CN106851937A - A kind of method and device of gesture control desk lamp - Google Patents
A kind of method and device of gesture control desk lamp Download PDFInfo
- Publication number
- CN106851937A CN106851937A CN201710061195.4A CN201710061195A CN106851937A CN 106851937 A CN106851937 A CN 106851937A CN 201710061195 A CN201710061195 A CN 201710061195A CN 106851937 A CN106851937 A CN 106851937A
- Authority
- CN
- China
- Prior art keywords
- gesture
- user
- desk lamp
- feature data
- gesture feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention provides a kind of method and device of gesture control desk lamp, wherein, the method includes:When desk lamp is in gesture control pattern, the image of at least one gesture that collection user makes in the image acquisition region of desk lamp;The gesture feature data of the image zooming-out user according to collection;Determine the corresponding desk lamp control signal of gesture feature data of user;Desk lamp is controlled to perform corresponding function according to desk lamp control signal.In the present invention, when desk lamp is in gesture control pattern, the gesture according to the user to gathering is identified, to control desk lamp to perform corresponding function, so so that user's control desk lamp becomes very convenient.
Description
Technical field
The present invention relates to desk lamp and technical field of hand gesture recognition, in particular to a kind of method of gesture control desk lamp
And device.
Background technology
With the development of society, desk lamp more and more appeared in daily life, also, desk lamp work(
Can be also more and more, such as, present desk lamp can be used to gather image, play audio or video etc., the function of desk lamp
More, the controlling switch on desk lamp is also more.
In the prior art, when user is in the parameter such as certain function using desk lamp or the brightness, the sound that adjust desk lamp,
User is generally required to be switched with the button switch or touch control that hand goes to touch on desk lamp, but, the position that user sits sometimes
Farther out, or user has water or oil stain etc. to potential range desk lamp on hand, it has not been convenient to go to touch the switch of desk lamp.
The content of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of method and device of gesture control desk lamp, to solve
Certainly in the prior art, switched using the button switch on desk lamp or touch control, it has not been convenient to the problem of user's control desk lamp.
In a first aspect, a kind of method of gesture control desk lamp is the embodiment of the invention provides, wherein, the method includes:
When desk lamp is in gesture control pattern, user makes in the image acquisition region of the desk lamp at least one is gathered
The image of individual gesture;
Described image according to collection extracts the gesture feature data of the user;
Determine the corresponding desk lamp control signal of gesture feature data of the user;
The desk lamp is controlled to perform corresponding function according to the desk lamp control signal.
With reference in a first aspect, the embodiment of the invention provides the first possible implementation of above-mentioned first aspect, its
In, the corresponding desk lamp control signal of gesture feature data for determining the user, including:
By each the gesture feature number in the gesture feature data of the user and the gesture feature information bank for pre-building
According to being matched;
The corresponding desk lamp control signal of the gesture feature data of the user is determined according to matching result.
With reference to the first possible implementation of first aspect, the of above-mentioned first aspect is the embodiment of the invention provides
Two kinds of possible implementations, wherein, the gesture feature data by the user and the gesture feature information for pre-building
Gesture feature data in storehouse are matched, including:
Calculate each gesture feature data in the gesture feature data of the user and the gesture feature information bank it
Between Euclidean distance;
Determined according to the Euclidean distance every in the gesture feature data of the user and the gesture feature information bank
The matching result of individual gesture feature data.
With reference in a first aspect, the embodiment of the invention provides the third possible implementation of above-mentioned first aspect, its
In, the corresponding desk lamp control signal of gesture feature data for determining the user, including:
The gesture feature data of the user are entered with each the gesture feature data in the gesture database for pre-building
Row matching;
The gesture mark of the user is determined according to matching result;
Gesture mark and the gesture identification database for pre-building according to the user, determine the gesture mark of the user
Know corresponding desk lamp control signal.
With reference in a first aspect, the embodiment of the invention provides the 4th kind of possible implementation of above-mentioned first aspect, its
In, the described image according to collection extracts the gesture feature data of the user, including:
Obtain the gray-scale map of the described image of collection;
According to the gray value of each pixel on the gray-scale map, process of convolution at least one times is carried out to the gray-scale map,
Obtain the gesture feature data of the user.
With reference in a first aspect, the embodiment of the invention provides the 5th kind of possible implementation of above-mentioned first aspect, its
In, when the user makes two gestures in the image acquisition region of the desk lamp,
The image of the gesture that user described in continuous acquisition makes;
The first gesture characteristic and second gesture characteristic of the user are extracted from described image;
Determine the first gesture characteristic and the corresponding desk lamp control signal of the second gesture characteristic.
Second aspect, the embodiment of the invention provides a kind of device of gesture control desk lamp, wherein, described device includes:
Image capture module, for when desk lamp is in gesture control pattern, collection user to adopt in the image of the desk lamp
The image of at least one gesture that collection region is made;
Extraction module, the gesture feature data of the user are extracted for the described image according to collection;
Determining module, the corresponding desk lamp control signal of gesture feature data for determining the user;
Control module, for controlling the desk lamp to perform corresponding function according to the desk lamp control signal.
With reference to second aspect, present aspect embodiment provides the first possible implementation of above-mentioned second aspect, its
In, the determining module includes:
First matching unit, for by the gesture feature data of the user and the gesture feature information bank for pre-building
Each gesture feature data matched;
First determining unit, the corresponding desk lamp control of gesture feature data for determining the user according to matching result
Signal.
With reference to the first possible implementation of second aspect, the of above-mentioned second aspect is the embodiment of the invention provides
Two kinds of possible implementations, wherein, first matching unit is additionally operable to,
Calculate each gesture feature data in the gesture feature data of the user and the gesture feature information bank it
Between Euclidean distance;In determining the gesture feature data of the user and the gesture feature information bank according to the Euclidean distance
Each gesture feature data matching result.
With reference to second aspect, the third possible implementation of above-mentioned second aspect is the embodiment of the invention provides, its
In, the determining module includes:
Second matching unit, for will be every in the gesture feature data of the user and the gesture database for pre-building
Individual gesture feature data are matched;
Second determining unit, the gesture for determining the user according to matching result is identified;
3rd determining unit, for being identified and the gesture identification database that pre-builds according to the gesture of the user, really
The gesture of the fixed user identifies corresponding desk lamp control signal.
A kind of method and device of gesture control desk lamp is the embodiment of the invention provides, when desk lamp is in gesture control pattern
When, the gesture according to the user to gathering is identified, to control desk lamp to perform corresponding function, so so that user's control
Desk lamp becomes very convenient.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be attached to what is used needed for embodiment
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, thus be not construed as it is right
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 shows the flow chart of the method for the gesture control desk lamp that the embodiment of the present invention 1 is provided;
Fig. 2 shows the gesture feature that user is determined in the method for the gesture control desk lamp that the embodiment of the present invention 1 is provided
The flow chart of the corresponding desk lamp control signal of data;
Fig. 3 shows second hand of determination user in the method for the gesture control desk lamp that the embodiment of the present invention 1 is provided
The flow chart of the corresponding desk lamp control signal of gesture characteristic;
Fig. 4 shows the structural representation of the device of the gesture control desk lamp that the embodiment of the present invention 2 is provided.
Specific embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
Middle accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only
It is a part of embodiment of the invention, rather than whole embodiments.The present invention generally described and illustrated in accompanying drawing herein is real
The component for applying example can be arranged and designed with a variety of configurations.Therefore, it is of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the scope of claimed invention, but is merely representative of selected reality of the invention
Apply example.Based on embodiments of the invention, the institute that those skilled in the art are obtained on the premise of creative work is not made
There is other embodiment, belong to the scope of protection of the invention.
In view of in the prior art, when user is in certain function using desk lamp or the brightness, the sound that adjust desk lamp etc.
During parameter, generally require user and switched with the button switch or touch control that hand goes to touch on desk lamp, but, user sits sometimes
Position potential range desk lamp farther out, or user has water or oil stain etc. on hand, it has not been convenient to go to touch the switch of desk lamp.It is based on
This, the embodiment of the invention provides a kind of method and device of gesture control desk lamp, is described below by embodiment.
Embodiment 1
A kind of method of gesture control desk lamp is the embodiment of the invention provides, as shown in figure 1, the method comprising the steps of
S110-S140, it is specific as follows.
S110, when desk lamp is in gesture control pattern, collection user makes at least in the image acquisition region of desk lamp
One image of gesture.
The control model of desk lamp includes gesture control pattern and mode switching control in the embodiment of the present invention, when user makes
When using desk lamp, being actually needed according to oneself, the control model of selection desk lamp.
When user selects the gesture control pattern of desk lamp, image capture device on desk lamp is automatically turned on, in real time or
The images of gestures of taken at regular intervals user.
Above-mentioned image capture device can be mounted in the camera on desk lamp, the camera can be monocular cam or
Person's binocular camera.
When user needs control desk lamp, such as, when adjusting the parameters such as the brightness of desk lamp, user can in advance be good hand
Gesture, ready-made gesture should be placed in the image acquisition region of desk lamp, or hand is placed in the IMAQ of desk lamp with preset posture
Region, and gesture is made in image acquisition region, the gesture that user makes can be one, or multiple, on desk lamp
Image capture device gathers the gesture of user, obtains the image of the gesture of user.
If ready-made gesture to be placed in user the image acquisition region of desk lamp, and is no longer converted in image acquisition region
Gesture, at this moment, the gesture only one of which of the user that image capture device is collected, if hand is placed in platform by user with preset posture
The image acquisition region of lamp, then makes a gesture in image acquisition region, and at this moment, image capture device can collect user
Initial sign and final gesture, initial sign and final gesture according to user determine corresponding control signal, certainly, user
Multiple gestures can also be made in image acquisition region, at this moment, desk lamp control signal can be determined according to multiple gestures of user, this
The specific number of the gesture that inventive embodiments are not made to user under desk lamp is defined.
S120, the gesture feature data of the image zooming-out user according to collection.
The gesture feature data of the above-mentioned image zooming-out user according to collection, specifically include:Obtain the ash of the image of collection
Degree figure;According to the gray value of each pixel on above-mentioned gray-scale map, process of convolution at least one times is carried out to above-mentioned gray-scale map, obtained
The gesture feature data of user.
The image of the gesture of image capture device collection is coloured image, therefore, it is necessary first to obtain the cromogram of collection
The gray-scale map of picture, detailed process includes:R, G, B value of each pixel on the image of collection are obtained, according to each pixel
R, G, B value, the corresponding gray scale of each pixel is calculated using floating-point arithmetic, integer method, displacement method, mean value method etc.
Value, the RGB of each pixel on original image is replaced with gray value, so, obtains the gray-scale map of original image.
Furthermore it is also possible to pass through that the image of collection is converted into gray-scale map using television industry standard conversion matrix, or
The image that will be gathered by HLS (Hue Lightness Saturation, colourity, brightness, saturation degree) model conversion algorithms is turned
Change gray-scale map into, specific method of the embodiment of the present invention not to obtaining gray-scale map is defined.
Gray-scale map to above-mentioned acquisition can carry out a convolution algorithm, it is also possible to multiple convolution computing be carried out, to above-mentioned
The number of times that gray-scale map carries out convolution algorithm is more, and the gesture feature data for obtaining are more accurate.
When process of convolution is carried out to above-mentioned gray-scale map, it is necessary first to obtain each pixel on above-mentioned gray-scale map corresponding
Gray value, obtains the gray matrix of above-mentioned gray-scale map, such as, the size of above-mentioned gray-scale map is 10 × 10, then obtain above-mentioned every
The corresponding gray value of individual pixel, the gray matrix being made up of the gray value of each pixel on the gray-scale map is also 10 × 10.
It is substantially exactly to carry out convolution algorithm, convolution to the gray matrix of gray-scale map that convolution algorithm is carried out to above-mentioned gray-scale map
The formula of computing is as follows:
Wherein, in above-mentioned formula, conv represents the characteristic to being obtained after gray matrix convolution algorithm, and σ represents sharp
Function living, imgMat represents gray matrix, and W represents convolution kernel,Convolution operation is represented, b represents bias.
It is above-mentioned that convolution algorithm is carried out to gray matrix, substantially it is to be weighted average calculating operation in gray matrix, in above-mentioned fortune
In calculation, equivalent to weights, gray matrix imgMat is equivalent to the function being averaged for convolution kernel W.Above-mentioned convolution kernel W is also a square
Battle array, the concrete numerical value in the size and matrix of matrix can be selected according to practical application, and the present invention is not to above-mentioned convolution
The specific size and numerical value of core W are defined.
If the size of the convolution kernel W for choosing is 3 × 3, the size of gray matrix is 10 × 10, then gray matrix is carried out
After convolution algorithm, the size of the gray matrix obtained after convolution is (10-3+1) × (10-3+1), that is, obtain 8 × 8 ash
Degree matrix, each element in the gray matrix that will be obtained adds bias b, each element in the matrix after obtaining
It is input in activation primitive σ.
Above-mentioned activation primitive σ can be using such as minor function:
In above-mentioned formula, f (x) is the value entered after line activating to the element in the gray matrix that is obtained after convolution, and x is represented
Element in the gray matrix obtained after convolution.
Multiple convolution computing can be carried out continuously to above-mentioned gray matrix, finally give the gesture feature of user in gray-scale map
Data, gesture feature data obtained above are substantially a characteristic value.
The above-mentioned number of times that convolution algorithm is carried out to gray-scale map is relevant with the size of the convolution kernel for convolution algorithm chosen
System, such as, the size of the gray-scale map of above-mentioned acquisition is 10 × 10, and unit is pixel, when the volume for convolution algorithm chosen
When the size of product core is 3 × 3, after a convolution algorithm is carried out to above-mentioned gray-scale map, the size of the gray-scale map for obtaining is 8 × 8, then
Secondary to carry out process of convolution to 8 × 8 gray-scale map using above-mentioned convolution kernel, the size of the gray-scale map for obtaining is 6 × 6, continuously to upper
Stating gray-scale map carries out multiple convolution computing, obtains the gesture feature data in above-mentioned gray-scale map.
S130, determines the corresponding desk lamp control signal of gesture feature data of user.
Wherein it is determined that the corresponding desk lamp control signal of the gesture feature data of user specifically includes the following two kinds situation.
The first situation, directly the gesture feature data according to user determine its corresponding desk lamp control signal, including
Step S210-S220, it is specific as follows.
S210, by each the gesture feature number in the gesture feature data of user and the gesture feature information bank for pre-building
According to being matched.
S220, the corresponding desk lamp control signal of the gesture feature data of user is determined according to matching result.
Wherein, above-mentioned gesture feature information bank pre-builds, is to use method control provided in an embodiment of the present invention
Just had built up before desk lamp processed, the specific process set up includes:The various gestures image of user is gathered, every kind of hand is extracted
Gesture feature data in gesture image, and the corresponding desk lamp control signal of every kind of gesture feature data is defined, such as, Ke Yiding
It is the signal for controlling volume to increase that the corresponding gesture feature data of this gesture of adopted fist are corresponding, or, hand can also be defined
Gesture by open configuration to this state correspondence control volume increase signal of clenching fist, specifically using a kind of gesture or two kinds of gestures,
Or a kind of control signal of various gestures correspondence, can be configured according to actual needs, and the embodiment of the present invention is not to every kind of
The corresponding gesture of control signal is defined, and above-mentioned simply citing is illustrated, and defines every kind of gesture feature data corresponding
After desk lamp control signal, by every kind of gesture feature data, desk lamp control signal, and gesture feature data and desk lamp control signal
Between corresponding relation storage in gesture characteristic information storehouse.
When user is when using gesture control desk lamp, the images of gestures of user is gathered, and extract gesture feature image pair
After the gesture feature data answered, by each the gesture feature number in the gesture feature data of user and above-mentioned gesture feature information bank
According to being matched, specifically include:Calculate each the gesture feature number in the gesture feature data and gesture feature information bank of user
Euclidean distance between;In determining the gesture feature data of above-mentioned user and gesture feature information bank according to above-mentioned Euclidean distance
Each gesture feature data matching result.
Euclidean distance is also referred to as euclidean metric, is a conventional distance definition, and it represents two points in n-dimensional space
Between actual distance, in embodiments of the present invention, by calculate two gesture feature data between Euclidean distance, to user
Gesture feature data be identified.
Being calculated as follows for Euclidean distance is shown:
Assuming that two points in two-dimensional space:A(x1, y1)、B(x2, y2), then two-dimensional space Euclidean distance computing formula is:
ρ (A, B)=sqrt [(x1-x2)2+(y1-y2)2]
N-dimensional space is a point set, and point concentration each point P can be expressed as (p1, p2…pi), wherein, i=1,2 ... n,
Then two point C=(c in n-dimensional space1,c2,…,ci) and D=(d1,d2,…,di) between the computing formula of Euclidean distance be:
In embodiments of the present invention, C can be the gesture feature data of user, and D is any in gesture feature information bank
One gesture feature data, ciAny one characteristic value in the gesture feature data of user, diIt is gesture feature information database
In arbitrary characteristics value in any one gesture feature data.
So, exist in gesture feature information bank how many gesture feature data can just calculate how many Euclideans away from
From, the Euclidean distance of minimum is chosen from above-mentioned multiple Euclidean distances, and it is default to judge whether the Euclidean distance is less than or equal to
Threshold value, if it is, the corresponding gesture feature data of the Euclidean distance are defined as the gesture feature data of user, and should
The corresponding desk lamp control signal of gesture feature data is defined as the corresponding desk lamp control signal of gesture feature data of user.
Above-mentioned predetermined threshold value is a value set in advance, when the above-mentioned Euclidean distance for calculating is default less than or equal to this
During threshold value, two gesture feature Data Matchings are illustrated.
If above-mentioned minimum Euclidean distance is more than above-mentioned predetermined threshold value, at this moment, will be unable to determine the gesture feature of user
The corresponding desk lamp control signal of data, desk lamp can send prompting, point out user the gesture None- identified, please make corresponding again
Gesture.
If the minimum Euclidean distance of above-mentioned selection has multiple, that is, the equal situation of several Euclidean distances is occurred in that, and
It is that minimum Euclidean distance is equal, at this moment, no matter whether the Euclidean distance of minimum is less than or equal to predetermined threshold value, cannot all determines
Go out the corresponding desk lamp control signal of gesture feature data of user, desk lamp can send prompting, point out the current gesture pair of None- identified
The desk lamp control signal answered, asks user to make corresponding gesture again.
Second situation, first identifies the gesture of user according to the gesture feature data of user, and it is determined further according to gesture
Corresponding desk lamp control signal, including step S310-S330, it is specific as follows.
S310, the gesture feature data of user are entered with each the gesture feature data in the gesture database for pre-building
Row matching;
S320, the gesture mark of user is determined according to matching result;
S330, gesture mark and the gesture identification database for pre-building according to user, determines the gesture mark of user
Corresponding desk lamp control signal.
Above-mentioned gesture database and gesture identification database are all pre-build, are provided using the embodiment of the present invention
Method control desk lamp before, first set up gesture database and gesture identification database, wherein, in above-mentioned gesture database,
The corresponding relation being stored between various gestures characteristic, various gestures mark and gesture feature data and gesture mark.
In above-mentioned gesture identification database, the various gestures that are stored with mark, desk lamp control signal and gesture mark and
Corresponding relation between desk lamp control signal.
Wherein, the gesture mark in gesture database and gesture identification database is identical.
Above-mentioned gesture mark can be the title of every kind of gesture, or the coding of customized every kind of gesture feature,
It is, of course, also possible to be other, as long as in various gestures can be distinguished and ensureing gesture identification database and gesture database
Gesture mark it is consistent.
In embodiments of the present invention, after the gesture feature data of user are extracted, the gesture feature data of user are calculated
With the Euclidean distance between each the gesture feature data in gesture database, determine that the gesture of user is special according to the Euclidean distance
Levy the corresponding gesture mark of data.
After the gesture feature data for determining user corresponding mark, looked into from gesture identification database according to the mark
The gesture is looked for identify corresponding desk lamp control signal, the gesture feature data that the desk lamp control signal is defined as into user are corresponding
Desk lamp control signal.
User can be one in the gesture that the image acquisition region of desk lamp is made, such as, fist is placed in platform by user
At the image acquisition region of lamp, the gesture made can also be two, such as, user is made that an action clenched fist, this
When, the initial palm open configuration of user and final two states of fist can be defined as the gesture of user, i.e., at this moment
User is made that two gestures, it is, of course, also possible to be multiple gestures, user is described in detail below in the image acquisition areas of desk lamp
Course of work during two gestures is made in domain, specifically includes:
When user makes two gestures in the image acquisition region of desk lamp, the figure of the gesture that continuous acquisition user makes
Picture;The first gesture characteristic and second gesture characteristic of user are extracted from above-mentioned image;Determine above-mentioned first gesture
Characteristic and the corresponding desk lamp control signal of second gesture characteristic.
Wherein, when user makes two gestures under desk lamp, at this moment, the image of the gesture of the user for collecting includes using
State in the initial state of the gesture at family, final state and user gesture change procedure, in embodiments of the present invention, only by user's
The initial state of gesture and final state are assured that out the corresponding desk lamp control signal of the gesture of user, therefore, it can the figure from collection
The initial state gesture feature data of user are extracted in first image as in, the initial state gesture feature data of user are designated as to use
The first gesture characteristic at family, extracts the final state gesture feature number of user from the last frame image in the image of collection
According to, the final state gesture feature data of user are designated as the second gesture characteristic of user, the first gesture by user is special afterwards
Levy data and second gesture characteristic determines its corresponding desk lamp control signal jointly.
S140, controls desk lamp to perform corresponding function according to desk lamp control signal.
After the gesture for finding user corresponding desk lamp control signal, control desk lamp performs corresponding function.
In addition to this it is possible to the sliding trace of the finger of user is identified, in the slip rail of the finger to user
When mark is identified, the image of the finger sliding trace of many framed users of continuous acquisition is identified in described image between finger
Position, because the pickup area of image capture device is fixed, will not move with the slip of finger, therefore, with setting about
The movement of finger, in every two field picture, the position of finger differs, therefore, by mobile image, make adjacent two field pictures
In finger finger tip overlap, the center position of adjacent two field pictures is found, by between the central point of adjacent two field pictures
Line is defined as the sliding trace of finger tip.
Therefore, in embodiments of the present invention, it is also possible to which desk lamp is controlled by the sliding trace of finger.
The method of gesture control desk lamp provided in an embodiment of the present invention, when desk lamp is in gesture control pattern, according to right
The gesture of the user of collection is identified, to control desk lamp to perform corresponding function, so so that user's control desk lamp becomes very
It is convenient.
Embodiment 2
A kind of device of gesture control desk lamp is the embodiment of the invention provides, the device can be control chip, such as,
CPLD (Complex Programmable Logic Device, CPLD) control chip, the chip is installed
On desk lamp, as shown in figure 4, the device includes image capture module 410, extraction module 420, determining module 430 and control mould
Block 440;
Above-mentioned image capture module 410, for when desk lamp is in gesture control pattern, gathering image of the user in desk lamp
The image of at least one gesture that pickup area is made;
Said extracted module 420, for the gesture feature data of the image zooming-out user according to collection;
Above-mentioned determining module 430, the corresponding desk lamp control signal of gesture feature data for determining user;
Above-mentioned control module 440, for controlling desk lamp to perform corresponding function according to desk lamp control signal.
Wherein, above-mentioned determining module 430, determining the corresponding desk lamp control signal of gesture feature data of user can pass through
First matching unit and the first determining unit are realized, specifically included:
Above-mentioned first matching unit, for by the gesture feature data of user and the gesture feature information data for pre-building
Each gesture feature data in storehouse are matched;Above-mentioned first determining unit, the hand for determining user according to matching result
The corresponding desk lamp control signal of gesture characteristic.
Above-mentioned first matching unit is by the gesture feature data of user and the gesture feature information database for pre-building
Each gesture feature data matched, specifically include:
Above-mentioned first matching unit is additionally operable to, in the gesture feature data and gesture feature information bank of the above-mentioned user of calculating
Euclidean distance between each gesture feature data;The gesture feature data and hand of above-mentioned user are determined according to above-mentioned Euclidean distance
The matching result of each the gesture feature data in gesture characteristic information storehouse.
In addition, above-mentioned determining module 430 determines that the corresponding desk lamp control signal of gesture feature data of user can also lead to
Cross the second matching unit, the second determining unit and the 3rd determining unit to realize, specifically include:
Above-mentioned second matching unit, for will be every in the gesture feature data of user and the gesture database for pre-building
Individual gesture feature data are matched;Above-mentioned second determining unit, the gesture for determining user according to matching result is identified;On
The 3rd determining unit is stated, for the gesture identification database for identifying and pre-building according to the gesture of user, the hand of user is determined
Gesture identifies corresponding desk lamp control signal.
The method of gesture control desk lamp provided in an embodiment of the present invention, when desk lamp is in gesture control pattern, according to right
The gesture of the user of collection is identified, to control desk lamp to perform corresponding function, so so that user's control desk lamp becomes very
It is convenient.
The device of the gesture control desk lamp that the embodiment of the present invention is provided can be specific hardware or installation in equipment
In software or firmware in equipment etc..The technique effect of the device that the embodiment of the present invention is provided, its realization principle and generation and
Preceding method embodiment is identical, is to briefly describe, and device embodiment part does not refer to part, in referring to preceding method embodiment
Corresponding contents.It is apparent to those skilled in the art that, for convenience and simplicity of description, described above is
The specific work process of system, device and unit, may be referred to the corresponding process in above method embodiment, no longer go to live in the household of one's in-laws on getting married herein
State.
In embodiment provided by the present invention, it should be understood that disclosed apparatus and method, can be by other sides
Formula is realized.Device embodiment described above is only schematical, for example, the division of the unit, only one kind are patrolled
Collect function to divide, there can be other dividing mode when actually realizing, but for example, multiple units or component can combine or can
To be integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or discussed each other
Coupling or direct-coupling or communication connection can be the INDIRECT COUPLING or communication link of device or unit by some communication interfaces
Connect, can be electrical, mechanical or other forms.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme
's.
In addition, during each functional unit in the embodiment that the present invention is provided can be integrated in a processing unit, also may be used
Being that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.
If the function is to realize in the form of SFU software functional unit and as independent production marketing or when using, can be with
Storage is in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used to so that a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the invention.
And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
It should be noted that:Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined in individual accompanying drawing, then it need not be further defined and explained in subsequent accompanying drawing, additionally, term " the
One ", " second ", " the 3rd " etc. are only used for distinguishing description, and it is not intended that indicating or implying relative importance.
Finally it should be noted that:Embodiment described above, specific embodiment only of the invention, is used to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that:Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent is carried out to which part technical characteristic;And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of embodiment of the present invention technical scheme.Should all cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of method of gesture control desk lamp, it is characterised in that methods described includes:
When desk lamp is in gesture control pattern, at least one hand that collection user makes in the image acquisition region of the desk lamp
The image of gesture;
Described image according to collection extracts the gesture feature data of the user;
Determine the corresponding desk lamp control signal of gesture feature data of the user;
The desk lamp is controlled to perform corresponding function according to the desk lamp control signal.
2. method according to claim 1, it is characterised in that the gesture feature data of the determination user are corresponding
Desk lamp control signal, including:
The gesture feature data of the user are entered with each the gesture feature data in the gesture feature information bank for pre-building
Row matching;
The corresponding desk lamp control signal of the gesture feature data of the user is determined according to matching result.
3. method according to claim 2, it is characterised in that the gesture feature data by the user are built with advance
Gesture feature data in vertical gesture feature information bank are matched, including:
Calculate between each the gesture feature data in the gesture feature data and the gesture feature information bank of the user
Euclidean distance;
Each hand in the gesture feature data of the user and the gesture feature information bank is determined according to the Euclidean distance
The matching result of gesture characteristic.
4. method according to claim 1, it is characterised in that the gesture feature data of the determination user are corresponding
Desk lamp control signal, including:
Each gesture feature data in the gesture feature data of the user and the gesture database for pre-building are carried out
Match somebody with somebody;
The gesture mark of the user is determined according to matching result;
Gesture mark and the gesture identification database for pre-building according to the user, determine that the gesture mark of the user is right
The desk lamp control signal answered.
5. method according to claim 1, it is characterised in that the described image according to collection extracts the user's
Gesture feature data, including:
Obtain the gray-scale map of the described image of collection;
According to the gray value of each pixel on the gray-scale map, process of convolution at least one times is carried out to the gray-scale map, obtained
The gesture feature data of the user.
6. method according to claim 1, it is characterised in that when the user does in the image acquisition region of the desk lamp
When going out two gestures,
The image of the gesture that user described in continuous acquisition makes;
The first gesture characteristic and second gesture characteristic of the user are extracted from described image;
Determine the first gesture characteristic and the corresponding desk lamp control signal of the second gesture characteristic.
7. a kind of device of gesture control desk lamp, it is characterised in that described device includes:
Image capture module, for when desk lamp is in gesture control pattern, user to be in the image acquisition areas of the desk lamp for collection
The image of at least one gesture that domain is made;
Extraction module, the gesture feature data of the user are extracted for the described image according to collection;
Determining module, the corresponding desk lamp control signal of gesture feature data for determining the user;
Control module, for controlling the desk lamp to perform corresponding function according to the desk lamp control signal.
8. device according to claim 7, it is characterised in that the determining module includes:
First matching unit, for will be every in the gesture feature data of the user and the gesture feature information bank for pre-building
Individual gesture feature data are matched;
First determining unit, the corresponding desk lamp control letter of gesture feature data for determining the user according to matching result
Number.
9. device according to claim 8, it is characterised in that first matching unit is additionally operable to,
Calculate between each the gesture feature data in the gesture feature data and the gesture feature information bank of the user
Euclidean distance;Determined according to the Euclidean distance every in the gesture feature data of the user and the gesture feature information bank
The matching result of individual gesture feature data.
10. device according to claim 7, it is characterised in that the determining module includes:
Second matching unit, for by each hand in the gesture feature data of the user and the gesture database for pre-building
Gesture characteristic is matched;
Second determining unit, the gesture for determining the user according to matching result is identified;
3rd determining unit, for the gesture identification database for identifying and pre-building according to the gesture of the user, determines institute
The gesture for stating user identifies corresponding desk lamp control signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710061195.4A CN106851937A (en) | 2017-01-25 | 2017-01-25 | A kind of method and device of gesture control desk lamp |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710061195.4A CN106851937A (en) | 2017-01-25 | 2017-01-25 | A kind of method and device of gesture control desk lamp |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106851937A true CN106851937A (en) | 2017-06-13 |
Family
ID=59123017
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710061195.4A Pending CN106851937A (en) | 2017-01-25 | 2017-01-25 | A kind of method and device of gesture control desk lamp |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106851937A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108209926A (en) * | 2018-01-08 | 2018-06-29 | 西安科技大学 | Human Height measuring system based on depth image |
CN109302780A (en) * | 2017-07-25 | 2019-02-01 | 美的智慧家居科技有限公司 | The control method of lighting apparatus and device, storage medium in domestic environment |
CN109447005A (en) * | 2018-11-01 | 2019-03-08 | 珠海格力电器股份有限公司 | A kind of gesture identification method, device, storage medium and electric appliance |
CN110162173A (en) * | 2019-05-06 | 2019-08-23 | 上海翎腾智能科技有限公司 | A kind of gesture interaction method and intelligent desk lamp of the intelligent desk lamp based on AI |
CN110941187A (en) * | 2018-09-21 | 2020-03-31 | 珠海格力电器股份有限公司 | Household appliance control method and device |
CN111107701A (en) * | 2018-10-25 | 2020-05-05 | 松下电气机器(北京)有限公司 | Lamp controller and lighting system |
CN111396775A (en) * | 2020-04-14 | 2020-07-10 | 佛山市艾温特智能科技有限公司 | Multifunctional table lamp and game implementation method thereof |
CN114489462A (en) * | 2021-12-31 | 2022-05-13 | 广州视声智能股份有限公司 | Wireless key switch panel and control method thereof |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073843A (en) * | 2010-11-05 | 2011-05-25 | 沈阳工业大学 | Non-contact rapid hand multimodal information fusion identification method |
CN102609093A (en) * | 2012-02-16 | 2012-07-25 | 中国农业大学 | Method and device for controlling video playing by using gestures |
CN105095882A (en) * | 2015-08-24 | 2015-11-25 | 珠海格力电器股份有限公司 | Method and apparatus for gesture identification |
CN106054627A (en) * | 2016-06-12 | 2016-10-26 | 珠海格力电器股份有限公司 | Control method and device based on gesture recognition and air conditioner |
-
2017
- 2017-01-25 CN CN201710061195.4A patent/CN106851937A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073843A (en) * | 2010-11-05 | 2011-05-25 | 沈阳工业大学 | Non-contact rapid hand multimodal information fusion identification method |
CN102609093A (en) * | 2012-02-16 | 2012-07-25 | 中国农业大学 | Method and device for controlling video playing by using gestures |
CN105095882A (en) * | 2015-08-24 | 2015-11-25 | 珠海格力电器股份有限公司 | Method and apparatus for gesture identification |
CN106054627A (en) * | 2016-06-12 | 2016-10-26 | 珠海格力电器股份有限公司 | Control method and device based on gesture recognition and air conditioner |
Non-Patent Citations (1)
Title |
---|
魏英姿等: "玉米籽粒完整性识别的深度学习方法", 《沈阳理工大学学报》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109302780A (en) * | 2017-07-25 | 2019-02-01 | 美的智慧家居科技有限公司 | The control method of lighting apparatus and device, storage medium in domestic environment |
CN109302780B (en) * | 2017-07-25 | 2020-11-24 | 美智光电科技股份有限公司 | Control method and device for lighting equipment in home environment and storage medium |
CN108209926A (en) * | 2018-01-08 | 2018-06-29 | 西安科技大学 | Human Height measuring system based on depth image |
CN110941187A (en) * | 2018-09-21 | 2020-03-31 | 珠海格力电器股份有限公司 | Household appliance control method and device |
CN111107701A (en) * | 2018-10-25 | 2020-05-05 | 松下电气机器(北京)有限公司 | Lamp controller and lighting system |
CN111107701B (en) * | 2018-10-25 | 2022-02-01 | 松下电气机器(北京)有限公司 | Lamp controller and lighting system |
CN109447005A (en) * | 2018-11-01 | 2019-03-08 | 珠海格力电器股份有限公司 | A kind of gesture identification method, device, storage medium and electric appliance |
CN110162173A (en) * | 2019-05-06 | 2019-08-23 | 上海翎腾智能科技有限公司 | A kind of gesture interaction method and intelligent desk lamp of the intelligent desk lamp based on AI |
CN111396775A (en) * | 2020-04-14 | 2020-07-10 | 佛山市艾温特智能科技有限公司 | Multifunctional table lamp and game implementation method thereof |
CN114489462A (en) * | 2021-12-31 | 2022-05-13 | 广州视声智能股份有限公司 | Wireless key switch panel and control method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106851937A (en) | A kind of method and device of gesture control desk lamp | |
CN110532984B (en) | Key point detection method, gesture recognition method, device and system | |
CN104573706B (en) | A kind of subject image recognition methods and its system | |
CN103164022B (en) | Many fingers touch method and device, portable terminal | |
CN102520796B (en) | Sight tracking method based on stepwise regression analysis mapping model | |
CN106537305A (en) | Touch classification | |
CN104364733A (en) | Position-of-interest detection device, position-of-interest detection method, and position-of-interest detection program | |
CN104583912A (en) | System and method for perceiving images with multimodal feedback | |
CN101661329A (en) | Operating control method and device of intelligent terminal | |
CN103201710A (en) | Image processing system, image processing method, and storage medium storing image processing program | |
US11429985B2 (en) | Information processing device calculating statistical information | |
CN103020885A (en) | Depth image compression | |
CN110399822A (en) | Action identification method of raising one's hand, device and storage medium based on deep learning | |
CN108762497A (en) | Body feeling interaction method, apparatus, equipment and readable storage medium storing program for executing | |
CN114092576A (en) | Image processing method, device, equipment and storage medium | |
CN107169427A (en) | One kind is applied to psychologic face recognition method and device | |
CN109934072A (en) | Personnel statistical method and device | |
WO2021147473A1 (en) | Model training method, content generation method, and related devices | |
CN107734119A (en) | A kind of method, storage medium and terminal for adjusting screen intensity | |
CN109799905B (en) | Hand tracking method and advertising machine | |
CN109919164A (en) | The recognition methods of user interface object and device | |
CN110363149B (en) | Handwriting processing method and device | |
CN115061577A (en) | Hand projection interaction method, system and storage medium | |
CN115187972A (en) | Dish identification method based on feature comparison | |
CN114581535A (en) | Method, device, storage medium and equipment for marking key points of user bones in image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |
|
RJ01 | Rejection of invention patent application after publication |