CN110348275A - Gesture identification method, device, smart machine and computer readable storage medium - Google Patents
Gesture identification method, device, smart machine and computer readable storage medium Download PDFInfo
- Publication number
- CN110348275A CN110348275A CN201810307857.6A CN201810307857A CN110348275A CN 110348275 A CN110348275 A CN 110348275A CN 201810307857 A CN201810307857 A CN 201810307857A CN 110348275 A CN110348275 A CN 110348275A
- Authority
- CN
- China
- Prior art keywords
- time series
- gesture
- acceleration
- resultant force
- angular speed
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000001133 acceleration Effects 0.000 claims abstract description 114
- 230000006870 function Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 230000005484 gravity Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 241001269238 Data Species 0.000 claims description 2
- 230000003993 interaction Effects 0.000 abstract description 5
- 238000004422 calculation algorithm Methods 0.000 description 12
- 230000006854 communication Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001404 mediated effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000009527 percussion Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention discloses a kind of gesture identification method, smart machine and storage mediums, belong to human-computer interaction technique field.This method comprises: obtaining the acceleration and angular speed data of gesture to be identified, and it is filtered；Acceleration resultant force time series is calculated according to acceleration information；Dimension is carried out to acceleration resultant force time series and angular speed time series to be uniformly processed；Acceleration resultant force time series and angular speed time series after dimension is uniformly processed according to default rule carry out branch mailbox；Acceleration after branch mailbox is matched with angular speed time series with the gesture template library prestored with joint efforts, determines the classification of gesture to be identified.The embodiment of the present invention can be in the case where not increasing sensor cost, the effective difference of regular gesture data spatially, otherness caused by reducing due to the variation of speed or the variation of strength, to realize efficient, accurate gesture identification, can be widely applied in the smart machine high to user-interaction experience.
Description
Technical field
The present invention relates to human-computer interaction technique fields, more particularly to one kind to be based on IMU (Inertial measurement
Unit, Inertial Measurement Unit) gesture identification method, device, smart machine and computer readable storage medium.
Background technique
Gesture interaction is a kind of naturally convenient and fast human-computer interaction means, has the characteristics that simple, intuitive, is easy to learn and use, can be with
The wish of people is intuitively showed.More and more the universal of smart machine bring the new purposes of gesture identification and side
To.The sensing equipment of the various high-precisions, low-power consumption that are equipped on smart machine also makes the approach of gesture identification more diversified.Mesh
Before, common gesture identification includes the number of ways such as photoelectric induction device, infrared detecting device, IMU and acceleration transducer.
Wherein, IMU is the device for measuring object triaxial attitude angle (or angular speed) and acceleration, can use the acceleration of smart machine
Spend the data during sensor, the sensors acquisition gesture such as gyroscope, then carry out gesture identification, make user accomplish at any time with
Ground easily carries out gesture interaction.
DTW (Dynamic Time Warping, dynamic time consolidation) algorithm is a kind of common Gesture Recognition Algorithm, is passed
System using Euclidean distance carry out template between gap measurement when, the length of two templates should be identical, i.e., data point is one by one
It is corresponding.Since the length of gesture data might not be equal, need to handle gesture data, so that it reaches alignment
Effect.DTW algorithm can have the function that data are regular by the way that data are stretched on a timeline or compressed, thus to solve shape
In state it is similar but in time can not very well corresponding data comparison.
However, due to acceleration transducer and gyroscope can because the gesture habit of user (for example strength and speed is big
It is small) occur either large or small variation, same gesture can the different data of output, cause acceleration and angular speed have in amplitude compared with
Big difference, i.e. spatial diversity.Spatial diversity is not the real difference of different gestures, on the contrary, if in this, as feature, together
One gesture is also possible to thus lead to the failure of identification.Although DTW algorithm can on a timeline be adaptively adjusted data,
But can not make and be effectively treated on amplitude (spatial diversity), that is, lack the adaptability changed to space scale.
Summary of the invention
In view of this, the embodiment of the present invention is designed to provide a kind of gesture identification method, device, smart machine and meter
Calculation machine readable storage medium storing program for executing, to solve the technical issues of DTW algorithm lacks adaptability change to space scale, thus diminution by
The otherness caused by the variation of speed or the variation of strength.
It is as follows that the present invention solves technical solution used by above-mentioned technical problem:
According to an aspect of an embodiment of the present invention, a kind of gesture identification method provided includes:
The acceleration and angular speed data of gesture to be identified are obtained, and are filtered；
Acceleration resultant force time series is calculated according to acceleration information；
Dimension is carried out to acceleration resultant force time series and angular speed time series to be uniformly processed；
Acceleration resultant force time series and angular speed time series after dimension is uniformly processed according to default rule into
Row branch mailbox；
By the acceleration resultant force time series and angular speed time series after branch mailbox and the gesture template library progress prestored
Match, determines the classification of gesture to be identified.
Other side according to an embodiment of the present invention, a kind of gesture identifying device provided include:
Gesture acquisition module, for obtaining the acceleration and angular speed data of gesture to be identified；
Filter module, for being filtered to acceleration and angular speed data；
Resultant force computing module, for calculating acceleration resultant force time series according to acceleration information；
Dimension unified modules, for being carried out at dimension unification to acceleration resultant force time series and angular speed time series
Reason；
Branch mailbox module, for the acceleration resultant force time series and angle speed after dimension is uniformly processed according to default rule
It spends time series and carries out branch mailbox；
Matching module, for by after branch mailbox acceleration resultant force time series and angular speed time series and the gesture that prestores
Template library is matched, and determines the classification of gesture to be identified.
Another aspect according to an embodiment of the present invention, a kind of smart machine provided include memory, processor and deposit
The computer program that can be run on a memory and on a processor is stored up, above-mentioned hand is realized when computer program is executed by processor
The step of gesture recognition methods.
Another aspect according to an embodiment of the present invention is stored with calculating on a kind of computer readable storage medium provided
Machine program, when computer program is executed by processor, the step of realizing above-mentioned gesture identification method.
Gesture identification method, device, smart machine and computer readable storage medium provided in an embodiment of the present invention, can be
It is unified by carrying out dimension to acceleration resultant force time series and angular speed time series in the case where not increasing sensor cost
Processing and branch mailbox, the effective difference of regular gesture data spatially, reduce due to the variation of speed or the variation of strength and
Caused otherness can be widely applied to the intelligence high to user-interaction experience and set to realize efficient, accurate gesture identification
In standby.
Detailed description of the invention
Fig. 1 is a kind of flow chart for gesture identification method that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow chart of gesture template matching method provided by Embodiment 2 of the present invention；
Fig. 3 is the function structure chart of three gesture identifying device of the embodiment of the present invention；
Fig. 4 is the function structure chart for the intelligent terminal that the embodiment of the present invention four provides.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
In order to be clearer and more clear technical problems, technical solutions and advantages to be solved, tie below
Drawings and examples are closed, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only
To explain the present invention, it is not intended to limit the present invention.
Embodiment one
As shown in Figure 1, a kind of gesture identification method provided in an embodiment of the present invention includes:
S101, the acceleration and angular speed data for obtaining gesture to be identified, and be filtered.
Specifically, generally acquiring acceleration and angular speed by the acceleration transducer and gyroscope that configure in smart machine
Data, acceleration and angular speed data are used to describe the information of gesture behavior.But non-targeted gesture can be adulterated in collection process
Signal needs to be filtered to avoid its influence.Filtering mode has very much, and experiment and investigation obtain, the frequency of gesture behavior
Rate is typically in 3.5HZ hereinafter, so using using 3.5HZ is the low-pass filter of cutoff frequency to acceleration and angular speed data
It is filtered relatively good.
S102, acceleration resultant force time series is calculated according to acceleration information.
Specifically, common acceleration transducer can use 3-axis acceleration sensor, in orthogonal three axis of X, Y, Z
The component of acceleration is acquired respectively, and the component on three axis can generate biggish gap because of the variation of equipment posture, equipment
The variation of posture cannot directly be expressed as the situation of change of power during gesture, if calculating separately three axis using DTW
Total gap that gap obtains two samples can not measure the real difference between gesture well.So needing to close three axis components
As the vector sum of original resultant force, due to adulterating gravity in the resultant force that acquires, therefore gravity is subtracted.I.e. a certain moment, three axis
Resultant force subtract gravity be exactly the moment generate acceleration resultant force.The power but generated in this way is a scalar, and there is no directions
It is directed toward, and the angular velocity data that gyroscope provides can make up the missing of information on direction.It can be calculated by using the following formula
The time series that acceleration resultant force changes over time:
Wherein, s indicates acceleration resultant force, a(xt)、a(yt)、a(zt))T moment is respectively indicated on x-axis, y-axis and z-axis direction
Acceleration, g indicate acceleration of gravity.
S103, acceleration resultant force time series and angular speed time series progress dimension are uniformly processed.
Specifically, can make the gesture of friction speed under different strength, the speed of gesture motion also can be largely
The size for influencing gesture data causes acceleration and angular speed to have biggish difference, i.e. spatial diversity in amplitude.But space
Difference is not the real difference of different gestures, on the contrary, if same gesture is also possible to thus cause to identify in this, as feature
Failure.If the Euclidean distance between DTW algorithm directly comparative sample, can amplify due to the difference that gesture speed difference generates
Otherwise general character or difference are masked, unreasonable result is obtained.DTW algorithm is can be by the drawing to data time shaft
Stretch or compress the regular effect for reaching data, solve the similar but time in form it is upper can not fine corresponding data comparison,
But effective processing cannot be made on spatial diversity.So needing through normalized, by Data Integration to unification
Under dimension, thus otherness caused by reducing due to the variation of speed or the variation of strength.
When carrying out dimension unification to acceleration resultant force time series and angular speed time series, if directly by sequence
A section is integrally compressed or be stretched to data, i.e., using the methods of linear normalization, is easy because some very big or minimum
Singular value lead to the loss of effective information.Therefore use zero-mean method for normalizing more reasonable.
It can be specifically uniformly processed using the dimension that following formula carries out acceleration resultant force time series:
Wherein, S(t)Indicate the acceleration resultant force of t moment, meanSIndicate all acceleration resultant forces of whole section of time series
Mean value, stdSIndicate the standard deviation of all acceleration resultant forces of whole section of time series.
It can be uniformly processed using the dimension that following formula carries out angular speed time series:
Wherein, w(t)Indicate the angular speed of t moment, meanwIndicate all angular velocity vector sizes of whole section of time series
Mean value, stdwIndicate the standard deviation of all angular velocity vector sizes of whole section of time series.
S104, dimension is uniformly processed according to default rule after acceleration resultant force time series and angular speed time sequence
Column carry out branch mailbox.
Specifically, small-scale variation can occur for gesture motion during a gesture, it can not directly be utilized,
It needs to be further processed.It i.e. will be in the acceleration resultant force time series using the first preset piecewise function
The acceleration resultant force size at each moment is mapped as discrete acceleration resultant force value, using the discrete acceleration resultant force value table
State the acceleration resultant force time series.Using the second preset piecewise function by each moment in the angular speed time series
Angular velocity vector size be mapped as discrete magnitude of angular velocity, the angular speed time is stated using the discrete magnitude of angular velocity
Sequence.
It is operated by data branch mailbox, thus bring difference can be reduced to a certain extent.Experiments verify that can adopt
Branch mailbox is carried out with following branch mailbox table:
Table 1: acceleration resultant force branch mailbox table
| Acceleration resultant force magnitude range | Cabinet |
| 0~0.25stdS | 0 |
| 0.25stdS~0.5stdS | 0.5 |
| 0.5stdS~stdS | 1 |
| stdS~1.5stdS | 1.5 |
| 1.5stdS~2stdS | 2 |
| >2stdS | 3 |
Note: stdSRefer to stdSIndicate the standard deviation of all acceleration resultant forces of whole section of acceleration resultant force time series.
According to upper table 1, power within the scope of resultant force, the resultant force with the digital representation in cabinet, such as t moment is S(t)
Size be 0.2 when, be in 0~0.25stdSBetween, then set S(t)It is 0.
Table 2: angular speed branch mailbox table
| Angular speed size | Cabinet |
| 0~0.25stdw | 0 |
| 0.25stdw~0.5stdw | 0.5 |
| 0.5stdw~stdw | 1 |
| 1stdw~1.5stdw | 1.5 |
| 1.5stdw~2stdw | 2 |
| >2stdw | 3 |
Note: stdwIndicate the standard deviation of all angular velocity vector sizes of whole section of angular speed time series.
According to upper table 2, angular speed in angular velocity range, with the angle speed of the digital representation in cabinet, such as t moment
Spend w(t)Size be 0.2stdw, then w is set(t)It is 0.
S105, the acceleration after branch mailbox is matched with angular speed time series with the gesture template library prestored with joint efforts,
Determine the classification of gesture to be identified.
Gesture identification method provided in an embodiment of the present invention, can be in the case where not increasing sensor cost, by adding
Speed resultant force time series and angular speed time series carry out dimension and are uniformly processed and branch mailbox, and effective regular gesture data is in sky
Between on difference, reduce due to otherness caused by the variation of speed or the variation of strength, to realize efficient, accurate hand
Gesture identification, can be widely applied in the smart machine high to user-interaction experience.
Embodiment two
As shown in Fig. 2, the method for gesture template matching provided in an embodiment of the present invention includes:
S1051, by the acceleration resultant force time series and angular speed time series and preset gesture template library after branch mailbox
In the target gesture data of each major class be compared, choosing major class belonging to the smallest target gesture template of difference is object set
It closes.
Wherein, the pre-stored double-deck classification model library on intelligent devices of preset gesture template library.In order to guarantee to identify
Precision would generally generate numerous samples in advance for each gesture, at the step S101~step S104 of above-described embodiment one
Then reason is obtained with other same gesture average Euclidean apart from the smallest sample deposit template library using DTW algorithm as template.
Above steps may be repeated multiple times can be generated multiple gesture templates, to construct complete template library.
Although the accuracy of identification can be effectively improved in this way, with increasing for gesture type, template matching
Operand will significantly increase, and consume more resources, and especially various intelligent movable equipment etc. are to storage, calculating and function
Consumption is again extremely sensitive, so needing to reduce algorithm complexity using efficient template matching algorithm.The Europe obtained due to DTW algorithm
Formula distance is to discriminate between the standard of different gestures, and the Euclidean distance that similar gesture is calculated is also relatively, it is possible to
Compared by different level according to this to improve comparison efficiency, gesture is divided into different major class, i.e., similar gesture is divided into a major class.
I.e. as unit of the specific other all samples of gesture class, calculates the DTW between all gesture classifications and be averaged regular distance, setting
The gesture classification that distance between classification is less than threshold value is classified as a major class by class threshold.It is arrived secondly, calculating each sample in major class
Gap between all samples of other in major class, the i.e. regular distance of DTW choose other the smallest samples of template average distance into major class
This target template as this major class.Calculation amount is concentrated mainly on the template training generation phase of early period by the method, but in hand
The operand of gesture cognitive phase will greatly reduce.
S1052, by the acceleration resultant force time series after branch mailbox and all in angular speed time series and target collection
Gesture data is compared, and determines that classification belonging to the smallest gesture of difference is the classification of gesture to be identified.
Further, since the gesture data of input may not be identification target, thus need to be arranged a threshold value as Europe
The boundary of formula distance then determines that it fails to match when Euclidean distance is greater than threshold value, to realize fault-tolerant function.
The method of gesture template matching provided in an embodiment of the present invention, by first with the target template in each major class into
Row compares, and chooses the smallest classification of gap and is further compared, and other major class will not be considered any further.It in this way can will be right
All templates are compared one by one to be switched to segment template and compares, and lowers template matching quantity, to improve matching efficiency.
Embodiment three
As shown in figure 3, a kind of gesture identifying device provided in an embodiment of the present invention includes gesture acquisition module 10, filtering mould
Block 20, resultant force sequence computing module 30, dimension unified modules 40, branch mailbox module 50, template matching module 60, in which:
Gesture acquisition module 10, for obtaining the acceleration and angular speed data of gesture to be identified.
Filter module 20, for being filtered to acceleration and angular speed data.
Resultant force sequence computing module 30, for calculating acceleration resultant force time series according to acceleration information.
Dimension unified modules 40, for being carried out at dimension unification to acceleration resultant force time series and angular speed time series
Reason.
Branch mailbox module 50, for after dimension is uniformly processed according to default rule acceleration resultant force time series and angle
Velocity Time sequence carries out branch mailbox.
Template matching module 60, for by after branch mailbox acceleration resultant force time series and angular speed time series with prestore
Gesture template library matched, determine the classification of gesture to be identified.
In some embodiments, template matching module 60 further comprises:
First determination unit 601, for by the acceleration resultant force time series and angular speed time series after branch mailbox and in advance
If gesture template library in the target gesture data of each major class be compared, choose belonging to the smallest target gesture template of difference
Major class be target collection.
Second determination unit 601, for by the acceleration resultant force time series and angular speed time series and mesh after branch mailbox
All gesture datas in mark set are compared, and determine that classification belonging to the smallest gesture of difference is the class of gesture to be identified
Not.
Gesture identifying device provided in an embodiment of the present invention, can be in the case where not increasing sensor cost, by adding
Speed resultant force time series and angular speed time series carry out dimension and are uniformly processed and branch mailbox, and effective regular gesture data is in sky
Between on difference, reduce due to otherness caused by the variation of speed or the variation of strength, to realize efficient, accurate hand
Gesture identification, can be widely applied in the smart machine high to user-interaction experience.
Example IV
As shown in figure 4, a kind of smart machine provided in an embodiment of the present invention includes memory, processor and is stored in described
It is real when the computer program is executed by the processor on memory and the computer program that can run on the processor
The step of existing gesture identification method.
Smart machine can be implemented in a variety of manners.For example, smart machine described in the present invention may include such as
Smart phone, tablet computer, laptop, palm PC, personal digital assistant (Personal Digital
Assistant, PDA), portable media player (Portable Media Player, PMP), navigation device, wearable set
The fixed terminals such as the mobile terminals such as standby, Intelligent bracelet, pedometer, and number TV, desktop computer.
It will be illustrated by taking mobile terminal as an example in subsequent descriptions, it will be appreciated by those skilled in the art that in addition to special
Except element for moving purpose, the construction of embodiment according to the present invention can also apply to the terminal of fixed type.
Referring to Fig. 4, a kind of hardware structural diagram of its mobile terminal of each embodiment to realize the present invention, the shifting
Dynamic terminal 100 may include: RF (Radio Frequency, radio frequency) unit 101, WiFi module 102, audio output unit
103, A/V (audio/video) input unit 104, sensor 105, display unit 106, user input unit 107, interface unit
108, the components such as memory 109, processor 110 and power supply 111.It will be understood by those skilled in the art that shown in Fig. 1
Mobile terminal structure does not constitute the restriction to mobile terminal, and mobile terminal may include components more more or fewer than diagram,
Perhaps certain components or different component layouts are combined.
It is specifically introduced below with reference to all parts of the Fig. 4 to mobile terminal:
Radio frequency unit 101 can be used for receiving and sending messages or communication process in, signal sends and receivees, specifically, by base station
Downlink information receive after, to processor 110 handle；In addition, the data of uplink are sent to base station.In general, radio frequency unit 101
Including but not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier, duplexer etc..In addition, penetrating
Frequency unit 101 can also be communicated with network and other equipment by wireless communication.Any communication can be used in above-mentioned wireless communication
Standard or agreement, including but not limited to GSM (Global System of Mobile communication, global system for mobile telecommunications
System), GPRS (General Packet Radio Service, general packet radio service), CDMA2000 (Code
Division Multiple Access 2000, CDMA 2000), WCDMA (Wideband Code Division
Multiple Access, wideband code division multiple access), TD-SCDMA (Time Division-Synchronous Code
Division Multiple Access, TD SDMA), FDD-LTE (Frequency Division
Duplexing-Long Term Evolution, frequency division duplex long term evolution) and TDD-LTE (Time Division
Duplexing-Long Term Evolution, time division duplex long term evolution) etc..
WiFi belongs to short range wireless transmission technology, and mobile terminal can help user to receive and dispatch electricity by WiFi module 102
Sub- mail, browsing webpage and access streaming video etc., it provides wireless broadband internet access for user.Although Fig. 1 shows
Go out WiFi module 102, but it is understood that, and it is not belonging to must be configured into for mobile terminal, it completely can be according to need
It to omit within the scope of not changing the essence of the invention.
Audio output unit 103 can be in call signal reception pattern, call mode, record mould in mobile terminal 100
When under the isotypes such as formula, speech recognition mode, broadcast reception mode, by radio frequency unit 101 or WiFi module 102 it is received or
The audio data stored in memory 109 is converted into audio signal and exports to be sound.Moreover, audio output unit 103
Audio output relevant to the specific function that mobile terminal 100 executes can also be provided (for example, call signal receives sound, disappears
Breath receives sound etc.).Audio output unit 103 may include loudspeaker, buzzer etc..
A/V input unit 104 is for receiving audio or video signal.A/V input unit 104 may include graphics processor
(Graphics Processing Unit, GPU) 1041 and microphone 1042, graphics processor 1041 is in video acquisition mode
Or the image data of the static images or video obtained in image capture mode by image capture apparatus (such as camera) carries out
Reason.Treated, and picture frame may be displayed on display unit 106.Through graphics processor 1041, treated that picture frame can be deposited
Storage is sent in memory 109 (or other storage mediums) or via radio frequency unit 101 or WiFi module 102.Mike
Wind 1042 can connect in telephone calling model, logging mode, speech recognition mode etc. operational mode via microphone 1042
Quiet down sound (audio data), and can be audio data by such acoustic processing.Audio that treated (voice) data can
To be converted to the format output that can be sent to mobile communication base station via radio frequency unit 101 in the case where telephone calling model.
Microphone 1042 can be implemented various types of noises elimination (or inhibition) algorithms and send and receive sound to eliminate (or inhibition)
The noise generated during frequency signal or interference.
Mobile terminal 100 further includes at least one sensor 105, such as optical sensor, motion sensor and other biographies
Sensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein ambient light sensor can be according to environment
The light and shade of light adjusts the brightness of display panel 1061, and proximity sensor can close when mobile terminal 100 is moved in one's ear
Display panel 1061 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (general
For three axis) size of acceleration, it can detect that size and the direction of gravity when static, can be used to identify the application of mobile phone posture
(such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.；
The fingerprint sensor that can also configure as mobile phone, pressure sensor, iris sensor, molecule sensor, gyroscope, barometer,
The other sensors such as hygrometer, thermometer, infrared sensor, details are not described herein.
In embodiments of the present invention, sensor 105 includes acceleration transducer and angular-rate sensor, acceleration transducer
3-axis acceleration sensor can be used, angular-rate sensor can use gyroscope, to acquire the acceleration of user gesture
Data and angular velocity data.
Display unit 106 is for showing information input by user or being supplied to the information of user.Display unit 106 can wrap
Display panel 1061 is included, liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode can be used
Forms such as (Organic Light-Emitting Diode, OLED) configure display panel 1061.
User input unit 107 can be used for receiving the number or character information of input, and generate the use with mobile terminal
Family setting and the related key signals input of function control.Specifically, user input unit 107 may include touch panel 1071 with
And other input equipments 1072.Touch panel 1071, also referred to as touch screen collect the touch operation of user on it or nearby
(for example user uses any suitable objects or attachment such as finger, stylus on touch panel 1071 or in touch panel 1071
Neighbouring operation), and corresponding attachment device is driven according to preset formula.Touch panel 1071 may include touch detection
Two parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation band
The signal come, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by it
It is converted into contact coordinate, then gives processor 110, and order that processor 110 is sent can be received and executed.In addition, can
To realize touch panel 1071 using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves.In addition to touch panel
1071, user input unit 107 can also include other input equipments 1072.Specifically, other input equipments 1072 can wrap
It includes but is not limited in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, operating stick etc.
It is one or more, specifically herein without limitation.
Further, touch panel 1071 can cover display panel 1061, when touch panel 1071 detect on it or
After neighbouring touch operation, processor 110 is sent to determine the type of touch event, is followed by subsequent processing device 110 according to touch thing
The type of part provides corresponding visual output on display panel 1061.Although in Fig. 1, touch panel 1071 and display panel
1061 be the function that outputs and inputs of realizing mobile terminal as two independent components, but in certain embodiments, it can
The function that outputs and inputs of mobile terminal is realized so that touch panel 1071 and display panel 1061 is integrated, is not done herein specifically
It limits.
Interface unit 108 be used as at least one external device (ED) connect with mobile terminal 100 can by interface.For example,
External device (ED) may include wired or wireless headphone port, external power supply (or battery charger) port, wired or nothing
Line data port, memory card port, the port for connecting the device with identification module, audio input/output (I/O) end
Mouth, video i/o port, ear port etc..Interface unit 108 can be used for receiving the input from external device (ED) (for example, number
It is believed that breath, electric power etc.) and the input received is transferred to one or more elements in mobile terminal 100 or can be with
For transmitting data between mobile terminal 100 and external device (ED).
Memory 109 can be used for storing software program and various data.Memory 109 can mainly include storing program area
The storage data area and, wherein storing program area can (such as the sound of application program needed for storage program area, at least one function
Sound playing function, image player function etc.) etc.；Storage data area can store according to mobile phone use created data (such as
Audio data, phone directory etc.) etc..In addition, memory 109 may include high-speed random access memory, it can also include non-easy
The property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
In embodiments of the present invention, memory 109 stores the program of above-mentioned realization gesture identification method.
Processor 110 is the control centre of mobile terminal, utilizes each of various interfaces and the entire mobile terminal of connection
A part by running or execute the software program and/or module that are stored in memory 109, and calls and is stored in storage
Data in device 109 execute the various functions and processing data of mobile terminal, to carry out integral monitoring to mobile terminal.Place
Managing device 110 may include one or more processing units；Preferably, processor 110 can integrate application processor and modulatedemodulate is mediated
Manage device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is main
Processing wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 110.
In embodiments of the present invention, processor 110 executes real when the program of the gesture identification method stored on memory 109
The step of gesture identification method now as described in Figure 1:
S101, the acceleration and angular speed data for obtaining gesture to be identified, and be filtered；
S102, acceleration resultant force time series is calculated according to acceleration information；
S103, acceleration resultant force time series and angular speed time series progress dimension are uniformly processed；
S104, dimension is uniformly processed according to default rule after acceleration resultant force time series and angular speed time sequence
Column carry out branch mailbox；
S105, by after branch mailbox acceleration resultant force time series and angular speed time series and the gesture template library that prestores into
Row matching, determines the classification of gesture to be identified.
Mobile terminal 100 can also include the power supply 111 (such as battery) powered to all parts, it is preferred that power supply 111
Can be logically contiguous by power-supply management system and processor 110, to realize management charging by power-supply management system, put
The functions such as electricity and power managed.
Although Fig. 4 is not shown, mobile terminal 100 can also be including bluetooth module etc., and details are not described herein.
It should be noted that above-mentioned intelligent terminal embodiment and embodiment of the method belong to same design, implemented
Journey is shown in embodiment of the method in detail, and the technical characteristic in embodiment of the method is corresponding applicable in terminal embodiment, here no longer
It repeats.
Intelligent terminal provided in an embodiment of the present invention, can be in the case where not increasing sensor cost, by acceleration
Resultant force time series and angular speed time series carry out dimension and are uniformly processed and branch mailbox, and effective regular gesture data is spatially
Difference, reduce due to otherness caused by the variation of speed or the variation of strength, to realize that efficient, accurate gesture is known
Not.
In addition, the embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable storage medium
It is stored with the program of gesture identification in matter, realizes that the embodiment of the present invention provides when the program of the gesture identification is executed by processor
Gesture identification method the step of.
It should be noted that gesture identification program embodiment and embodiment of the method on above-mentioned computer readable storage medium
Belong to same design, implements process referring particularly to embodiment of the method, and the technical characteristic in embodiment of the method is above-mentioned
Corresponding in the embodiment of computer readable storage medium to be applicable in, which is not described herein again.
Preferred embodiments of the present invention have been described above with reference to the accompanying drawings, not thereby limiting the scope of the invention.This
Without departing from the scope and spirit of the invention, there are many variations to implement the present invention by field technical staff, for example as one
The feature of a embodiment can be used for another embodiment and obtain another embodiment.It is all to use institute within technical concept of the invention
Any modifications, equivalent replacements, and improvements of work, should all be within interest field of the invention.
Claims (10)
1. a kind of gesture identification method, which is characterized in that this method comprises:
The acceleration and angular speed data of gesture to be identified are obtained, and are filtered；
Acceleration resultant force time series is calculated according to the acceleration information；
Dimension is carried out to the acceleration resultant force time series and angular speed time series to be uniformly processed；
Acceleration resultant force time series and angular speed time series after the dimension is uniformly processed according to default rule into
Row branch mailbox；
By after branch mailbox acceleration resultant force time series and angular speed time series match with the gesture template library prestored, really
The classification of fixed gesture to be identified.
2. gesture identification method according to claim 1, which is characterized in that described be filtered include:
It uses and the acceleration information and angular velocity data is carried out using 3.5HZ as the Butterworth LPF of cutoff frequency
Filtering processing.
3. gesture identification method according to claim 1, which is characterized in that described calculated according to the acceleration information adds
Speed resultant force time series includes being calculated using the following equation:
Wherein, s indicates acceleration resultant force, a(xt)、a(yt)、a(zt))Respectively indicate acceleration of the t moment on x-axis, y-axis and z-axis direction
Degree, g indicate acceleration of gravity.
4. gesture identification method according to claim 1, which is characterized in that described to the acceleration resultant force time series
Dimension is carried out to be uniformly processed including calculating as follows:
Wherein, S(t)Indicate the acceleration resultant force of t moment, meanSIndicate the mean value of all acceleration resultant forces of whole section of time series,
stdSIndicate the standard deviation of all acceleration resultant forces of whole section of time series；
The angular velocity time series carries out dimension and is uniformly processed including calculating as follows:
Wherein, w(t)Indicate the angular speed of t moment, meanwIndicate the mean value of all angular velocity vector sizes of whole section of time series,
stdwIndicate the standard deviation of all angular velocity vector sizes of whole section of time series.
5. gesture identification method according to claim 1, which is characterized in that it is described according to default rule to the dimension
Acceleration resultant force time series and the angular speed time series after being uniformly processed carry out branch mailbox
It is using the first preset piecewise function that the acceleration resultant force at each moment in the acceleration resultant force time series is big
It is small to be mapped as discrete acceleration resultant force value, the acceleration resultant force time sequence is stated using the discrete acceleration resultant force value
Column；
The angular velocity vector size at each moment in the angular speed time series is mapped using the second preset piecewise function
For discrete magnitude of angular velocity, the angular speed time series is stated using the discrete magnitude of angular velocity.
6. gesture identification method according to claim 1, which is characterized in that by the acceleration resultant force time series after branch mailbox
It is matched with angular speed time series with the gesture template library prestored, determines that the classification of gesture to be identified includes:
It will be each in the acceleration resultant force time series and angular speed time series and preset gesture template library after the branch mailbox
The target gesture data of major class is compared, and choosing major class belonging to the smallest target gesture template of difference is target collection.
By the acceleration resultant force time series and angular speed time series after branch mailbox and all gesture numbers in the target collection
According to being compared, determine that classification belonging to the smallest gesture of difference is the classification of gesture to be identified.
7. a kind of gesture identifying device, which is characterized in that the device includes:
Gesture acquisition module, for obtaining the acceleration and angular speed data of gesture to be identified；
Filter module, for being filtered to the acceleration and angular speed data；
Resultant force computing module, for calculating acceleration resultant force time series according to the acceleration information；
Dimension unified modules, for being carried out at dimension unification to the acceleration resultant force time series and angular speed time series
Reason；
Branch mailbox module, for the acceleration resultant force time series and angle speed after the dimension is uniformly processed according to default rule
It spends time series and carries out branch mailbox；
Template matching module, for by after branch mailbox acceleration resultant force time series and angular speed time series and the gesture that prestores
Template library is matched, and determines the classification of gesture to be identified.
8. gesture identifying device according to claim 7, which is characterized in that the template matching module includes:
First determination unit, for by after the branch mailbox acceleration resultant force time series and angular speed time series with it is preset
The target gesture data of each major class is compared in gesture template library, is chosen big belonging to the smallest target gesture template of difference
Class is target collection.
Second determination unit, for by the acceleration resultant force time series and angular speed time series and the object set after branch mailbox
All gesture datas in conjunction are compared, and determine that classification belonging to the smallest gesture of difference is the classification of gesture to be identified.
9. a kind of smart machine, which is characterized in that the smart machine includes memory, processor and is stored in the memory
Computer program that is upper and can running on the processor, is realized when the computer program is executed by the processor as weighed
Benefit require any one of 1 to 7 described in gesture identification method the step of.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program when the computer program is executed by processor, realizes the gesture identification as described in any one of claim 1 to 6
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810307857.6A CN110348275A (en) | 2018-04-08 | 2018-04-08 | Gesture identification method, device, smart machine and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810307857.6A CN110348275A (en) | 2018-04-08 | 2018-04-08 | Gesture identification method, device, smart machine and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110348275A true CN110348275A (en) | 2019-10-18 |
Family
ID=68173397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810307857.6A Pending CN110348275A (en) | 2018-04-08 | 2018-04-08 | Gesture identification method, device, smart machine and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110348275A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111580666A (en) * | 2020-05-11 | 2020-08-25 | 清华大学 | Equipment control method, electronic equipment, equipment control system and storage medium |
| CN112114665A (en) * | 2020-08-23 | 2020-12-22 | 西北工业大学 | Hand tracking method based on multi-mode fusion |
| CN112363659A (en) * | 2020-11-09 | 2021-02-12 | 平安普惠企业管理有限公司 | APP interface operation method and device, electronic equipment and storage medium |
| CN112527118A (en) * | 2020-12-16 | 2021-03-19 | 郑州轻工业大学 | Head posture recognition method based on dynamic time warping |
| CN116360603A (en) * | 2023-05-29 | 2023-06-30 | 中数元宇数字科技(上海)有限公司 | Interaction method, device, medium and program product based on time sequence signal matching |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103345627A (en) * | 2013-07-23 | 2013-10-09 | 清华大学 | Action recognition method and device |
| CN104866099A (en) * | 2015-05-27 | 2015-08-26 | 东南大学 | Error compensation method for improving gesture identification precision of intelligent device based on motion sensor |
| US20150346834A1 (en) * | 2014-06-02 | 2015-12-03 | Samsung Electronics Co., Ltd. | Wearable device and control method using gestures |
| CN105184325A (en) * | 2015-09-23 | 2015-12-23 | 歌尔声学股份有限公司 | Human body action recognition method and mobile intelligent terminal |
| CN107026928A (en) * | 2017-05-24 | 2017-08-08 | 武汉大学 | A kind of behavioural characteristic identification authentication method and device based on mobile phone sensor |
-
2018
- 2018-04-08 CN CN201810307857.6A patent/CN110348275A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103345627A (en) * | 2013-07-23 | 2013-10-09 | 清华大学 | Action recognition method and device |
| US20150346834A1 (en) * | 2014-06-02 | 2015-12-03 | Samsung Electronics Co., Ltd. | Wearable device and control method using gestures |
| CN104866099A (en) * | 2015-05-27 | 2015-08-26 | 东南大学 | Error compensation method for improving gesture identification precision of intelligent device based on motion sensor |
| CN105184325A (en) * | 2015-09-23 | 2015-12-23 | 歌尔声学股份有限公司 | Human body action recognition method and mobile intelligent terminal |
| CN107026928A (en) * | 2017-05-24 | 2017-08-08 | 武汉大学 | A kind of behavioural characteristic identification authentication method and device based on mobile phone sensor |
Non-Patent Citations (2)
| Title |
|---|
| 姚桂林, 姚鸿勋, 姜峰: "一种基于DTW/ISODATA算法的多层分类器手语识别方法", 计算机工程与应用, 31 August 2005 (2005-08-31), pages 45 - 47 * |
| 王海鹏;龚岩;刘武;李泽;张思美: "一种时空多尺度适应的手势识别方法研究", 计算机科学, vol. 44, no. 12, 31 December 2017 (2017-12-31), pages 287 - 291 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111580666A (en) * | 2020-05-11 | 2020-08-25 | 清华大学 | Equipment control method, electronic equipment, equipment control system and storage medium |
| CN111580666B (en) * | 2020-05-11 | 2022-04-29 | 清华大学 | Equipment control method, electronic equipment, equipment control system and storage medium |
| CN112114665A (en) * | 2020-08-23 | 2020-12-22 | 西北工业大学 | Hand tracking method based on multi-mode fusion |
| CN112363659A (en) * | 2020-11-09 | 2021-02-12 | 平安普惠企业管理有限公司 | APP interface operation method and device, electronic equipment and storage medium |
| CN112527118A (en) * | 2020-12-16 | 2021-03-19 | 郑州轻工业大学 | Head posture recognition method based on dynamic time warping |
| CN112527118B (en) * | 2020-12-16 | 2022-11-25 | 郑州轻工业大学 | Head posture recognition method based on dynamic time warping |
| CN116360603A (en) * | 2023-05-29 | 2023-06-30 | 中数元宇数字科技(上海)有限公司 | Interaction method, device, medium and program product based on time sequence signal matching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110348275A (en) | Gesture identification method, device, smart machine and computer readable storage medium | |
| CN108459797B (en) | Control method of folding screen and mobile terminal | |
| CN110740259A (en) | Video processing method and electronic equipment | |
| CN107835321A (en) | A kind of incoming call processing method and mobile terminal | |
| CN107817939A (en) | A kind of image processing method and mobile terminal | |
| CN107809526A (en) | End application sorting technique, mobile terminal and computer-readable recording medium | |
| CN111127509B (en) | Target tracking method, apparatus and computer readable storage medium | |
| CN107707729A (en) | A kind of terminal go out screen or bright screen method, terminal and computer-readable recording medium | |
| CN110365853B (en) | Prompting method and electronic equipment | |
| CN108521658A (en) | Reduce interference method, mobile terminal and computer readable storage medium | |
| CN111554321A (en) | Noise reduction model training method and device, electronic equipment and storage medium | |
| CN107632757A (en) | A kind of terminal control method, terminal and computer-readable recording medium | |
| CN109901809A (en) | A kind of display control method, equipment and computer readable storage medium | |
| CN108415641A (en) | A kind of processing method and mobile terminal of icon | |
| CN108196776A (en) | A kind of terminal split screen method, terminal and computer readable storage medium | |
| CN110139018A (en) | Camera controls the control method for movement and terminal of mould group, camera | |
| CN107463324A (en) | A kind of image display method, mobile terminal and computer-readable recording medium | |
| CN108257104A (en) | A kind of image processing method and mobile terminal | |
| CN109710130A (en) | A kind of display methods and terminal | |
| CN109754823A (en) | A kind of voice activity detection method, mobile terminal | |
| CN109819102A (en) | A kind of navigation bar control method and mobile terminal, computer readable storage medium | |
| CN109193975A (en) | A kind of wireless charging device and terminal | |
| CN109388326A (en) | A kind of electronic equipment, the control method and device of dual-screen electronic device | |
| CN107656727A (en) | A kind of font object library generating method and mobile terminal | |
| CN109871176A (en) | A kind of object displaying method and terminal device |
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 |