CN109325969A - A kind of intelligence smoke machine hearth dynamic foreign matter detecting method - Google Patents

A kind of intelligence smoke machine hearth dynamic foreign matter detecting method Download PDF

Info

Publication number
CN109325969A
CN109325969A CN201811152673.3A CN201811152673A CN109325969A CN 109325969 A CN109325969 A CN 109325969A CN 201811152673 A CN201811152673 A CN 201811152673A CN 109325969 A CN109325969 A CN 109325969A
Authority
CN
China
Prior art keywords
pixel
image
foreign matter
initial pictures
frame
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
Application number
CN201811152673.3A
Other languages
Chinese (zh)
Inventor
陈小平
陈超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Foshan Viomi Electrical Technology Co Ltd
Original Assignee
Foshan Viomi Electrical Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Foshan Viomi Electrical Technology Co Ltd filed Critical Foshan Viomi Electrical Technology Co Ltd
Priority to CN201811152673.3A priority Critical patent/CN109325969A/en
Publication of CN109325969A publication Critical patent/CN109325969A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/254—Analysis of motion involving subtraction of images
    • 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
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • 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
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Processing (AREA)

Abstract

Intelligent smoke machine hearth dynamic foreign matter detecting method, intelligent smoke machine system are provided with visual imaging module, target area are imaged, and imaging picture is sent to processing module；Processing module receives the imaging picture that visual imaging module is sent and carries out mobile foreign matter judgement, and judging result is delivered to main control module；Kinematic system receives the control signal of main control module output, and cooking stove is driven to be collapsed or opened；Main control module is connect with visual imaging module, processing module and kinematic system respectively, and control visual imaging module is imaged, and the judging result information of receiving processing module output outputs control signals to kinematic system according to judging result information；When the defeated judging result information of processing module is there are when dynamic foreign matter, main control module output control information prevents cooking stove from transferring, and otherwise controls cooking stove decentralization.Can detection hearth regional space controls cooking stove decentralization with the presence or absence of foreign matter in cooking stove decentralization process again, have the characteristics that safe.

Description

A kind of intelligence smoke machine hearth dynamic foreign matter detecting method
Technical field
The present invention relates to cooking apparatus technical fields, more particularly to a kind of intelligent smoke machine hearth dynamic foreign bodies detection side Method.
Background technique
Cooking stove is one of indispensable kitchen appliance in people's life, in order to save space or need for other purposes It wants, formula cooking stove can be collapsed and enter people's lives.
Gathering formula cooking stove can be put in the use of hearth region when need to use, and collapse again after use.But It is that gathering formula cooking stove in the prior art does not have foreign bodies detection function, if there are different in hearth region in cooking stove decentralization process Object often will appear phenomena such as cooking stove damages.
Therefore, in view of the shortcomings of the prior art, to provide a kind of intelligent smoke machine hearth dynamic foreign matter detecting method existing to overcome Technical deficiency is very necessary.
Summary of the invention
A kind of intelligent smoke machine hearth dynamic foreign matter is provided it is an object of the invention to avoid the deficiencies in the prior art place Detection method, can detection hearth regional space controls cooking stove decentralization with the presence or absence of foreign matter in cooking stove decentralization process again, have The features such as safe.
The object of the present invention is achieved by the following technical measures.
A kind of intelligent smoke machine hearth dynamic foreign matter detecting method is provided, intelligent smoke machine hearth dynamic foreign matter detection system is passed through It carries out, intelligent smoke machine hearth dynamic foreign matter detection system is provided with
Visual imaging module, is imaged target area, and imaging picture is sent to processing module；
Processing module receives the imaging picture that visual imaging module is sent and carries out mobile foreign matter judgement, and judgement is tied Fruit is delivered to main control module；
Kinematic system receives the control signal of main control module output, and cooking stove is driven to be collapsed or opened；
Main control module is connect with visual imaging module, processing module and kinematic system respectively, control visual imaging module into Row imaging, the judging result information of receiving processing module output, outputs control signals to kinematic system according to judging result information；
When the defeated judging result information of processing module is there are when dynamic foreign matter, main control module output control information makes Cooking stove cannot transfer, and otherwise control cooking stove decentralization.
Preferably, above-mentioned intelligent smoke machine hearth dynamic foreign matter detecting method drives cooking stove to be transferred in kinematic system In the process, main control module control visual imaging module carries out imaging picture collection, and judging result is delivered to master control by processing module Module, main control module control the movement of kinematic system according to current judging result.
Preferably, above-mentioned intelligent smoke machine hearth dynamic foreign matter detecting method, processing module are acquired with visual imaging module Imaging picture is handled as initial pictures, and initial pictures are grayscale image, and initial pictures collected are serialized, and are successively led to Later the initial pictures of frame and the initial pictures of previous frame are handled, obtain it is each after frame initial pictures to correspond to the dynamic at moment different Object judging result；
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 of the dynamic foreign matter judging result at quarter 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) gray average is carried out to denoising image to count to obtain gray average；
(4) gray average is compared with threshold value, when gray average is greater than threshold value, judges that target area has dynamic Otherwise foreign matter judges no foreign matter.
Preferably, above-mentioned intelligent smoke machine hearth dynamic foreign matter detecting method, in step (1), to collected initial pictures Progress frame difference operates to obtain frame difference image:
Processing module makes the difference a later frame image with previous frame image according to the sequencing of the initial pictures received, Obtain the highlighted frame difference image in dynamic area.
Preferably, above-mentioned intelligent smoke machine hearth dynamic foreign matter detecting method, the step (2) use frame difference image and open fortune It calculates and carries out denoising, obtain denoising image, carried out especially by such as under type: etching operation first being carried out to frame difference image, with The noise in image and tiny spine are eliminated, narrow connection is disconnected；Expansive working is carried out to the image after corrosion again, restores former Obvious characteristic in frame difference image.
Preferably, above-mentioned intelligent smoke machine hearth dynamic foreign matter detecting method, the target area of visual imaging module acquisition with Region S indicates that any one frame initial pictures are the imaging of corresponding 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.
Preferably, above-mentioned intelligent smoke machine hearth dynamic foreign matter detecting method carries out corrosion behaviour to frame difference image in step (2) Make, specifically comprises the following steps:
2-11 arbitrarily defines a convolution kernel α；
Convolution kernel α and frame difference image are carried out convolution by 2-12；When convolution kernel α 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 α traversal frame difference image process, minimum value The gray scale of pixel matrix P passes through matrix PH={ pk,qIndicate；
Corresponding cover of the gray scale of pixel matrix P is given pixel C by 2-13, obtains corrosion image；
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；
Corresponding cover of the gray scale of maximum value pixel matrix O is given pixel R, obtains expanding image, obtained expansion by 2-13 Image is to denoise image.
Preferably, above-mentioned intelligent smoke machine hearth dynamic foreign matter detecting method, step (3) carry out gray average to denoising image Statistics is that the gray value summation for all pixels point for removing dryness image is obtained gray average divided by the number of pixel again；
Threshold value is 0.05 in step (4).
Preferably, above-mentioned intelligent smoke machine hearth dynamic foreign matter detecting method, the visual imaging module are provided with camera, phase Machine is equipped with wide-angle lens, the wide-angle lens towards hearth region, the wide angular range of the wide-angle lens be 180-210 °；
The visual imaging module is additionally provided with optical light filter；The optical light filter is assemblied in the wide-angle lens, The optical filter is the optical filter that can filter natural light；
It is additionally provided with infrared light compensating lamp, the optical source wavelength of the infrared light compensating lamp is 850-980nm.
The visual imaging module is assemblied in smoke machine main body or hearth or is assemblied in wall or is assemblied in bracket, furnace Stove folds the smoke machine collapsed in wall or gathering above hearth by kinematic system.
Intelligent smoke machine hearth dynamic foreign matter detecting method of the invention, is provided with visual imaging module, to target area into Row imaging, and imaging picture is sent to processing module；Processing module receives the imaging picture that visual imaging module is sent and goes forward side by side The mobile foreign matter judgement of row, and judging result is delivered to main control module；Kinematic system receives the control letter of main control module output Number, drive cooking stove to be collapsed or opened；Main control module connects with visual imaging module, processing module and kinematic system respectively It connects, control visual imaging module is imaged, the judging result information of receiving processing module output, defeated according to judging result information Signal is controlled out to kinematic system；When the defeated judging result information of processing module is there are when dynamic foreign matter, main control module is defeated Control information prevents cooking stove from transferring out, otherwise controls cooking stove decentralization.Hearth region can be detected in cooking stove decentralization process again Space controls cooking stove decentralization with the presence or absence of foreign matter, has the characteristics that safe.
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 the structural schematic diagram of the visual imaging module of embodiment 1.
Fig. 2 is the exploded view of Fig. 1.
Fig. 3 is a kind of structural schematic diagram of kitchen ventilator.
Fig. 4 is that kinematic system drives the schematic diagram of cigarette stove in opened condition.
Fig. 5 is the schematic diagram that kinematic system drives cigarette stove progress collapse state.
Fig. 6 is the schematic diagram that kinematic system drives cigarette stove in collapsed state.
In Fig. 1 into Fig. 6, comprising:
Visual imaging module 1,
Camera lens 121, expansion bracket 122, mounting seat 123,
Sensitive chip 124, pcb board 125,
Optical filtering portion 11,
Light compensating lamp 2,
Smoke machine main body 3,
Cooking stove 500,
Stand 600.
Specific embodiment
The invention will be further described with the following Examples.
Embodiment 1.
A kind of intelligence smoke machine hearth dynamic foreign matter detecting method, by intelligent smoke machine hearth dynamic foreign matter detection system into Row, intelligent smoke machine hearth dynamic foreign matter detection system are provided with
Visual imaging module, is imaged target area, and imaging picture is sent to processing module；
Processing module receives the imaging picture that visual imaging module is sent and carries out mobile foreign matter judgement, and judgement is tied Fruit is delivered to main control module；
Kinematic system receives the control signal of main control module output, and cooking stove is driven to be collapsed or opened；
Main control module is connect with visual imaging module, processing module and kinematic system respectively, control visual imaging module into Row imaging, the judging result information of receiving processing module output, outputs control signals to kinematic system according to judging result information；
When the defeated judging result information of processing module is there are when dynamic foreign matter, main control module output control information makes Cooking stove cannot transfer, and otherwise control cooking stove decentralization.
During kinematic system drives cooking stove to be transferred, main control module controls visual imaging module and carries out image Judging result is delivered to main control module by piece acquisition, processing module, and main control module controls kinetic system according to current judging result The movement of system.
Wherein, as shown in Figure 1 and Figure 2, visual imaging module 1 is provided with camera, and camera is equipped with wide-angle lens 121, wide-angle Camera lens 121 is towards targeted imaging region, that is, hearth region.
Wherein, the wide angular range of wide-angle lens 121 is 180-210 °.Wide-angle lens 121 can be set to monocular camera lens or Binocular head.The setting of wide-angle lens 121 can obtain more preferably comprehensive target object image.
The camera is additionally provided with optical light filter, and optical light filter is assemblied in wide-angle lens 121.Specifically, optical filter is The optical filter of natural light can be filtered.
The wide-angle of camera lens 121 is bigger, and collected targeted imaging region information is more, but the invalid information in image simultaneously Also can be more, very big interference, such as color, inverted image, reflective, distortion, noise can be caused to judgement, it is high to acquisition in order to exclude The interference of quality image is equipped with optical light filter by wide-angle lens 121, most of natural light is filtered off, thus the external world The interference such as environment light and inverted image are all filtered, and the pullous gray level image of acquired image is made.
Specifically, as shown in Fig. 2, smog vision imaging device 1 is provided with wide-angle lens 121, for stretching for focal length to be arranged Contracting frame 122, mounting seat 123, sensitive chip 124 and pcb board 125,121 fixing assembling of wide-angle lens are stretched in expansion bracket 122 Frame 122 is assemblied in mounting seat 123, and sensitive chip 124 is welded in pcb board 125, and mounting seat 123 is assemblied in pcb board 125, filter Mating plate 11 is assemblied in the top of sensitive chip 124, is successively camera lens 121, expansion bracket 122, mounting seat 123, filter from top to bottom Mating plate 11, sensitive chip 124 and pcb board 125.
It should be noted that sensitive chip 124 of the invention is common knowledge, as long as realizing that light captures and is converted to electronics The function of signal can serve as sensitive chip 124 of the invention, therefore the model of sensitive chip 124 is not repeated herein.
It should be noted that visual imaging module can be assemblied in hearth or be assemblied in wall or be assemblied in above hearth Smoke machine or be assemblied in bracket.As long as can be realized the position to target area imaging.
In addition, the intelligence smoke machine is additionally provided with infrared light compensating lamp 2, the optical source wavelength of infrared light compensating lamp 2 is 850-980nm.
It is preferred that 2 optical source wavelength of infrared light compensating lamp is 940nm, light compensating lamp 2 is set as the lamp group of 6W power.
By the infrared light compensating lamp 2 for 850-980nm wavelength of arranging in pairs or groups, so that Infrared irradiation is in target area, wide-angle lens The region of 121 pairs of light source light-illuminatings by light compensating lamp 2 carries out Image Acquisition, keeps the image information captured more obvious clear It is clear, and further improve the distance range of acquisition.
It should be noted that the position of light compensating lamp 2 can be set in the shell body position of visual imaging module, can also set It is placed in the smoke machine main body 33 installed when visual imaging module use, also can be set in wall or by other sides such as brackets Formula positioning.
Attached drawing 3 illustrates visual imaging module, light compensating lamp 2 is mounted on the structure of smoke machine main body 3, can in actual use With flexible setting according to specific needs.
Visual imaging module is for being imaged target area, and processing module is for carrying out image procossing.Processing module Judged with mobile foreign matter is carried out, and judging result is delivered to main control module.
Processing module can realize that this technology is general knowledge known in this field, and details are not described herein by the chip of STM32.
Cooking stove 500 is folded by kinematic system and is collapsed, smoke machine of the foldable gathering in wall or gathering above hearth. Attached drawing 4 to 6 illustrates a kind of fold and collapses in the structural schematic diagram of the kinematic system of wall, and kinematic system is usually provided with stand 600 and driving motor, driving motor driving cooking stove 500 carries out 90 degree and rotates to withdraw again to be folded to wall.
There are many modes for the structure of kinematic system, stand can also be driven far from hearth by driving motor, will be on stand Cooking stove 500 be retracted in the object of the top of cooking stove 500, in kitchen ventilator.Two ways only is enumerated herein, it is no longer superfluous herein It states.
The intelligence smoke machine hearth dynamic foreign matter detecting method, it is main during kinematic system drives cooking stove to be transferred Control module control visual imaging module carries out imaging picture collection, and judging result is delivered to main control module, master control by processing module Module controls the movement of kinematic system according to current judging result.
Specifically, processing module is handled using the imaging picture that visual imaging module acquires as initial pictures, initially Image is grayscale image, and initial pictures collected are serialized, and passes sequentially through the initial pictures of rear frame and the initial pictures of previous frame It is handled, obtains the dynamic foreign matter judging result that each rear frame initial pictures correspond to the moment；
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 of the dynamic foreign matter judging result at quarter 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) gray average is carried out to denoising image to count to obtain gray average；
(4) gray average is compared with threshold value, when gray average is greater than threshold value, judges that target area has dynamic Otherwise foreign matter judges no foreign matter.
In step (1), to collected initial pictures carry out frame difference operate to obtain frame difference image be specifically:
Processing module makes the difference a later frame image with previous frame image according to the sequencing of the initial pictures received, Obtain the highlighted frame difference image in dynamic area.
The target area of visual imaging module acquisition indicates with region S, any one frame initial pictures for corresponding region S at Picture；
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.
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 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 α；
Convolution kernel α and frame difference image are carried out convolution by 2-12；When convolution kernel α 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 α traversal frame difference image process, minimum value The gray scale of pixel matrix P passes through matrix PH={ pk,qIndicate；
Corresponding cover of the gray scale of pixel matrix P is given pixel C by 2-13, obtains corrosion image；
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；
Corresponding cover of the gray scale of maximum value pixel matrix O is given pixel R, obtains expanding image, obtained expansion by 2-13 Image is to denoise image.
It is that will remove dryness the gray value summation of all pixels point of image that step (3), which carries out gray average statistics to denoising image, Gray average is obtained divided by the number of pixel again；Threshold value is 0.05 in step (4).
Main control module is connect with visual imaging module, processing module and kinematic system respectively, control visual imaging module into Row imaging, the judging result information of receiving processing module output, outputs control signals to kinematic system according to judging result information； When the defeated judging result information of processing module be there are when dynamic foreign matter, main control module output control information prevent cooking stove from Otherwise decentralization controls cooking stove decentralization.
The present invention can ensure not will receive foreign matter damage in cigarette stove decentralization process, have the characteristics that using safe.
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 (9)

1. a kind of intelligence smoke machine hearth dynamic foreign matter detecting method, which is characterized in that examined by intelligent smoke machine hearth dynamic foreign matter Examining system carries out, and intelligent smoke machine hearth dynamic foreign matter detection system is provided with
Visual imaging module, is imaged target area, and imaging picture is sent to processing module；
Processing module receives the imaging picture that visual imaging module is sent and carries out mobile foreign matter judgement, and judging result is defeated It send to main control module；
Kinematic system receives the control signal of main control module output, and cooking stove is driven to be collapsed or opened；
Main control module is connect with visual imaging module, processing module and kinematic system respectively, control visual imaging module carry out at Picture, the judging result information of receiving processing module output, outputs control signals to kinematic system according to judging result information；
When the defeated judging result information of processing module is there are when dynamic foreign matter, main control module output control information makes cooking stove It cannot transfer, otherwise control cooking stove decentralization.
2. intelligent smoke machine hearth dynamic foreign matter detecting method according to claim 1, which is characterized in that drive cooking stove in kinematic system During being transferred, main control module control visual imaging module carries out imaging picture collection, and processing module is by judging result It is delivered to main control module, main control module controls the movement of kinematic system according to current judging result.
3. according to the intelligent smoke machine hearth dynamic foreign matter detecting method of claim 2, which is characterized in that processing module is with visual imaging The imaging picture of module acquisition is handled as initial pictures, and initial pictures are grayscale image, and initial pictures collected are by sequence The initial pictures of columnization, the initial pictures and previous frame that pass sequentially through rear frame are handled, and it is corresponding to obtain each rear frame initial pictures The dynamic foreign matter judging result at moment；
It is handled every time by the initial pictures of rear frame and the initial pictures of previous frame, obtains the moment locating for rear frame initial pictures The step process of dynamic foreign matter judging result 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) gray average is carried out to denoising image to count to obtain gray average；
(4) gray average is compared with threshold value, when gray average is greater than threshold value, it is different judges that target area has dynamic Otherwise object judges no foreign matter.
4. intelligence smoke machine hearth dynamic foreign matter detecting method according to claim 3, which is characterized in that right in step (1) Collected initial pictures progress frame difference operates to obtain frame difference image:
A later frame image is made the difference with previous frame image, is obtained according to the sequencing of the initial pictures received by processing module The highlighted frame difference image in dynamic area.
5. intelligence smoke machine hearth dynamic foreign matter detecting method according to claim 2, which is characterized in that the step (2) Denoising is carried out using opening operation to frame difference image, denoising image is obtained, is carried out especially by such as under type: first to frame difference figure Narrow connection is disconnected as carrying out etching operation to eliminate noise and the tiny spine in image；Again to the image after corrosion into Row expansive working restores the obvious characteristic in former frame difference image.
6. intelligent smoke machine hearth dynamic foreign matter detecting method according to claim 5, which is characterized in that
The target area of visual imaging module 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 pictures A 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 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 pictures B In the i-th row, the corresponding gray value of jth column pixel, 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,jRepresent frame difference figure As the i-th row, the corresponding gray value of jth column pixel in D, the subregion in frame difference image D where the i-th row, jth column pixel is DSi,j；
In frame difference image, | dhi,j|=0 region is in black；|dhi,j| ≠ 0 region is in be highlighted.
7. intelligence smoke machine hearth dynamic foreign matter detecting method according to claim 6, it is characterised in that: right in step (2) Frame difference image carries out etching operation, specifically comprises the following steps:
2-11 arbitrarily defines a convolution kernel α；
Convolution kernel α and frame difference image are carried out convolution by 2-12；When convolution kernel α traverses frame difference image, extracts convolution kernel and covered The pixel grey scale minimum value p of the convolution results and pixel C being overlapped with convolution kernel center in region；
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 α traversal frame difference image process, minimum value pixel The gray scale of dot matrix P passes through matrix PH={ pk,qIndicate；
Corresponding cover of the gray scale of pixel matrix P is given pixel C by 2-13, obtains corrosion image；
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, extracts convolution kernel and covered The pixel grey scale maximum value o of the convolution results and pixel R being overlapped with convolution kernel center in region；
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 pixel The gray scale of dot matrix O passes through matrix OH={ ol,vIndicate；
Corresponding cover of the gray scale of maximum value pixel matrix O is given pixel R, obtains expanding image, obtained expanding image by 2-13 As denoise image.
8. intelligence smoke machine hearth dynamic foreign matter detecting method according to claim 7, it is characterised in that:
It is to remove the gray value summation for all pixels point for removing dryness image again that step (3), which carries out gray average statistics to denoising image, Gray average is obtained with the number of pixel；
Threshold value is 0.05 in step (4).
9. intelligence smoke machine hearth dynamic foreign matter detecting method according to claim 8, it is characterised in that: the visual imaging Module is provided with camera, and camera is equipped with wide-angle lens, and the wide-angle lens is towards hearth region, the wide-angle of the wide-angle lens Range is 180-210 °；
The visual imaging module is additionally provided with optical light filter；The optical light filter is assemblied in the wide-angle lens, described Optical filter is the optical filter that can filter natural light；
It is additionally provided with infrared light compensating lamp, the optical source wavelength of the infrared light compensating lamp is 850-980nm.
The visual imaging module is assemblied in smoke machine main body or hearth or is assemblied in wall or is assemblied in bracket, and cooking stove is logical It crosses kinematic system and folds the smoke machine collapsed in wall or gathering above hearth.
CN201811152673.3A 2018-09-29 2018-09-29 A kind of intelligence smoke machine hearth dynamic foreign matter detecting method Pending CN109325969A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811152673.3A CN109325969A (en) 2018-09-29 2018-09-29 A kind of intelligence smoke machine hearth dynamic foreign matter detecting method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811152673.3A CN109325969A (en) 2018-09-29 2018-09-29 A kind of intelligence smoke machine hearth dynamic foreign matter detecting method

Publications (1)

Publication Number Publication Date
CN109325969A true CN109325969A (en) 2019-02-12

Family

ID=65265187

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811152673.3A Pending CN109325969A (en) 2018-09-29 2018-09-29 A kind of intelligence smoke machine hearth dynamic foreign matter detecting method

Country Status (1)

Country Link
CN (1) CN109325969A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN207019134U (en) * 2017-06-21 2018-02-16 广东万和热能科技有限公司 Range hood
CN108535287A (en) * 2018-03-29 2018-09-14 多科智能装备（常熟）有限公司 Based on X-Ray imaging techniques foreign matter detection system, method and device
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
CN108548199A (en) * 2018-03-08 2018-09-18 佛山市云米电器科技有限公司 A kind of intelligent fume exhauster wind speed is adjusted a wage scale method and device
CN108561931A (en) * 2018-07-02 2018-09-21 珠海格力电器股份有限公司 Smoke guide plate control method and device, range hood and readable storage medium
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

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN207019134U (en) * 2017-06-21 2018-02-16 广东万和热能科技有限公司 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
CN108548199A (en) * 2018-03-08 2018-09-18 佛山市云米电器科技有限公司 A kind of intelligent fume exhauster wind speed is adjusted a wage scale method and device
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
CN108535287A (en) * 2018-03-29 2018-09-14 多科智能装备（常熟）有限公司 Based on X-Ray imaging techniques foreign matter detection system, method and device
CN108561931A (en) * 2018-07-02 2018-09-21 珠海格力电器股份有限公司 Smoke guide plate control method and device, range hood and readable storage medium

Similar Documents

Publication Publication Date Title
JP4895797B2 (en) Wrinkle detection device, wrinkle detection method and program
US20090240108A1 (en) Capsule endoscopy system and method of controlling operation of capsule endoscope
CN108918519A (en) A kind of cell smear image obtains and analysis system
EP1329850A3 (en) Apparatus, program and method for detecting both stationary objects and moving objects in an image
CN104434022B (en) For carrying out the optics array system and method for pupil tracing with reflex reflection
KR20160050755A (en) Electronic Device and Method for Recognizing Iris by the same
CN103312972B (en) Electronic installation and its its focalization method
CN111583193B (en) Pistachio nut framework extraction device based on geometric contour template matching and algorithm thereof
CN115205278B (en) Electric automobile chassis scratch detection method and system
CN110166648A (en) A kind of camera detection locking means and device based on optical imagery
CN105973900A (en) Defect detection system and detection method for solar cell component
CN106993158A (en) A kind of active infrared night-viewing DAS (Driver Assistant System) based on image restoration
CN109325969A (en) A kind of intelligence smoke machine hearth dynamic foreign matter detecting method
CN107277383A (en) Optical detection apparatus and its synchronization adjustment method
WO2002061672A3 (en) System and method for extracting a point of interest of an object in front of a computer controllable display captured by an imaging device
CN106934349A (en) Dual camera is imaged and iris capturing identification integration apparatus
CN108055513A (en) Panoramic video security monitoring device
CN109089032A (en) A kind of smog vision imaging device
CN109389075B (en) Intelligent smoke machine lens fuzzy self-checking method
CN105954295A (en) Helmet top facing defect detection system and method
CN201440274U (en) Target detection equipment and image acquisition device used by same
JP4457077B2 (en) Obstacle detection system and obstacle detection method
CN109373378B (en) Cooking bench foreign matter detecting system and smoke ventilator with same
CN1664848A (en) Non-contact type self-feedback iris image acquisition device
CN208255900U (en) A kind of micro- expression acquisition device of human face

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