CN106054627A - Control method and device based on gesture recognition and air conditioner - Google Patents
Control method and device based on gesture recognition and air conditioner Download PDFInfo
- Publication number
- CN106054627A CN106054627A CN201610410987.3A CN201610410987A CN106054627A CN 106054627 A CN106054627 A CN 106054627A CN 201610410987 A CN201610410987 A CN 201610410987A CN 106054627 A CN106054627 A CN 106054627A
- Authority
- CN
- China
- Prior art keywords
- gesture
- information
- fingers
- model
- hand direction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004378 air conditioning Methods 0.000 claims description 27
- 230000008878 coupling Effects 0.000 claims description 23
- 238000010168 coupling process Methods 0.000 claims description 23
- 238000005859 coupling reaction Methods 0.000 claims description 23
- 230000013011 mating Effects 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- User Interface Of Digital Computer (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a control method and device based on gesture recognition and an air conditioner. The control method comprises the following steps: obtaining a gesture image; extracting gesture information in the gesture image; carrying out pre-stored gesture model searching and comparison according to the gesture information to obtain a matched gesture model; and controlling a device to be controlled according to a control command corresponding to the matched gesture model, wherein the gesture information comprises the number of stretched fingers and/ or direction of fingers, and/or direction of the back of a hand. The method can realize gesture recognition with the number and direction of the fingers or palm direction of the hand being served as gesture judgment parameters, and can carry out recognition in a pattern manner without judgment of a lot of tracks, thereby greatly reducing gesture recognition complexity, and improving gesture recognition efficiency. The provided control device and the air conditioner comprising the device also have the advantages above.
Description
Technical field
The present invention relates to equipment control technical field, particularly relate to a kind of control method based on gesture identification, device and
Air-conditioning.
Background technology
Under the overall background of industry 4.0, machine vision development industrially is advanced by leaps and bounds, and gesture identification is in machine vision
Field is in occupation of the biggest proportion, it appears extremely important.Because gesture is the way the most convenient, the most natural of people and machine communication
Footpath.Traditional control method can not meet user more directly perceived, convenient, naturally require that.In the control of air-conditioning
All the more so, the demand controlling gesture is strong.
But generally use the movement locus control mode as control gesture, control gesture identification computationally intensive, gesture
Matching efficiency is low.
Summary of the invention
Based on this, it is necessary to in conventional art, gesture mates the problem that recall precision is low, it is provided that one can be effective
Shorten the control method based on gesture identification of gesture identification searching route, device and the air-conditioning comprising this device.
For realizing a kind of based on gesture identification the control method that the object of the invention provides, comprise the following steps:
Obtain images of gestures;
Extract the gesture information in described images of gestures;
Search, according to described gesture information, the gesture model that comparison prestores, obtain mating gesture model;
According to the control command that described coupling gesture model is corresponding, device to be controlled is controlled;
Wherein, described gesture information includes the quantity thrusted out one's fingers, and/or finger orientation, and/or the back of the hand direction.
As the embodiment of a kind of control method based on gesture identification, described device to be controlled is air-conditioning.
As the embodiment of a kind of control method based on gesture identification, described finger orientation includes vertical direction
Upper and lower both direction;Described the back of the hand direction includes the front and rear both direction of horizontal direction.
As the embodiment of a kind of control method based on gesture identification, described images of gestures is for adopt by video camera
One two field picture of collection.
As the embodiment of a kind of control method based on gesture identification, when described gesture information includes thrusting out one's fingers
Quantity, during two or more in finger orientation, and the back of the hand direction, when carrying out mating gesture model and searching, described in every kind
Gesture information searches comparison layer as a gesture information, uses the mode of layering successively to carry out institute according to different gesture informations
State the lookup of coupling gesture model.
As the embodiment of a kind of control method based on gesture identification, when described gesture information includes reaching
When the quantity, finger orientation and the back of the hand direction that refer to, the described gesture model prestored according to the lookup comparison of described gesture information, obtain
Coupling gesture model comprises the following steps:
It is identified described quantity, finger orientation and the back of the hand direction thrusted out one's fingers respectively setting, obtains current gesture
The quantity identity thrusted out one's fingers of image, finger orientation mark and the back of the hand direction signs or palm of the hand direction signs;
The quantity identity thrusted out one's fingers described, described finger orientation identify with described the back of the hand direction signs or palm of the hand side
It is combined according to preset order to mark, obtains described gesture information mark;
Described gesture information mark and the gesture information in the described gesture model prestored are identified layering compare,
To the coupling gesture model matched;
Wherein, every kind of described gesture information is that a gesture information searches comparison layer.
A kind of control device based on gesture identification based on same inventive concept, including:
Image collection module, is used for obtaining images of gestures;
Information extraction modules, for extracting the gesture information in described images of gestures;
Information comparison module, for searching, according to described gesture information, the gesture model that comparison prestores, obtains mating gesture
Model;
Control module, is controlled device to be controlled according to the control command that described coupling gesture model is corresponding;
Wherein, described gesture information includes the quantity thrusted out one's fingers, and/or finger orientation, and/or the back of the hand direction.
As a kind of embodiment controlling device based on gesture identification, described device to be controlled is air-conditioning.
As a kind of embodiment controlling device based on gesture identification, described finger orientation includes vertical direction
Upper and lower both direction;Described the back of the hand direction includes the front and rear both direction of horizontal direction.
As a kind of embodiment controlling device based on gesture identification, described gesture information includes thrusting out one's fingers
Quantity, two or more in finger orientation, and the back of the hand direction, when carrying out mating gesture model and searching, by every kind of described gesture
Information searches comparison layer, described information comparison module as a gesture information, uses the mode of layering successively according to different
Gesture information carries out the lookup of described coupling gesture model.
As a kind of embodiment controlling device based on gesture identification, described gesture information includes thrusting out one's fingers
Quantity, finger orientation and the back of the hand direction, described information comparison module includes:
Message identification submodule, for marking described quantity, finger orientation and the back of the hand direction thrusted out one's fingers respectively
Know set, obtain the quantity identity thrusted out one's fingers of current images of gestures, finger orientation mark and the back of the hand direction signs or
Palm of the hand direction signs;
Identifier combination submodule, identifies for the quantity identity thrusted out one's fingers described, described finger orientation with described hands
Back of the body direction signs or palm of the hand direction signs are combined according to preset order, obtain described gesture information mark;
Model Matching submodule, for by described gesture information mark and the gesture information in the described gesture model prestored
Mark layering is compared, and obtains the coupling gesture model matched;
Wherein, every kind of described gesture information is that a gesture information searches comparison layer.
The present invention also provides for a kind of air-conditioning simultaneously, is provided with control based on the gesture identification dress described in aforementioned any one
Put.
The beneficial effect comprise that a kind of based on gesture identification the control method that the present invention provides, pass through staff
Finger quantity, direction or palm of the hand direction judge that parameter carries out gesture identification as gesture, it can be by the form of figure
Be identified, and need not the judgement of substantial amounts of track, thus be substantially reduced gesture identification complexity, the most just can improve gesture
The efficiency identified is accordingly, rapider to the control meeting of the equipment such as air-conditioning by gesture.And, increase finger and direction
After parameter, it is possible to the quantity of the control gesture of utilization is more, it is possible to meet requirement.And during gesture information gathers, hands
Refer to that the change resolution of other gesture shapes relatively is higher.The control device based on gesture identification that present invention simultaneously provides, and
The air-conditioning comprising this device also has aforesaid advantage.
Accompanying drawing explanation
Fig. 1 is the schematic diagram utilizing gesture to be controlled air-conditioning;
Fig. 2 is the flow chart of a specific embodiment of a kind of control method based on gesture identification of the present invention;
Fig. 3 be a kind of control method based on gesture identification of the present invention a specific embodiment in gesture model kind divide
Schematic diagram;
Fig. 4 be a kind of control method based on gesture identification of the present invention a specific embodiment in carry out gesture model coupling
Flow chart;
Fig. 5 is the structural representation of a kind of specific embodiment controlling device based on gesture identification of the present invention;
Fig. 6 be a kind of control method based on gesture identification of the present invention a specific embodiment in information comparison module constitute
Schematic diagram.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing to the present invention's
Control method based on gesture identification, device and be provided with the specific embodiment party of air-conditioning controlling device based on gesture identification
Formula illustrates.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not used to limit this
Bright.
First, as it is shown in figure 1, the control method based on gesture identification of the present invention is to apply in control equipment.Wanting
After arranging the control method of the present invention in the equipment (air-conditioning 02 in Fig. 1) controlled, user 01 stands in before equipment the most permissible
Utilize some specific gestures that equipment is controlled.Heighten as controlled the temperature of air-conditioning, reduce, and the control air-conditioning that uses gesture
Close.Certainly, when equipment is controlled by gesture to be passed through, equipment itself can be configured with and control parts communication with it and be connected
Image acquisition equipment, such as photographic head.The gesture of user can be obtained by image acquisition equipment, and is transferred at device interior
Reason.Or some specific data are transferred to device interior after first image being carried out certain process by vision facilities self again
Control unit so that equipment is capable of identify that the gesture instruction of user, and according to gesture instruction, equipment is controlled.
As the photographic head being equipped with the ov2659 lens sensors that OmniVision company produces can be used in air-conditioning to make
For image acquisition equipment.
Concrete, an embodiment of present invention control method based on gesture identification, as in figure 2 it is shown, comprise the following steps:
S100, obtains images of gestures.
As long as images of gestures one two field picture obtained in the embodiment of the present invention is the most permissible, without continuous acquisition multiframe hands
Gesture image.The result that its follow-up each step is all based on a two field picture is carried out.Certainly, if for image information extraction
Necessary, it is possible to gather a frame background image in advance, in order to use the mode compared that the effective information in described images of gestures is entered
Row extracts.But the images of gestures used still is a two field picture.
It addition, the opportunity of the acquisition for equipment images of gestures, as a kind of embodiment, can arrange in a device away from
From sensor, when detecting in the range of certain distance, then open the gesture identification function of equipment (such as air-conditioning), and shoot and (obtain
Take) images of gestures.And the when of shooting described images of gestures, it is also possible to set when detecting in use reaches certain limit certain
Shoot after time.As detected, user arrived after in the range of one meter (distance can be according to specifically used scene settings), at 3 seconds
Start to shoot photo when of (it can also be provided that other times, as 5 seconds etc.).More preferably, can be continuously or at interval of one
Fix time (such as 0.5 second) shoot a pictures, using shooting one group of photo as the photo group currently carrying out gesture identification and right
Photo group selects, and definition is the highest, or the most obvious picture of hand shape image is as final images of gestures.
S200, extracts the gesture information in described images of gestures.
Described gesture information includes the quantity thrusted out one's fingers, and/or finger orientation, and/or the back of the hand direction.That is, can be independent
By the quantity thrusted out one's fingers as gesture information, it is possible to independent finger orientation or the back of the hand direction (or palm of the hand direction) are as gesture
Information.Wherein, the quantity thrusted out one's fingers includes 0,1,2,3,4,5, i.e. there are six different information, in gesture identification, typically
One information can a corresponding control action.Therefore, if only with the quantity thrusted out one's fingers as the gesture information extracted
Words, then can perform six kinds of controls by gesture to air-conditioning.And for using finger orientation as reference parameter, then can carry out
The quantity of control action to draw according to concrete division.Because, for direction, can be as required in the range of 360 degree between
Divide every certain angle.As divided an angle direction at interval of 30 degree, then mark off 12 different directions, the most merely
Use finger orientation as gesture information, equipment can be carried out control different in 12.
But, it is contemplated that the convenience of user operation and the accuracy of identification, the division of angle should not be the most intensive.Relatively
Good, can planar divide and angularly etc. separate 8 directions, it is simple to identify and operate.
The position that equipment is higher usually it is arranged on, for the back of the hand direction, it is also preferred that the left can wrap in view of image collecting device
Include four direction upper and lower, forward and backward.Wherein.Refer to the upper and lower of short transverse when user (people) is stood up and down.And be front and back
Refer to relative device distance (apart near for front or apart from remote for before can).
Certainly, in order to more preferably, more fully to equipment be controlled, the quantity that three kinds of parameters thrust out one's fingers, finger orientation,
And the back of the hand direction can optional two kinds be applied in combination.More preferably, it is possible to use three kinds of parameters to the ginseng as gesture identification simultaneously
Number.
Also, it should be noted corresponding with the back of the hand, in other embodiments, certainly may be used without the conduct of palm of the hand direction
The parameter of one gesture information, and replace aforesaid the back of the hand direction.It will be understood that the back of the hand direction and palm of the hand direction are in judgement side
The aspects such as formula are all essentially identical.
S300, searches, according to described gesture information, the gesture model that comparison prestores, and obtains mating gesture model.
It should be noted that after step S200 extracts gesture information, can first preserve in the buffer.And equipment prestores
Gesture model is typically stored in the storage chip of equipment.When comparing, can be used directly gesture information in caching with
Prestore compares.
S400, is controlled device to be controlled according to the control command that described coupling gesture model is corresponding.
After finding coupling gesture model, i.e. determine control equipment to be carried out, then can be by the control list of equipment
Equipment is controlled by unit's (main control chip).I.e. transmitting control commands is to the corresponding parts of equipment.
The control method based on gesture identification of the embodiment of the present invention, by finger quantity, direction or the palm of the hand of staff
As gesture, direction judges that parameter carries out gesture identification, it can be identified by the form of figure, and need not substantial amounts of rail
The judgement of mark, thus it is substantially reduced gesture identification complexity, the most just can improve the efficiency of gesture identification, accordingly, pass through
Gesture can be rapider to the control of the equipment such as air-conditioning.And, after increasing finger and directioin parameter, it is possible to the control hands of utilization
The quantity of gesture is more, it is possible to meet requirement.And during gesture information gathers, finger is relative to the change of other gesture shapes
Resolution is higher.
Wherein in the control method based on gesture identification of an embodiment, gesture information comprises finger orientation and also wraps
Containing the back of the hand direction or finger orientation.Wherein, finger orientation includes the upper and lower both direction of vertical direction.The two direction is easy to
User operates.And the image collecting device of general device is arranged on top position, and gather the image of its oblique front lower place,
Being analyzed acquired image when, finger orientation upwardly or downwardly can be easier to identification.The back of the hand direction or hands
Heart direction includes the front and rear both direction of horizontal direction.Equally, the image obtained for image collecting device, to fore-and-aft direction
The back of the hand position be easier to identification.Therefore, use finger up and down and before and after the back of the hand as in gesture identification parameter, especially finger
Mode down and before and after the back of the hand, faster, gesture identification is in hgher efficiency for image processing speed.
More preferably, when gesture information includes the quantity that thrusts out one's fingers, two or more in finger orientation, and the back of the hand direction
Time, when carrying out mating gesture model lookup, every kind of described gesture information is searched comparison layer as a gesture information, can adopt
Successively carry out mating the lookup of gesture model according to different gesture informations by the mode of layering.
When gesture information includes the quantity that thrusts out one's fingers, during two or more in finger orientation, and the back of the hand direction, accordingly
, the gesture model prestored also can comprise two or more parameter.And, when prestoring gesture model, multiple word bank can be divided to enter
Row storage is such as.Concrete, as shown in Figure 3, it is assumed that the quantity simultaneously select finger orientation, thrusting out one's fingers and the conduct of the back of the hand direction
The reference parameter of gesture, and finger orientation includes upper and lower two kinds, the back of the hand direction includes both front and back, the quantity bag thrusted out one's fingers
Include zero finger, a finger, two fingers, three fingers, four fingers and six kinds of five fingers.Therefore, the gesture after combination includes zero hands altogether
Refer to go forward (zero finger stretches out, finger orientation upwards, the back of the hand direction forward) ..., five fingers are gone forward;And before zero under finger
(zero finger stretches out, finger orientation downwards, the back of the hand direction forward) ..., under five fingers before, totally 24 kinds.Certainly, for zero finger
Situation about stretching out carrying out graphical analysis when with to have finger to stretch out slightly different.In other embodiments, can select to put
Abandon the gesture using zero finger to stretch out.As it can be seen, when carrying out the gesture model storage preset, can be first according to finger side
To difference gesture model is divided into two big classes and is stored in two different word banks.Thus carrying out coupling gesture model
Retrieval (lookup) time, the direction of finger can be first determined whether, it is judged that after completing then can further in corresponding word bank continue
Carry out the comparison of gesture model.In this example, it is judged that after complete finger orientation, continue to judge the side of the back of the hand in gesture information
To, and continue according to judged result in two less word banks, search the number that thrusts out one's fingers matched.So, in front two-layer
In the comparison of (finger orientation layer, the back of the hand direction layer), each comparison can get rid of the gesture model preset of half, and this is the most significantly
Shorten the time that coupling gesture model is searched, accelerate the progress of gesture identification.
It is pointed out that in the embodiment shown in Fig. 3, be finger orientation to be divided parameter as ground floor, by hands
Back of the body direction divides parameter as second time.In other embodiments, the back of the hand direction can be divided ginseng as ground floor completely
Number, divides parameter using finger orientation as two layers.Possibly even the number thrusted out one's fingers is divided parameter as ground floor, and
Finger orientation or the back of the hand direction are divided parameter as the second layer.
In another embodiment, gesture information also includes quantity, finger orientation and three kinds of the back of the hand direction thrusted out one's fingers.
It uses setting identification position, and the mode using flag to combine carries out mating comparison and the lookup of gesture model.Concrete,
In this embodiment, as shown in Figure 4, step S300, search the gesture model that prestores of comparison according to described gesture information, obtain
Tennis partner's potential model comprises the following steps:
S310, is identified the quantity thrusted out one's fingers, finger orientation and the back of the hand direction respectively setting, obtains current gesture
The quantity identity thrusted out one's fingers of image, finger orientation mark and the back of the hand direction signs or palm of the hand direction signs.
As two parameter values up and down for finger orientation fingerD can be respectively set to identify 1 and identify 0, i.e. judge
Go out finger orientation upwards time, then fingerD=1;And judge when finger orientation is downward, then fingerD=0.For the back of the hand side
Before and after trickD, two parameter values also may be set to 1 and 0, i.e. when judging that the back of the hand direction is forward, then trickD=1 sentences
Break the back of the hand direction backward time, then trickD=0.And for six parameter values 0 of number fingerC that thrusts out one's fingers, 1,2,3,
4,5,0,1,2,3,4,5 can be respectively set as, i.e. have a finger to stretch out, then fingerC=1, there are 6 fingers to stretch out, then
FingerC=6.
S320, the quantity identity thrusted out one's fingers described, described finger orientation mark with described the back of the hand direction signs or
Palm of the hand direction signs are combined according to preset order, obtain described gesture information mark.
Described preset order refers to, putting in order of mark.As for gesture " after on three fingers ", (three fingers stretch out
FingerC=3, finger orientation upwards fingerD=1 and the back of the hand direction trickD=0 backward), according to finger orientation, the back of the hand side
Can get gesture information to the order to the quantity that thrusts out one's fingers and be designated " 103 ".
S330, identifies described gesture information mark with the gesture information in the described gesture model prestored and compares,
Obtain the coupling gesture model matched.
Certainly, when using flag type gesture mode identification, described in the gesture model that prestores also be to deposit with flag
Storage, the combination of each flag just represents a kind of gesture, such as " 110 ", " 101 ", " 014 " etc..Carry out gesture model identification again
When to have only to carry out array comparison the most permissible, recognition efficiency is higher.
The AM3354 processor that Texas Instruments can be used to produce such as above-mentioned control method based on gesture identification,
Linux system is run.
Based on same inventive concept, also provide for a kind of control device based on gesture identification, owing to this system solves problem
Principle control method based on gesture identification to a kind of aforementioned method similar, therefore, the enforcement of this device can be according to aforementioned
The concrete steps of method realize, and repeat no more in place of repetition.
As it is shown in figure 5, the control device based on gesture identification of one of them embodiment, including image collection module 100,
Information extraction modules 200, information comparison module 300 and control module 400.
Wherein, image collection module 100, it is used for obtaining images of gestures;Information extraction modules 200, is used for extracting described hands
Gesture information in gesture image;Information comparison module 300, for searching, according to described gesture information, the gesture mould that comparison prestores
Type, obtains mating gesture model;Control module 400, according to control command corresponding to described coupling gesture model to be controlled
Equipment is controlled.
And the gesture information in the embodiment of the present invention includes the quantity that thrusts out one's fingers, and/or finger orientation, and/or the back of the hand
Direction.That is, described gesture information can by the one in the quantity thrusted out one's fingers, finger orientation and the back of the hand direction (palm of the hand direction) or
Two kinds or three kinds parameters of person are constituted.It is of course also possible to additionally also include some other parameter.
Judge that parameter carries out gesture identification by the finger quantity of staff, direction or palm of the hand direction as gesture, its energy
Enough be identified by the form of figure, and need not the judgement of substantial amounts of track, thus be substantially reduced gesture identification complexity,
The most just can improve the efficiency of gesture identification, accordingly, rapider to the control meeting of the equipment such as air-conditioning by gesture.And,
After increasing finger and directioin parameter, it is possible to the quantity of the control gesture of utilization is more, it is possible to meet requirement.And at gesture information
During collection, finger is higher relative to the change resolution of other gesture shapes.
The control device based on gesture identification of the present invention may be provided in the equipment such as air-conditioning, thus realizes the equipment such as air-conditioning
Gesture control.
Wherein in the control device based on gesture identification of an embodiment, described finger orientation includes vertical direction
Upper and lower both direction.Described the back of the hand direction includes the front and rear both direction of horizontal direction.Obtain according to image in general device
What fetching was put arranges position, easily determines the finger orientation of above-below direction and the back of the hand of fore-and-aft direction from acquired image
Direction.Therefore, use the finger orientation of above-below direction and the back of the hand direction of fore-and-aft direction as the judgement parameter energy of gesture identification
Enough improve the accuracy of gesture identification.
And the described images of gestures being used for gesture information extraction can be to be gathered by image capture device (such as video camera)
A two field picture.The control device based on gesture identification of the embodiment of the present invention can carry out sentencing of gesture by a two field picture
Disconnected, without multiple image is identified carrying out the identification of gesture simultaneously.And the gesture model prestored is the quiet of foundation
States model.Reduce the difficulty of gesture identification such that it is able to more rapid, carry out identification and the judgement of gesture accurately.
Wherein in an embodiment, use search and the identification of the mode type gesture model of flag.As gesture is believed
Breath includes quantity, finger orientation and three kinds of the back of the hand direction parameter thrusted out one's fingers.Then, as shown in Figure 6, information comparison module
300 include: message identification submodule 310, identifier combination submodule 320 and Model Matching submodule 330.
Wherein, message identification submodule 310, for respectively to described quantity, finger orientation and the back of the hand side thrusted out one's fingers
To being identified setting, obtain the quantity identity thrusted out one's fingers of current images of gestures, finger orientation mark and the back of the hand direction
Mark or palm of the hand direction signs;Identifier combination submodule 320, for the quantity identity thrusted out one's fingers described, described finger
Direction signs are combined according to preset order with described the back of the hand direction signs or palm of the hand direction signs, obtain described gesture letter
Breath mark;Model Matching submodule 330, for by described gesture information mark and the gesture letter in the described gesture model prestored
Breath mark is compared, and obtains the coupling gesture model matched.
The control device based on gesture identification of the embodiment of the present invention uses different flags to carry out design parameter value
Mark, and determine a complete gesture information in the way of flag combination.Thus carry out gesture model identification follow-up
Time have only to step-by-step and carry out the comparison of numeral or other identifiers.It also is able to improve the efficiency of gesture model identification.
It is preferred that when described gesture information includes the quantity that thrusts out one's fingers, two kinds in finger orientation, and the back of the hand direction with
Time upper, when carrying out mating gesture model lookup, every kind of described gesture information was searched comparison layer, institute as a gesture information
State information comparison module, use the mode of layering successively to carry out looking into of described coupling gesture model according to different gesture informations
Look for.
It should be noted that when carrying out layering and searching, described in the gesture mould model that prestores the most just be divided into many
Individual word bank carries out storing.After lookup starts, it is first determined the gesture model the possible correspondence of current gesture information should be at which
In individual big storehouse, and get rid of all of gesture model prestored in other storehouses.Carrying out next layer of lookup when, then the most true
Further determining that in fixed big storehouse in which word bank, making a look up the most in layer, gesture model searching route is short, speed
Degree is fast.
Meanwhile, also provide for a kind of air-conditioning, this air-conditioning is provided with the control based on gesture identification of aforementioned any embodiment
Device.Air-conditioning can be controlled by user by gesture.
It will appreciated by the skilled person that all or part of flow process realizing in above-described embodiment method can be led to
Crossing computer program and complete to instruct relevant hardware, described program can be stored in a computer read/write memory medium
In, this program is upon execution, it may include such as the flow process of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic
Dish, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access
Memory, RAM) etc..
Each technical characteristic of embodiment described above can combine arbitrarily, for making description succinct, not to above-mentioned reality
The all possible combination of each technical characteristic executed in example is all described, but, as long as the combination of these technical characteristics is not deposited
In contradiction, all it is considered to be the scope that this specification is recorded.
Embodiment described above only have expressed the several embodiments of the present invention, and it describes more concrete and detailed, but also
Therefore the restriction to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that, for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, it is also possible to make some deformation and improvement, these broadly fall into the guarantor of the present invention
Protect scope.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (12)
1. a control method based on gesture identification, it is characterised in that comprise the following steps:
Obtain images of gestures;
Extract the gesture information in described images of gestures;
Search, according to described gesture information, the gesture model that comparison prestores, obtain mating gesture model;
According to the control command that described coupling gesture model is corresponding, device to be controlled is controlled;
Wherein, described gesture information includes the quantity thrusted out one's fingers, and/or finger orientation, and/or the back of the hand direction.
Control method based on gesture identification the most according to claim 1, it is characterised in that described device to be controlled is
Air-conditioning.
Control method based on gesture identification the most according to claim 1, it is characterised in that described finger orientation includes hanging down
Nogata to upper and lower both direction;Described the back of the hand direction includes the front and rear both direction of horizontal direction.
Control method based on gesture identification the most according to claim 1, it is characterised in that described images of gestures is for passing through
One two field picture of camera acquisition.
Control method based on gesture identification the most according to claim 1, it is characterised in that described gesture information includes stretching
Going out the quantity of finger, two or more in finger orientation, and the back of the hand direction, when carrying out mating gesture model and searching, by every kind
Described gesture information searches comparison layer as a gesture information, uses the mode of layering successively to enter according to different gesture informations
The lookup of the described coupling gesture model of row.
Control method based on gesture identification the most according to claim 1, it is characterised in that described gesture information includes
Quantity, finger orientation and the back of the hand direction thrusted out one's fingers, the described gesture model prestored according to the lookup comparison of described gesture information,
Obtain mating gesture model to comprise the following steps:
It is identified described quantity, finger orientation and the back of the hand direction thrusted out one's fingers respectively setting, obtains current images of gestures
The quantity identity thrusted out one's fingers, finger orientation mark and the back of the hand direction signs or palm of the hand direction signs;
The quantity identity thrusted out one's fingers described, described finger orientation identify with described the back of the hand direction signs or palm of the hand direction sign
Know and be combined according to preset order, obtain described gesture information mark;
Described gesture information mark and the gesture information in the described gesture model prestored are identified layering compare, obtain phase
The coupling gesture model of coupling;
Wherein, every kind of described gesture information is that a gesture information searches comparison layer.
7. a control device based on gesture identification, it is characterised in that including:
Image collection module, is used for obtaining images of gestures;
Information extraction modules, for extracting the gesture information in described images of gestures;
Information comparison module, for searching, according to described gesture information, the gesture model that comparison prestores, obtains mating gesture model;
Control module, is controlled device to be controlled according to the control command that described coupling gesture model is corresponding;
Wherein, described gesture information includes the quantity thrusted out one's fingers, and/or finger orientation, and/or the back of the hand direction.
Control device based on gesture identification the most according to claim 7, it is characterised in that described device to be controlled is
Air-conditioning.
Control device based on gesture identification the most according to claim 7, it is characterised in that described finger orientation includes hanging down
Nogata to upper and lower both direction;Described the back of the hand direction includes the front and rear both direction of horizontal direction.
Control device based on gesture identification the most according to claim 7, it is characterised in that described gesture information includes
The quantity thrusted out one's fingers, two or more in finger orientation, and the back of the hand direction, when carrying out mating gesture model and searching, will be every
Plant described gesture information and search comparison layer, described information comparison module as a gesture information, use the mode of layering successively
The lookup of described coupling gesture model is carried out according to different gesture informations.
11. control devices based on gesture identification according to claim 7, it is characterised in that wrap in described gesture information
Including quantity, finger orientation and the back of the hand direction thrusted out one's fingers, described information comparison module includes:
Message identification submodule, for being identified setting to described quantity, finger orientation and the back of the hand direction thrusted out one's fingers respectively
Fixed, obtain the quantity identity thrusted out one's fingers of current images of gestures, finger orientation mark and the back of the hand direction signs or the palm of the hand
Direction signs;
Identifier combination submodule, identifies for the quantity identity thrusted out one's fingers described, described finger orientation with described the back of the hand side
It is combined according to preset order to mark or palm of the hand direction signs, obtains described gesture information mark;
Model Matching submodule, for by described gesture information mark and the gesture information mark in the described gesture model prestored
Layering is compared, and obtains the coupling gesture model matched;
Wherein, every kind of described gesture information is that a gesture information searches comparison layer.
12. 1 kinds of air-conditionings, it is characterised in that be provided with the control based on gesture identification described in any one of claim 7 to 11
Device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610410987.3A CN106054627B (en) | 2016-06-12 | 2016-06-12 | Control method and device based on gesture recognition and air conditioner |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610410987.3A CN106054627B (en) | 2016-06-12 | 2016-06-12 | Control method and device based on gesture recognition and air conditioner |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106054627A true CN106054627A (en) | 2016-10-26 |
CN106054627B CN106054627B (en) | 2020-02-11 |
Family
ID=57171054
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610410987.3A Active CN106054627B (en) | 2016-06-12 | 2016-06-12 | Control method and device based on gesture recognition and air conditioner |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106054627B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106789461A (en) * | 2016-12-12 | 2017-05-31 | 北京小米移动软件有限公司 | The method and device of intelligent home device connection |
CN106851937A (en) * | 2017-01-25 | 2017-06-13 | 触景无限科技(北京)有限公司 | A kind of method and device of gesture control desk lamp |
CN108131784A (en) * | 2017-12-21 | 2018-06-08 | 珠海格力电器股份有限公司 | Air conditioning control method, system and air-conditioning |
CN108131808A (en) * | 2017-12-08 | 2018-06-08 | 厦门瑞为信息技术有限公司 | Air conditioning control device and method based on classification gesture identification |
WO2020029489A1 (en) * | 2018-08-10 | 2020-02-13 | 珠海格力电器股份有限公司 | Home appliance control method centering on air conditioner |
CN110876077A (en) * | 2018-09-04 | 2020-03-10 | 深圳Tcl新技术有限公司 | Control method of smart television, mobile terminal and computer readable storage medium |
CN111290579A (en) * | 2020-02-10 | 2020-06-16 | Oppo广东移动通信有限公司 | Control method and device of virtual content, electronic equipment and computer readable medium |
CN113432281A (en) * | 2021-06-30 | 2021-09-24 | 珠海格力电器股份有限公司 | Equipment control method, device, equipment and storage medium |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1635455A (en) * | 2003-12-30 | 2005-07-06 | 上海科技馆 | Method for controlling virtual aquatic animal activity using gesture |
WO2008085788A2 (en) * | 2007-01-06 | 2008-07-17 | Apple Inc. | Detecting and interpreting real-world and security gestures on touch and hover sensitive devices |
CN102117117A (en) * | 2010-01-06 | 2011-07-06 | 致伸科技股份有限公司 | System and method for control through identifying user posture by image extraction device |
CN102236412A (en) * | 2010-04-30 | 2011-11-09 | 宏碁股份有限公司 | Three-dimensional gesture recognition system and vision-based gesture recognition method |
US20120060127A1 (en) * | 2010-09-06 | 2012-03-08 | Multitouch Oy | Automatic orientation of items on a touch screen display utilizing hand direction |
CN103375880A (en) * | 2012-04-27 | 2013-10-30 | 珠海格力电器股份有限公司 | Remote control device and method of air conditioner |
CN103488296A (en) * | 2013-09-25 | 2014-01-01 | 华为软件技术有限公司 | Somatosensory interaction gesture control method and somatosensory interaction gesture control device |
CN103699225A (en) * | 2013-12-17 | 2014-04-02 | 深圳市威富多媒体有限公司 | Method for interacting with mobile terminal through hand shape and device for implementing same |
US20140109023A1 (en) * | 2010-01-08 | 2014-04-17 | Microsoft Corporation | Assigning gesture dictionaries |
CN103777748A (en) * | 2012-10-26 | 2014-05-07 | 华为技术有限公司 | Motion sensing input method and device |
US20140257532A1 (en) * | 2013-03-05 | 2014-09-11 | Electronics And Telecommunications Research Institute | Apparatus for constructing device information for control of smart appliances and method thereof |
CN104252225A (en) * | 2013-06-27 | 2014-12-31 | 南京迈瑞生物医疗电子有限公司 | Motion control medical equipment and medical equipment motion control method |
US20150088282A1 (en) * | 2013-09-24 | 2015-03-26 | Fibar Group sp. z o. o. | Touch-less swipe control |
CN104866097A (en) * | 2015-05-22 | 2015-08-26 | 厦门日辰科技有限公司 | Hand-held signal output apparatus and method for outputting signals from hand-held apparatus |
CN105204351A (en) * | 2015-08-24 | 2015-12-30 | 珠海格力电器股份有限公司 | Air-conditioning unit control method and device |
CN105302302A (en) * | 2015-10-15 | 2016-02-03 | 广东欧珀移动通信有限公司 | Application control method and device |
CN105446481A (en) * | 2015-11-11 | 2016-03-30 | 周谆 | Gesture based virtual reality human-machine interaction method and system |
CN105549408A (en) * | 2015-12-31 | 2016-05-04 | 歌尔声学股份有限公司 | Wearable device and control method thereof, intelligent household server and control method thereof, and system |
CN105653029A (en) * | 2015-12-25 | 2016-06-08 | 乐视致新电子科技(天津)有限公司 | Method and system for obtaining immersion feel in virtual reality system as well as intelligent glove |
-
2016
- 2016-06-12 CN CN201610410987.3A patent/CN106054627B/en active Active
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1635455A (en) * | 2003-12-30 | 2005-07-06 | 上海科技馆 | Method for controlling virtual aquatic animal activity using gesture |
WO2008085788A2 (en) * | 2007-01-06 | 2008-07-17 | Apple Inc. | Detecting and interpreting real-world and security gestures on touch and hover sensitive devices |
CN102117117A (en) * | 2010-01-06 | 2011-07-06 | 致伸科技股份有限公司 | System and method for control through identifying user posture by image extraction device |
US20140109023A1 (en) * | 2010-01-08 | 2014-04-17 | Microsoft Corporation | Assigning gesture dictionaries |
CN102236412A (en) * | 2010-04-30 | 2011-11-09 | 宏碁股份有限公司 | Three-dimensional gesture recognition system and vision-based gesture recognition method |
US20120060127A1 (en) * | 2010-09-06 | 2012-03-08 | Multitouch Oy | Automatic orientation of items on a touch screen display utilizing hand direction |
CN103375880A (en) * | 2012-04-27 | 2013-10-30 | 珠海格力电器股份有限公司 | Remote control device and method of air conditioner |
CN103777748A (en) * | 2012-10-26 | 2014-05-07 | 华为技术有限公司 | Motion sensing input method and device |
US20140257532A1 (en) * | 2013-03-05 | 2014-09-11 | Electronics And Telecommunications Research Institute | Apparatus for constructing device information for control of smart appliances and method thereof |
CN104252225A (en) * | 2013-06-27 | 2014-12-31 | 南京迈瑞生物医疗电子有限公司 | Motion control medical equipment and medical equipment motion control method |
US20150088282A1 (en) * | 2013-09-24 | 2015-03-26 | Fibar Group sp. z o. o. | Touch-less swipe control |
CN103488296A (en) * | 2013-09-25 | 2014-01-01 | 华为软件技术有限公司 | Somatosensory interaction gesture control method and somatosensory interaction gesture control device |
CN103699225A (en) * | 2013-12-17 | 2014-04-02 | 深圳市威富多媒体有限公司 | Method for interacting with mobile terminal through hand shape and device for implementing same |
CN104866097A (en) * | 2015-05-22 | 2015-08-26 | 厦门日辰科技有限公司 | Hand-held signal output apparatus and method for outputting signals from hand-held apparatus |
CN105204351A (en) * | 2015-08-24 | 2015-12-30 | 珠海格力电器股份有限公司 | Air-conditioning unit control method and device |
CN105302302A (en) * | 2015-10-15 | 2016-02-03 | 广东欧珀移动通信有限公司 | Application control method and device |
CN105446481A (en) * | 2015-11-11 | 2016-03-30 | 周谆 | Gesture based virtual reality human-machine interaction method and system |
CN105653029A (en) * | 2015-12-25 | 2016-06-08 | 乐视致新电子科技(天津)有限公司 | Method and system for obtaining immersion feel in virtual reality system as well as intelligent glove |
CN105549408A (en) * | 2015-12-31 | 2016-05-04 | 歌尔声学股份有限公司 | Wearable device and control method thereof, intelligent household server and control method thereof, and system |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106789461A (en) * | 2016-12-12 | 2017-05-31 | 北京小米移动软件有限公司 | The method and device of intelligent home device connection |
CN106851937A (en) * | 2017-01-25 | 2017-06-13 | 触景无限科技(北京)有限公司 | A kind of method and device of gesture control desk lamp |
CN108131808A (en) * | 2017-12-08 | 2018-06-08 | 厦门瑞为信息技术有限公司 | Air conditioning control device and method based on classification gesture identification |
CN108131808B (en) * | 2017-12-08 | 2020-03-27 | 厦门瑞为信息技术有限公司 | Air conditioner control device and method based on hierarchical gesture recognition |
CN108131784A (en) * | 2017-12-21 | 2018-06-08 | 珠海格力电器股份有限公司 | Air conditioning control method, system and air-conditioning |
WO2020029489A1 (en) * | 2018-08-10 | 2020-02-13 | 珠海格力电器股份有限公司 | Home appliance control method centering on air conditioner |
CN110876077A (en) * | 2018-09-04 | 2020-03-10 | 深圳Tcl新技术有限公司 | Control method of smart television, mobile terminal and computer readable storage medium |
CN110876077B (en) * | 2018-09-04 | 2022-05-06 | 深圳Tcl新技术有限公司 | Control method of smart television, mobile terminal and computer readable storage medium |
CN111290579A (en) * | 2020-02-10 | 2020-06-16 | Oppo广东移动通信有限公司 | Control method and device of virtual content, electronic equipment and computer readable medium |
CN111290579B (en) * | 2020-02-10 | 2022-05-20 | Oppo广东移动通信有限公司 | Control method and device of virtual content, electronic equipment and computer readable medium |
CN113432281A (en) * | 2021-06-30 | 2021-09-24 | 珠海格力电器股份有限公司 | Equipment control method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106054627B (en) | 2020-02-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106054627A (en) | Control method and device based on gesture recognition and air conditioner | |
CN105518744B (en) | Pedestrian recognition methods and equipment again | |
CN106845357B (en) | A kind of video human face detection and recognition methods based on multichannel network | |
CN101477631B (en) | Method, equipment for extracting target from image and human-machine interaction system | |
CN104463117B (en) | A kind of recognition of face sample collection method and system based on video mode | |
CN105554385B (en) | A kind of remote multi-modal biological characteristic recognition methods and its system | |
KR101355974B1 (en) | Method and devices for tracking multiple object | |
JP5863423B2 (en) | Information processing apparatus, information processing method, and program | |
CN108197587A (en) | A kind of method that multi-modal recognition of face is carried out by face depth prediction | |
CN109117797A (en) | A kind of face snapshot recognition method based on face quality evaluation | |
CN101477626B (en) | Method for detecting human head and shoulder in video of complicated scene | |
CN103366154B (en) | Reconfigurable clear path detection system | |
CN108229277A (en) | Gesture identification, control and neural network training method, device and electronic equipment | |
KR20200041253A (en) | Binocular pedestrian detection system having dual-stream deep learning neural network and the methods of using the same | |
CN105825268A (en) | Method and system for data processing for robot action expression learning | |
JP3727798B2 (en) | Image surveillance system | |
CN105046206B (en) | Based on the pedestrian detection method and device for moving prior information in video | |
EP4174716A1 (en) | Pedestrian tracking method and device, and computer readable storage medium | |
CN106030610A (en) | Real-time 3D gesture recognition and tracking system for mobile devices | |
CN110414381A (en) | Tracing type face identification system | |
JP6109288B2 (en) | Information processing apparatus, information processing method, and program | |
CN109117753A (en) | Position recognition methods, device, terminal and storage medium | |
CN110032932A (en) | A kind of human posture recognition method based on video processing and decision tree given threshold | |
CN109297489A (en) | A kind of indoor navigation method based on user characteristics, electronic equipment and storage medium | |
CN109903339A (en) | A kind of video group personage's position finding and detection method based on multidimensional fusion feature |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |