the gray values of other pixels in the gray value and center pixel vertex neighborhood of image, and filter is calculated according to formula (I)
The edge detection value X of central pixel point at each positionz, z is label when filter Y traversal denoises image,
F, g is the matrix serial number of pixel, and 1≤f≤t, 1≤g≤t, e are pixel of the filter at each position
The gray value of the denoising image at place；α is weight coefficient, corresponding with filter location.
3-3, by central pixel point edge detection value X of the filter at each positionzWith center pixel vertex neighborhood its
The gray value of its pixel subtracts each other, and judges whether the absolute value of difference is greater than threshold value Δ；
Statistics is greater than the quantity of threshold value, if quantity is more thanDetermine the central pixel point pair of filter present position
The pixel position for the denoising image answered is marginal point, and is marked；
3-4, complete denoising image of filter traversal, obtains the markd marginal point of institute, obtains preliminary area-of-interest.
Because people is when cooking operation, hand can brandished always, can include oil smoke and manpower in the image after frame difference is complete
The interference region of the moving objects such as operation, needs the influence in exclusive PCR region, this is also before carrying out oil smoke concentration identification
Where the difficult point of the invention patent.
But the direction of motion of oil smoke has randomness, the direction of motion of manpower, slice is relatively unambiguous and feature is different,
Numerically performance is exactly that grey value difference is larger, thus:
1) oil smoke moving region is lower than the brightness of manpower, slice moving region on the image after frame difference, so corresponding oil
The gray value mean value in cigarette district domain is also below manpower, the gray average of slice moving region；
2) grey value profile of oil smoke moving region is relatively concentrated on the image after frame difference, and the moving region of manpower, slice
The gray value on boundary is larger compared with the jump of the central area in region, so the image in the region is not smooth enough, corresponding gray value
Variance is larger.
Using the two characteristics, step (4) is specifically to carry out gray average, segment smoothing to each initial area-of-interest
Degree calculates, and obtains the corresponding gray average of each initial area-of-interest and gray scale smoothness, and satisfaction simultaneously is calculated
Gray average is less than gray threshold, gray scale smoothness is less than the initial area-of-interest of gray scale smoothness threshold as region of interest
Other initial area-of-interests are determined as interference region by domain.
Gray threshold, gray scale smoothness threshold magnitude can flexible setting according to specific needs, details are not described herein.Step
Suddenly (4) complete the identification in oil smoke region and the exclusion of interference region.
The area-of-interest extracted in step (5) to step (4) carries out statistics of histogram respectively, is tied according to statistics
Fruit divides oil smoke concentration grade, specifically:
By all pixels in region of interest area image, according to the size of gray value, the frequency of its appearance is counted；
Further according to the concentration scale quantity that needs divide, 10 are taken as siding-to-siding block length, counts the pixel in each gray scale interval
Number is put, the corresponding oil smoke that divides of the pixel number in each gray scale interval is corresponding concentration scale.
It should be noted that the selection of siding-to-siding block length is not limited to 10, other quantity also can choose.
The criteria for classifying of oil smoke concentration can specifically be set, such as setting dense smoke, medium grade cigarette or low cigarette, specific value with
Subject to actual demand, details are not described herein.
The kitchen fume concentration detection method of the present embodiment provides one kind and is different from infrared projection method and physical measure
A kind of oil smoke concentration detection method.The kitchen fume concentration detection method based on image procossing, hardly examined distance
Influence, it can be achieved that oil smoke concentration non-contact real-time detection, have many advantages, such as high accuracy and real-time.Oil smoke concentration information
It is sent to blast velocity control module, wind speed adjusting is carried out according to the oil smoke concentration information controlled wind speed adjuster that processing module is sent,
Wind conditions can be accurately adjusted, oil smoke suction is effectively carried out.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention rather than protects to the present invention
The limitation of range, although the invention is described in detail with reference to the preferred embodiments, those skilled in the art should be managed
Solution, can with modification or equivalent replacement of the technical solution of the present invention are made, without departing from technical solution of the present invention essence and
Range.
Claims (10)
1. a kind of kitchen ventilator for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that
Smoke machine main body is provided with
Visual imaging module carries out continuous imaging to target area, and the Video stream information that picture is imaged is sent to processing mould
Block；Visual imaging module is provided with camera, and the camera is equipped with 180 ° of wide-angle lens, a part of vision of 180 ° of wide-angle lens
Region overlay hearth region, the human body working region of a part of visual zone covering hearth upper outer of 180 ° of wide-angle lens；
Image processing module receives the Video stream information for the imaging picture that visual imaging module is sent, is judged by frame difference method
As picture detection zone in whether have human body, if there is there are the images that human body then gives up the corresponding moment in detection zone
Piece does not have the imaging picture of human body as initial imaging picture using in the detection zone of reservation, is carried out according to initial imaging picture
Processing obtains oil smoke concentration information, by oil smoke concentration information conveyance to blast velocity control module；
Blast velocity control module carries out wind speed adjusting according to the oil smoke concentration information controlled wind speed adjuster that processing module is sent.
2. the kitchen ventilator according to claim 1 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that
Image processing module is handled based on picture is imaged, and imaging picture is grayscale image, imaging picture collected
It is serialized, the imaging picture of the imaging picture and previous frame that pass sequentially through rear frame carries out the processing of frame difference, obtains each rear frame imaging
The human motion target area of picture.
3. the kitchen ventilator according to claim 2 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that
Specific steps process is as follows:
1) handles the imaging picture of rear frame and the imaging picture of previous frame progress frame difference to obtain the frame difference figure for being used for human testing
Picture；
2) judges whether there is human motion mesh according to the gray average of each subregion of the frame difference image for human testing
Mark region.
4. the kitchen ventilator according to claim 3 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that
The target area of imaging device acquisition indicates that the imaging that picture is corresponding region S is imaged in any one frame with region S；
Imaging picture is made of m*n pixel,
The gray value of the pixel of frame imaging picture A is indicated afterwards with matrix A H, AH={ ahi,j, ahi,jPicture A is imaged in frame after representative
In the i-th row, the corresponding gray value of jth column pixel, i be pixel where row, j be pixel where column, 1≤i≤m, 1≤j≤
n；The subregion in frame imaging picture A where the i-th row, jth column pixel is AS afterwardsi,j；
The gray value of pixel of previous frame imaging picture B indicates with matrix B H, BH={ bhi,j, bhi,jRepresent previous frame imaging picture B
In the i-th row, the corresponding gray value of jth column pixel, the subregion in previous frame imaging picture B where the i-th row, jth column pixel is
BSi,j；
The grey scale pixel value of frame difference image D for human testing indicates with matrix D H, DH={ dhi,j}={ | ahi,j-bhi,j
|, dhi,jThe i-th row, the corresponding gray value of jth column pixel in the frame difference image D for human testing are represented, human testing is used for
Frame difference image D in subregion where the i-th row, jth column pixel be DSi,j。
5. the kitchen ventilator according to claim 4 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that institute
Stating step 2) is specifically: statistics is for gray value in the frame difference image D of human testing | dhi,jThe subregion of | > θ is as mobile human
Body target area, remaining regional determination are non-moving human region；
Wherein, θ is threshold value, and θ is more than or equal to 25.
6. the kitchen ventilator according to claim 5 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that θ
Equal to 30.
7. the kitchen ventilator according to claim 6 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that institute
It states visual imaging module and is additionally provided with light compensating lamp, the visual field range of the irradiation area covering camera of light compensating lamp, the light filling
The optical source wavelength of lamp is 850-980nm.
8. the kitchen ventilator according to claim 7 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that institute
Stating light compensating lamp is infrared light compensating lamp, and the optical source wavelength of infrared light compensating lamp is 940nm, and the power of infrared light compensating lamp is 6w.
9. the kitchen ventilator according to claim 8 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that figure
As processing module is handled based on picture initially is imaged, initial imaging picture collected is serialized, and is successively led to
Later the initial imaging picture of frame and the initial imaging picture of previous frame are handled, and are obtained each rear frame and are initially imaged locating for picture
The current kitchen fume concentration at moment；
It is handled every time by the initial imaging picture of the initial imaging picture of rear frame and previous frame, obtains the initial image of rear frame
The step process of the current kitchen fume concentration at moment locating for piece is as follows:
(1) the initial imaging picture of rear frame and the initial imaging picture of previous frame frame difference is carried out to handle to obtain frame difference image；
(2) denoising is carried out to frame difference image in a manner of opening operation, obtains denoising image；
(3) edge detection is carried out to denoising image, marker motion region is as initial area-of-interest；
(4) gray average calculating and segment smoothing degree is carried out to initial area-of-interest to calculate, will meet simultaneously gray average and
The region of smoothness requirements is as next step area-of-interest, and other regions are as interference elimination；
(5) area-of-interest extracted to step (4) counts respectively, divides oil smoke concentration grade according to statistical result.
10. the kitchen ventilator according to claim 9 for carrying out wind speed adjusting based on dual area Image Acquisition, which is characterized in that
In step (1), frame difference carried out to collected initial imaging picture operate to obtain frame difference image be specifically: image procossing mould
A later frame image is made the difference with previous frame image according to the sequencing of the initial imaging picture received, obtains dynamic area by root tuber
The highlighted frame difference image in domain；
The step (2) carries out denoising using opening operation to frame difference image, denoising image is obtained, especially by such as under type
It carries out: etching operation first being carried out to frame difference image and disconnects narrow connection to eliminate noise and the tiny spine in image；Again
Expansive working is carried out to the image after corrosion, restores the smoke characteristics in former frame difference image；
The step (3) carries out edge detection to denoising image, and marker motion region is as initial area-of-interest, specifically:
It detects the edge of frame difference image highlight regions and is marked, using the region marked as initial area-of-interest；
The step (4) is specifically to carry out gray average, the calculating of segment smoothing degree to each initial area-of-interest, is obtained each
The initial corresponding gray average of area-of-interest and gray scale smoothness will meet the gray average being calculated simultaneously and be less than gray scale
Threshold value, gray scale smoothness are less than the initial area-of-interest of gray scale smoothness threshold as area-of-interest, by other initial senses
Interest region is determined as interference region；
Step (5), the area-of-interest extracted to step (4) carry out statistics of histogram respectively, are drawn according to statistical result
Divide oil smoke concentration grade, specifically:
By all pixels in region of interest area image, according to the size of gray value, the frequency of its appearance is counted；
Further according to the concentration scale quantity that needs divide, the pixel number in each gray scale interval, each gray scale interval are counted
The corresponding oil smoke that divides of interior pixel number is corresponding concentration scale.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811152689.4A CN109028237A (en) | 2018-09-29 | 2018-09-29 | The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811152689.4A CN109028237A (en) | 2018-09-29 | 2018-09-29 | The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109028237A true CN109028237A (en) | 2018-12-18 |
Family
ID=64615527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811152689.4A Pending CN109028237A (en) | 2018-09-29 | 2018-09-29 | The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109028237A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109631111A (en) * | 2018-12-29 | 2019-04-16 | 佛山市云米电器科技有限公司 | It is a kind of that the automatic cigarette stove system that food data bank compares can be sought with health |
| CN109654560A (en) * | 2018-12-29 | 2019-04-19 | 佛山市云米电器科技有限公司 | It is a kind of can according to use oils carry out kitchen air quality assessment kitchen ventilator |
| CN109798566A (en) * | 2018-12-29 | 2019-05-24 | 佛山市云米电器科技有限公司 | A kind of and mobile united kitchen ventilator of video equipment |
| CN112902257A (en) * | 2021-02-05 | 2021-06-04 | 宁波方太厨具有限公司 | Control method and system for air volume of range hood, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0520563A (en) * | 1991-07-17 | 1993-01-29 | Hochiki Corp | Smoke detector using image processing |
| CN104501257A (en) * | 2014-12-23 | 2015-04-08 | 浙江大学宁波理工学院 | Automatic extractor hood speed regulating control method based on image analysis and automatic extractor hood speed regulating control system based on image analysis |
| CN106644542A (en) * | 2016-12-02 | 2017-05-10 | 宁波方太厨具有限公司 | Extractor hood extraction performance assessment method |
| CN108375095A (en) * | 2018-01-19 | 2018-08-07 | 青岛海尔智慧厨房电器有限公司 | A kind of control method and range hood of range hood |
| CN108534196A (en) * | 2018-03-08 | 2018-09-14 | 佛山市云米电器科技有限公司 | The cooking apparatus and its interlock method of noise reduction system and vision detection system linkage |
| CN108564091A (en) * | 2018-03-08 | 2018-09-21 | 佛山市云米电器科技有限公司 | Target area weak boundary extracting method and oil smoke concentration detection and interference elimination method |
| CN108563991A (en) * | 2018-03-08 | 2018-09-21 | 佛山市云米电器科技有限公司 | Kitchen fume concentration division methods and oil smoke concentration detection and interference elimination method |
-
2018
- 2018-09-29 CN CN201811152689.4A patent/CN109028237A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0520563A (en) * | 1991-07-17 | 1993-01-29 | Hochiki Corp | Smoke detector using image processing |
| CN104501257A (en) * | 2014-12-23 | 2015-04-08 | 浙江大学宁波理工学院 | Automatic extractor hood speed regulating control method based on image analysis and automatic extractor hood speed regulating control system based on image analysis |
| CN106644542A (en) * | 2016-12-02 | 2017-05-10 | 宁波方太厨具有限公司 | Extractor hood extraction performance assessment method |
| CN108375095A (en) * | 2018-01-19 | 2018-08-07 | 青岛海尔智慧厨房电器有限公司 | A kind of control method and range hood of range hood |
| CN108534196A (en) * | 2018-03-08 | 2018-09-14 | 佛山市云米电器科技有限公司 | The cooking apparatus and its interlock method of noise reduction system and vision detection system linkage |
| CN108564091A (en) * | 2018-03-08 | 2018-09-21 | 佛山市云米电器科技有限公司 | Target area weak boundary extracting method and oil smoke concentration detection and interference elimination method |
| CN108563991A (en) * | 2018-03-08 | 2018-09-21 | 佛山市云米电器科技有限公司 | Kitchen fume concentration division methods and oil smoke concentration detection and interference elimination method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109631111A (en) * | 2018-12-29 | 2019-04-16 | 佛山市云米电器科技有限公司 | It is a kind of that the automatic cigarette stove system that food data bank compares can be sought with health |
| CN109654560A (en) * | 2018-12-29 | 2019-04-19 | 佛山市云米电器科技有限公司 | It is a kind of can according to use oils carry out kitchen air quality assessment kitchen ventilator |
| CN109798566A (en) * | 2018-12-29 | 2019-05-24 | 佛山市云米电器科技有限公司 | A kind of and mobile united kitchen ventilator of video equipment |
| CN112902257A (en) * | 2021-02-05 | 2021-06-04 | 宁波方太厨具有限公司 | Control method and system for air volume of range hood, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109028226A (en) | The kitchen ventilator of oil smoke concentration judgement is carried out based on dual area Image Acquisition | |
| CN108596849B (en) | Single image defogging method based on sky region segmentation | |
| CN109028237A (en) | The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition | |
| JP4307496B2 (en) | Facial part detection device and program | |
| CN107347151B (en) | Binocular camera occlusion detection method and device | |
| JP6521845B2 (en) | Device and method for measuring periodic fluctuation linked to heart beat | |
| CN103702015B (en) | Exposure control method for human face image acquisition system under near-infrared condition | |
| CN109028232A (en) | A kind of band moves the kitchen ventilator and oil smoke concentration detection method of vision detection system | |
| CN109190624A (en) | Kitchen fume concentration detection method based on image procossing | |
| CN109447063A (en) | A kind of kitchen fume concentration detection method based on image procossing | |
| CN110390673B (en) | Cigarette automatic detection method based on deep learning in monitoring scene | |
| CN109084350A (en) | A kind of kitchen ventilator and oil smoke concentration detection method having filtering functions vision-based detection module | |
| CN111839519B (en) | Non-contact respiratory frequency monitoring method and system | |
| CN109028230A (en) | Have the stove and oil smoke concentration detection method of gesture control vision-based detection function | |
| CN109255326A (en) | A kind of traffic scene smog intelligent detecting method based on multidimensional information Fusion Features | |
| CN109028223A (en) | Have the kitchen ventilator and oil smoke concentration detection method of gesture control vision-based detection function | |
| CN106503651A (en) | A kind of extracting method of images of gestures and system | |
| Osma-Ruiz et al. | Segmentation of the glottal space from laryngeal images using the watershed transform | |
| CN109389604A (en) | A kind of kitchen fume image detection interference elimination method | |
| 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 | |
| CN112488165A (en) | Infrared pedestrian identification method and system based on deep learning model | |
| CN108827967A (en) | Oil smoke image-pickup method and oil smoke concentration detection and interference elimination method | |
| CN110111368B (en) | Human body posture recognition-based similar moving target detection and tracking method | |
| CN109089032A (en) | A kind of smog vision imaging device | |
| CN109373377A (en) | A kind of kitchen ventilator and oil smoke concentration detection method with fixed vision detection system |
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 |